Intelligent monitoring system based on scenarized linkage and fault pre-judgment

Abstract

The invention relates to the technical field of intelligent monitoring, in particular to an intelligent monitoring system based on scenarized linkage and fault pre-judgment, which comprises an intelligent monitoring unit deployed in an intelligent equipment box body of a monitoring site and used for collecting internal environment data of the box body and accessed monitoring equipment data, linkage control and power supply scheduling are executed based on a received strategy instruction or a local rule; the remote management platform is used for performing scenarized strategy configuration, fault prediction and positioning based on artificial intelligence, and global energy consumption optimization analysis, and issuing a strategy instruction to the intelligent monitoring unit; the communication transmission unit is connected with the intelligent monitoring units and the remote management platform, and provides a cooperative communication link among the plurality of intelligent monitoring units; accurate matching of the operation parameters and the linkage logic in different application scenes is realized, the problems of false alarm and alarm omission caused by fixed configuration are avoided, and the applicability and reliability of the system in multiple scenes are greatly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent monitoring, and particularly relates to an intelligent monitoring system based on scene-based linkage and fault prediction. BACKGROUND

[0002] With the deepening of the construction of safe city, the upgrading of intelligent transportation and the intelligent transformation of industrial production, intelligent monitoring equipment boxes, as the core bearing and protection units of front-end monitoring equipment (cameras, sensors, etc.), have been widely used in urban public security prevention and control, road traffic monitoring, coal mine production supervision, natural disaster warning and other fields. As the energy center and communication hub of the front-end monitoring system, the running stability of such equipment boxes directly determines the continuity of monitoring data collection, the safety of equipment operation and the efficiency of operation and maintenance management. Therefore, the industry's requirements for power supply stability, state sensing capability, fault handling efficiency and scene adaptation flexibility of the equipment boxes continue to improve.

[0003] However, the existing intelligent monitoring equipment boxes and supporting management systems have the following problems:

[0004] Scene adaptation mechanism is rigid: the running parameters (such as temperature alarm threshold, power output strategy) of the existing system are mostly uniformly fixed, which cannot adapt to the environmental characteristics and business needs of different scenes, and is prone to false alarms or missed alarms.

[0005] Fault warning and positioning capability is weak: the existing system mostly relies on the passive mode of alarm after fault occurs, lacks trend analysis and fault prediction capability of device running state, and fault positioning is limited to device physical location, with slow maintenance response.

[0006] Extensive load and energy consumption management: lacking real-time sensing and adaptive control mechanism for load state, mostly using full-power power supply mode all day, which is high in energy consumption and prone to equipment damage. SUMMARY

[0007] The present application aims to solve at least one of the problems raised in the background art. To achieve the purpose of the present application, the following technical solutions are adopted:

[0008] An intelligent monitoring system based on scene-based linkage and fault prediction, comprising:

[0009] An intelligent monitoring unit deployed in the box body of the intelligent device box at the monitoring site, for collecting internal environment data and monitoring device data connected to the box body, and performing linkage control and power supply scheduling based on received strategy instructions or local rules;

[0010] A remote management platform for scene-based strategy configuration, artificial intelligence-based fault prediction and positioning, and global performance and energy optimization analysis, and issuing strategy instructions to the intelligent monitoring unit;

[0011] The communication transmission unit connects the intelligent monitoring unit and the remote management platform, and provides a collaborative communication link between multiple intelligent monitoring units.

[0012] A further improvement is that the intelligent monitoring unit includes:

[0013] The core controller uses a multi-core embedded processor and has a built-in linkage logic parsing unit and a local scheduling unit to coordinate and control the work of each module in the intelligent monitoring unit and execute policy instructions and local preset rules from the remote management platform.

[0014] The enclosure environment sensing module is connected to the core controller and is used to collect environmental physical quantities inside the smart device enclosure;

[0015] The device status sensing module, connected to the core controller, is used to monitor the electrical operating parameters of the connected monitoring devices;

[0016] The intelligent power distribution module is connected to the core controller and provides multiple controlled AC power outputs. Each output has independent on / off control, power metering and circuit protection functions.

[0017] A further improvement is that the intelligent monitoring unit also includes:

[0018] The load analysis module is connected to the current sampling output of the device status sensing module. It runs a real-time power calculation algorithm internally to periodically calculate the instantaneous active power of each connected monitoring device.

[0019] The load analysis module compares the calculated real-time power with the preset rated power threshold of the monitoring device, and dynamically classifies the load status of each monitoring device into three levels: high load, normal load, and light load.

[0020] The load analysis module periodically reports the load status level and real-time power value of each monitored device to the remote management platform through the core controller, and provides it to the local scheduling unit as a basis for local scheduling.

[0021] A further improvement is that the local scheduling unit is configured to execute the following fine-grained energy management strategy based on load status:

[0022] When a monitoring device is under light load, the intelligent power distribution module is controlled to reduce the output voltage of its power supply circuit or switch to intermittent power supply mode.

[0023] When the total load power exceeds the preset safety threshold, the intelligent power distribution module is controlled to cut off the power supply to the lowest priority device according to the preset priority order of monitoring devices.

[0024] A further improvement is that the intelligent monitoring unit also includes:

[0025] The data storage and forwarding module includes non-volatile memory and a separate communication processor;

[0026] When the network connection between the communication transmission unit and the remote management platform is interrupted, the core controller automatically writes the key data collected by the enclosure environment sensing module and the equipment status sensing module into the non-volatile memory for temporary storage.

[0027] The communication processor continuously detects the network connection status. Once it detects that communication with the remote management platform has been restored, it automatically starts the resume transmission process and uploads the temporarily stored data in batches according to time order and priority.

[0028] A further improvement is that the intelligent power distribution module specifically includes:

[0029] It has at least 5 independently controllable AC220V output ports, each with a maximum current carrying capacity of not less than 8A, and supports on / off control via remote network commands and local hardware switches.

[0030] A precision metering chip integrated into each port is used to collect the effective voltage value, effective current value, active power and cumulative energy consumption data of that port in real time.

[0031] The built-in automatic reclosing protection unit provides undervoltage, overvoltage, leakage current and overcurrent protection, and the action threshold of each protection function can be remotely set and adjusted through the remote management platform.

[0032] A further improvement is that the remote management platform includes a scenario policy library and a policy distribution engine, wherein:

[0033] The scenario strategy library stores a variety of predefined strategy templates in the form of a database. Each strategy template corresponds to a monitoring scenario. The strategy template includes at least: a set of alarm thresholds for environmental parameters for the corresponding monitoring scenario, a logic diagram of the linkage between devices, a list of business priorities for each monitoring device, and recommended energy efficiency management parameters.

[0034] The policy delivery engine provides a graphical policy editing interface, allowing users to modify or completely customize new policies based on templates. The policy delivery engine compiles the edited policies into a binary instruction set or structured configuration file that can be recognized and executed by the core controller, and delivers them to one or more designated intelligent monitoring units through the communication transmission unit.

[0035] A further improvement is that the remote management platform also includes a fault prediction center, which is used to receive and store the equipment status time-series data reported by all intelligent monitoring units; the fault prediction center uses a machine learning model to perform trend analysis on the time-series data to predict the probability and time window of failure of specific electrical components or functional modules, and generates early warning information.

[0036] When generating early warning information, the fault prediction center simultaneously performs the following operations:

[0037] Based on the identifier of the intelligent monitoring unit corresponding to the early warning information, retrieve its geographical location information and the corresponding operation and maintenance responsibility information; automatically generate a digital maintenance work order containing fault prediction details, equipment location, handling suggestions and responsible person, and push it to the work order management module of the remote management platform.

[0038] A further improvement is that the remote management platform also includes an energy efficiency analysis engine, which is used to periodically statistically analyze the energy consumption data reported by all intelligent monitoring units, including:

[0039] By comparing the energy consumption differences of different intelligent monitoring units in the same period, inefficient nodes with abnormally high energy consumption per unit load can be identified.

[0040] Analyze the overall energy consumption pattern of a group of intelligent monitoring units in the same area over time;

[0041] Based on the analysis results, an energy efficiency analysis report is generated, and optimization suggestions are provided to the strategy delivery engine based on the findings in the report. These suggestions are used to adjust the energy efficiency management parameters of relevant intelligent monitoring units or to mark devices that may require hardware checks.

[0042] A further improvement is that the communication transmission unit includes:

[0043] The platform communication channel is used for data transmission between the remote management platform and the intelligent monitoring unit. This channel uses a wired network as the primary link and is configured with a wireless network as the backup link.

[0044] The inter-node coordination channel is used for direct data interaction between multiple intelligent monitoring units. This channel is implemented using a wireless self-organizing network based on Mesh networking technology. Through the inter-node coordination channel, multiple intelligent monitoring units automatically form a logical backup cluster. When a node in the cluster goes offline for any reason, its pre-set backup node will automatically take over the task of receiving and temporarily storing its critical data through the inter-node coordination channel until the node is restored or maintenance personnel intervene.

[0045] The beneficial effects of this invention are as follows:

[0046] In terms of scenario adaptation, this invention relies on a scenario-based strategy library and a flexible configuration mechanism to achieve accurate matching of operating parameters and linkage logic under different application scenarios, avoiding false alarms and missed alarms caused by fixed configurations, and greatly improving the applicability and reliability of the system in multiple scenarios.

[0047] At the fault management level, through multi-dimensional time-series data collection and machine learning model analysis, early warning of faults and accurate location of internal fault modules are achieved, transforming the traditional passive emergency repair mode into proactive early warning operation and maintenance, significantly shortening the fault repair cycle and reducing the risk of system downtime.

[0048] In terms of energy consumption optimization, based on real-time front-end load perception and refined energy management strategies, the power supply mode is dynamically adjusted. Under the premise of ensuring the core monitoring functions, unnecessary energy consumption is effectively reduced. At the same time, through the overload active protection mechanism, equipment damage caused by sudden load changes is avoided, and the stability of equipment operation is improved.

[0049] In terms of system reliability, the dual design of primary and backup communication channels and inter-node collaborative backup ensures that critical data is not lost when the network is interrupted and that monitoring data is not interrupted when a single device fails, thus guaranteeing the continuity of data acquisition and transmission.

[0050] Furthermore, the backend management platform's global energy efficiency analysis and intelligent work order management form a data-driven optimization loop, standardize the operation and maintenance process, improve overall operation and maintenance efficiency and system operating efficiency, and provide a comprehensive solution for the intelligent upgrade in the field of intelligent monitoring. Attached Figure Description

[0051] Figure 1 This is a partial module architecture diagram of an intelligent monitoring system based on scenario-based linkage and fault prediction according to the present invention. Detailed Implementation

[0052] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0053] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0054] Please refer to the attached document. Figure 1 This invention proposes an intelligent monitoring system based on scenario-based linkage and fault prediction, comprising:

[0055] The intelligent monitoring unit is deployed inside an intelligent equipment box at the monitoring site. It is used to collect environmental data inside the box and data from connected monitoring equipment, and to execute linkage control and power supply scheduling based on received policy instructions or local rules.

[0056] The remote management platform is used for scenario-based strategy configuration, AI-based fault prediction and location, and global performance optimization analysis, and issues strategy instructions to the intelligent monitoring unit.

[0057] The communication transmission unit connects the intelligent monitoring unit and the remote management platform, and provides a collaborative communication link between multiple intelligent monitoring units.

[0058] Understandably, the intelligent monitoring unit, as the front-end execution carrier, is deployed in the on-site intelligent equipment box. Its core responsibility is two-way data processing. On the one hand, it collects the internal environment of the box (such as temperature and humidity) and the operating data of the connected monitoring equipment (such as cameras). On the other hand, it receives policy instructions, executes linkage control and power supply scheduling (such as power on / off and power adjustment), and supports the autonomous execution of local rules.

[0059] The remote management platform, as the core backend hub, adapts to the needs of multiple scenarios through scenario-based strategies, uses artificial intelligence models (such as LSTM) to analyze data to predict faults, and coordinates global energy consumption optimization to form a management closed loop of "configuration-analysis-optimization".

[0060] The communication transmission unit undertakes a dual communication task: first, to ensure stable data interaction between the front end and the back end; second, to build a collaborative link for multiple intelligent monitoring units, providing a foundation for subsequent node backup. The three work together to achieve automated and intelligent operation of the entire system through a process of data collection by the intelligent monitoring unit, analysis and decision-making by the remote management platform, instruction issuance by the communication transmission unit, and execution and feedback by the intelligent monitoring unit.

[0061] Specifically, in this embodiment, the intelligent monitoring unit includes a core controller, a housing environment sensing module, an equipment status sensing module, and an intelligent power distribution module.

[0062] Specifically, the core controller employs a multi-core embedded processor based on the ARM Cortex-A series architecture, running a Linux embedded operating system. It incorporates a linkage logic parsing unit and a local scheduling unit to coordinate and control the operation of each module within the intelligent monitoring unit, and to execute policy instructions and locally preset rules from the remote management platform. The core controller is also responsible for data aggregation and reporting, uploading the environmental data, equipment status data, and energy consumption data collected by the enclosure environment sensing module and the equipment status sensing module to the remote management platform via the communication transmission unit.

[0063] Understandably, the core controller ensures multi-task parallel processing capabilities. Its built-in linkage logic parsing unit is responsible for translating the policy instructions issued by the backend, converting abstract policies into specific signals that can be executed by each module; while the local scheduling unit generates real-time scheduling instructions based on real-time collected data and local preset rules, realizing a dual mode of local autonomous decision-making and backend remote control.

[0064] The enclosure environment sensing module is connected to the core controller. The enclosure environment sensing module integrates an I2C interface digital temperature and humidity sensor (measurement range -40℃-85℃, accuracy ±0.5℃), a capacitive water immersion sensor (detection sensitivity ≤1mm), and a triaxial MEMS vibration sensor (range ±16g, frequency response range 0.5Hz-2000Hz). These sensors are installed inside the smart device enclosure and are used to collect environmental physical quantities inside the smart device enclosure.

[0065] Understandably, the enclosure environment sensing module uses high-precision sensors to collect physical quantities such as temperature, humidity, water immersion status, and vibration amplitude inside the enclosure. The collected data is transmitted to the core controller in real time to provide environmental basis for strategy execution.

[0066] The device status sensing module is connected to the core controller and includes an open-type AC current transformer (accuracy class 0.5), a voltage sampling divider circuit (input range AC 0-300V), and a DC shunt, used to monitor the electrical operating parameters of the connected monitoring equipment.

[0067] Understandably, the equipment status sensing module is directly linked to the intelligent power distribution module and monitoring equipment, capturing electrical parameters such as voltage, current, and power factor in real time. At the same time, it monitors the protection action status of the power distribution module, ensuring that the core controller has a comprehensive understanding of the equipment's operating status and providing data support for fault prediction and load optimization.

[0068] The intelligent power distribution module is connected to the core controller and provides multiple controlled AC power outputs. Each output has independent on / off control, power metering and circuit protection functions.

[0069] Specifically, the intelligent power distribution module includes:

[0070] It has at least 5 independently controllable AC220V output ports, each with a maximum current carrying capacity of no less than 8A and a total current carrying capacity of no less than 40A, which can provide stable power supply for multiple cameras at the same time; it supports on / off control via remote network commands and local hardware switches.

[0071] A precision metering chip integrated into each port is used to collect real-time data on the port's RMS voltage, RMS current, active power, and cumulative energy consumption. The collected data is synchronized to the core controller in real time, providing accurate data support for load analysis and energy consumption optimization.

[0072] The built-in automatic reclosing protection unit provides undervoltage, overvoltage, leakage current, and overcurrent protection, and the action thresholds for each protection function can be remotely set and adjusted via the remote management platform. Specifically, the undervoltage protection threshold can be remotely configured within the range of 180-200V, the overvoltage protection threshold is adjustable within the range of 220-240V, the leakage current protection threshold is 5-30mA, and the overcurrent protection threshold is 8-10A. When an abnormality is detected, the power supply to the corresponding port is immediately cut off, and a protection action feedback signal is sent to the core controller to trigger an alarm, thus preventing equipment damage or safety hazards.

[0073] In a preferred embodiment of this invention, the intelligent monitoring unit further includes a load analysis module.

[0074] The load analysis module is connected to the current sampling output of the device status sensing module. It runs a real-time power calculation algorithm internally to periodically calculate the instantaneous active power of each connected monitoring device.

[0075] The load analysis module compares the calculated real-time power with the preset rated power threshold of the monitoring device, and dynamically classifies the load status of each monitoring device into three levels: high load, normal load, and light load.

[0076] The load analysis module periodically reports the load status level and real-time power value of each monitored device to the remote management platform through the core controller, and provides it to the local scheduling unit as a basis for local scheduling.

[0077] Specifically, the local scheduling unit is configured to execute the following fine-grained energy management strategy based on load status:

[0078] When a monitoring device is under light load, the intelligent power distribution module is controlled to reduce the output voltage of its power supply circuit or switch to intermittent power supply mode.

[0079] When the total load power exceeds the preset safety threshold, the intelligent power distribution module is controlled to cut off the power supply to the lowest priority device according to the preset priority order of monitoring devices.

[0080] Understandably, when a single monitoring device is under light load (e.g., real-time power ≤ 30% of rated power), the local dispatch unit will control the intelligent power distribution module to perform two optimization actions: reduce the output voltage of the device's power supply circuit (e.g., reduce it to 70%-80% of the rated voltage without affecting the monitoring function); or switch to intermittent power supply mode (the cycle can be configured through the backend). The two optimization actions can be selected according to the actual scenario, and the core purpose is to reduce ineffective energy consumption while ensuring basic monitoring needs.

[0081] When the total load power exceeds a preset safety threshold (e.g., 90% of the total rated current of the intelligent power distribution module), the system prioritizes core business operations. Based on a preset priority list of monitoring devices (configured by the backend management platform, e.g., setting snapshot cameras as the highest priority), it automatically cuts off power to the lowest priority devices until the total load drops to a safe range. This action prevents power module damage or complete front-end system failure due to overload, achieving proactive overload protection.

[0082] In a preferred embodiment of this invention, the intelligent monitoring unit further includes a graded lightning protection module, a network communication module, and a backup power supply module.

[0083] The graded surge protection module adopts a three-level surge protection architecture. The first level is located at the high-voltage input terminal with a current carrying capacity Imax(8 / 20μs)≥40KA. The second level is located at the power module input terminal with a current carrying capacity Imax(8 / 20μs)≥20KA. The third level is located at the network port and meets the ITU-T K21 standard (10 / 700μs 6KV(40Ω)). Each surge protection unit has a built-in leakage current sensor and status monitoring chip.

[0084] The network communication module has five built-in 10 / 100 / 1000Base-Tx RJ45 electrical ports, one 100 / 1000M SFP optical port, and integrates a 4G / 5G full network compatibility module and a GPS positioning module (positioning accuracy ±5m).

[0085] The backup power module can use a lithium iron phosphate battery pack (capacity 12V / 10Ah) or a supercapacitor, and supports automatic switching after the mains power fails, so as to continuously supply power to the critical modules for a period of time.

[0086] In a preferred embodiment of this invention, the intelligent monitoring unit further includes a data storage and forwarding module.

[0087] Specifically, the data storage and forwarding module includes a non-volatile memory and a separate communication processor.

[0088] When the network connection between the communication transmission unit and the remote management platform is interrupted, the core controller automatically writes the key data collected by the enclosure environment sensing module and the equipment status sensing module into the non-volatile memory for temporary storage.

[0089] The communication processor continuously detects the network connection status. Once it detects that communication with the remote management platform has been restored, it automatically starts the resume transmission process and uploads the temporarily stored data in batches according to time order and priority.

[0090] Understandably, when the network connection between the communication transmission unit and the remote management platform is interrupted, the core controller automatically triggers a data storage mechanism, writing key data (such as fault alarm data, abnormal equipment status data, and energy consumption data of core monitoring equipment) collected by the enclosure environment sensing module and the equipment status sensing module into non-volatile memory in timestamp order; the communication processor continuously probes the network connection status (e.g., the probe cycle is 1 second / time), and once it detects that communication with the remote management platform has been restored, it immediately sends a resume signal to the core controller. The core controller controls the module to start the resume process, uploading the stored data in batches to the remote management platform in time order and priority (e.g., fault data first, status data second, and energy consumption data last) to ensure that no data is lost.

[0091] In this embodiment, the remote management platform includes a scenario policy library and a policy distribution engine, wherein:

[0092] The scenario strategy library stores a variety of predefined strategy templates in the form of a database. Each strategy template corresponds to a monitoring scenario. The strategy template includes at least: a set of alarm thresholds for environmental parameters for the corresponding monitoring scenario, a logic diagram of the linkage between devices, a list of business priorities for each monitoring device, and recommended energy efficiency management parameters.

[0093] Understandably, the scenario strategy library stores various predefined strategy templates in the form of a database. Each template precisely matches a typical monitoring scenario, such as "urban traffic monitoring," "coal mine production monitoring," and "safe city security monitoring." The template contains four core components: a set of environmental parameter alarm thresholds (e.g., upper and lower alarm limits for temperature, humidity, and water immersion), a diagram of the linkage logic between devices (e.g., starting a temperature-controlled fan when the temperature is ≥50℃, cutting off power to non-core devices and triggering audible and visual alarms when water immersion occurs), a list of business priorities for each monitoring device (core devices are set to the highest priority), and recommended energy efficiency management parameters (e.g., light load judgment threshold, intermittent power supply cycle, etc.). Users can directly select a template without having to configure it from scratch.

[0094] The policy delivery engine provides a graphical policy editing interface, allowing users to modify or completely customize new policies based on templates. The policy delivery engine compiles the edited policies into a binary instruction set or structured configuration file that can be recognized and executed by the core controller, and delivers them to one or more designated intelligent monitoring units through the communication transmission unit.

[0095] Understandably, the policy delivery engine provides a graphical policy editing interface, supporting two configuration methods: one is to modify parameters based on an existing template (such as adjusting the temperature alarm threshold), and the other is to completely customize a new policy (supporting drag-and-drop configuration of linkage logic, requiring no professional programming knowledge). After editing, the engine compiles the policy into a binary instruction set or a JSON-formatted structured configuration file that the core controller can recognize, ensuring that the front end can accurately parse and execute it.

[0096] Users can choose to precisely deploy to a single intelligent monitoring unit, or batch deploy to multiple intelligent monitoring units in the same area or scenario. After successful deployment, the platform provides real-time confirmation information, and the core controller automatically updates its local policy and takes effect immediately. This module's design allows the system to quickly adapt to the environmental characteristics and business needs of different scenarios, significantly reducing manual configuration costs and avoiding false alarms and missed alarms caused by fixed parameters.

[0097] In this embodiment, the remote management platform further includes a fault prediction center, which is used to receive and store the device status time-series data reported by all intelligent monitoring units; the fault prediction center uses a machine learning model to perform trend analysis on the time-series data to predict the probability and time window of failure of specific electrical components or functional modules, and generates early warning information.

[0098] Specifically, the core data foundation of the fault prediction center is the time-series data of equipment status reported by all intelligent monitoring units, including voltage / current fluctuation data of intelligent power distribution modules, energy consumption data of metering chips, action records of protection units, and operating status data of linkage execution modules. The data retention period is no less than one year, providing sufficient samples for trend analysis.

[0099] The core algorithm uses an LSTM (Long Short-Term Memory) machine learning model, which is trained and optimized through a large amount of historical fault data and has the ability to mine time-series data trends: it continuously analyzes the stored real-time data, and when it detects feature changes, such as the frequency of current fluctuations in the power module increasing by more than 50% week-on-week or the leakage current of the surge protection module continuously rising to the preset warning threshold, the model will calculate the probability of the module failing and its remaining lifespan, with a prediction accuracy of no less than 90%, and generate warning information containing risk levels (high / medium / low).

[0100] When generating early warning information, the fault prediction center simultaneously performs the following operations:

[0101] Based on the identifier of the intelligent monitoring unit corresponding to the early warning information, retrieve its geographical location information and the corresponding operation and maintenance responsibility information; automatically generate a digital maintenance work order containing fault prediction details, equipment location, handling suggestions and responsible person, and push it to the work order management module of the remote management platform.

[0102] Specifically, after generating an early warning message, the system automatically retrieves the GPS location information of the intelligent monitoring unit, its maintenance responsibility area, and the contact information of the responsible person. It then integrates the fault prediction details (fault module, predicted fault time, and handling suggestions) to generate a standardized digital work order, which is then pushed to the platform's work order management module to ensure timely maintenance response.

[0103] In a preferred embodiment of this implementation, the remote management platform further includes an energy efficiency analysis engine, which is used to periodically statistically analyze the energy consumption data reported by all intelligent monitoring units, including:

[0104] By comparing the energy consumption differences of different intelligent monitoring units during the same period, inefficient nodes with abnormally high energy consumption per unit load can be identified.

[0105] Analyze the overall energy consumption pattern of a group of intelligent monitoring units in the same area over time.

[0106] Based on the analysis results, an energy efficiency analysis report is generated, and optimization suggestions are provided to the strategy delivery engine based on the findings in the report. These suggestions are used to adjust the energy efficiency management parameters of relevant intelligent monitoring units or to mark devices that may require hardware checks.

[0107] Understandably, the core function of the energy efficiency analysis engine is to periodically analyze the energy consumption data reported by all intelligent monitoring units. The analysis period supports three options by default: daily, weekly, and monthly, which users can customize. The analysis dimensions include the energy consumption statistics of a single intelligent monitoring unit (daily / weekly / monthly energy consumption, energy consumption per unit load), the overall energy consumption change pattern of a group of intelligent monitoring units in the same area (such as the difference in energy consumption between peak and off-peak hours), and the comparison of energy consumption in different scenarios (such as the energy consumption levels of urban traffic monitoring and coal mine production monitoring).

[0108] When the unit load energy consumption of a certain intelligent monitoring unit is more than 30% higher than that of other devices in the same scenario, it is automatically marked as an inefficient node, and the possible reasons for its high energy consumption are analyzed (such as unreasonable power supply strategy or hardware aging). At the same time, the change pattern of regional energy consumption over time is analyzed to provide a basis for strategy optimization.

[0109] The energy efficiency analysis report visually displays energy consumption data and energy-saving potential across various dimensions. Through optimization suggestions, it provides specific parameter adjustment recommendations to the policy delivery engine for inefficient nodes (such as reducing power supply to light loads and shortening intermittent power supply cycles). For changes in regional energy consumption, it suggests optimizing energy efficiency management parameters in scenario policies (such as extending device sleep time during off-peak hours at night). Optimization suggestions can be implemented in two ways: first, after user confirmation, the policy delivery engine automatically sends the optimization parameters to the corresponding intelligent monitoring unit without manual intervention; second, it marks devices requiring hardware checks, generates maintenance work orders, and reminds maintenance personnel to conduct on-site troubleshooting.

[0110] In addition, the remote management platform also provides a graphical monitoring interface that displays the real-time operating status (online / offline, power supply status, load level), internal environmental data, energy consumption data, alarm information, etc. of all intelligent monitoring units; it also supports electronic map integration, marking the location and status of intelligent monitoring units on the map (e.g., green for normal operation, yellow for warning, and red for fault).

[0111] In this embodiment, the communication transmission unit includes:

[0112] The platform communication channel is used for data transmission between the remote management platform and the intelligent monitoring unit. This channel uses a wired network as the primary link and is configured with a wireless network as the backup link.

[0113] The inter-node coordination channel is used for direct data interaction between multiple intelligent monitoring units. This channel is implemented using a wireless self-organizing network based on Mesh networking technology. Through the inter-node coordination channel, multiple intelligent monitoring units automatically form a logical backup cluster. When a node in the cluster goes offline for any reason, its pre-set backup node will automatically take over the task of receiving and temporarily storing its critical data through the inter-node coordination channel until the node is restored or maintenance personnel intervene.

[0114] Specifically, the communication transmission unit includes two independent channels. The first channel is the platform communication channel, which is specifically responsible for data transmission between the intelligent monitoring unit and the remote management platform. It adopts a dual-mode architecture with wired as the primary and wireless as backup. The primary link is fiber optic or Ethernet with a bandwidth of not less than 1000Mbps and a packet loss rate of ≤0.1%, suitable for high-speed transmission of conventional data (in-box environmental data, energy consumption data, control commands, etc.). The backup link is a 4G / 5G wireless network that supports full network compatibility and has a transmission rate of not less than 10Mbps. When the primary link is interrupted due to fiber breakage, equipment failure, or other reasons, the link detection module (integrated in the core controller) automatically switches to the backup link within 1 second to ensure the real-time uploading of fault alarm data and critical status data.

[0115] The second channel is the inter-node collaboration channel, used for direct data interaction between multiple intelligent monitoring units. It is implemented using a wireless self-organizing network based on Mesh networking technology, with a communication latency of ≤50ms. Multiple intelligent monitoring units deployed in the same area automatically form a logical backup cluster through this channel. Each intelligent monitoring unit has 1-2 neighboring intelligent monitoring units preset as backup nodes. When a node in the cluster goes offline due to power failure, malfunction, or other reasons, its preset backup nodes will automatically receive the offline node's critical data (such as video streams from core monitoring equipment) through this channel, temporarily store it, and upload it to the remote management platform until the offline node recovers or maintenance personnel intervene.

[0116] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0117] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. Those skilled in the art can make other variations or modifications based on the above description. It is neither necessary nor possible to exhaustively describe all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. An intelligent monitoring system based on scenario-based linkage and fault prediction, characterized in that, The intelligent monitoring unit is arranged in the intelligent equipment box of the monitoring site, and is used for collecting the internal environment data of the box and the data of the monitoring equipment connected thereto, and performing linkage control and power supply scheduling based on the received policy instruction or local rules. The remote management platform is used for scene-based policy configuration, artificial intelligence-based fault prediction and positioning, and global performance and energy optimization analysis, and issues a policy instruction to the intelligent monitoring unit. The communication transmission unit connects the intelligent monitoring unit and the remote management platform, and provides a cooperative communication link between a plurality of intelligent monitoring units. The intelligent monitoring unit comprises: 2.The intelligent monitoring system based on scene-based linkage and fault prediction of claim 1, wherein, The core controller adopts a multi-core embedded processor, and has a built-in linkage logic analysis unit and a local scheduling unit, which are used for coordinating the work of various modules in the intelligent monitoring unit, and executing the policy instruction from the remote management platform and the local preset rules. The box environment sensing module is connected with the core controller, and is used for collecting the environmental physical quantity in the intelligent equipment box. The device state sensing module is connected with the core controller, and is used for monitoring the electrical operating parameters of the connected monitoring equipment. The intelligent power distribution module is connected with the core controller, and provides a plurality of controlled alternating current power outputs, each of which has independent on-off control, power metering and circuit protection functions. The intelligent monitoring unit further comprises: 3.The intelligent monitoring system based on scene-based linkage and fault prediction of claim 2, characterized in that, The load analysis module is input-connected to the current sampling output of the device state sensing module, internally runs a real-time power calculation algorithm, and periodically calculates the instantaneous active power of each connected monitoring equipment. The load analysis module compares the calculated real-time power with a preset rated power threshold of the monitoring equipment, and dynamically divides the load state of each monitoring equipment into three levels of high load, normal load and light load. The load analysis module periodically reports the load state level and real-time power value of each monitoring equipment to the remote management platform through the core controller, and provides the local scheduling unit as a basis for local scheduling. The local scheduling unit is configured to execute the following fine energy management strategies based on the load state:

4. The intelligent monitoring system based on scene-based linkage and fault prediction according to claim 3, characterized in that, When a monitoring equipment is in a light load state, the intelligent power distribution module is controlled to reduce the output voltage of the power supply circuit or switch to an intermittent power supply mode. When the total load power exceeds a preset safety threshold, the intelligent power distribution module is controlled to cut off the power supply of the lowest priority equipment according to the preset priority order of the monitoring equipment. The intelligent monitoring unit further comprises:

5. The intelligent monitoring system based on scene-based linkage and fault prediction according to claim 2, characterized in that, The data temporary storage and forwarding module comprises a non-volatile memory and an independent communication processor. When the network connection between the communication transmission unit and the remote management platform is interrupted, the core controller automatically writes the key data collected by the box environment sensing module and the device state sensing module into the non-volatile memory for temporary storage. The communication processor continuously detects the network connection state, and once the communication with the remote management platform is restored, it automatically starts the resume transmission process to upload the temporarily stored data in chronological order and priority. The intelligent power distribution module specifically comprises:

6. The intelligent monitoring system based on scene-based linkage and fault prediction according to claim 2, characterized in that, ​ At least 5 groups of independently controllable AC 220V output ports, each group of ports with a maximum carrying current of not less than 8A, supporting on-off control with local hardware switches through remote network instructions; A precision metering chip integrated in each group of ports for real-time collection of voltage effective value, current effective value, active power and cumulative power consumption data of the port; An automatic reclosing protection unit built-in, providing under-voltage, over-voltage, leakage and over-current protection, and the action threshold of each protection function supports remote setting and adjustment through the remote management platform.

7. The intelligent monitoring system based on scene-based linkage and fault prediction according to any one of claims 1-6, characterized in that, The remote management platform includes a scene strategy library and a strategy issuing engine, wherein: The scene strategy library stores a plurality of predefined strategy templates in the form of a database, each strategy template corresponding to a monitoring scene, and the strategy template at least includes: a set of environmental parameter alarm thresholds for the corresponding monitoring scene, a linkage logic relationship diagram between devices, a business priority list of each monitoring device, and recommended energy efficiency management parameters; The strategy issuing engine provides a graphical strategy editing interface, allowing users to modify or completely customize new strategies based on templates; the strategy issuing engine compiles the edited strategy into a binary instruction set or structured configuration file that can be recognized and executed by the core controller, and issues it to one or more designated intelligent monitoring units through the communication transmission unit. 8.The intelligent monitoring system based on scene-based linkage and fault prediction of claim 7, wherein, The remote management platform further includes a fault prediction center, which is used to receive and store device state time series data reported by all intelligent monitoring units; the fault prediction center uses a machine learning model to analyze the trend of the time series data to predict the probability and time window of failure of a specific electrical component or functional module, and generates an early warning information; When generating the early warning information, the fault prediction center synchronously performs the following operations: According to the identifier of the intelligent monitoring unit corresponding to the early warning information, retrieve its geographic location information and operation and maintenance responsibility information; automatically generate a digital maintenance work order containing fault prediction details, device location, processing suggestions and responsible person, and push it to the work order management module of the remote management platform.

9. The intelligent monitoring system based on scene-based linkage and fault prediction of claim 7, wherein, The remote management platform further includes an energy efficiency analysis engine, which is used to periodically statistically analyze energy consumption data reported by all intelligent monitoring units, including: By comparing the energy consumption differences of different intelligent monitoring units in the same period, identify the inefficient nodes with abnormally high energy consumption under unit load; Analyze the overall energy consumption change pattern of a group of intelligent monitoring units in the same area over time; According to the analysis results, generate an energy efficiency analysis report, and based on the findings in the report, provide optimization suggestions for the strategy issuing engine for adjusting the energy efficiency management parameters of related intelligent monitoring units, or marking potential devices that need to be checked for hardware.

10. The intelligent monitoring system based on scene-based linkage and fault prediction of claim 7, wherein, The communication transmission unit includes: A platform communication channel for data transmission between the remote management platform and the intelligent monitoring unit, which uses wired network as the main link and configures wireless network as the backup link; Inter-node cooperative channel for direct data interaction between multiple intelligent monitoring units, which is realized by wireless self-organizing network based on Mesh networking technology, through which multiple intelligent monitoring units automatically form a logical backup cluster; when a node in the cluster is offline due to some reason, its pre-set backup node will automatically take over the reception and temporary storage of its key data through the inter-node cooperative channel until the node is restored or the operation and maintenance personnel intervene.

Images