Intelligent equipment remote monitoring management system based on Internet of Things

Abstract

The invention discloses an intelligent equipment remote monitoring and management system based on the Internet of Things, which relates to the technical field of equipment monitoring and management and comprises a multi-dimensional intelligent cooperation module, a self-adaptive dynamic optimization module and a real-time intelligent decision module based on edge calculation. The system is characterized in that the multi-dimensional intelligent cooperation module and the adaptive dynamic optimization module share data through a cloud database, and an optimization result of the adaptive dynamic optimization module is provided for the real-time intelligent decision module based on edge calculation. According to the invention, by designing the multi-dimensional intelligent cooperation module and the group intelligence optimization module based on equipment group behavior analysis, the functions of data sharing cooperation and load balancing resource optimization among equipment are realized, and the problems of equipment operation data isolation and incapability of information sharing cooperation response in a traditional system are solved; the cooperation and information sharing capability of the system is improved, the resource and load balance is optimized, and the overall stability and reliability of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment monitoring and management, and in particular to an intelligent equipment remote monitoring and management system based on the Internet of Things. Background Art

[0002] With the rapid development of industrial Internet of Things and intelligent manufacturing, remote monitoring and management systems for intelligent equipment have become increasingly important. Traditional equipment management systems usually rely on a single data collection, processing and analysis model, which makes it difficult to effectively cope with complex and changing environments and diverse equipment requirements. At the same time, with the increase in the number and types of equipment, problems such as management efficiency, energy consumption and equipment maintenance costs have gradually become prominent.

[0003] In order to improve the management efficiency of smart devices, optimize resource allocation and extend the service life of equipment, this application proposes a remote monitoring and management system for smart devices based on the Internet of Things, which integrates multiple technologies such as multi-dimensional intelligent collaboration, adaptive dynamic optimization, edge computing and environmental perception. It can realize information sharing and intelligent collaboration between devices, improve the system's adaptability and response speed, reduce energy consumption and carbon emissions while ensuring system stability and equipment operation safety, and promote green and environmentally friendly development.

[0004] Patent document CN113741357B discloses an intelligent management system and method for pressure detection based on the Internet of Things. The above patent achieves the goal of improving the level of remote monitoring and digital management of concrete pressure detection, and realizing scientific production scheduling management, traceable detection process, and clear equipment status. However, the above patent cannot realize the functions of data sharing and coordination between devices and load balancing resource optimization.

[0005] Patent document CN105404194B discloses an IoT-based smart toilet management system and a fault monitoring method thereof. The above patent realizes the IoT of products, remote monitoring and surveillance, proactive fault diagnosis and uploading to a designated server, but the above patent cannot dynamically adjust monitoring strategies and equipment parameters according to equipment status and environmental changes.

[0006] Patent document CN118444619B discloses an intelligent management system for borosilicate glass processing based on the Internet of Things. The above patent realizes the ability to promptly handle abnormal conditions of various types of operating equipment during the production process. The remote monitoring module uses the Internet of Things technology, and the intelligent control module allows remote access and operation, allowing managers to monitor the production status from anywhere and make necessary adjustments. However, the above patent cannot realize the local equipment's rapid processing and analysis of data and emergency decision-making and adjustment functions.

[0007] Patent document CN114281048B discloses an AGV intelligent management system based on the Industrial Internet. The above patent realizes key data that can be used for online real-time monitoring of AGVs, provides two-way services for customers and AGV projects, is conducive to AGV fault diagnosis and analysis, and is of promoting significance for improving the AGV life cycle; through the remote interactive control function, AGVs can be remotely monitored and data viewed, but the above patent cannot realize abnormal analysis and processing of equipment monitoring and operating power adjustment functions.

[0008] In summary, the above patents cannot realize the functions of data sharing and coordination between devices and load balancing resource optimization, dynamic adjustment of monitoring strategies and device parameters according to device status and environmental changes, local rapid processing and analysis of data and emergency decision-making and adjustment functions, and abnormal analysis and processing of device monitoring and operating power adjustment functions, resulting in increased energy consumption, unstable system operation, response delays and shortened service life of smart devices; To this end, the present application proposes an intelligent device remote monitoring and management system based on the Internet of Things that can realize data sharing collaboration and load balancing resource optimization among devices, dynamically adjust monitoring strategies and device parameters according to device status and environmental changes, quickly process and analyze data locally and make emergency decisions and adjust equipment monitoring exceptions, and adjust operating power. Summary of the invention

[0009] The purpose of the present invention is to provide a remote monitoring and management system for intelligent devices based on the Internet of Things, so as to solve the technical problems proposed in the above-mentioned background technology that the functions of data sharing and coordination among devices and load balancing resource optimization, dynamic adjustment of monitoring strategies and equipment parameters according to equipment status and environmental changes, local rapid processing and analysis of data and emergency decision-making adjustment functions of equipment, and abnormal analysis and processing of equipment monitoring and operating power adjustment functions cannot be realized, resulting in increased energy consumption, unstable system operation, response delays and shortened service life of intelligent devices.

[0010] To achieve the above object, the present invention provides the following technical solution: a remote monitoring and management system for intelligent devices based on the Internet of Things, comprising a multi-dimensional intelligent collaboration module, an adaptive dynamic optimization module and a real-time intelligent decision-making module based on edge computing, characterized in that: the multi-dimensional intelligent collaboration module and the adaptive dynamic optimization module share data through a cloud database, and the optimization result of the adaptive dynamic optimization module is provided to the real-time intelligent decision-making module based on edge computing; The multi-dimensional intelligent collaboration module is used to obtain the status information of nearby devices and dynamically adjust its own operating parameters; the multi-dimensional intelligent collaboration module provides the functions of intelligent data sharing, adaptive collaboration algorithm and event-driven automatic collaboration among devices; The intelligent data sharing between devices means that each device shares energy consumption, temperature and electromagnetic interference data with nearby devices through the cloud database according to its own operating status and environmental conditions; the adaptive collaboration algorithm means that the system adopts an adaptive multi-device collaboration algorithm to analyze the data consistency and differences in the device group, and dynamically judge and select the optimal data source; the event-driven automatic collaboration means that when a device detects an abnormal event / load change, the collaboration mode is triggered, and the device will send a collaboration request to the nearby device.

[0011] Preferably, the adaptive dynamic optimization module is used to analyze the equipment operating environment and data characteristics in real time, and automatically adjust the monitoring strategy and analysis model; The adaptive dynamic optimization module provides dynamic monitoring frequency adjustment, adaptive analysis model and personalized monitoring strategy; Dynamic monitoring frequency adjustment means that the system intelligently adjusts the monitoring frequency according to the working status of the equipment and the real-time operating environment; the adaptive analysis model means that the system introduces an adaptive analysis model library, and dynamically switches the analysis model through a deep learning algorithm according to the operating modes and environmental changes of different devices; the personalized monitoring strategy means that based on historical data and equipment types, the adaptive optimization module can formulate personalized monitoring strategies for different devices.

[0012] Preferably, the real-time intelligent decision-making module based on edge computing introduces edge computing function in each device, so that the device has autonomous real-time intelligent decision-making capability, and performs intelligent analysis and rapid response of local data; The real-time intelligent decision-making module based on edge computing provides localized data analysis, distributed anomaly detection and real-time response mechanism; Localized data analysis means that each device has a built-in lightweight edge computing module that can perform preliminary data analysis and anomaly detection locally; distributed anomaly detection means that the system uses the distributed structure between devices, and each device performs dual detection on the abnormal status of adjacent devices; real-time response mechanism means that after the device detects an anomaly locally, it autonomously executes the preset emergency response plan.

[0013] Preferably, the adaptive dynamic optimization module is connected to a scene perception module based on environment adaptation through IoT data sharing, and the scene perception module based on environment adaptation is used to actively identify the external environment in which the device is located and adjust the monitoring strategy according to the scene; The scene perception module based on environmental adaptation includes: multi-dimensional environmental sensors, scene adaptation algorithms and adaptive strategy libraries; Multi-dimensional environmental sensors mean that each device is integrated with environmental sensors, including light, temperature and humidity, noise and vibration sensors, which can perceive changes in the surrounding environment in real time; the scene adaptation algorithm means that the system's built-in scene recognition algorithm can classify different scenes according to the data collected by the multi-dimensional environmental sensors, including indoor and outdoor, high and low temperature, and high and low humidity scenes; the adaptive strategy library means that the system has a set of strategy libraries for different scenarios, and each scene corresponds to a set of preset monitoring parameters and thresholds.

[0014] Preferably, the edge computing-based real-time intelligent decision-making module is connected to a scenario-based intelligent decision-making engine in the system through an Internet of Things database, and the scenario-based intelligent decision-making engine is used to dynamically adjust the decision-making plan according to the real-time scenario of the device; The scenario-based intelligent decision engine provides scenario classification, dynamic decision matrix and real-time intelligent adjustment functions; Scenario classification means that the system uses data clustering algorithms to classify the device operating status, environmental information and load conditions, and triggers different decision-making plans in different scenarios; the dynamic decision matrix means that a dynamic decision matrix is ​​built into the system, which matches the optimal device control parameters including operating mode, transmission frequency and power consumption level according to the scenario classification results and the current status of the device.

[0015] Preferably, the multi-dimensional intelligent collaboration module is connected to a group intelligent optimization module based on device group behavior analysis through IoT data sharing, and the group intelligent optimization module based on device group behavior analysis is used to optimize the overall system management by analyzing the group behavior patterns of multiple devices; The group intelligence optimization module based on device group behavior analysis provides device group behavior analysis, distributed group control and automated group response functions; Equipment group behavior analysis means that the system analyzes the group behavior of multiple devices through clustering and pattern recognition algorithms. The group behavior includes working sequence, energy consumption pattern and abnormal fluctuation, identifies the behavior pattern in the group, and discovers the overall operation rules at the system level; distributed group control means that based on the results of equipment group behavior analysis, the system performs load balancing and resource optimization among devices; automated group response means that when overall abnormalities are detected, including group equipment overload and excessive group energy consumption, the system automatically optimizes the response at the group level.

[0016] Preferably, the real-time intelligent decision-making module based on edge computing is connected to an intelligent repair module based on anomaly identification and fault root cause analysis through an Internet of Things database, and the intelligent repair module based on anomaly identification and fault root cause analysis is used to perform anomaly identification, fault root cause analysis and self-repair on the equipment; The intelligent repair module based on anomaly identification and fault root cause analysis includes: abnormal feature extraction, fault root cause analysis and intelligent repair operations; Abnormal feature extraction means extracting abnormal features in equipment operation through data mining algorithms to form an abnormal pattern library; fault root cause analysis means that after the system detects an abnormality, it triggers the fault root cause analysis algorithm to locate possible sources of faults by analyzing the equipment's operating data and status history, and provides a diagnostic report; intelligent repair operation means that when the cause of the fault is clear and can be repaired, the system triggers the intelligent repair operation, which includes restarting the equipment, adjusting parameters, and switching to spare components.

[0017] Preferably, the real-time intelligent decision-making module based on edge computing and the scene perception module based on environment adaptation are connected to a resource conservation and environmentally friendly management module based on intelligent analysis through an Internet of Things database, and the resource conservation and environmentally friendly management module based on intelligent analysis is used to perform green management through dynamic resource optimization, energy consumption detection and environmental protection index control; The resource conservation and environmentally friendly management module based on intelligent analysis provides dynamic energy consumption monitoring and control, intelligent resource allocation and carbon emission tracking functions; Dynamic energy consumption monitoring and control means that the system monitors the energy consumption level of each device in real time, and dynamically adjusts power and resource allocation according to the actual operation of the equipment; intelligent resource allocation means predicting the operating load of each device based on the results of group behavior analysis and optimizing resource allocation; carbon emission tracking means that the system integrates a carbon emission monitoring module, which can estimate carbon emission energy based on the operating energy consumption and environmental conditions of the equipment, and provide environmental protection data and energy-saving operations.

[0018] Preferably, the multi-dimensional intelligent collaboration module provides comprehensive environmental and status data for the scenario-based intelligent decision-making engine, the adaptive dynamic optimization module optimizes the monitoring strategy through analysis of environmental data, and provides the optimization results to the real-time intelligent decision-making module based on edge computing.

[0019] Preferably, the data stream of the multi-dimensional intelligent collaboration module is used as the data analysis input of the anomaly identification and fault root cause analysis module, and the scene perception module based on environmental adaptation provides the adaptive dynamic optimization module with an optimization strategy for scene data application adaptation.

[0020] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention realizes the functions of data sharing and coordination among devices and load balancing resource optimization by designing a multi-dimensional intelligent collaboration module and a group intelligent optimization module based on device group behavior analysis, solves the problems of isolated device operation data and inability to share information and coordinate responses in traditional systems, improves the system's collaboration and information sharing capabilities, optimizes resources and load balancing, and improves the overall stability and reliability of the system; 2. The present invention is designed with an adaptive dynamic optimization module and a scene perception module based on environmental adaptation, which realizes dynamic adjustment of monitoring strategies and equipment parameters according to equipment status and environmental changes, solves the problem that fixed monitoring strategies cannot be flexibly adjusted according to environmental changes, resulting in low monitoring efficiency and poor equipment operation effect, reduces unnecessary monitoring frequency, reduces system energy consumption, prolongs equipment life, and improves system adaptability; 3. The present invention is designed with a real-time intelligent decision-making module based on edge computing and a scenario-based intelligent decision-making engine, which realizes the local rapid processing and analysis of data and emergency decision-making and adjustment functions of the device, solves the problem of response delay caused by relying on cloud-based centralized computing, which makes it difficult to deal with emergency situations, improves the system response speed, reduces the data transmission burden, and improves the system stability and flexibility; 4. The present invention realizes the abnormal analysis and processing of equipment monitoring and the operation power adjustment function by designing an abnormality identification and fault root cause analysis module and a resource conservation and environmentally friendly management module based on intelligent analysis, solves the problem that traditional systems are difficult to detect abnormalities in time and locate and process them that affect system stability, improves equipment operation efficiency, and significantly reduces carbon emissions and energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic diagram of the remote monitoring management process of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] See also Figure 1 , an embodiment provided by the present invention: a remote monitoring and management system for intelligent devices based on the Internet of Things, comprising a multi-dimensional intelligent collaboration module, an adaptive dynamic optimization module and a real-time intelligent decision-making module based on edge computing, characterized in that: the multi-dimensional intelligent collaboration module and the adaptive dynamic optimization module share data through a cloud database, and the optimization result of the adaptive dynamic optimization module is provided to the real-time intelligent decision-making module based on edge computing; The multi-dimensional intelligent collaboration module is used to obtain the status information of nearby devices and dynamically adjust its own operating parameters; the multi-dimensional intelligent collaboration module provides the functions of intelligent data sharing, adaptive collaboration algorithm and event-driven automatic collaboration among devices; The intelligent data sharing between devices means that each device shares the energy consumption, temperature and electromagnetic interference data with adjacent devices through the cloud database according to its own operating status and environmental conditions; the adaptive collaboration algorithm means that the system adopts an adaptive multi-device collaboration algorithm to analyze the data consistency and differences in the device group, and dynamically judge and select the optimal data source; the event-driven automatic collaboration means that when a device detects an abnormal event / load change, the collaboration mode is triggered, and the device will send a collaboration request to the adjacent device; The multi-dimensional intelligent collaboration module is connected to a group intelligent optimization module based on device group behavior analysis through IoT data sharing. The group intelligent optimization module based on device group behavior analysis is used to optimize the overall system management by analyzing the group behavior patterns of multiple devices. The group intelligence optimization module based on device group behavior analysis provides device group behavior analysis, distributed group control and automated group response functions; Equipment group behavior analysis means that the system analyzes the group behavior of multiple devices through clustering and pattern recognition algorithms. Group behavior includes working sequence, energy consumption mode and abnormal fluctuation, identifies the behavior pattern in the group, and finds the overall operation law at the system level; distributed group control means that based on the results of equipment group behavior analysis, the system performs load balancing and resource optimization among devices; automated group response means that when overall abnormalities are detected, including group equipment overload and excessive group energy consumption, the system automatically optimizes the response at the group level; Furthermore, after the system is started, each device is monitored through a multi-dimensional intelligent collaboration module, such as recording the device's energy consumption, temperature, and electromagnetic interference data. These data are uploaded to the cloud database every 5 seconds to ensure real-time synchronization and storage of data. The multi-dimensional intelligent collaboration module continuously monitors device data and analyzes the real-time operating status of the device. For example, if device A detects that the temperature of the adjacent device B has risen significantly, the cooling demand may increase. The multi-dimensional intelligent collaboration module of device A can determine whether it needs to adjust its own load or operating parameters in advance to reduce electromagnetic interference with B. If device B is abnormal, such as the temperature exceeds the set threshold during operation, the event-driven collaborative response mechanism is triggered, and device B sends a collaboration request to the surrounding devices to respond to the abnormality. At this time, nearby devices such as devices A and C make adjustments based on the request and appropriately reduce the operating power to reduce the risk of overall temperature rise. The group intelligence optimization module based on equipment group behavior analysis adopts clustering and pattern recognition algorithms to analyze all equipment data collected from the cloud and identify the behavior patterns of each equipment group, including working sequence, energy consumption fluctuations and frequency of abnormal events. In the case of uneven load on the production line, the group intelligence optimization module based on equipment group behavior analysis balances the load of each device according to the analysis results. Assuming that the loads of devices A and B are high, while device C is relatively idle, the system will appropriately allocate some work tasks to C, so as to achieve optimal allocation of resources. If it is detected that the overall energy consumption of the system is high, such as the group temperature and current exceed the preset thresholds, the system automatically executes a response mechanism at the group level. For example, the system switches low-priority devices to standby mode, or reduces the power output of some devices to solve the overall energy consumption problem. This group optimization reduces energy consumption while ensuring production efficiency, thus achieving environmental protection and energy-saving goals.

[0024] See also Figure 1 , an embodiment provided by the present invention: a remote monitoring and management system for intelligent devices based on the Internet of Things, wherein the adaptive dynamic optimization module is used to analyze the device operating environment and data characteristics in real time, and automatically adjust the monitoring strategy and analysis model; The adaptive dynamic optimization module provides dynamic monitoring frequency adjustment, adaptive analysis model and personalized monitoring strategy; Dynamic monitoring frequency adjustment means that the system intelligently adjusts the monitoring frequency according to the working status and real-time operating environment of the equipment; Adaptive analysis model means that the system introduces an adaptive analysis model library, and dynamically switches the analysis model through deep learning algorithms according to the operating modes and environmental changes of different equipment; Personalized monitoring strategy means that based on historical data and equipment types, the adaptive optimization module can formulate personalized monitoring strategies for different equipment; The adaptive dynamic optimization module is connected to a scene perception module based on environment adaptation through IoT data sharing, and the scene perception module based on environment adaptation is used to actively identify the external environment in which the device is located and adjust the monitoring strategy according to the scene; The scene perception module based on environmental adaptation includes: multi-dimensional environmental sensors, scene adaptation algorithms and adaptive strategy libraries; Multi-dimensional environmental sensors are integrated on each device, including light, temperature and humidity, noise and vibration sensors, to sense changes in the surrounding environment in real time; scene adaptive algorithms are built-in scene recognition algorithms that can classify different scenes according to the data collected by multi-dimensional environmental sensors, including indoor and outdoor, high and low temperature, high and low humidity scenes; adaptive strategy library is a set of strategy libraries for different scenarios, and each scenario corresponds to a set of preset monitoring parameters and thresholds; Furthermore, the system sets basic monitoring frequencies for different devices, such as collecting temperature and energy consumption data once every minute and motion status data every 30 seconds. When the device has a large temperature rise, the adaptive dynamic optimization module determines the abnormal working state based on the real-time monitoring data and automatically increases the monitoring frequency, such as adjusting the temperature monitoring frequency to once every 10 seconds, so that the system can track the temperature rise more timely. Since the device operation mode will change with events, task volume and environmental changes, the system dynamically switches the model through the deep learning algorithm in the adaptive analysis model library. In low load mode, the system selects the "low power mode". The analysis model makes lightweight predictions on energy consumption and temperature changes. In high-load mode, the system switches to the "high-precision monitoring mode" model to conduct detailed analysis of temperature, current fluctuations and other key parameters, improve sensitivity to anomalies, and ensure the safety of equipment under high-intensity tasks. Based on the historical operation data of each device and the characteristics of different types of equipment, the system formulates personalized monitoring strategies for each device. The system analyzes the historical data of each device through a deep learning algorithm and dynamically adjusts monitoring parameters, such as setting a more sensitive temperature alarm threshold for devices with easily fluctuating temperatures, and reducing the monitoring frequency for low-frequency devices to save energy. Environmental sensors are integrated on each device to collect data about the environment around the device, including optical fiber, temperature and humidity, noise and vibration, etc., and upload the data to the system. The scene adaptive algorithm identifies the scene type of the device based on the data of the environmental sensor. For example, the system determines that the warehouse equipment is in a "high temperature and high humidity" environment and classifies it as a "high temperature and high humidity scene". This information is transmitted to the adaptive dynamic optimization module to activate the high-frequency monitoring mode in this scene. If the system detects strong noise and vibration signals near the device, the scene adaptive algorithm identifies the "vibration interference scene" and activates a specific monitoring strategy to ensure that the device is not affected by strong vibration. In the "high temperature and high humidity" scene, the adaptive strategy library will enable a lower temperature alarm threshold (for example, 40°C) for the device and increase the sampling frequency of temperature and humidity. In the "vibration interference" scene, the system reduces the power output of the device to reduce possible interference and starts a reinforced fault detection algorithm to monitor the device status. The linkage between the adaptive dynamic optimization module and the environmental perception module improves the operating stability and response speed of the device in complex environments, reduces the risk of equipment failure, and reduces energy consumption.

[0025] See also Figure 1 , an embodiment provided by the present invention: a remote monitoring and management system for intelligent devices based on the Internet of Things, wherein the real-time intelligent decision-making module based on edge computing introduces edge computing functions into each device, so that the device has autonomous real-time intelligent decision-making capabilities, and performs intelligent analysis and rapid response of local data; The real-time intelligent decision-making module based on edge computing provides localized data analysis, distributed anomaly detection and real-time response mechanism; Localized data analysis means that each device has a built-in lightweight edge computing module, which can perform preliminary data analysis and anomaly detection locally; distributed anomaly detection means that the system uses the distributed structure between devices, and each device performs dual detection of the abnormal status of adjacent devices; real-time response mechanism means that after the device detects an anomaly locally, it autonomously executes the preset emergency treatment plan; The edge computing-based real-time intelligent decision-making module is connected to a scenario-based intelligent decision-making engine in the system through an IoT database, and the scenario-based intelligent decision-making engine is used to dynamically adjust the decision-making plan according to the real-time scenario of the device; The scenario-based intelligent decision engine provides scenario classification, dynamic decision matrix and real-time intelligent adjustment functions; Scenario classification means that the system uses data clustering algorithms to classify the device operating status, environmental information and load conditions, triggering different decision plans in different scenarios; dynamic decision matrix means that a dynamic decision matrix is ​​built into the system, which matches the optimal device control parameters including operating mode, transmission frequency and power consumption level according to the scenario classification results and the current status of the device; Furthermore, each device has a built-in lightweight edge computing module, which has the ability to analyze local data and respond quickly. For example, the device monitors its own current, temperature and vibration data in real time through the edge computing module. During normal operation, the system collects data every 10 seconds and analyzes it locally to generate an operation trend report. The edge computing module realizes data sharing through the Internet of Things network, so that devices can collaborate on abnormal analysis. For example, if device A detects abnormal vibration, it sends an abnormal reminder to the adjacent device B through the Internet of Things. Device B double confirms whether device A is indeed in an abnormal state based on its own detected data and the abnormal information received from device A. If both devices confirm that device A is in an abnormal state, the emergency response mechanism is triggered. The system uploads this information to the central database in the cloud and activates the preset emergency plan of device A, such as adjusting power or entering protection mode to avoid further damage. When the edge computing module detects an abnormal device, the system will autonomously execute the preset emergency treatment plan locally on the device. For example, when a handling robot detects that the temperature is too high, the system will automatically reduce its operating speed to reduce the heat generated, and re-check whether the temperature has dropped to a safe range within 1 minute. Assuming that the system temporarily loses network connection, the edge computing module of the device can still operate independently and perform local emergency processing. For example, when an automatic sorting machine detects abnormal vibration in an offline state, the edge computing module will immediately switch to low-power mode and reduce the processing frequency to reduce the equipment load and ensure the basic safety of the equipment; Through cluster analysis, the system learns that the current device is in a "high load, high temperature" situation. The decision engine automatically matches the "frequency reduction and power consumption reduction" decision plan to reduce the device's operating frequency and power consumption level. When the "low load, normal temperature" situation is identified, the system matches the "high-efficiency mode" to increase the device's transmission frequency and power consumption level to improve production efficiency. The scenario intelligent decision engine matches the control parameters in the decision matrix based on the results of scenario classification and the current status of the device. For example: In the "high load" scenario, the system selects a lower power consumption level and reduces the operating frequency, thereby slowing down the temperature rise of the equipment and avoiding equipment damage caused by overheating. When the system detects that the device switches from the "high load" scenario to the "low load" scenario, the system automatically adjusts to the high-efficiency mode and increases the transmission frequency to ensure that high production efficiency can be maintained during low-load production periods. Through the distributed detection and local real-time response mechanism of edge computing, the equipment can respond quickly in abnormal situations and reduce the overall probability of system failure. The dynamic decision matrix selects the optimal operating parameters for the equipment, effectively reducing the excessive energy consumption and load pressure of the equipment and improving energy efficiency. The scenario intelligent decision engine can identify different equipment operating scenarios in real time and dynamically adjust equipment parameters to make the system more adaptable to complex situations in the production environment and improve production efficiency and safety.

[0026] See also Figure 1 , an embodiment provided by the present invention: a remote monitoring and management system for intelligent devices based on the Internet of Things, wherein the real-time intelligent decision-making module based on edge computing is connected to an intelligent repair module based on abnormality identification and fault root cause analysis through an Internet of Things database, and the intelligent repair module based on abnormality identification and fault root cause analysis is used to perform abnormality identification, fault root cause analysis and self-repair on the device; The intelligent repair module based on anomaly identification and fault root cause analysis includes: abnormal feature extraction, fault root cause analysis and intelligent repair operations; Abnormal feature extraction is to extract abnormal features in equipment operation through data mining algorithms to form an abnormal pattern library; fault root cause analysis is that after the system detects an abnormality, it triggers the fault root cause analysis algorithm to locate possible fault sources by analyzing the equipment's operating data and status history, and provides a diagnostic report; intelligent repair operation is that when the cause of the fault is clear and can be repaired, the system triggers the intelligent repair operation, which includes restarting the equipment, adjusting parameters, and switching to spare components; Furthermore, the edge computing module collects data such as temperature, vibration, power, and sensor feedback in real time during the operation of the equipment. When a sudden current rise or temperature fluctuation is detected, the edge computing module automatically triggers the abnormal feature extraction algorithm. The system uses a data mining algorithm to extract abnormal features from the data, such as the continuous rise mode of equipment temperature or the power overload fluctuation feature. After the abnormal feature extraction stage is completed, the system further confirms whether it is a real fault. The system marks it as a possible fault and starts the root cause analysis. The system analyzes the real-time data and historical status information of the equipment to find the potential root cause of the abnormality. For faults caused by overheating or temporary excessive load, the system automatically triggers a short shutdown and restart operation of the equipment to eliminate occasional faults. When the temperature of the equipment rises but there is no hardware damage, the system reduces the operating speed of the equipment or adjusts the power to reduce the equipment load and ensure continuous and stable operation. If the system detects that the fault source is a specific component and the equipment has a built-in spare component, the system automatically switches to the spare component to ensure the continuous operation of the equipment. After completing the repair operation, the system enters a short monitoring state to detect the repair effect and ensure that the fault will not recur.

[0027] See also Figure 1 , an embodiment provided by the present invention: a remote monitoring and management system for intelligent devices based on the Internet of Things, wherein the real-time intelligent decision-making module based on edge computing and the scene perception module based on environmental adaptation are connected to a resource conservation and environmentally friendly management module based on intelligent analysis through an Internet of Things database, and the resource conservation and environmentally friendly management module based on intelligent analysis is used to perform green management through dynamic resource optimization, energy consumption detection and environmental protection index control; The resource conservation and environmentally friendly management module based on intelligent analysis provides dynamic energy consumption monitoring and control, intelligent resource allocation and carbon emission tracking functions; Dynamic energy consumption monitoring and control means that the system monitors the energy consumption level of each device in real time, and dynamically adjusts the power and resource allocation according to the actual operation of the device; intelligent resource allocation means predicting the operating load of each device based on the results of group behavior analysis, and optimizing resource allocation; carbon emission tracking means that the system integrates a carbon emission monitoring module, which can estimate the carbon emission energy according to the operating energy consumption and environmental conditions of the equipment, and provide environmental protection data and energy-saving operations; The multi-dimensional intelligent collaboration module provides comprehensive environment and status data for the scenario-based intelligent decision engine. The adaptive dynamic optimization module optimizes the monitoring strategy through the analysis of environmental data and provides the optimization results to the real-time intelligent decision module based on edge computing. The data stream of the multi-dimensional intelligent collaboration module is used as the data analysis input of the anomaly identification and fault root cause analysis module, and the scene perception module based on environmental adaptation provides the adaptive dynamic optimization module with an optimization strategy for scene data application adaptation; Furthermore, the system obtains the energy consumption data of the equipment, including power consumption, current load, temperature, etc., through the real-time intelligent decision-making module based on edge computing. The module based on edge computing performs a preliminary local analysis of the data to quickly determine whether there is an abnormal energy consumption. When the system detects that the equipment enters idle or low-load mode, it automatically reduces the power output of the equipment to reduce energy consumption. All energy consumption data are shared with the resource-saving and environmentally friendly management module based on intelligent analysis through the Internet of Things database for global analysis. Based on the behavioral analysis and historical data of the equipment group, the system can predict the load fluctuations of each equipment during the production process. The resource-saving and environmentally friendly management module generates a resource allocation plan for each equipment based on the group behavior prediction results. The carbon emission tracking module of the system collects the energy consumption information of the equipment in real time, and estimates the carbon emissions of the equipment based on the equipment type, power consumption and usage time using the built-in carbon emission calculation model. Once the carbon emission level approaches the threshold, the system will obtain environmental data through the scene perception module based on environmental adaptation to determine whether there is a possibility of reducing power or performing shift operations. The system optimizes control based on the judgment results and provides environmental protection data to the management end so that managers can further supervise and adjust production plans.

[0028] Working principle: First, the multi-dimensional intelligent collaboration module collects and integrates the operating status and environmental data of the equipment in real time, and shares the data among the equipment to provide a comprehensive information foundation; Then, the adaptive dynamic optimization module dynamically adjusts the monitoring strategy and operating parameters of each device according to the real-time status of the device and environmental changes to ensure that the system is always in the best state. For emergencies and emergencies, the edge computing module quickly analyzes and makes decisions locally to ensure response speed. Finally, the system analyzes the group behavior of devices through a group intelligence optimization module based on device group behavior analysis, balances the load and optimizes resource allocation, thereby achieving collaborative work of devices and efficient operation of the system.

[0029] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A remote monitoring and management system for intelligent devices based on the Internet of Things, including a multi-dimensional intelligent collaboration module, an adaptive dynamic optimization module and a real-time intelligent decision-making module based on edge computing, characterized in that: The multi-dimensional intelligent collaboration module and the adaptive dynamic optimization module share data through a cloud database, and the optimization result of the adaptive dynamic optimization module is provided to the real-time intelligent decision-making module based on edge computing; The multi-dimensional intelligent collaboration module is used to obtain the status information of nearby devices and dynamically adjust its own operating parameters; the multi-dimensional intelligent collaboration module provides the functions of intelligent data sharing, adaptive collaboration algorithm and event-driven automatic collaboration among devices; The intelligent data sharing between devices means that each device shares energy consumption, temperature and electromagnetic interference data with nearby devices through the cloud database according to its own operating status and environmental conditions; the adaptive collaboration algorithm means that the system adopts an adaptive multi-device collaboration algorithm to analyze the data consistency and differences in the device group, and dynamically judge and select the optimal data source; the event-driven automatic collaboration means that when a device detects an abnormal event / load change, the collaboration mode is triggered, and the device will send a collaboration request to the nearby device.

2. According to claim 1, the remote monitoring and management system for intelligent devices based on the Internet of Things is characterized by: The adaptive dynamic optimization module is used to analyze the equipment operating environment and data characteristics in real time and automatically adjust the monitoring strategy and analysis model; The adaptive dynamic optimization module provides dynamic monitoring frequency adjustment, adaptive analysis model and personalized monitoring strategy; Dynamic monitoring frequency adjustment means that the system intelligently adjusts the monitoring frequency according to the working status of the equipment and the real-time operating environment; the adaptive analysis model means that the system introduces an adaptive analysis model library, and dynamically switches the analysis model through a deep learning algorithm according to the operating modes and environmental changes of different devices; the personalized monitoring strategy means that based on historical data and equipment types, the adaptive optimization module can formulate personalized monitoring strategies for different devices.

3. According to the IoT-based smart device remote monitoring and management system of claim 1, it is characterized by: The real-time intelligent decision-making module based on edge computing introduces edge computing functions into each device, so that the device has the ability to make autonomous real-time intelligent decisions and perform intelligent analysis and rapid response of local data; The real-time intelligent decision-making module based on edge computing provides localized data analysis, distributed anomaly detection and real-time response mechanism; Localized data analysis means that each device has a built-in lightweight edge computing module that can perform preliminary data analysis and anomaly detection locally; distributed anomaly detection means that the system uses the distributed structure between devices, and each device performs dual detection on the abnormal status of adjacent devices; real-time response mechanism means that after the device detects an anomaly locally, it autonomously executes the preset emergency response plan.

4. According to claim 2, the remote monitoring and management system for intelligent devices based on the Internet of Things is characterized by: The adaptive dynamic optimization module is connected to a scene perception module based on environment adaptation through IoT data sharing, and the scene perception module based on environment adaptation is used to actively identify the external environment in which the device is located and adjust the monitoring strategy according to the scene; The scene perception module based on environmental adaptation includes: multi-dimensional environmental sensors, scene adaptation algorithms and adaptive strategy libraries; Multi-dimensional environmental sensors mean that each device is integrated with environmental sensors, including light, temperature and humidity, noise and vibration sensors, which can perceive changes in the surrounding environment in real time; the scene adaptation algorithm means that the system's built-in scene recognition algorithm can classify different scenes according to the data collected by the multi-dimensional environmental sensors, including indoor and outdoor, high and low temperature, and high and low humidity scenes; the adaptive strategy library means that the system has a set of strategy libraries for different scenarios, and each scene corresponds to a set of preset monitoring parameters and thresholds.

5. According to claim 3, the remote monitoring and management system for intelligent devices based on the Internet of Things is characterized by: The edge computing-based real-time intelligent decision-making module is connected to a scenario-based intelligent decision-making engine in the system through an IoT database, and the scenario-based intelligent decision-making engine is used to dynamically adjust the decision-making plan according to the real-time scenario of the device; The scenario-based intelligent decision engine provides scenario classification, dynamic decision matrix and real-time intelligent adjustment functions; Scenario classification means that the system uses data clustering algorithms to classify the device operating status, environmental information and load conditions, and triggers different decision-making plans in different scenarios; the dynamic decision matrix means that a dynamic decision matrix is ​​built into the system, which matches the optimal device control parameters including operating mode, transmission frequency and power consumption level according to the scenario classification results and the current status of the device.

6. The remote monitoring and management system for intelligent devices based on the Internet of Things according to claim 1 is characterized in that: The multi-dimensional intelligent collaboration module is connected to a group intelligent optimization module based on device group behavior analysis through IoT data sharing. The group intelligent optimization module based on device group behavior analysis is used to optimize the overall system management by analyzing the group behavior patterns of multiple devices. The group intelligence optimization module based on device group behavior analysis provides device group behavior analysis, distributed group control and automated group response functions; Equipment group behavior analysis means that the system analyzes the group behavior of multiple devices through clustering and pattern recognition algorithms. The group behavior includes working sequence, energy consumption pattern and abnormal fluctuation, identifies the behavior pattern in the group, and discovers the overall operation rules at the system level; distributed group control means that based on the results of equipment group behavior analysis, the system performs load balancing and resource optimization among devices; automated group response means that when overall abnormalities are detected, including group equipment overload and excessive group energy consumption, the system automatically optimizes the response at the group level.

7. According to claim 3, the remote monitoring and management system for intelligent devices based on the Internet of Things is characterized by: The real-time intelligent decision-making module based on edge computing is connected to an intelligent repair module based on anomaly identification and fault root cause analysis through an Internet of Things database. The intelligent repair module based on anomaly identification and fault root cause analysis is used to perform anomaly identification, fault root cause analysis and self-repair on the equipment; The intelligent repair module based on anomaly identification and fault root cause analysis includes: abnormal feature extraction, fault root cause analysis and intelligent repair operations; Abnormal feature extraction means extracting abnormal features in equipment operation through data mining algorithms to form an abnormal pattern library; fault root cause analysis means that after the system detects an abnormality, it triggers the fault root cause analysis algorithm to locate possible sources of faults by analyzing the equipment's operating data and status history, and provides a diagnostic report; intelligent repair operation means that when the cause of the fault is clear and can be repaired, the system triggers the intelligent repair operation, which includes restarting the equipment, adjusting parameters, and switching to spare components.

8. The remote monitoring and management system for intelligent devices based on the Internet of Things according to claim 3 is characterized by: The real-time intelligent decision-making module based on edge computing and the scene perception module based on environmental adaptation are connected to the resource conservation and environmentally friendly management module based on intelligent analysis through the Internet of Things database. The resource conservation and environmentally friendly management module based on intelligent analysis is used to perform green management through dynamic resource optimization, energy consumption detection and environmental protection index control; The resource conservation and environmentally friendly management module based on intelligent analysis provides dynamic energy consumption monitoring and control, intelligent resource allocation and carbon emission tracking functions; Dynamic energy consumption monitoring and control means that the system monitors the energy consumption level of each device in real time, and dynamically adjusts power and resource allocation according to the actual operation of the equipment; intelligent resource allocation means predicting the operating load of each device based on the results of group behavior analysis and optimizing resource allocation; carbon emission tracking means that the system integrates a carbon emission monitoring module, which can estimate carbon emission energy based on the operating energy consumption and environmental conditions of the equipment, and provide environmental protection data and energy-saving operations.

9. The remote monitoring and management system for intelligent devices based on the Internet of Things according to claim 1, characterized in that: The multi-dimensional intelligent collaboration module provides comprehensive environment and status data for the scenario-based intelligent decision-making engine. The adaptive dynamic optimization module optimizes the monitoring strategy through analysis of environmental data and provides the optimization results to the real-time intelligent decision-making module based on edge computing.

10. The remote monitoring and management system for intelligent devices based on the Internet of Things according to claim 1, characterized in that: The data stream of the multi-dimensional intelligent collaboration module is used as the data analysis input of the anomaly identification and fault root cause analysis module, and the scene perception module based on environmental adaptation provides the adaptive dynamic optimization module with an optimization strategy for scene data application adaptation.

Images