Method and system for judging abnormity of weak current equipment of Internet of Things

Abstract

The invention relates to a weak current equipment abnormity judgment method and system based on the Internet of Things. The method comprises the steps that multi-dimensional parameters such as temperature, current, voltage and vibration frequency are collected through nodes of the Internet of Things, and a dynamic tracking identifier is generated; performing dynamic parameter association analysis on edge nodes, and establishing a real-time coupling degree relationship between parameters; according to the analysis result, evaluating the abnormity level in a grading manner, and distinguishing the primary abnormity of single parameter deviation and the advanced abnormity of multi-parameter collaborative deviation; the cloud platform starts a differential verification mechanism for different levels of anomalies, primary anomalies are transversely compared, and advanced anomalies execute full-life-cycle backtracking verification; the system comprises a data acquisition module, an edge calculation module, an analysis and evaluation module and a cloud analysis platform, and can realize the method. According to the invention, through dynamic coupling degree analysis and a hierarchical verification mechanism, the abnormality judgment accuracy is remarkably improved, and false alarms caused by environmental interference are effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of weak current equipment detection based on the Internet of Things, and in particular to a method and system for determining abnormality of weak current equipment in the Internet of Things. Background Art

[0002] In the fields of smart buildings, industrial automation, etc., weak current equipment is a key infrastructure, and its stable operation is directly related to the reliability of the entire system. The current industry generally uses Internet of Things technology to monitor the status of weak current equipment, and deploys various sensors to collect equipment operating parameters in real time. However, this monitoring method faces a prominent problem: the traditional abnormality judgment method mainly relies on the threshold alarm mechanism of a single parameter. When a parameter is detected to exceed the preset threshold range, it is judged as abnormal. Although this method is simple and direct, it has obvious misjudgment problems. In the actual operating environment, weak current equipment often has parameter fluctuations due to factors such as ambient temperature fluctuations and instantaneous power interference. These fluctuations are often within the tolerance range of the equipment and will not cause actual failures, but frequently trigger false alarms.

[0003] Existing technologies attempt to improve this problem by introducing simple multi-parameter correlation analysis. For example, they monitor temperature and current parameters simultaneously, and only determine an abnormality when both exceed a threshold. However, this improvement remains at the static correlation level and cannot capture the complex dynamic coupling relationship between parameters. In particular, when early potential faults occur in the equipment, the various parameters often exhibit asynchronous and nonlinear change characteristics, causing existing methods to either miss real faults or continue to generate a large number of false alarms. Summary of the Invention

[0004] To this end, the technical problem to be solved by the present invention is to overcome the problem of abnormal detection of weak current equipment in the existing technology, provide a method and system for judging abnormalities of networked weak current equipment, improve the accuracy of abnormality judgment, and effectively filter out false alarms caused by other interference through dynamic coupling analysis.

[0005] To solve the above technical problems, the present invention provides a method for determining abnormality of weak current equipment in the Internet of Things, comprising the following steps:

[0006] The multi-dimensional operating parameters of the target weak current equipment are collected in real time through the IoT node network. The multi-dimensional operating parameters include at least temperature parameters, current parameters, voltage parameters and vibration frequency parameters. Each IoT node generates a unique dynamic tracking identifier for the collected data.

[0007] Transmit multi-dimensional operating parameters with dynamic tracking identifiers to edge computing nodes, where dynamic parameter correlation analysis is performed. This includes establishing a dynamic mapping relationship between current parameters and historical normal parameter ranges, calculating the real-time coupling between parameters, and analyzing the coupling change pattern of other related parameters when a parameter deviates from its historical normal range.

[0008] Based on the results of dynamic parameter correlation analysis, a hierarchical assessment of abnormality probability is performed: a phenomenon in which a single parameter deviates but the coupling degree remains normal is marked as a primary abnormality, and a phenomenon in which multiple parameters deviate in coordination and the coupling degree is abnormal is marked as a high-level abnormality. An assessment report is generated that includes the abnormality level and equipment status profile.

[0009] The assessment report is uploaded to the cloud analysis platform, which activates different levels of verification mechanisms based on the abnormality level: for primary abnormalities, horizontal comparison verification of similar devices is initiated; for high-level abnormalities, full life cycle retrospective verification of the equipment is initiated. The final abnormality judgment result is generated after eliminating the possibility of misjudgment through the verification mechanism.

[0010] In one embodiment of the present invention, the dynamic tracking identifier includes: a timestamp and device location information, wherein:

[0011] When performing dynamic parameter correlation analysis on the edge computing node, a parameter comparison library for device groups in the same area is first established based on the device location information in the dynamic tracking identifier, and then a parameter time series change trajectory is constructed based on the timestamp information.

[0012] When assessing the likelihood of anomalies, the system uses timestamp information to identify sudden or gradual deviations of parameters, and compares the operating status differences of devices in the same area based on device location information.

[0013] When verifying on the cloud analysis platform, similar devices in the same physical environment are selected for horizontal comparison based on the device location information, and the historical evolution trend of the device parameters is traced based on the timestamp information.

[0014] In one embodiment of the present invention, the process of establishing a dynamic mapping relationship between current parameters and historical normal parameter intervals and calculating the real-time coupling degree between the parameters includes:

[0015] Establish a dynamic parameter window at the edge computing node, cache current and historical parameter data in a sliding time block manner, and extract features of various parameters within each time block. The extracted features include but are not limited to: parameter fluctuation amplitude features, change rate features, periodic repetition features, and abnormal pulse features;

[0016] An adaptive correlation matrix is ​​used to construct a dynamic mapping relationship between parameters. Each element in the matrix represents the intensity of the coordinated change of the characteristic vectors of two parameters within a sliding time window. The implicit correlation between parameters is identified by tracking the evolution trend of the matrix elements in real time.

[0017] The coupling degree calculation is performed based on the adaptive correlation matrix. The calculation process includes: first identifying the dominant parameter and the following parameter in the parameter group, then analyzing the response delay time and amplitude matching of the following parameter when the dominant parameter changes, and finally comprehensively evaluating the real-time coupling strength between the parameters based on the response characteristics.

[0018] In one embodiment of the present invention, the process of establishing a dynamic mapping relationship further includes:

[0019] A parameter-adaptive benchmark model is established at the edge computing node. The environmental perception module collects temperature and humidity data of the device's environment in real time and encodes the environmental data into an environmental feature vector.

[0020] Activate the corresponding historical parameter sub-interval library according to the environmental feature vector, and store the sub-intervals according to different environmental conditions. Each sub-interval contains the parameter fluctuation range of at least three complete cycles of normal operation of the equipment under the environmental conditions;

[0021] Perform dynamic calibration of parameter intervals, and perform similarity matching between the current environment feature vector and the environment features of each sub-interval. When the matching degree exceeds the preset threshold, the sub-interval is used as the reference interval. Otherwise, the three sub-intervals with the highest matching degree are weighted and fused to generate a temporary reference interval.

[0022] When calculating the real-time coupling degree, a parameter deviation direction consistency factor is introduced. When multiple parameters deviate from their reference intervals upward or downward at the same time, the coupling degree calculation weight is increased. When the parameter deviation directions are inconsistent, the coupling degree calculation weight is reduced.

[0023] In one embodiment of the present invention, the device status portrait includes:

[0024] The parameter status matrix uses the physical structure diagram of the equipment as the base, marking the real-time status of the associated parameters at the corresponding component positions, including: temperature parameters, current parameters, voltage parameters and vibration frequency parameters;

[0025] The abnormal impact range map is based on the equipment electrical schematic diagram and mechanical connection diagram, and is marked with different color areas, including: directly affected core areas, possibly affected related areas, and currently normal isolation areas.

[0026] In one embodiment of the present invention, the process of initiating horizontal comparison and verification of similar devices for a primary anomaly includes:

[0027] Based on the installation location characteristics and functional attributes of the abnormal equipment, select the same model equipment with the same power distribution circuit, the same physical installation location, or recently maintained equipment from the equipment inventory library as the comparison object;

[0028] Collect the current operating parameters of the comparison objects and select the comparison objects that match the abnormal equipment working conditions as the valid comparison group;

[0029] Compare and analyze abnormal device parameters with the group fluctuation range of the effective comparison group, mark specific parameters that exceed the group range and analyze their correlation with the individual characteristics of the device;

[0030] Based on the comparison results, verification conclusions of group consistency abnormality, individual specific abnormality or gradual group abnormality are generated, which correspond to different judgments on environmental factors, equipment failure or early stage of systematic degradation.

[0031] In one embodiment of the present invention, the process of retrospective verification of the entire life cycle of a high-level abnormal startup device includes:

[0032] Integrate equipment factory benchmark parameters, previous maintenance records, historical abnormal data and environmental change characteristics to build a complete life cycle digital archive;

[0033] A hierarchical backtracking mechanism is used to sequentially perform short-term parameter gradient analysis, mid-term performance drift assessment, and full lifecycle benchmark comparison, forming a comprehensive diagnostic view covering different time scales;

[0034] Based on time series analysis and physical connection relationships, the propagation path of the first abnormal point is tracked to generate a fault evolution chain including spatiotemporal evolution characteristics and degradation acceleration;

[0035] The comprehensive retrospective analysis results output engineering decision conclusions including root cause determination, recoverability assessment, disposal priority recommendations and preventive measures plans.

[0036] In one embodiment of the present invention, the following steps are also included: according to the type and level of the final abnormality determination result, the corresponding control strategy is adaptively triggered, including: starting parameter fine-tuning instructions for primary abnormalities, starting equipment isolation instructions for high-level abnormalities and generating maintenance work orders.

[0037] To solve the above technical problems, the present invention further provides a weak current device abnormality judgment system for the Internet of Things, comprising:

[0038] A data acquisition module is used to collect multi-dimensional operating parameters of target weak current equipment in real time through the Internet of Things node network. The multi-dimensional operating parameters include at least temperature parameters, current parameters, voltage parameters and vibration frequency parameters. Each Internet of Things node is equipped with a dynamic identification generation unit for generating a unique dynamic tracking identification for the collected data;

[0039] an edge computing module, communicatively connected to the data acquisition module, configured to receive multi-dimensional operating parameters with dynamic tracking identifiers and perform correlation analysis on the dynamic parameters, including establishing a dynamic mapping relationship between the current parameters and historical normal parameter intervals, calculating the real-time coupling degree between the parameters, and analyzing the coupling degree change pattern of other related parameters when a parameter deviates from its historical normal interval;

[0040] A hierarchical assessment module, in communication with the edge computing module, is configured to perform hierarchical assessment of anomaly likelihood based on the results of dynamic parameter correlation analysis, marking a phenomenon in which a single parameter deviates but the coupling degree remains normal as a primary anomaly, and marking a phenomenon in which multiple parameters deviate in coordination and the coupling degree is abnormal as a high-level anomaly, and generating an assessment report including the anomaly level and a device status profile;

[0041] The cloud analysis platform is in communication with the edge computing module and is used to activate different levels of verification mechanisms according to the abnormality level in the assessment report, activate horizontal comparison verification of the same type of equipment for primary abnormalities, and activate full life cycle retrospective verification of the equipment for high-level abnormalities. The final abnormality judgment result is generated after eliminating the possibility of misjudgment through the verification mechanism.

[0042] In one embodiment of the present invention, it also includes: a control strategy execution module, which is in communication with the cloud analysis platform and adaptively triggers the corresponding control strategy according to the type and level of the final abnormality judgment result, including: starting parameter fine-tuning instructions for primary abnormalities, starting equipment isolation instructions for advanced abnormalities and generating maintenance work orders.

[0043] The above technical solution of the present invention has the following advantages over the prior art:

[0044] The method for determining abnormalities in weak-current devices in the Internet of Things (IoT) of the present invention performs dynamic parameter correlation analysis at edge computing nodes. Instead of viewing the limit violations of each parameter in isolation, an intelligent evaluation system based on the real-time coupling between parameters is established.

[0045] Specifically, when a parameter is detected to deviate from the historical normal range, the coupling change patterns of other related parameters will be analyzed synchronously. This dynamic correlation analysis can effectively distinguish normal fluctuations from real anomalies. For example, when the temperature parameter increases alone while related parameters such as current and vibration maintain a normal coupling relationship, it can be accurately judged that this may be a normal fluctuation caused by changes in ambient temperature. Conversely, when multiple parameters deviate collaboratively and the coupling degree is abnormal, it can be determined as a real equipment failure.

[0046] In addition, the intelligent classification of "primary anomalies" and "advanced anomalies" is introduced through a hierarchical assessment mechanism, which enables accurate identification of abnormal situations. The multi-level verification mechanism adopted by the cloud analysis platform provides double protection for the judgment results, and differentiated verification processes are initiated for different levels of anomalies, which not only ensures the accuracy of judgment but also optimizes the allocation of system resources.

[0047] From the technical effect point of view, the abnormality judgment method of weak-current equipment in the Internet of Things of the present invention significantly improves the accuracy of abnormality judgment, and effectively filters out false alarms caused by environmental interference through dynamic coupling analysis; at the same time, the hierarchical evaluation mechanism can detect potential fault signs early and avoid small faults from turning into big problems; through the collaborative processing architecture of edge computing and cloud platform, it takes into account the real-time requirements while ensuring the analysis accuracy, providing a complete solution for the intelligent operation and maintenance of weak-current equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below based on specific embodiments of the present invention in conjunction with the accompanying drawings, wherein:

[0049] Figure 1 This is a flowchart of the steps of the method for determining abnormality of weak current equipment in the Internet of Things of the present invention;

[0050] Figure 2 This is a flowchart of the steps of constructing a dynamic mapping relationship and calculating a real-time coupling degree according to the present invention;

[0051] Figure 3 This is a flowchart of the steps for solving the impact of the environment on abnormal judgment of weak current equipment when constructing a dynamic mapping relationship in the present invention;

[0052] Figure 4 It is a flow chart of the steps of the present invention for horizontal comparison and verification of primary abnormal startup of the same type of equipment;

[0053] Figure 5 This is a flowchart of the steps of the present invention for retrospective verification of the entire life cycle of advanced abnormal startup equipment;

[0054] Figure 6 This is a structural framework diagram of the weak current equipment abnormality judgment system of the Internet of Things of the present invention. DETAILED DESCRIPTION

[0055] The present invention will be further described below with reference to the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it. However, the embodiments are not intended to limit the present invention.

[0056] Reference Figure 1 As shown, the present invention discloses a method for determining abnormality of weak current equipment in the Internet of Things, comprising the following steps:

[0057] S10. Collect multi-dimensional operating parameters of the target weak current equipment in real time through the Internet of Things node network. The multi-dimensional operating parameters include at least temperature parameters, current parameters, voltage parameters, and vibration frequency parameters. Each Internet of Things node generates a unique dynamic tracking identifier for the collected data.

[0058] In this embodiment, the collection of multi-dimensional operating parameters breaks through the limitations of traditional single parameter monitoring. Through the synchronous collection of multi-dimensional parameters, a comprehensive data basis is provided for subsequent analysis. Compared with the existing technology that only focuses on a few key parameters, this multi-dimensional data collection method can capture a complete portrait of the equipment's operating status. In particular, the introduction of non-traditional monitoring parameters such as vibration frequency can detect potential failures of mechanical components earlier; at the same time, the addition of dynamic tracking identification ensures the traceability of data during transmission and processing, creating conditions for data correlation analysis across nodes and time periods.

[0059] S20, transmitting the multi-dimensional operating parameters with dynamic tracking identifiers to the edge computing node, and performing dynamic parameter correlation analysis at the edge computing node, specifically including: establishing a dynamic mapping relationship between the current parameters and the historical normal parameter range, calculating the real-time coupling degree between the parameters, and when a parameter deviates from its historical normal range, analyzing the coupling degree change pattern of other related parameters;

[0060] Traditional methods usually perform simple threshold comparisons in the cloud, but this solution establishes a dynamic mapping relationship between current parameters and historical normal ranges on the edge side, and calculates the real-time coupling degree between each parameter; its working principle is to establish a dynamic model through machine learning to analyze the interaction relationship between parameters in real time. When a parameter deviates from the normal range, the system will not immediately alarm, but will further analyze the coupling degree change pattern of other related parameters.

[0061] This processing method has significant advantages: on the one hand, edge computing reduces data transmission delays, making analysis more timely; on the other hand, dynamic coupling analysis can identify nonlinear relationships between parameters, which is completely impossible with the fixed threshold method; for example, some faults may initially manifest as slight changes in multiple parameters at the same time. Each parameter is within the normal range when viewed individually, but the coupling degree has become abnormal. This potential fault can only be effectively identified through this solution.

[0062] S30. Based on the results of the dynamic parameter correlation analysis, perform a graded assessment of the likelihood of anomalies: a phenomenon in which a single parameter deviates but the coupling degree remains normal is marked as a primary anomaly; a phenomenon in which multiple parameters deviate in concert and the coupling degree is abnormal is marked as a high-level anomaly. An assessment report is generated that includes the anomaly level and a device status profile.

[0063] Based on the results of dynamic analysis, anomalies are classified into two levels: primary and advanced. This grading mechanism is designed based on the general principles of fault development: single-parameter anomalies often correspond to temporary interference or early potential problems, while multi-parameter coordinated anomalies usually indicate a substantial failure. Compared to existing alarm methods, this graded assessment has multiple advantages: first, it significantly reduces the false alarm rate and avoids overreaction to temporary fluctuations; second, by distinguishing anomaly levels, it provides operations and maintenance personnel with more accurate decision-making basis; finally, the generated device status profile can intuitively display fault characteristics, significantly improving fault diagnosis efficiency, especially the ability to identify primary anomalies. This allows the system to issue warnings before a failure causes substantial damage, achieving true preventive maintenance.

[0064] S40. The assessment report is uploaded to the cloud analysis platform. The cloud analysis platform activates different levels of verification mechanisms based on the abnormality level: for primary abnormalities, horizontal comparison verification is initiated for similar devices; for high-level abnormalities, full life cycle retrospective verification of the device is initiated. The final abnormality determination result is generated after the possibility of misjudgment is eliminated through the verification mechanism;

[0065] The cloud analysis platform has designed differentiated verification paths based on anomalies. Because different types of anomalies have different root causes for misjudgment, targeted verification strategies must be adopted to effectively filter out false positives. These include:

[0066] For primary anomalies, we initiate a horizontal comparison and verification of similar devices. If similar fluctuations in the same parameters are observed in other similar devices in the same environment, this is likely a systemic phenomenon caused by environmental interference (such as grid transients or temperature changes), rather than a device failure. This verification method can effectively identify and filter out most false alarms caused by external factors.

[0067] For advanced anomalies, full lifecycle retrospective verification is triggered. This is because real equipment failures often have gradual characteristics in the time dimension. By tracing the evolution trend of similar parameters in the history of the equipment (such as the slow increase in vibration frequency and the gradual distortion of the current waveform), it is possible to distinguish between sudden interference (such as instantaneous impact) and the actual equipment degradation process. This verification mechanism is particularly good at eliminating misjudgments caused by short-term abnormal interference (such as lightning strikes and operational shocks), while improving the accuracy of identifying potential faults.

[0068] This technical solution builds a complete closed-loop system of "dynamic perception-correlation analysis-tiered assessment-verification and troubleshooting". Through multi-dimensional parameter collection and dynamic tracking and identification, it constructs a spatiotemporal and temporal continuous device status portrait, providing rich and structured input for subsequent analysis. It introduces real-time coupling calculation on the edge side to capture the implicit physical correlation between parameters, thereby distinguishing real faults from random noise. Through the coordination of tiered assessment and verification mechanisms, a progressive diagnostic process is formed: first, preliminary screening is carried out through coupling analysis, and then misjudgment is eliminated through differentiated verification. This deeply integrates the distributed computing power of the Internet of Things with the physical characteristics of device failures, resolving the contradiction between false alarm rate and missed alarm rate in traditional methods.

[0069] In practical applications, abnormal performance of weak current equipment often has significant temporal and spatial correlation. Therefore, the dynamic tracking identifiers collected include timestamps and device location information. These information must be combined with the timestamps and device location information for subsequent dynamic parameter correlation analysis, abnormality classification assessment, and cloud platform verification. The specific process includes:

[0070] After the edge computing node obtains operating parameters with timestamps and device location information, it first uses the device location information to intelligently build a comparison library for groups of devices in the same area. This is because devices in the same physical environment (such as the same distribution cabinet or the same floor) are subject to similar environmental interference. After establishing this spatial association model, when a device parameter is abnormal, the operating status of its neighboring devices can be immediately compared. If similar fluctuations occur simultaneously in multiple devices in the same area, it can be determined that the cause is environmental factors rather than the device itself. This group intelligent judgment based on location information significantly improves the anti-interference capability. At the same time, the parameter time series change trajectory is constructed using timestamp information. This not only includes simple historical data backtracking, but more importantly, it identifies the pattern characteristics of parameter deviation. Sudden deviations usually correspond to external interference such as operational errors or instantaneous shocks, while gradual deviations may indicate equipment aging or potential failures. This time domain pattern recognition enables the system to distinguish between sudden anomalies and chronic failures.

[0071] When entering the anomaly classification and assessment stage, the synergistic effect of spatiotemporal information is further exploited. Timestamp information is used to assist in determining the nature of the anomaly. For example, if a temperature parameter rises sharply within a few minutes and, combined with its historical data, exhibits periodic fluctuations, it can be inferred that it is a temporary overload rather than a device failure. Device location information is used to perform spatial state comparisons. For example, if multiple sensors in the same cable trench simultaneously detect a temperature increase, it is likely a systemic risk caused by poor heat dissipation rather than a problem with a single device. This spatiotemporal cross-validation mechanism significantly improves the accuracy of primary anomaly determination and effectively avoids the overreaction of traditional methods to temporary fluctuations.

[0072] The value of spatiotemporal information is most fully demonstrated in the cloud platform verification phase. Groups of devices of the same type and environment, selected based on device location information, form a natural reference system. Through horizontal comparison, truly abnormal individual devices can be quickly identified. This spatial clustering-based analysis method is particularly suitable for identifying faults caused by local factors (such as poor contact and local overheating). The full life cycle traceability supported by timestamp information reveals deeper patterns. For example, a vibration parameter has shown a slow upward trend in the past three months. Even if the current value is still within the theoretical threshold, the system can provide early warning of bearing wear risks. This verification strategy that combines spatiotemporal dimensions enables the system to quickly respond to sudden faults and capture progressive degradation, achieving predictive maintenance while ensuring real-time performance.

[0073] From a technical perspective, the introduction of spatiotemporal identification enables the system to acquire three-dimensional judgment capabilities (parameter value, time, and space). Compared with the traditional single-parameter threshold method, this multi-dimensional analysis method can identify "what kind of anomaly occurs when, where, and under what conditions", thereby upgrading anomaly judgment from simple status monitoring to true root cause analysis. It is particularly noteworthy that spatiotemporal information in this solution is not used in isolation, but forms a closed loop through the collaborative mechanism of "edge real-time processing-cloud deep verification". The timestamp ensures the continuity of the analysis sequence, and the location information ensures the accuracy of the spatial correlation. The organic combination of the two ultimately achieves accurate diagnosis of anomalies in weak current equipment in complex industrial environments.

[0074] In actual engineering, the operating status of weak current equipment is affected by multiple factors such as load changes and environmental interference. The normal range of parameters is dynamic, and there are complex interactions between different parameters. In this embodiment, by establishing a dynamic correlation model between parameters, the complex interactions between different parameters are explored, and it is possible to distinguish between real faults and normal operating fluctuations. Specifically, referring to Figure 2 As shown in the figure, the process of establishing a dynamic mapping relationship between the current parameters and the historical normal parameter range and calculating the real-time coupling degree between the parameters includes:

[0075] S21. Establish a dynamic parameter window at the edge node, cache current and historical parameter data in a sliding time block manner, and extract features of various parameters in each time block. The extracted features include but are not limited to: parameter fluctuation amplitude features, change rate features, periodic repetition features, and abnormal pulse features;

[0076] This sliding time block processing method not only retains the recent change trend of the parameters (such as the data of the past 15 minutes), but also avoids the computational burden brought by processing the entire historical data; the feature extraction performed in each time block does not simply record the numerical value, but captures the essential characteristics of the parameter behavior - the fluctuation amplitude reflects the degree of parameter deviation, the change rate identifies sudden abnormalities, the periodic characteristics discover regular interference, and the pulse characteristics capture instantaneous faults. This multi-dimensional feature description provides rich and accurate input for subsequent analysis.

[0077] S22. Use an adaptive correlation matrix to construct a dynamic mapping relationship between parameters. Each element in the matrix represents the intensity of the coordinated change of the characteristic vectors of two parameters within a sliding time window. By tracking the evolution trend of the matrix elements in real time, the implicit correlation between the parameters is identified.

[0078] In this embodiment, each element in the matrix reflects the intensity of the coordinated changes in the characteristics of the two parameters in real time, thereby capturing the dynamic relationship between the parameters. For example, it has been found in engineering practice that the transformer temperature and load current have an approximately square relationship under normal circumstances, but this relationship changes when the cooling system is abnormal. By tracking the evolution of matrix elements in real time, this implicit correlation change can be discovered, which is more sensitive and reliable than monitoring temperature or current values ​​alone. The matrix update mechanism uses a sliding window method, which not only ensures real-time performance but also maintains the stability of the analysis. This balanced design is precisely targeted at the characteristics of industrial field data that are often subject to noise interference.

[0079] S23, performing coupling calculation based on the adaptive correlation matrix, the calculation process includes: first identifying the leading parameter and the following parameter in the parameter group, then analyzing the response delay time and amplitude matching degree of the following parameter when the leading parameter changes, and finally evaluating the real-time coupling strength between the parameters based on the comprehensive response characteristics;

[0080] The correlation matrix-based coupling calculation uses a dominant-follower analysis framework. This design is derived from the thinking mode of engineers when diagnosing faults: engineers usually first identify the parameter that first exhibits an abnormality (the dominant parameter) and then observe the response of other parameters (the following parameters) to determine the nature of the fault. By identifying the dominant-follower relationship in the parameter group, analyzing the response delay (for example, temperature changes usually lag behind current changes) and amplitude matching (for example, whether the increase in vibration amplitude is proportional to the increase in current), the final coupling strength assessment contains both numerical relationships and timing characteristics. This multi-dimensional coupling analysis can accurately distinguish between true faults (parameter coupling relationship destruction) and measurement interference (only a single parameter is abnormal).

[0081] In engineering application environments, the normal range of operating parameters of the same equipment under different environmental conditions (such as high temperature in summer and low temperature in winter) varies significantly. Traditional methods using fixed thresholds or simple seasonal adjustment factors are difficult to accurately reflect this complex change. Therefore, when establishing a dynamic mapping relationship, the impact of the environment on the abnormal judgment of weak current equipment must also be considered. Figure 3 As shown, the following steps are also included:

[0082] S24. First, key environmental data such as temperature and humidity are collected in real time through the environmental perception module. These data are encoded as feature vectors rather than simple numerical records. This is because the environmental impact of the construction site is often coupled by multiple factors (for example, the combined effect of high temperature and high humidity is far greater than the impact of a single factor). This encoding method retains the interaction information between environmental factors, laying the foundation for subsequent precise matching.

[0083] S25. The environmental feature vector is then used to activate the corresponding historical parameter sub-interval library, using the equipment's own historical operating data as a judgment benchmark. Each sub-interval library stores the parameter fluctuation range of the equipment's complete operating cycle (such as day and night, production batches, etc.) under specific environmental conditions, ensuring that the benchmark data is statistically representative. Through this environment-parameter associated storage method, the historical operating conditions closest to the current environment can be automatically identified, solving the problem of poor environmental adaptability of traditional methods.

[0084] S26. When dynamically calibrating parameter intervals, rather than simply selecting the most matching subinterval, an intelligent fusion mechanism is designed: for environmental conditions with a clear match, the corresponding subinterval is directly used. For transitional or abnormal environments (such as extreme weather), a temporary benchmark is generated through weighted fusion of multiple subintervals. This approach ensures both accuracy in common environments and robustness in abnormal environments. For example, when spring temperatures fluctuate significantly, winter and summer subinterval data are automatically fused to generate a reasonable benchmark that matches the current transition season, avoiding misjudgments due to gradual environmental changes. The generation process of the temporary benchmark interval takes into account the similarity weights of environmental characteristics, making the final benchmark more consistent with current actual conditions. This dynamic adjustment mechanism significantly enhances adaptability to climate change.

[0085] S27. The parameter deviation direction consistency factor introduced in the coupling calculation link. Engineering experience shows that real faults usually cause related parameters to change in the same direction (such as the current and temperature rise simultaneously during overload), while measurement interference or local anomalies often manifest as inconsistent parameter change directions. By analyzing the consistency of the parameter deviation direction, it is possible to effectively distinguish between systemic faults and local anomalies. This design makes the coupling assessment more consistent with the actual operation rules of the equipment. In specific implementation, when multiple parameters deviate upward or downward synchronously, the coupling weight between these parameters is enhanced, because this coordinated change is more likely to reflect a real fault; when the parameter change direction is chaotic, the weight is reduced to avoid misjudging unrelated fluctuations as related faults. This weight adjustment strategy based on physical mechanisms significantly improves the accuracy of compound fault judgments while reducing false alarms caused by environmental fluctuations.

[0086] Specifically, when generating an assessment report that includes anomaly levels and equipment status portraits, it is necessary to design the equipment status portrait from an engineering application perspective so that each visualization element is targeted at the actual needs of on-site operation and maintenance. The equipment status portrait includes: a parameter status matrix and an anomaly impact range diagram, where:

[0087] The parameter status matrix uses the physical structure of the equipment as a display base, marking the real-time status of its associated parameters at the corresponding component locations. For example, temperature parameters are displayed in the form of heat maps at the heating parts of the equipment, current parameters are displayed in the form of dynamic flow bars on the circuit traces, vibration frequency parameters are displayed in the form of spectrum diagrams at the mechanical moving parts, and voltage parameters are displayed in the form of color scale diagrams at the power access points. This design enables engineers to intuitively locate abnormal parameters to specific components, eliminating the process of converting parameter numbers and physical locations.

[0088] The abnormal impact range diagram is generated based on the electrical and mechanical connection relationship of the equipment and is marked with different color areas. For example: the red area clearly identifies the parts that need priority treatment, and the yellow area indicates the related components that may be involved. This display method helps the operation and maintenance team predict the impact of the fault and prepare maintenance plans for related components in advance.

[0089] Reference Figure 4 As shown in the figure, the process of initiating horizontal comparison and verification of the same type of equipment for primary anomalies includes the following steps:

[0090] S411. Based on the installation location characteristics and functional attributes of the abnormal device, select the same type of equipment with the same power distribution circuit, the same physical installation location, or recently maintained equipment from the equipment inventory database as the comparison object;

[0091] Based on the physical location and electrical characteristics of abnormal equipment, comparable similar equipment is intelligently screened. Equipment on the same distribution circuit shares the same power quality, equipment in the same installation location is subject to similar environmental stresses, and equipment that has been recently maintained provides a health benchmark reference. This multi-dimensional screening strategy ensures the representativeness of the comparison sample.

[0092] S412. Collect the current operating parameters of the comparison objects and select the comparison objects that match the abnormal equipment working conditions as the valid comparison group;

[0093] The preliminary comparison objects are matched with working conditions in detail. The working condition matching includes quantitative evaluation of three dimensions: load rate, operating time and environmental similarity. Equipment with the same model but large differences in actual operating status is eliminated to form a truly comparable and effective comparison group. This dynamic screening mechanism overcomes the limitations of traditional methods that simply compare by equipment type.

[0094] S413. Compare and analyze the abnormal device parameters with the group fluctuation range of the valid comparison group, mark the specific parameters that exceed the group range, and analyze their correlation with the individual characteristics of the device;

[0095] After obtaining a valid comparison group, a fixed theoretical threshold is no longer used. Instead, a dynamic normal range is established based on the actual operating data of the group equipment. The parameter deviations of abnormal equipment are compared with this living benchmark. This group intelligent analysis method can adapt to environmental changes. For example, when the ambient temperature generally rises, causing the temperature parameters of all similar equipment to rise synchronously, it can identify that this is a normal phenomenon rather than an individual equipment failure.

[0096] S414. Generate verification conclusions of group consistency abnormality, individual specific abnormality, or gradual group abnormality based on the comparison results, corresponding to different judgments of environmental factors, equipment failure, or early stage of systemic degradation, respectively;

[0097] Specifically, three types of typical conclusions were formed through verification decisions, each corresponding to a different engineering disposal plan: group anomalies indicate the need to check public systems (such as power supply and heat dissipation), individual anomalies point to equipment maintenance, and gradual anomalies warn that batch replacement may be required; this structured output directly connects to the on-site maintenance process, allowing the IoT data analysis results to be seamlessly integrated into the existing operation and maintenance system.

[0098] Reference Figure 5 As shown in the figure, the process of retrospective verification of the entire life cycle of the advanced abnormal startup device includes the following steps:

[0099] S421. Integrate equipment factory baseline parameters, previous maintenance records, historical abnormal data, and environmental change characteristics to build a complete life cycle digital archive;

[0100] By integrating the full-dimensional historical data of the equipment to build a digital archive of its life cycle, this archive is not a simple accumulation of data, but rather a spatiotemporal alignment and structured processing of factory baseline parameters, previous maintenance records, historical abnormal data and environmental change characteristics to form a traceable equipment "gene map"; for example, when a communication device has intermittent signal interruption, the archive can quickly retrieve the signal stability test curve of the device at the factory, the batch information of modules replaced in the past, the historical handling records of similar faults, and the temperature and humidity change data of the installation environment. The organic integration of this information provides a three-dimensional data foundation for subsequent analysis.

[0101] S422. Use a hierarchical backtracking mechanism to sequentially perform short-term parameter gradient analysis, mid-term performance drift assessment, and full lifecycle benchmark comparison to form a comprehensive diagnostic view covering different time scales;

[0102] A hierarchical backtracking mechanism is used for multi-time scale analysis. Its technical mechanism lies in the fact that different types of fault clues are distributed in different time dimensions. Among them: short-term parameter gradual change analysis focuses on data changes in the last 72 hours. Through minute-level parameter reproduction, it can capture subtle signs before a fault occurs, such as periodic current fluctuations that begin 48 hours before a power module completely fails; medium-term performance drift assessment focuses on parameter change trends within 3 months. This cross-cycle analysis can identify progressive degradation of equipment, such as the slow increase in connector contact resistance; full life cycle benchmark comparison compares the current status with the factory standard to determine whether the equipment has undergone essential changes; specifically, the analysis of these three time dimensions is not isolated, but mutually verified - short-term anomalies may be explained by medium-term trends, and long-term deviations can provide a reference benchmark for medium-term changes. This cross-validation greatly improves the reliability of diagnostic conclusions.

[0103] S423. Based on time series analysis and physical connection relationships, the propagation path of the first abnormal point is tracked to generate a fault evolution chain including spatiotemporal evolution characteristics and degradation acceleration.

[0104] The fault evolution chain generation process combines physical connection analysis and temporal pattern recognition. It first determines the spatiotemporal coordinates of the anomaly's origin. Then, along the equipment's electrical connections and mechanical transmission paths, combined with component replacement information in maintenance records, a fault propagation model is constructed. This process pays special attention to the time delay and amplitude amplification effects of anomaly propagation. For example, when an abnormal motor current is detected, the vibration changes of the mechanical load it drives are traced back, and the temporal correlation and amplitude relationship between the two are analyzed to determine whether the problem is with the motor itself or caused by an abnormal load. This physical mechanism-based tracing method can effectively avoid misjudgments that may occur with purely data-driven analysis.

[0105] S424. The comprehensive retrospective analysis results output includes engineering decision conclusions including root cause determination, recoverability assessment, disposal priority recommendations, and preventive measures.

[0106] The engineering decision-making conclusions generated in this embodiment are not simple anomaly classifications, but rather a disposal plan encompassing four key dimensions: The root cause determination is based on full lifecycle data tracing, distinguishing between different causes such as design defects, material aging, improper operation, or environmental factors; the recoverability assessment comprehensively considers the current status of the equipment, maintenance history, and age to determine the economic and technical feasibility of repairs; the disposal priority recommendation determines the urgency of the response based on the speed of fault propagation and the scope of impact; and the preventive measures plan specifically proposes suggestions for design improvements, operating specifications, or enhanced monitoring. This structured output model enables complex analysis results to be directly converted into engineering action guidelines, significantly enhancing the practical value of the IoT monitoring system.

[0107] Specifically, in actual applications, after determining that the weak current equipment is abnormal, the following steps are also included:

[0108] S50. Adaptively trigger the corresponding control strategy based on the type and level of the final abnormality determination result:

[0109] Start parameter fine-tuning instructions for primary anomalies, start device isolation instructions for advanced anomalies and generate maintenance work orders, and at the same time update the historical normal parameter range and coupling degree benchmark of the edge computing node.

[0110] After the abnormality is determined, differentiated response mechanisms are designed based on the type and level of the abnormality. For primary abnormalities, an alarm or shutdown will not be triggered immediately. Instead, parameter fine-tuning will be attempted first. This flexible processing method fully considers the common parameter fluctuation characteristics in industrial environments. For example, if the temperature parameter of a distribution cabinet is detected to be slightly high but related parameters such as current and vibration are normal, the ventilation equipment speed will be automatically adjusted or a slight load reduction will be recommended. This gentle intervention not only avoids production interruptions but also effectively controls risks.

[0111] The generation of parameter fine-tuning instructions is not a simple numerical adjustment, but a combination of the equipment's operating history and environmental conditions to calculate a safe and economical adjustment range to ensure that new problems will not be caused by over-adjustment.

[0112] For advanced anomalies, a more stringent equipment isolation process is initiated. Unlike simple power outage protection, the isolation instructions in this solution are executed in stages: first, the current operating status and data snapshot are recorded, then an orderly shutdown is performed according to the equipment operating procedures, and finally a maintenance work order with detailed diagnostic information is generated. This standardized isolation procedure avoids the secondary damage that may be caused by sudden power outages, while also preserving complete fault site data for subsequent maintenance.

[0113] The maintenance work order generation process integrates equipment archival information, abnormality feature analysis, and historical maintenance records. It not only identifies fault symptoms but also provides possible root cause analysis and repair suggestions, significantly improving on-site maintenance efficiency. For example, when a motor system experiences multiple parameter anomalies such as current, temperature, and vibration, the generated work order will mark the correlation pattern of the abnormal parameters, prompting focused inspection of bearings or windings, and attaching the most recent handling record of a similar fault. This intelligent work order system significantly shortens troubleshooting time.

[0114] In addition, after each exception handling, whether it is parameter fine-tuning or device isolation, the reference benchmark of the edge computing node will be updated according to the handling effect. For primary exceptions, the historical normal parameter range is mainly updated, and a gradual adjustment strategy is adopted to absorb new normal operation data while retaining the original benchmark characteristics to avoid benchmark drift caused by a single exception; for high-level exceptions, the coupling degree benchmark is updated synchronously and the correlation model between parameters is recalibrated. This dynamic learning capability enables the system to adapt to changes in operating characteristics caused by long-term factors such as equipment aging and environmental changes; for example, the performance of a weak current equipment changes after seasonal maintenance. By continuously updating the benchmark data, the system can quickly adapt to the new operating status and maintain monitoring accuracy.

[0115] To implement the above method, refer to Figure 6 As shown, the present invention also discloses a weak current device abnormality judgment system for the Internet of Things, which can implement the above method, and the system includes:

[0116] A data acquisition module is used to collect multi-dimensional operating parameters of target weak current equipment in real time through the Internet of Things node network. The multi-dimensional operating parameters include at least temperature parameters, current parameters, voltage parameters and vibration frequency parameters. Each Internet of Things node is equipped with a dynamic identification generation unit for generating a unique dynamic tracking identification for the collected data;

[0117] an edge computing module, communicatively connected to the data acquisition module, configured to receive multi-dimensional operating parameters with dynamic tracking identifiers and perform correlation analysis on the dynamic parameters, including establishing a dynamic mapping relationship between the current parameters and historical normal parameter intervals, calculating the real-time coupling degree between the parameters, and analyzing the coupling degree change pattern of other related parameters when a parameter deviates from its historical normal interval;

[0118] A hierarchical assessment module, in communication with the edge computing module, is configured to perform hierarchical assessment of anomaly likelihood based on the results of dynamic parameter correlation analysis, marking a phenomenon in which a single parameter deviates but the coupling degree remains normal as a primary anomaly, and marking a phenomenon in which multiple parameters deviate in coordination and the coupling degree is abnormal as a high-level anomaly, and generating an assessment report including the anomaly level and a device status profile;

[0119] The cloud analysis platform is in communication with the edge computing module and is used to activate different levels of verification mechanisms according to the abnormality level in the assessment report, activate horizontal comparison verification of the same type of equipment for primary abnormalities, and activate full life cycle retrospective verification of the equipment for high-level abnormalities. The final abnormality judgment result is generated after eliminating the possibility of misjudgment through the verification mechanism.

[0120] Specifically, the system also includes: a control strategy execution module, which is connected to the cloud analysis platform in communication, and adaptively triggers the corresponding control strategy according to the type and level of the final abnormality judgment result, including: fine-tuning instructions for parameters for primary abnormalities, and isolation instructions for equipment for advanced abnormalities and generating maintenance work orders.

[0121] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0122] Obviously, the above embodiments are merely examples for clarity of explanation and are not intended to limit the implementation methods. Those skilled in the art will appreciate that other variations or modifications can be made based on the above description. It is not necessary and impossible to enumerate all implementation methods here. Obvious variations or modifications arising therefrom remain within the scope of protection of the present invention.

Claims

1. A method for determining abnormality of weak current equipment in the Internet of Things, characterized in that: The following steps are involved: The multi-dimensional operating parameters of the target weak current equipment are collected in real time through the IoT node network. The multi-dimensional operating parameters include at least temperature parameters, current parameters, voltage parameters and vibration frequency parameters. Each IoT node generates a unique dynamic tracking identifier for the collected data. Transmit multi-dimensional operating parameters with dynamic tracking identifiers to edge computing nodes, where dynamic parameter correlation analysis is performed. This includes establishing a dynamic mapping relationship between current parameters and historical normal parameter ranges, calculating the real-time coupling between parameters, and analyzing the coupling change pattern of other related parameters when a parameter deviates from its historical normal range. Based on the results of dynamic parameter correlation analysis, a hierarchical assessment of abnormality probability is performed: a phenomenon in which a single parameter deviates but the coupling degree remains normal is marked as a primary abnormality, and a phenomenon in which multiple parameters deviate in coordination and the coupling degree is abnormal is marked as a high-level abnormality. An assessment report is generated that includes the abnormality level and equipment status profile. The assessment report is uploaded to the cloud analysis platform, which activates different levels of verification mechanisms based on the abnormality level: for primary abnormalities, horizontal comparison verification of similar devices is initiated; for high-level abnormalities, full life cycle retrospective verification of the equipment is initiated. The final abnormality judgment result is generated after eliminating the possibility of misjudgment through the verification mechanism.

2. The method for determining abnormality of weak current equipment in the Internet of Things according to claim 1, wherein: The dynamic tracking identifier includes: a timestamp and device location information, wherein: When performing dynamic parameter correlation analysis on the edge computing node, a parameter comparison library for device groups in the same area is first established based on the device location information in the dynamic tracking identifier, and then a parameter time series change trajectory is constructed based on the timestamp information. When assessing the likelihood of anomalies, the system uses timestamp information to identify sudden or gradual deviations of parameters, and compares the operating status differences of devices in the same area based on device location information. When verifying on the cloud analysis platform, similar devices in the same physical environment are selected for horizontal comparison based on the device location information, and the historical evolution trend of the device parameters is traced based on the timestamp information.

3. The method for determining abnormality of weak current equipment in the Internet of Things according to claim 1, wherein: The process of establishing a dynamic mapping relationship between current parameters and historical normal parameter ranges and calculating the real-time coupling degree between parameters includes: Establish a dynamic parameter window at the edge computing node, cache current and historical parameter data in a sliding time block manner, and extract features of various parameters within each time block. The extracted features include but are not limited to: parameter fluctuation amplitude features, change rate features, periodic repetition features, and abnormal pulse features; An adaptive correlation matrix is ​​used to construct a dynamic mapping relationship between parameters. Each element in the matrix represents the intensity of the coordinated change of the characteristic vectors of two parameters within a sliding time window. The implicit correlation between parameters is identified by tracking the evolution trend of the matrix elements in real time. The coupling degree calculation is performed based on the adaptive correlation matrix. The calculation process includes: first identifying the dominant parameter and the following parameter in the parameter group, then analyzing the response delay time and amplitude matching of the following parameter when the dominant parameter changes, and finally comprehensively evaluating the real-time coupling strength between the parameters based on the response characteristics.

4. The method for determining abnormality of weak current equipment in the Internet of Things according to claim 3, wherein: The process of establishing a dynamic mapping relationship also includes: A parameter-adaptive benchmark model is established at the edge computing node. The environmental perception module collects temperature and humidity data of the device's environment in real time and encodes the environmental data into an environmental feature vector. Activate the corresponding historical parameter sub-interval library according to the environmental feature vector, and store the sub-intervals according to different environmental conditions. Each sub-interval contains the parameter fluctuation range of at least three complete cycles of normal operation of the equipment under the environmental conditions; Perform dynamic calibration of parameter intervals, and perform similarity matching between the current environment feature vector and the environment features of each sub-interval. When the matching degree exceeds the preset threshold, the sub-interval is used as the reference interval. Otherwise, the three sub-intervals with the highest matching degree are weighted and fused to generate a temporary reference interval. When calculating the real-time coupling degree, a parameter deviation direction consistency factor is introduced. When multiple parameters deviate from their reference intervals upward or downward at the same time, the coupling degree calculation weight is increased. When the parameter deviation directions are inconsistent, the coupling degree calculation weight is reduced.

5. The method for determining abnormality of weak current equipment in the Internet of Things according to claim 1, wherein: The device status portrait includes: The parameter status matrix uses the physical structure diagram of the equipment as the base, marking the real-time status of the associated parameters at the corresponding component positions, including: temperature parameters, current parameters, voltage parameters and vibration frequency parameters; The abnormal impact range map is based on the equipment electrical schematic diagram and mechanical connection diagram, and is marked with different color areas, including: directly affected core areas, possibly affected related areas, and currently normal isolation areas.

6. The method for determining abnormality of weak current equipment in the Internet of Things according to claim 1, wherein: The process of initiating horizontal comparison and verification of similar equipment for primary anomalies includes: Based on the installation location characteristics and functional attributes of the abnormal equipment, select the same model equipment with the same power distribution circuit, the same physical installation location, or recently maintained equipment from the equipment ledger library as the comparison object; Collect the current operating parameters of the comparison objects and select the comparison objects that match the abnormal equipment working conditions as the valid comparison group; Compare and analyze abnormal device parameters with the group fluctuation range of the effective comparison group, mark specific parameters that exceed the group range and analyze their correlation with the individual characteristics of the device; Based on the comparison results, verification conclusions of group consistency abnormality, individual specific abnormality or gradual group abnormality are generated, which correspond to different judgments on environmental factors, equipment failure or early stage of systematic degradation.

7. The method for determining abnormality of weak current equipment in the Internet of Things according to claim 1, wherein: The process of retrospective verification of the entire life cycle of advanced abnormal startup equipment includes: Integrate equipment factory benchmark parameters, previous maintenance records, historical abnormal data and environmental change characteristics to build a complete life cycle digital archive; A hierarchical backtracking mechanism is used to sequentially perform short-term parameter gradient analysis, mid-term performance drift assessment, and full lifecycle benchmark comparison, forming a comprehensive diagnostic view covering different time scales; Based on time series analysis and physical connection relationships, the propagation path of the first abnormal point is tracked to generate a fault evolution chain including spatiotemporal evolution characteristics and degradation acceleration; The comprehensive retrospective analysis results output engineering decision conclusions including root cause determination, recoverability assessment, disposal priority recommendations and preventive measures plans.

8. The method for determining abnormality of weak current equipment in the Internet of Things according to claim 1, wherein: The following steps are also included: Based on the type and level of the final abnormality determination result, the corresponding control strategy is adaptively triggered, including: fine-tuning parameters for primary abnormalities, and isolating equipment for advanced abnormalities and generating maintenance work orders.

9. A weak current equipment abnormality judgment system for the Internet of Things, characterized by: include: A data acquisition module is used to collect multi-dimensional operating parameters of target weak current equipment in real time through the Internet of Things node network. The multi-dimensional operating parameters include at least temperature parameters, current parameters, voltage parameters and vibration frequency parameters. Each Internet of Things node is equipped with a dynamic identification generation unit for generating a unique dynamic tracking identification for the collected data; an edge computing module, communicatively connected to the data acquisition module, configured to receive multi-dimensional operating parameters with dynamic tracking identifiers and perform correlation analysis on the dynamic parameters, including establishing a dynamic mapping relationship between the current parameters and historical normal parameter intervals, calculating the real-time coupling degree between the parameters, and analyzing the coupling degree change pattern of other related parameters when a parameter deviates from its historical normal interval; A hierarchical assessment module, in communication with the edge computing module, is configured to perform hierarchical assessment of anomaly likelihood based on the results of dynamic parameter correlation analysis, marking a phenomenon in which a single parameter deviates but the coupling degree remains normal as a primary anomaly, and marking a phenomenon in which multiple parameters deviate in coordination and the coupling degree is abnormal as a high-level anomaly, and generating an assessment report including the anomaly level and a device status profile; The cloud analysis platform is in communication with the edge computing module and is used to activate different levels of verification mechanisms according to the abnormality level in the assessment report, activate horizontal comparison verification of the same type of equipment for primary abnormalities, and activate full life cycle retrospective verification of the equipment for high-level abnormalities. The final abnormality judgment result is generated after eliminating the possibility of misjudgment through the verification mechanism.

10. The weak current device abnormality judgment system of the Internet of Things according to claim 9, characterized in that: Also includes: The control strategy execution module communicates with the cloud analysis platform and adaptively triggers the corresponding control strategy based on the type and level of the final abnormality judgment result, including: starting parameter fine-tuning instructions for primary abnormalities, starting equipment isolation instructions for high-level abnormalities and generating maintenance work orders.

Images