Multi-circuit breaker monitoring method based on AI algorithm and internet of things management system

Abstract

The application discloses a kind of multi-circuit breaker monitoring method and internet of things management system based on AI algorithm, the method comprises: obtaining the sensing data of multiple circuit breakers in target area;According to the sensing data of the multiple circuit breakers, based on graph network algorithm, establish circuit breaker data network;The circuit breaker data network is input into the abnormal prediction AI model trained in advance, to obtain the abnormal prediction result corresponding to each circuit breaker;In response to the monitoring demand of any circuit breaker, according to the abnormal prediction result corresponding to the circuit breaker and at least one other circuit breaker, determine the abnormal risk of the circuit breaker.It can be seen that the present application can realize accurate abnormal risk assessment based on graph network and multi-circuit breaker association, improve the accuracy and reliability of the target area internet of things system monitoring, reduce the risk of circuit breaker failure.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a multi-circuit breaker monitoring method and IoT management system based on AI algorithms. Background Technology

[0002] With the increasing demand for intelligent monitoring of IoT systems, IoT enterprises are placing greater emphasis on reducing circuit breaker failure risks through accurate anomaly detection to ensure the stability of IoT systems. Existing technologies typically collect sensor data from individual circuit breakers, employing simple threshold analysis or traditional statistical models to assess equipment status, and formulate maintenance strategies based on independent monitoring results to ensure the safe operation of the IoT system. However, existing solutions lack networked analysis of the relationships between multiple circuit breakers and intelligent modeling for anomaly prediction. This makes it difficult to accurately assess the interaction between the target circuit breaker and other circuit breakers. The commonly used isolated monitoring methods are unsuitable for complex IoT system environments, resulting in insufficient accuracy in anomaly risk assessment, a tendency to miss potential faults, and limitations on the reliability and operational efficiency of IoT system monitoring. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a multi-circuit breaker monitoring method and IoT management system based on AI algorithm, which can realize accurate abnormal risk assessment based on graph network and multi-circuit breaker association, improve the accuracy and reliability of IoT system monitoring in target area, and reduce the risk of circuit breaker failure.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a multi-circuit breaker monitoring method based on an AI algorithm, the method comprising:

[0005] Acquire sensor data from multiple circuit breakers in the target area;

[0006] Based on the sensor data of the multiple circuit breakers, a circuit breaker data network is established using a graph network algorithm.

[0007] The circuit breaker data network is input into a pre-trained anomaly prediction AI model to obtain the anomaly prediction result for each circuit breaker.

[0008] In response to the monitoring requirement of any of the circuit breakers, the abnormal risk of the circuit breaker is determined based on the abnormal prediction results corresponding to the circuit breaker and at least one other circuit breaker.

[0009] As an optional implementation, in a first aspect of the invention, the sensing data includes at least one of current data, temperature data, humidity data, sound data, image data, and actuator signal data.

[0010] As an optional implementation, in the first aspect of the present invention, the step of establishing a circuit breaker data network based on the sensing data of the plurality of circuit breakers and using a graph network algorithm includes:

[0011] Each of the circuit breakers is defined as a graph node;

[0012] The parameter information of the corresponding circuit breaker and the sensing data are determined as the node parameter data of the graph node;

[0013] For any two graph nodes, the adjacency parameter between the two graph nodes is calculated based on the sensing data;

[0014] All the graph nodes and their corresponding adjacency parameters are used to define the circuit breaker data network.

[0015] As an optional implementation, in the first aspect of the invention, calculating the adjacency parameter between the two graph nodes based on the sensing data includes:

[0016] Calculate the data similarity between the sensor data corresponding to the circuit breakers of the two graph nodes;

[0017] Calculate the difference in data volume between the data volume of the sensor data corresponding to the circuit breaker corresponding to the two graph nodes;

[0018] The data matrix composed of the data similarity and the data volume difference is determined as the adjacency parameter between the two graph nodes.

[0019] As an optional implementation, in the first aspect of the present invention, the anomaly prediction AI model is trained using a training dataset that includes multiple training circuit breaker data networks and corresponding anomaly annotations; the training circuit breaker data network includes multiple training circuit breaker nodes, wherein each training circuit breaker node is annotated with corresponding node parameter data and circuit breaker anomaly annotations, and any two training circuit breaker nodes are annotated with adjacency parameters.

[0020] As an optional implementation, in the first aspect of the present invention, the anomaly prediction result and the circuit breaker anomaly label include anomaly type, anomaly probability, and expected anomaly occurrence time.

[0021] As an optional implementation, in the first aspect of the invention, determining the abnormal risk of the circuit breaker based on the abnormal prediction results corresponding to the circuit breaker and at least one other circuit breaker includes:

[0022] In the circuit breaker data network, other circuit breakers associated with the circuit breaker are identified to obtain at least one associated circuit breaker.

[0023] Calculate the average of the abnormal probabilities of all the associated circuit breakers to obtain the associated abnormal probability;

[0024] Calculate the average of the expected occurrence times of all associated circuit breakers to obtain the associated occurrence time;

[0025] Calculate the average probability of the associated anomaly probability and the anomaly probability of the circuit breaker;

[0026] Calculate the time difference between the associated anomaly probability and the expected time of anomaly occurrence for the circuit breaker;

[0027] Determine whether the average probability value is greater than a probability threshold and whether the time difference value is less than a time difference threshold to obtain a first determination result;

[0028] When the first judgment result is yes, calculate whether the similarity between the set of all the abnormal types of the associated circuit breakers and the abnormal type of the circuit breaker is greater than a preset similarity threshold, and obtain the second judgment result;

[0029] When the second judgment result is yes, the circuit breaker is determined to be a risk circuit breaker, and the anomaly type and the expected time of anomaly occurrence are determined as the risk parameters of the circuit breaker.

[0030] As an optional implementation, in a first aspect of the invention, determining other circuit breakers associated with the circuit breaker in the circuit breaker data network to obtain at least one associated circuit breaker includes:

[0031] For each other graph node that has the adjacency parameter with the graph node corresponding to the circuit breaker, obtain the data similarity and the data volume difference between the other graph node and the graph node corresponding to the circuit breaker.

[0032] Calculate the average of the data similarity and the difference in data volume to obtain the association parameters corresponding to the other graph node;

[0033] The circuit breakers corresponding to all other graph nodes whose associated parameters are greater than a preset parameter threshold are selected to obtain at least one associated circuit breaker.

[0034] A second aspect of this invention discloses an Internet of Things (IoT) management system, the system comprising:

[0035] The acquisition module is used to acquire sensor data from multiple circuit breakers in the target area;

[0036] A module is established to build a circuit breaker data network based on the sensor data of the multiple circuit breakers and a graph network algorithm.

[0037] The prediction module is used to input the circuit breaker data network into a pre-trained anomaly prediction AI model to obtain the anomaly prediction result for each circuit breaker.

[0038] A monitoring module is configured to, in response to a monitoring requirement for any of the circuit breakers, determine the abnormal risk of the circuit breaker based on the abnormal prediction results corresponding to the circuit breaker and at least one other circuit breaker.

[0039] As an optional implementation, in a second aspect of the invention, the sensing data includes at least one of current data, temperature data, humidity data, sound data, image data, and actuator signal data.

[0040] As an optional implementation, in a second aspect of the invention, the specific method by which the establishing module establishes a circuit breaker data network based on the sensing data of the plurality of circuit breakers and a graph network algorithm includes:

[0041] Each of the circuit breakers is defined as a graph node;

[0042] The parameter information of the corresponding circuit breaker and the sensing data are determined as the node parameter data of the graph node;

[0043] For any two graph nodes, the adjacency parameter between the two graph nodes is calculated based on the sensing data;

[0044] All the graph nodes and their corresponding adjacency parameters are used to define the circuit breaker data network.

[0045] As an optional implementation, in a second aspect of the invention, the specific method by which the establishing module calculates the adjacency parameters between the two graph nodes based on the sensing data includes:

[0046] Calculate the data similarity between the sensor data corresponding to the circuit breakers of the two graph nodes;

[0047] Calculate the difference in data volume between the data volume of the sensor data corresponding to the circuit breaker corresponding to the two graph nodes;

[0048] The data matrix composed of the data similarity and the data volume difference is determined as the adjacency parameter between the two graph nodes.

[0049] As an optional implementation, in the second aspect of the present invention, the anomaly prediction AI model is trained using a training dataset that includes multiple training circuit breaker data networks and corresponding anomaly annotations; the training circuit breaker data network includes multiple training circuit breaker nodes, wherein each training circuit breaker node is annotated with corresponding node parameter data and circuit breaker anomaly annotations, and any two training circuit breaker nodes are annotated with adjacency parameters.

[0050] As an optional implementation, in a second aspect of the present invention, the anomaly prediction result and the circuit breaker anomaly label include anomaly type, anomaly probability, and expected anomaly occurrence time.

[0051] As an optional implementation, in a second aspect of the invention, the monitoring module determines the specific method by which it determines the abnormal risk of the circuit breaker based on the abnormal prediction results corresponding to the circuit breaker and at least one other circuit breaker, including:

[0052] In the circuit breaker data network, other circuit breakers associated with the circuit breaker are identified to obtain at least one associated circuit breaker.

[0053] Calculate the average of the abnormal probabilities of all the associated circuit breakers to obtain the associated abnormal probability;

[0054] Calculate the average of the expected occurrence times of all associated circuit breakers to obtain the associated occurrence time;

[0055] Calculate the average probability of the associated anomaly probability and the anomaly probability of the circuit breaker;

[0056] Calculate the time difference between the associated anomaly probability and the expected time of anomaly occurrence for the circuit breaker;

[0057] Determine whether the average probability value is greater than a probability threshold and whether the time difference value is less than a time difference threshold to obtain a first determination result;

[0058] When the first judgment result is yes, calculate whether the similarity between the set of all the abnormal types of the associated circuit breakers and the abnormal type of the circuit breaker is greater than a preset similarity threshold, and obtain the second judgment result;

[0059] When the second judgment result is yes, the circuit breaker is determined to be a risk circuit breaker, and the anomaly type and the expected time of anomaly occurrence are determined as the risk parameters of the circuit breaker.

[0060] As an optional implementation, in a second aspect of the invention, the monitoring module identifies other circuit breakers associated with the circuit breaker in the circuit breaker data network, obtaining at least one associated circuit breaker in a specific manner, including:

[0061] For each other graph node that has the adjacency parameter with the graph node corresponding to the circuit breaker, obtain the data similarity and the data volume difference between the other graph node and the graph node corresponding to the circuit breaker.

[0062] Calculate the average of the data similarity and the difference in data volume to obtain the association parameters corresponding to the other graph node;

[0063] The circuit breakers corresponding to all other graph nodes whose associated parameters are greater than a preset parameter threshold are selected to obtain at least one associated circuit breaker.

[0064] A third aspect of the present invention discloses another Internet of Things (IoT) management system, the system comprising:

[0065] Memory containing executable program code;

[0066] A processor coupled to the memory;

[0067] The processor calls the executable program code stored in the memory to execute some or all of the steps in the AI-based multi-circuit breaker monitoring method disclosed in the first aspect of the present invention.

[0068] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the AI-based multi-circuit breaker monitoring method disclosed in the first aspect of the present invention.

[0069] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0070] This invention acquires sensor data from multiple circuit breakers in a target area and constructs a circuit breaker data network based on a graph network algorithm. This data is then input into a pre-trained anomaly prediction AI model to obtain anomaly prediction results for each circuit breaker. When responding to monitoring needs, the anomaly risk is determined by combining the prediction results of the target circuit breaker and other circuit breakers. This enables accurate anomaly risk assessment based on graph networks and multi-circuit breaker association, improving the accuracy and reliability of IoT system monitoring in the target area and reducing the risk of circuit breaker failure. Attached Figure Description

[0071] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0072] Figure 1 This is a flowchart illustrating a multi-circuit breaker monitoring method based on AI algorithms disclosed in an embodiment of the present invention.

[0073] Figure 2 This is a schematic diagram of the structure of an Internet of Things (IoT) management system disclosed in an embodiment of the present invention.

[0074] Figure 3 This is a schematic diagram of another IoT management system disclosed in an embodiment of the present invention.

[0075] Figure 4 This is a schematic diagram of the circuit breaker monitoring interface of a transparent IoT management system disclosed in an embodiment of the present invention. Detailed Implementation

[0076] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0077] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0078] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0079] This invention discloses a multi-circuit breaker monitoring method and IoT management system based on AI algorithms. It acquires sensor data from multiple circuit breakers in a target area and constructs a circuit breaker data network based on a graph network algorithm. This data is then input into a pre-trained anomaly prediction AI model to obtain anomaly prediction results for each circuit breaker. When responding to monitoring needs, the prediction results of the target circuit breaker and other circuit breakers are combined to determine its anomaly risk. This enables accurate anomaly risk assessment based on graph networks and multi-circuit breaker association, improving the accuracy and reliability of IoT system monitoring in the target area and reducing the risk of circuit breaker failure. Detailed explanations follow.

[0080] Example 1

[0081] Please see Figure 1 , Figure 1 This is a flowchart illustrating a multi-circuit breaker monitoring method based on an AI algorithm disclosed in an embodiment of the present invention. Figure 1 The described AI-based multi-circuit breaker monitoring method can be applied to data processing systems / data processing equipment / data processing servers (including local processing servers or cloud processing servers). Figure 1 As shown, the AI-based multi-circuit breaker monitoring method may include the following operations:

[0082] 101. Obtain sensor data from multiple circuit breakers in the target area.

[0083] 102. Based on the sensor data of multiple circuit breakers, establish a circuit breaker data network using a graph network algorithm.

[0084] 103. Input the circuit breaker data network into the pre-trained anomaly prediction AI model to obtain the anomaly prediction result for each circuit breaker.

[0085] 104. In response to the monitoring requirement of any circuit breaker, determine the abnormal risk of the circuit breaker based on the abnormal prediction results corresponding to the circuit breaker and at least one other circuit breaker.

[0086] Optionally, the target area can be a residential area, industrial park, commercial building or power grid node area, and the present invention does not limit it.

[0087] Optionally, the circuit breaker can be a low-voltage circuit breaker, a high-voltage circuit breaker, or a smart circuit breaker; the present invention does not limit the type of circuit breaker.

[0088] Optionally, the nodes of the circuit breaker data network can represent circuit breakers, and the edges can represent electrical connections, physical proximity relationships, or data associations between circuit breakers; this invention does not impose any limitations.

[0089] Optionally, the construction of the circuit breaker data network can be based on the spatiotemporal characteristics or topology of the sensor data, and this invention does not limit it.

[0090] Optionally, the anomaly prediction result can be anomaly probability, anomaly type, or anomaly severity; this invention does not limit this.

[0091] Optionally, the training of the anomaly prediction AI model can be based on historical sensor data, simulated fault data, or real-time feedback data, and this invention does not impose any limitations.

[0092] Optionally, the determination process can be based on a weighted fusion algorithm, a rule-based reasoning algorithm, or a machine learning classification algorithm, and this invention does not limit it.

[0093] Optionally, the calculation of the abnormal risk can be optimized by combining the circuit breaker's operating environment, historical fault records, or network topology, and this invention does not limit it.

[0094] In one specific implementation scheme, a smart IoT circuit breaker is implemented to fully monitor the circuit status in an area. This circuit breaker adopts a modular design, with independently packaged protection units, communication modules, and measurement units, supporting functional expansion. Its protection action time is ≤40ms under short-circuit conditions and ≤100ms under leakage conditions. It supports an edge computing architecture, enabling intelligent collaboration between local logical judgment and cloud-based big data analysis. Specifically, its technical approach is as follows:

[0095] Hardware platform: STM32F4 series MCU (floating-point arithmetic) + high-precision measurement chip;

[0096] Protection Algorithm: Improved RMS Algorithm (Full Cycle Fourier Analysis);

[0097] Communication protocol: Modbus RTU (wired) + MQTT over TLS (wireless encrypted transmission);

[0098] Structural design: Double-break contact system + magnetic blowout arc extinguishing grid (10kA breaking capacity verification).

[0099] Specifically, its structural design includes:

[0100] Contact system: Silver-nickel alloy main contacts + tungsten copper arc-starting angle (mechanical life ≥ 30,000 cycles);

[0101] Insulation design: 3.0mm creepage distance + flame retardant groove structure (passes GB / T 5169.11 glow wire test).

[0102] Specifically, the data acquisition functions of its sensing and monitoring system include:

[0103] Voltage / current: 128 samples per cycle (4kHz / channel);

[0104] Temperature monitoring: PT1000 patch sensor (±1℃ accuracy).

[0105] As can be seen, the above-described embodiments of the invention acquire sensor data from multiple circuit breakers in the target area and construct a circuit breaker data network based on a graph network algorithm. This data is then input into a pre-trained anomaly prediction AI model to obtain anomaly prediction results for each circuit breaker. When responding to monitoring needs, the anomaly risk is determined by combining the prediction results of the target circuit breaker and other circuit breakers. This enables accurate anomaly risk assessment based on graph networks and multi-circuit breaker association, improving the accuracy and reliability of IoT system monitoring in the target area and reducing the risk of circuit breaker failure.

[0106] As an optional embodiment, the sensing data in the above steps includes at least one of current data, temperature data, humidity data, sound data, image data, and actuator signal data.

[0107] As can be seen, the content of the sensing data is defined through the above optional embodiments to comprehensively characterize the working sensing characteristics of the circuit breaker, assist in realizing accurate anomaly risk assessment based on graph networks and multi-circuit breaker association, improve the accuracy and reliability of IoT system monitoring in the target area, and reduce the risk of circuit breaker failure.

[0108] As an optional embodiment, the step above, establishing a circuit breaker data network based on graph network algorithms using sensor data from multiple circuit breakers, includes:

[0109] Each circuit breaker is defined as a graph node;

[0110] The parameter information and sensor data of the corresponding circuit breaker are determined as the node parameter data of the node in the diagram.

[0111] For any two graph nodes, calculate the adjacency parameters between the two graph nodes based on the sensor data;

[0112] All graph nodes and their corresponding adjacency parameters are defined as the circuit breaker data network.

[0113] Optionally, this parameter information can be the rated current, rated voltage, model, or manufacturing batch of the circuit breaker; this invention does not impose any limitations on this.

[0114] Optionally, the adjacency parameter can be electrical connection strength, physical distance, data correlation, or communication delay, and the present invention does not limit it.

[0115] Optionally, the adjacency parameter can be calculated based on Euclidean distance, correlation coefficient analysis, or machine learning algorithms, and this invention does not limit it.

[0116] As can be seen, through the above optional embodiments, by setting each circuit breaker as a graph node and using its parameter information and sensor data as node parameter data, the adjacency parameters between any two graph nodes based on sensor data are calculated, and all graph nodes and adjacency parameters are integrated to form a circuit breaker data network. This enables accurate network construction based on node parameters and data association, improves the accuracy of circuit breaker anomaly prediction and the monitoring efficiency of the Internet of Things system, and reduces the risk of fault misjudgment.

[0117] As an optional embodiment, the step above, calculating the adjacency parameter between the two graph nodes based on the sensing data, includes:

[0118] Calculate the data similarity between the sensor data corresponding to the circuit breakers of the two graph nodes;

[0119] Calculate the difference in data volume between the sensor data corresponding to the circuit breakers of the two graph nodes;

[0120] The data matrix composed of data similarity and data volume difference is used as the adjacency parameter between the two graph nodes.

[0121] Optionally, the data similarity can be calculated based on cosine similarity, Euclidean distance, Pearson correlation coefficient, or dynamic time warping algorithm; this invention does not impose any limitations.

[0122] Optionally, the calculation of data similarity can be optimized by combining the temporal or statistical characteristics of the sensor data, and this invention does not limit it.

[0123] The amount of data can be the size of the data packet, the sampling frequency, the number of data points, or the total amount of data transmitted; this invention does not impose any limitations on this.

[0124] Optionally, the calculation of the data difference can be based on the absolute difference, relative difference, or normalized difference, and this invention does not limit it.

[0125] As can be seen, through the above optional embodiments, by calculating the data similarity and data volume difference between the sensor data of any two graph nodes corresponding to the circuit breakers, a data matrix is ​​formed as the adjacency parameter between the two graph nodes, thereby realizing the construction of accurate adjacency parameters based on similarity and data volume difference, improving the accuracy of the circuit breaker data network and the reliability of anomaly prediction, and reducing the risk of misjudgment of faults in the Internet of Things system.

[0126] As an optional embodiment, in the above steps, the anomaly prediction AI model is trained using a training dataset that includes multiple training circuit breaker data networks and corresponding anomaly annotations; the training circuit breaker data network includes multiple training circuit breaker nodes, wherein each training circuit breaker node is annotated with corresponding node parameter data and circuit breaker anomaly annotations, and any two training circuit breaker nodes are annotated with adjacency parameters.

[0127] Specifically, the anomaly prediction AI model is implemented as a graph neural network model, which includes:

[0128] Multi-level graph neural networks are used to perform multi-level parallel graph convolution operations on the input training circuit breaker data network to generate multi-scale embedding vectors of nodes and edges, thus constructing a multi-level graph neural network.

[0129] The embedding vector is used to construct a network for cross-layer fusion of embedding vectors from multi-level graph neural networks, and the Transformer module is introduced for global interaction modeling to obtain the embedding vectors.

[0130] The fully connected layer used for prediction is used to obtain the corresponding anomaly labels and make predictions based on a multi-level graph neural network and embedding vectors, and to optimize parameters by combining a loss function.

[0131] As can be seen, the above optional embodiments define the training details and characteristics of the training dataset for the anomaly prediction AI model, enabling the anomaly prediction AI model to achieve accurate anomaly risk assessment based on graph networks and multi-circuit breaker association, thereby improving the accuracy and reliability of IoT system monitoring in the target area and reducing the risk of circuit breaker failure.

[0132] As an optional embodiment, the anomaly prediction results and circuit breaker anomaly labels in the above steps include anomaly type, anomaly probability, and expected anomaly occurrence time.

[0133] As can be seen, the above optional embodiments limit the details of anomaly prediction results and anomaly labeling, enabling subsequent accurate anomaly risk assessment based on graph networks and multi-circuit breaker associations to be achieved based on the prediction results, thereby improving the accuracy and reliability of IoT system monitoring in the target area and reducing the risk of circuit breaker failure.

[0134] As an optional embodiment, the step described above, determining the abnormal risk of the circuit breaker based on the abnormal prediction results corresponding to the circuit breaker and at least one other circuit breaker, includes:

[0135] In the circuit breaker data network, identify other circuit breakers associated with the circuit breaker to obtain at least one associated circuit breaker.

[0136] Calculate the average of the abnormal probabilities of all associated circuit breakers to obtain the associated abnormal probability;

[0137] Calculate the average of the estimated occurrence times of all associated circuit breakers to obtain the associated occurrence time;

[0138] Calculate the average probability of the associated anomaly probability and the anomaly probability of the circuit breaker;

[0139] Calculate the time difference between the associated anomaly probability and the expected time of an anomaly occurrence for the circuit breaker;

[0140] Determine whether the average probability value is greater than the probability threshold and whether the time difference value is less than the time difference threshold to obtain the first judgment result;

[0141] When the first judgment result is yes, calculate whether the similarity between the set of all associated circuit breaker anomaly types and the anomaly type of the circuit breaker is greater than a preset similarity threshold, and obtain the second judgment result;

[0142] If the second judgment result is yes, the circuit breaker is determined to be a risk circuit breaker, and the anomaly type and the expected time of anomaly occurrence are determined as the risk parameters of the circuit breaker.

[0143] As can be seen, through the above optional embodiments, by identifying associated circuit breakers related to the target circuit breaker in the circuit breaker data network, calculating the average of their abnormal probability and the expected time of abnormal occurrence to obtain the associated abnormal probability and associated time of abnormal occurrence, and combining the abnormal probability and time of the target circuit breaker to calculate the average probability and time difference, it is determined whether the average probability exceeds the probability threshold and whether the time difference is less than the time difference threshold. If so, it is further determined whether the similarity between the set of abnormal types of associated circuit breakers and the abnormal type of the target circuit breaker exceeds the similarity threshold. If the similarity exceeds the threshold, the target circuit breaker is determined to be a risk circuit breaker, and the abnormal type and the expected time of abnormal occurrence are used as risk parameters. This achieves accurate risk assessment based on associated circuit breakers and multi-dimensional threshold judgment, improves the accuracy and reliability of IoT system monitoring, and reduces the risk of circuit breaker failure.

[0144] As an optional embodiment, the step described above, identifying other circuit breakers associated with the circuit breaker in the circuit breaker data network to obtain at least one associated circuit breaker, includes:

[0145] For each other graph node that has an adjacency parameter with the graph node corresponding to the circuit breaker, obtain the data similarity and data volume difference between the other graph node and the graph node corresponding to the circuit breaker.

[0146] Calculate the average of the data similarity and the difference in data volume to obtain the association parameters corresponding to the other graph nodes;

[0147] Filter out all other graph nodes whose associated parameters are greater than a preset parameter threshold and obtain at least one associated circuit breaker.

[0148] As can be seen, through the above optional embodiments, by obtaining the data similarity and data volume difference of other graph nodes that have adjacency parameters with the target circuit breaker graph node, calculating the average of the two as the association parameter, and filtering out the circuit breakers corresponding to other graph nodes whose association parameters exceed the preset threshold as associated circuit breakers, the accurate identification of associated circuit breakers based on data similarity and data volume differences can be achieved, thereby improving the accuracy of circuit breaker anomaly risk assessment and the monitoring efficiency of the Internet of Things system, and reducing the risk of fault misjudgment.

[0149] Example 2

[0150] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of an Internet of Things (IoT) management system disclosed in an embodiment of the present invention. Figure 2 The described IoT management system can be applied to data processing systems / data processing devices / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 2 As shown, the IoT management system may include:

[0151] The acquisition module 201 is used to acquire sensor data of multiple circuit breakers in the target area.

[0152] Module 202 is used to establish a circuit breaker data network based on the sensor data of multiple circuit breakers and a graph network algorithm.

[0153] The prediction module 203 is used to input the circuit breaker data network into a pre-trained anomaly prediction AI model to obtain the anomaly prediction result for each circuit breaker.

[0154] The monitoring module 204 is used to determine the abnormal risk of any circuit breaker in response to the monitoring requirement of any circuit breaker, based on the abnormal prediction results corresponding to the circuit breaker and at least one other circuit breaker.

[0155] As can be seen, the above-described embodiments of the invention acquire sensor data from multiple circuit breakers in the target area and construct a circuit breaker data network based on a graph network algorithm. This data is then input into a pre-trained anomaly prediction AI model to obtain anomaly prediction results for each circuit breaker. When responding to monitoring needs, the anomaly risk is determined by combining the prediction results of the target circuit breaker and other circuit breakers. This enables accurate anomaly risk assessment based on graph networks and multi-circuit breaker association, improving the accuracy and reliability of IoT system monitoring in the target area and reducing the risk of circuit breaker failure.

[0156] As an optional embodiment, the sensing data includes at least one of current data, temperature data, humidity data, sound data, image data, and actuator signal data.

[0157] As can be seen, the content of the sensing data is defined through the above optional embodiments to comprehensively characterize the working sensing characteristics of the circuit breaker, assist in realizing accurate anomaly risk assessment based on graph networks and multi-circuit breaker association, improve the accuracy and reliability of IoT system monitoring in the target area, and reduce the risk of circuit breaker failure.

[0158] As an optional embodiment, the module establishes a circuit breaker data network based on the sensor data of multiple circuit breakers and a graph network algorithm, including the following specific methods:

[0159] Each circuit breaker is defined as a graph node;

[0160] The parameter information and sensor data of the corresponding circuit breaker are determined as the node parameter data of the node in the diagram.

[0161] For any two graph nodes, calculate the adjacency parameters between the two graph nodes based on the sensor data;

[0162] All graph nodes and their corresponding adjacency parameters are defined as the circuit breaker data network.

[0163] As can be seen, through the above optional embodiments, by setting each circuit breaker as a graph node and using its parameter information and sensor data as node parameter data, the adjacency parameters between any two graph nodes based on sensor data are calculated, and all graph nodes and adjacency parameters are integrated to form a circuit breaker data network. This enables accurate network construction based on node parameters and data association, improves the accuracy of circuit breaker anomaly prediction and the monitoring efficiency of the Internet of Things system, and reduces the risk of fault misjudgment.

[0164] As an optional embodiment, the specific method by which the module calculates the adjacency parameters between the two graph nodes based on the sensor data includes:

[0165] Calculate the data similarity between the sensor data corresponding to the circuit breakers of the two graph nodes;

[0166] Calculate the difference in data volume between the sensor data corresponding to the circuit breakers of the two graph nodes;

[0167] The data matrix composed of data similarity and data volume difference is used as the adjacency parameter between the two graph nodes.

[0168] As can be seen, through the above optional embodiments, by calculating the data similarity and data volume difference between the sensor data of any two graph nodes corresponding to the circuit breakers, a data matrix is ​​formed as the adjacency parameter between the two graph nodes, thereby realizing the construction of accurate adjacency parameters based on similarity and data volume difference, improving the accuracy of the circuit breaker data network and the reliability of anomaly prediction, and reducing the risk of misjudgment of faults in the Internet of Things system.

[0169] As an optional embodiment, the anomaly prediction AI model is trained using a training dataset that includes multiple training circuit breaker data networks and corresponding anomaly annotations. The training circuit breaker data network includes multiple training circuit breaker nodes, each of which is labeled with corresponding node parameter data and circuit breaker anomaly annotations, and any two training circuit breaker nodes are labeled with adjacency parameters.

[0170] As can be seen, the above optional embodiments define the training details and characteristics of the training dataset for the anomaly prediction AI model, enabling the anomaly prediction AI model to achieve accurate anomaly risk assessment based on graph networks and multi-circuit breaker association, thereby improving the accuracy and reliability of IoT system monitoring in the target area and reducing the risk of circuit breaker failure.

[0171] As an optional embodiment, the anomaly prediction results and circuit breaker anomaly labels include the anomaly type, anomaly probability, and expected time of anomaly occurrence.

[0172] As can be seen, the above optional embodiments limit the details of anomaly prediction results and anomaly labeling, enabling subsequent accurate anomaly risk assessment based on graph networks and multi-circuit breaker associations to be achieved based on the prediction results, thereby improving the accuracy and reliability of IoT system monitoring in the target area and reducing the risk of circuit breaker failure.

[0173] As an optional embodiment, the monitoring module determines the specific method of abnormal risk of the circuit breaker based on the abnormal prediction results corresponding to the circuit breaker and at least one other circuit breaker, including:

[0174] In the circuit breaker data network, identify other circuit breakers associated with the circuit breaker to obtain at least one associated circuit breaker.

[0175] Calculate the average of the abnormal probabilities of all associated circuit breakers to obtain the associated abnormal probability;

[0176] Calculate the average of the estimated occurrence times of all associated circuit breakers to obtain the associated occurrence time;

[0177] Calculate the average probability of the associated anomaly probability and the anomaly probability of the circuit breaker;

[0178] Calculate the time difference between the associated anomaly probability and the expected time of an anomaly occurrence for the circuit breaker;

[0179] Determine whether the average probability value is greater than the probability threshold and whether the time difference value is less than the time difference threshold to obtain the first judgment result;

[0180] When the first judgment result is yes, calculate whether the similarity between the set of all associated circuit breaker anomaly types and the anomaly type of the circuit breaker is greater than a preset similarity threshold, and obtain the second judgment result;

[0181] If the second judgment result is yes, the circuit breaker is determined to be a risk circuit breaker, and the anomaly type and the expected time of anomaly occurrence are determined as the risk parameters of the circuit breaker.

[0182] As can be seen, through the above optional embodiments, by identifying associated circuit breakers related to the target circuit breaker in the circuit breaker data network, calculating the average of their abnormal probability and the expected time of abnormal occurrence to obtain the associated abnormal probability and associated time of abnormal occurrence, and combining the abnormal probability and time of the target circuit breaker to calculate the average probability and time difference, it is determined whether the average probability exceeds the probability threshold and whether the time difference is less than the time difference threshold. If so, it is further determined whether the similarity between the set of abnormal types of associated circuit breakers and the abnormal type of the target circuit breaker exceeds the similarity threshold. If the similarity exceeds the threshold, the target circuit breaker is determined to be a risk circuit breaker, and the abnormal type and the expected time of abnormal occurrence are used as risk parameters. This achieves accurate risk assessment based on associated circuit breakers and multi-dimensional threshold judgment, improves the accuracy and reliability of IoT system monitoring, and reduces the risk of circuit breaker failure.

[0183] As an optional embodiment, the monitoring module identifies other circuit breakers associated with the circuit breaker in the circuit breaker data network, obtaining a specific method for at least one associated circuit breaker, including:

[0184] For each other graph node that has an adjacency parameter with the graph node corresponding to the circuit breaker, obtain the data similarity and data volume difference between the other graph node and the graph node corresponding to the circuit breaker.

[0185] Calculate the average of the data similarity and the difference in data volume to obtain the association parameters corresponding to the other graph nodes;

[0186] Filter out all other graph nodes whose associated parameters are greater than a preset parameter threshold and obtain at least one associated circuit breaker.

[0187] As can be seen, through the above optional embodiments, by obtaining the data similarity and data volume difference of other graph nodes that have adjacency parameters with the target circuit breaker graph node, calculating the average of the two as the association parameter, and filtering out the circuit breakers corresponding to other graph nodes whose association parameters exceed the preset threshold as associated circuit breakers, the accurate identification of associated circuit breakers based on data similarity and data volume differences can be achieved, thereby improving the accuracy of circuit breaker anomaly risk assessment and the monitoring efficiency of the Internet of Things system, and reducing the risk of fault misjudgment.

[0188] In one specific implementation scheme, based on the monitoring scheme and IoT management system scheme disclosed in this invention, a transparent IoT management system is implemented. Its core algorithm, based on the circuit breaker monitoring method disclosed in this invention, monitors multiple smart circuit breakers and displays and alarms the graph network constructed during monitoring and the risk information. Its functional design includes:

[0189] 1. Equipment Map

[0190] 2. Equipment Management: Circuit breaker information, gateway information, circuit breaker type

[0191] 3. Group Management

[0192] 4. Alarm Management: Configuration of leakage current alarms, pending alarms, historical alarms, and alarm notifications.

[0193] 5. Statistical Reports: Energy Consumption Statistics, Alarm Statistics

[0194] 6. System Management: Leakage current self-test task, user management, role management, menu management, area management, dictionary management, parameter settings, notifications and announcements, and log management.

[0195] In one implementation scenario, multiple circuit breakers, along with their corresponding risk information and related monitoring information, can be used to... Figure 4 The circuit breaker is displayed in a way that prompts users and facilitates their management and monitoring.

[0196] Example 3

[0197] Please see Figure 3 , Figure 3 This is yet another IoT management system disclosed in the embodiments of the present invention. Figure 3 The described IoT management system is applied in a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the IoT management system may include:

[0198] Memory 301 storing executable program code;

[0199] Processor 302 coupled to memory 301;

[0200] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the AI-based multi-circuit breaker monitoring method described in Embodiment 1.

[0201] Example 4

[0202] This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps of the multi-circuit breaker monitoring method based on AI algorithm described in Embodiment 1.

[0203] Example 5

[0204] This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the AI ​​algorithm-based multi-circuit breaker monitoring method described in Embodiment 1.

[0205] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0206] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0207] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0208] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0209] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0210] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0211] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0212] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0213] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0214] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0215] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0216] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0217] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0218] Finally, it should be noted that the AI-based multi-circuit breaker monitoring method and IoT management system disclosed in the embodiments of this invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this invention.

Claims

1. A multi-circuit breaker monitoring method based on AI algorithm, characterized in that, The method includes: Acquire sensor data from multiple circuit breakers in the target area; Based on the sensor data of the multiple circuit breakers, a circuit breaker data network is established using a graph network algorithm, including: Each of the circuit breakers is defined as a graph node; The parameter information of the corresponding circuit breaker and the sensing data are determined as the node parameter data of the graph node; For any two graph nodes, calculate the data similarity between the sensor data corresponding to the circuit breaker corresponding to the two graph nodes; Calculate the difference in data volume between the data volume of the sensor data corresponding to the circuit breaker corresponding to the two graph nodes; The data matrix composed of the data similarity and the data volume difference is determined as the adjacency parameter between the two graph nodes; All the graph nodes and their corresponding adjacency parameters are identified as the circuit breaker data network; The circuit breaker data network is input into a pre-trained anomaly prediction AI model to obtain the anomaly prediction result for each circuit breaker. In response to the monitoring requirement of any of the circuit breakers, the abnormal risk of the circuit breaker is determined based on the abnormal prediction results corresponding to the circuit breaker and at least one other circuit breaker.

2. The multi-circuit breaker monitoring method based on AI algorithm according to claim 1, characterized in that, The sensing data includes at least one of current data, temperature data, humidity data, sound data, image data, and actuator signal data.

3. The multi-circuit breaker monitoring method based on AI algorithm according to claim 1, characterized in that, The anomaly prediction AI model is trained using a training dataset that includes multiple training circuit breaker data networks and corresponding anomaly annotations. The training circuit breaker data network includes multiple training circuit breaker nodes, each of which is labeled with corresponding node parameter data and circuit breaker anomaly annotations, and any two training circuit breaker nodes are labeled with adjacency parameters.

4. The multi-circuit breaker monitoring method based on AI algorithm according to claim 3, characterized in that, The anomaly prediction results and the circuit breaker anomaly labels include the anomaly type, anomaly probability, and the expected time of anomaly occurrence.

5. The multi-circuit breaker monitoring method based on AI algorithm according to claim 4, characterized in that, The step of determining the abnormal risk of the circuit breaker based on the abnormal prediction results corresponding to the circuit breaker and at least one other circuit breaker includes: In the circuit breaker data network, other circuit breakers associated with the circuit breaker are identified to obtain at least one associated circuit breaker. Calculate the average of the abnormal probabilities of all the associated circuit breakers to obtain the associated abnormal probability; Calculate the average of the expected occurrence times of all associated circuit breakers to obtain the associated occurrence time; Calculate the average probability of the associated anomaly probability and the anomaly probability of the circuit breaker; Calculate the time difference between the associated anomaly probability and the expected time of anomaly occurrence for the circuit breaker; Determine whether the average probability value is greater than a probability threshold and whether the time difference value is less than a time difference threshold to obtain a first determination result; When the first judgment result is yes, calculate whether the similarity between the set of all the abnormal types of the associated circuit breakers and the abnormal type of the circuit breaker is greater than a preset similarity threshold, and obtain the second judgment result; When the second judgment result is yes, the circuit breaker is determined to be a risk circuit breaker, and the anomaly type and the expected time of anomaly occurrence are determined as the risk parameters of the circuit breaker.

6. The multi-circuit breaker monitoring method based on AI algorithm according to claim 5, characterized in that, The step of identifying other circuit breakers associated with the circuit breaker in the circuit breaker data network to obtain at least one associated circuit breaker includes: For each other graph node that has the adjacency parameter with the graph node corresponding to the circuit breaker, obtain the data similarity and the data volume difference between the other graph node and the graph node corresponding to the circuit breaker. Calculate the average of the data similarity and the difference in data volume to obtain the association parameters corresponding to the other graph node; The circuit breakers corresponding to all other graph nodes whose associated parameters are greater than a preset parameter threshold are selected to obtain at least one associated circuit breaker.

7. An Internet of Things (IoT) management system, characterized in that, The system includes: The acquisition module is used to acquire sensor data from multiple circuit breakers in the target area; A module is established to build a circuit breaker data network based on the sensor data of the multiple circuit breakers and using a graph network algorithm, including: Each of the circuit breakers is defined as a graph node; The parameter information of the corresponding circuit breaker and the sensing data are determined as the node parameter data of the graph node; For any two graph nodes, calculate the data similarity between the sensor data corresponding to the circuit breaker corresponding to the two graph nodes; Calculate the difference in data volume between the data volume of the sensor data corresponding to the circuit breaker corresponding to the two graph nodes; The data matrix composed of the data similarity and the data volume difference is determined as the adjacency parameter between the two graph nodes; All the graph nodes and their corresponding adjacency parameters are identified as the circuit breaker data network; The prediction module is used to input the circuit breaker data network into a pre-trained anomaly prediction AI model to obtain the anomaly prediction result for each circuit breaker. A monitoring module is configured to, in response to a monitoring requirement for any of the circuit breakers, determine the abnormal risk of the circuit breaker based on the abnormal prediction results corresponding to the circuit breaker and at least one other circuit breaker.

8. An Internet of Things (IoT) management system, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the multi-circuit breaker monitoring method based on the AI ​​algorithm as described in any one of claims 1-6.

Images