Fault early warning system for remote monitoring of intelligent circuit breaker based on Internet of Things

Abstract

The invention discloses a fault early warning system for remote monitoring of an intelligent circuit breaker based on the Internet of Things, and relates to the technical field of power monitoring, the fault early warning system comprises a remote monitoring platform, the remote monitoring platform is in communication connection with a data acquisition and storage module, a cloud data analysis module, an abnormity diagnosis module, an abnormity positioning module and a fault early warning module, the modules are in electric signal connection; and the data acquisition and storage module is used for acquiring operation data of the intelligent circuit breaker in real time through a sensor and storing the operation data in the cloud server. The operation data of the intelligent circuit breaker are collected in real time and transmitted to the cloud for analysis, real-time monitoring of the state of the circuit breaker is achieved, once the system recognizes an abnormal mode, an early warning signal can be triggered immediately, the fault discovery time is greatly shortened, maintenance personnel can make a quick response and take measures in time, and the maintenance efficiency is improved. Fault expansion is effectively avoided, and the safety and stability of a power system are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power monitoring, and specifically relates to a fault warning system for remote monitoring of intelligent circuit breakers based on the Internet of Things. Background Art

[0002] The power system is one of the core infrastructures of modern society. Ensuring its safe, stable and efficient operation is crucial for ensuring economic development, social stability and the quality of people's lives. With the expansion of the scale of the power system and the progress of technology, the management and maintenance of power equipment have become more complex. Moreover, various faults are inevitable during the operation of the power system, such as overload, short circuit, leakage, etc. If these faults are not dealt with in time, they may cause serious electrical fires or equipment damage accidents. The circuit breaker is an important protection device in the power system, used to prevent abnormal conditions such as overload and short circuit in the circuit from damaging the system. When an electrical fault occurs, the circuit breaker can quickly cut off the current to avoid a wider range of power outages or equipment damage.

[0003] In the prior art, the long-term high-frequency use of the circuit breaker and environmental interference will reduce the service life of the circuit breaker, and then make it difficult for the circuit breaker to achieve the required application effect. The fixed-form manual inspection not only makes it difficult to quickly locate the abnormal circuit breaker, but also has a high maintenance cost. Therefore, how to apply Internet of Things technology to remotely monitor intelligent circuit breakers through the end-cloud collaboration method and quickly locate abnormal points to implement accurate fault warnings is the problem to be solved by the present invention. For this reason, a fault warning system for remote monitoring of intelligent circuit breakers based on the Internet of Things is proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide a fault warning system for remote monitoring of intelligent circuit breakers based on the Internet of Things to solve the problems raised in the above background art section.

[0005] To solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A fault warning system for remote monitoring of intelligent circuit breakers based on the Internet of Things, including a remote monitoring platform, which is communicatively connected to a data acquisition and storage module, a cloud data analysis module, an anomaly diagnosis module, an anomaly location module and a fault warning module. Among them, the modules are electrically connected to each other;

[0007] The data acquisition and storage module is used to collect the operation data of the intelligent circuit breaker in real time through sensors and store it in the cloud server;

[0008] The cloud data analysis module is used to perform feature analysis on the operation data of the intelligent circuit breaker and mark the operation state features with anomalies to obtain an anomaly feature sequence list;

[0009] The abnormal diagnosis module is used to identify the abnormal patterns of the intelligent circuit breaker by using the abnormal feature sequence list and combining with the fault diagnosis model pre-trained based on the neural network model;

[0010] The abnormal location module is used to locate the abnormal points by combining the geographical location information and operation data of the intelligent circuit breaker;

[0011] The fault warning module is used to issue a warning signal by combining the identified abnormal patterns of the intelligent circuit breaker, output a warning report including information on the abnormal type, location and severity, and then visually display the warning report.

[0012] A further improvement of the technical solution of the present invention is that: the data acquisition and storage module includes an intelligent sensor unit, an Internet of Things communication unit and a cloud storage unit;

[0013] Among them, the intelligent sensor unit is used to collect various operation data of the intelligent circuit breaker through various types of sensors deployed, including current, voltage, temperature, switch state, load and power quality;

[0014] The Internet of Things communication unit is used to transmit the operation data collected by the intelligent sensor unit to the cloud server in real time through Internet of Things technology;

[0015] The cloud storage unit is used to store the historical and real-time operation data of the intelligent circuit breaker in the cloud database.

[0016] A further improvement of the technical solution of the present invention is that: the intelligent sensor unit specifically includes:

[0017] In the area to be monitored, according to the layout and monitoring requirements of the intelligent circuit breaker, various types of sensors are deployed, and the operation data of the intelligent circuit breaker is continuously and synchronously collected at a preset sampling frequency. Among them, the sensors include current sensors, voltage sensors, temperature sensors, switch state sensors, load sensors and power quality sensors, etc., to obtain operation data including current, voltage, temperature, switch state, load and power quality;

[0018] Preprocess the collected operation data of the intelligent circuit breaker, including preprocessing operations such as filtering and normalization. Among them, high-frequency noise is removed through a filter, and normalization processing unifies the data to the same dimension range;

[0019] Integrate the preprocessed various operation data, arrange them in an orderly manner according to the data type and collection time, and form a structured data packet to clearly present the operation status information of the intelligent circuit breaker.

[0020] A further improvement of the technical solution of the present invention lies in that: the Internet of Things communication unit and the cloud storage unit specifically include:

[0021] The Internet of Things communication unit establishes a communication connection with the intelligent sensor unit, and according to the preset Internet of Things communication protocol, performs preliminary format conversion and encapsulation on the collected operation data, converts the operation data of the intelligent sensor into a standardized data frame that meets the requirements of remote transmission. Among them, the data frame includes a timestamp, a sensor identifier, a data type, and numerical information, ensuring the integrity and traceability of the data;

[0022] The encapsulated operation data is encrypted through the Internet of Things communication unit, and the AES encryption algorithm is used to ensure the security of the data during transmission. The encrypted operation data is transmitted to the cloud server in real time through the selected communication network;

[0023] The cloud storage unit receives the historical and real-time operation data of the intelligent circuit breaker transmitted by the Internet of Things communication unit and stores it in the cloud database.

[0024] A further improvement of the technical solution of the present invention lies in that: the cloud data analysis module includes a feature analysis unit and an anomaly marking integration unit;

[0025] Among them, the feature analysis unit is used to perform feature analysis on the operation data of the intelligent circuit breaker stored in the cloud server and extract the operation state features related to the abnormal analysis of the circuit breaker;

[0026] The anomaly marking integration unit is used to combine the historical operation data and the monitoring requirements, set the reference values of the operation state features, distinguish the operation state features with anomalies, and then integrate the operation state features to obtain an anomaly feature sequence list.

[0027] A further improvement of the technical solution of the present invention lies in that: the feature analysis unit specifically includes:

[0028] Perform feature analysis on the operation data of the intelligent circuit breaker stored in the cloud server, combine the historical operation data and the remote monitoring requirements of the intelligent circuit breaker, determine the operation data including current, voltage, temperature, switch state, load, and power quality, and then determine the operation state features associated with abnormal analysis;

[0029] Analyze the operation state features respectively extracted from the current, voltage, temperature, switch state, load, and power quality data, namely the current mutation rate, voltage deviation rate, temperature rise rate of key parts, abnormal tripping times, load imbalance degree, and harmonic distortion rate;

[0030] Integrate the extracted operating status features in a predefined format to form a structured feature dataset. The feature dataset includes the timestamp, feature type, and numerical information of each operating status feature, ensuring the traceability and integrity of the features.

[0031] A further improvement of the technical solution of the present invention lies in that: the abnormal marking integration unit specifically includes:

[0032] Analyze various operating status features in combination with historical operation data and monitoring requirements. By statistically analyzing the historical operation data, determine the normal operation range of each operating status feature, and in combination with the monitoring requirements of intelligent circuit breaker abnormal analysis, set corresponding reference values for each operating status feature. At the same time, obtain the latest operating status feature data from the cloud server to ensure the integrity and accuracy of the data;

[0033] Compare the extracted operating status feature data with the set reference values, calculate the deviation between the feature data and the reference values, and based on the preset deviation threshold, determine whether the deviation exceeds the normal range to identify whether there is an abnormality. If the feature data exceeds the deviation threshold defined by the reference value, it is determined that the operating status feature is abnormal, and then mark the abnormal operating status feature, and record the type and occurrence time information of the abnormality;

[0034] Integrate the marked operating status features according to the time sequence and feature type. Arrange each abnormal feature in chronological order of occurrence, and at the same time classify them according to the feature type to generate an abnormal feature sequence list. The abnormal feature sequence list includes the specific time, type, numerical value, and deviation degree information of each abnormal feature.

[0035] A further improvement of the technical solution of the present invention lies in that: the abnormal diagnosis module specifically includes:

[0036] Extract and mark the operating status features with abnormalities from the historical operation data, match the abnormal patterns of the intelligent circuit breaker based on the abnormal operating status features, which are respectively minor abnormalities and faults, and then integrate the marked operating status features and the matched abnormal patterns to obtain a dataset. Divide the dataset into a training set, a validation set, and a test set;

[0037] Select a neural network model as the basic architecture, determine the number of layers of the neural network, the number of neurons in each layer, the activation function, and the loss function parameters. Randomly initialize the weight and bias parameters of the neural network. Input the training set data into the neural network model. During the training process, use the validation set data to verify the model and evaluate the generalization ability of the model. After training, use the test set data to test the model and evaluate the accuracy and reliability of the model to obtain a fault diagnosis model;

[0038] Input the abnormal operating state features in the abnormal feature sequence list into the fault diagnosis model, compare them with various abnormal patterns, and output the confidence score to determine whether there is an abnormal pattern in the intelligent circuit breaker. Set the abnormal classification threshold T, and then analyze the output results to classify the abnormal patterns, namely minor abnormalities and faults.

[0039] A further improvement of the technical solution of the present invention lies in that: the calculation process of the confidence score is as follows:

[0040] For each operating state feature, calculate the relative deviation of its actual value from the reference value, and then take the absolute value of the relative deviation of each operating state feature;

[0041] Perform a radical calculation on the absolute value of the relative deviation of each operating state feature, set an adjustment parameter, apply an exponential decay function to the absolute value of the relative deviation of each operating state feature, and calculate the exponential decay factor;

[0042] Multiply the radical part of each operating state feature by the exponential decay factor, and sum all the operating state features to calculate the weighted deviation sum;

[0043] Sum the absolute values of the relative deviations of all operating state features, and perform an adjustment using the natural logarithm function. Then multiply the total number of operating state features by the natural logarithm adjustment term to calculate the denominator part;

[0044] Divide the weighted deviation sum as the numerator part by the denominator part to obtain the confidence score, in order to analyze the deviation degree between the actual value and the reference value of the operating state features.

[0045] A further improvement of the technical solution of the present invention lies in that: the abnormal location module specifically includes:

[0046] Collect the geographical location information and operation data of the intelligent circuit breaker. The geographical location information includes the installation position coordinates of the circuit breaker, and collect the output of the abnormal diagnosis module, including abnormal operating state features and diagnosis results. Associate and match the geographical location information with the corresponding operation data through a unique identifier (circuit breaker ID) to ensure that the position of each circuit breaker corresponds one-to-one with its operating state information;

[0047] Analyze the output of the abnormal diagnosis module, judge the intelligent circuit breakers with abnormal motion states, and locate the abnormal circuit breaker points corresponding to each abnormal operating state feature by matching the abnormal operating state features in the output of the abnormal diagnosis module with the geographical location information. Then, combine the historical operation data and maintenance records to analyze the frequency and potential causes of the abnormal circuit breaker points, providing support for maintenance decisions;

[0048] Using Geographic Information System (GIS) technology, mark the locations of intelligent circuit breakers with anomalies on an electronic map, and use different colors to distinguish the types of anomalies. Red indicates a fault, and yellow indicates a minor anomaly;

[0049] The fault warning module specifically includes:

[0050] Receive the abnormal mode information of the intelligent circuit breaker identified by the anomaly diagnosis module, analyze the abnormal mode, judge whether it reaches the warning condition, determine the existence of an abnormal mode that needs to be warned, immediately trigger a warning signal, and at the same time, extract the key information in the abnormal mode, including the type of anomaly, the location of the anomaly, and the severity;

[0051] Based on the triggered warning signal and the extracted key information, generate a warning report. Among them, the content of the warning report includes the type of anomaly, the location of occurrence, the time point of occurrence, the severity, and the recommended maintenance measures, and display the warning report through a visualization interface.

[0052] Due to the adoption of the above technical solution, the technical progress achieved by the present invention compared with the prior art is:

[0053] 1. The present invention provides a fault warning system for remote monitoring of intelligent circuit breakers based on the Internet of Things. By collecting the operation data of intelligent circuit breakers in real time and transmitting it to the cloud for analysis, real-time monitoring of the circuit breaker status is achieved. Once the system identifies an abnormal mode, it can immediately trigger a warning signal, greatly shortening the fault discovery time, enabling maintenance personnel to respond quickly and take measures in a timely manner, effectively avoiding the expansion of faults, and significantly improving the safety and stability of the power system.

[0054] 2. The present invention provides a fault warning system for remote monitoring of intelligent circuit breakers based on the Internet of Things. Using a neural network model to perform in-depth learning on the abnormal feature sequence list, combined with historical operation data and monitoring requirements, accurately identify the abnormal mode of intelligent circuit breakers. Compared with traditional manual inspections and simple threshold judgments, the accuracy and reliability of diagnosis are greatly improved. By accurately identifying the type and location of anomalies, it provides strong support for subsequent fault handling. Brief Description of the Drawings

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0056] Figure 1 It is a schematic diagram of the system function module of the present invention;

[0057] Figure 2 Schematic diagram of the working process of the abnormal diagnosis module of the present invention. Specific implementation manners

[0058] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0059] Embodiment 1, as Figure 1 、 Figure 2 shown, the present invention provides a fault warning system for remote monitoring of an intelligent circuit breaker based on the Internet of Things, including a remote monitoring platform, which is communicatively connected to a data acquisition and storage module, a cloud data analysis module, an abnormal diagnosis module, an abnormal location module, and a fault warning module. Among them, the modules are electrically connected to each other;

[0060] The data acquisition and storage module is used to collect the operation data of the intelligent circuit breaker in real time through sensors and store it in a cloud server. The data acquisition and storage module includes an intelligent sensor unit, an Internet of Things communication unit, and a cloud storage unit;

[0061] Among them, the intelligent sensor unit is used to collect various operation data of the intelligent circuit breaker through various types of sensors deployed, including current, voltage, temperature, switch state, load, and power quality. In the area to be monitored, according to the layout of the intelligent circuit breaker and the monitoring requirements, multiple types of sensors are deployed, and the operation data of the intelligent circuit breaker is continuously and synchronously collected at a preset acquisition frequency. Among them, the sensors include current sensors, voltage sensors, temperature sensors, switch state sensors, load sensors, and power quality sensors, etc., to obtain operation data including current, voltage, temperature, switch state, load, and power quality. The current and voltage sensors capture the changes in electrical parameters in the circuit, the temperature sensor monitors the temperature of key parts, the switch state sensor records the opening and closing conditions of the switch, the load sensor measures the load size, and the power quality sensor evaluates the stability and quality of the power. The collected operation data of the intelligent circuit breaker is preprocessed, including preprocessing operations such as filtering and normalization. Among them, high-frequency noise is removed through a filter, and the normalization process unifies the data to the same dimension range. The preprocessed various operation data is integrated and arranged in an orderly manner according to the type and acquisition time of the data to form a structured data packet, clearly presenting the operation state information of the intelligent circuit breaker;

[0062] The Internet of Things communication unit is used to transmit the operation data collected by the intelligent sensor unit to the cloud server in real time through Internet of Things technology, realizing remote data transmission, ensuring the timeliness and accuracy of data, while reducing the on-site wiring cost and maintenance difficulty; The cloud storage unit is used to store the historical and real-time operation data of the intelligent circuit breaker in the cloud database, support long-term data storage and query, provide efficient data storage and management capabilities, support the storage and retrieval of large-scale data. The Internet of Things communication unit establishes a communication connection with the intelligent sensor unit, and according to the preset Internet of Things communication protocol, performs preliminary format conversion and encapsulation on the collected operation data, converting the operation data of the intelligent sensor into a standardized data frame that meets the requirements of remote transmission. Among them, the data frame contains a timestamp, sensor identification, data type, and numerical information, ensuring the integrity and traceability of data. Encrypt the encapsulated operation data through the Internet of Things communication unit, using the AES encryption algorithm to ensure the security of data during transmission. Transmit the encrypted operation data to the cloud server in real time through the selected communication network. Among them, the Internet of Things communication unit supports the function of resuming interrupted transmission. When the network is interrupted, the operation data is temporarily stored in the local storage unit and automatically retransmitted after the network is restored, ensuring the integrity and continuity of data. The cloud storage unit receives the historical and real-time operation data of the intelligent circuit breaker transmitted by the Internet of Things communication unit and stores it in the cloud database. The operation data is classified and stored according to time sequence and data type, supporting long-term storage and fast query. Among them, the cloud database adopts a distributed storage architecture to ensure the high availability and fault tolerance of data. At the same time, the cloud storage unit establishes data indexes and metadata to optimize data retrieval efficiency and support the fast query and analysis of large-scale data;

[0063] The cloud data analysis module is used to analyze the characteristics of the operation data of the intelligent circuit breaker and mark the operation state characteristics with anomalies to obtain an anomaly feature sequence list. The cloud data analysis module includes a feature analysis unit and an anomaly marking and integration unit;

[0064] Among them, the feature analysis unit is used to perform feature analysis on the operation data of the intelligent circuit breaker stored in the cloud server, extract the operation state features related to the abnormal analysis of the circuit breaker, perform feature analysis on the operation data of the intelligent circuit breaker stored in the cloud server, determine the operation data including current, voltage, temperature, switch state, load, and power quality in combination with the historical operation data and the remote monitoring requirements of the intelligent circuit breaker, and then determine the operation state features associated with the abnormal analysis. Analyze the operation state features respectively extracted from the current, voltage, temperature, switch state, load, and power quality data, which are the current mutation rate, voltage deviation rate, temperature rise rate of key parts, number of abnormal trippings, load imbalance degree, and harmonic distortion rate. Among them, the current mutation rate is calculated by analyzing the current data collected by the current sensor, calculating the current change rate between adjacent time points, extracting the current value from the time series data, calculating the difference in current between adjacent time points, dividing the difference by the time interval to obtain the current change rate, and performing statistical analysis on the current change rate to identify the mutation point. The current mutation rate is used to detect abnormal current fluctuations in the circuit, such as short circuit or overload conditions; the voltage deviation rate is calculated by comparing the percentage deviation between the actual voltage and the rated voltage. The actual voltage value is collected from the voltage sensor, the difference between the actual voltage and the rated voltage is calculated, and the difference is divided by the rated voltage to obtain the deviation rate. Statistical analysis is performed on the deviation rate to identify abnormal conditions. The voltage deviation rate is used to evaluate the stability of the voltage. Excessively high deviation rates may affect the normal operation of the equipment and even cause equipment damage; the temperature rise rate of key parts is calculated by calculating the temperature change rate from the data collected by the temperature sensor. The temperature data of the key parts is collected from the temperature sensor, the difference in temperature between adjacent time points is calculated, and the difference is divided by the time interval to obtain the temperature rise rate. Statistical analysis is performed on the temperature rise rate to identify abnormal temperature rises. The temperature rise rate is used to detect the risk of equipment overheating; the number of abnormal trippings is calculated by counting the unplanned tripping events within a unit time. The tripping event data is collected from the switch state sensor, the number of trippings within a unit time is counted, and the planned tripping events are excluded to obtain the number of abnormal trippings. Statistical analysis is performed on the number of abnormal trippings to identify the equipment with frequent trippings. The number of abnormal trippings is used to identify potential circuit faults or equipment problems; the load imbalance degree is calculated by analyzing the differences in three-phase currents. The three-phase current data is collected from the current sensor, the average value of the three-phase currents is calculated, the difference between each phase current and the average value is calculated, and the difference is divided by the average value to obtain the load imbalance degree. Statistical analysis is performed on the imbalance degree to identify abnormal conditions. The load imbalance degree is used to evaluate the distribution of three-phase loads;The harmonic distortion rate is calculated by analyzing the data collected by the power quality sensor. The spectrum data of voltage and current are collected from the power quality sensor to identify the amplitudes of the fundamental wave and each harmonic. The total harmonic distortion rate is calculated, which is the ratio of the sum of the squares of the amplitudes of each harmonic to the amplitude of the fundamental wave. Statistical analysis is performed on the harmonic distortion rate to identify abnormal conditions. The harmonic distortion rate is used to evaluate the stability of the power system. The extracted operating state features are integrated in a predefined format to form a structured feature dataset. The feature dataset contains the timestamp, feature type, and numerical information of each operating state feature to ensure the traceability and integrity of the features;

[0065] The abnormal marking integration unit is used to set the reference values of the operating state features in combination with historical operation data and monitoring requirements, distinguish the operating state features with abnormalities, and then integrate the operating state features to obtain an abnormal feature sequence list. Analyze various operating state features in combination with historical operation data and monitoring requirements. By statistically analyzing the historical operation data, determine the normal operation range of each operating state feature, and in combination with the monitoring requirements of intelligent circuit breaker abnormal analysis, set corresponding reference values for each operating state feature. At the same time, obtain the latest operating state feature data from the cloud server to ensure the integrity and accuracy of the data. Compare the extracted operating state feature data with the set reference values, calculate the deviation between the feature data and the reference values, and based on the preset deviation threshold, judge whether the deviation exceeds the normal range to identify whether there is an abnormality. If the feature data exceeds the deviation threshold defined by the reference value, it is determined that the operating state feature has an abnormality, and then mark the abnormal operating state feature, record the type and occurrence time information of the abnormality, and integrate the marked operating state features in chronological order and feature type. Arrange each abnormal feature in chronological order of occurrence, and at the same time classify according to the feature type to generate an abnormal feature sequence list. The abnormal feature sequence list contains the specific time, type, value, and deviation degree information of each abnormal feature;

[0066] The abnormal diagnosis module is used to utilize the abnormal feature sequence list and combine the pre-trained fault diagnosis model based on the neural network model to identify the abnormal mode of the intelligent circuit breaker;

[0067] The abnormal location module is used to combine the geographical location information and operation data of the intelligent circuit breaker to locate the abnormal point, visually display the location of the abnormal intelligent circuit breaker, improve the response speed of maintenance personnel, quickly locate the problem, and reduce the maintenance cost;

[0068] The fault warning module is used to combine the identified abnormal mode of the intelligent circuit breaker to issue a warning signal and output a warning report including the abnormal type, location, and severity information, and then visually display the warning report.

[0069] Embodiment 2, such as Figure 1 、Figure 2 As shown in the figure, on the basis of Embodiment 1, the present invention provides a technical solution: Preferably, the abnormal diagnosis module specifically includes:

[0070] Extract and mark the operating state features with abnormalities from historical operation data, match the abnormal patterns of the intelligent circuit breaker based on the abnormal operating state features, which are respectively minor abnormalities and faults, and then integrate the marked operating state features and the matched abnormal patterns to obtain a data set. Divide the data set into a training set, a validation set, and a test set. Select a neural network model as the basic architecture, determine the number of layers of the neural network, the number of neurons in each layer, the activation function, and the loss function parameters. Randomly initialize the weight and bias parameters of the neural network. Input the training set data into the neural network model, obtain the output result through the calculations of each layer, compare the output result of the neural network model with the true label, calculate the loss value, which reflects the difference between the model prediction result and the true result. Calculate the gradient according to the loss value, and update the weight and bias parameters of the neural network model through the backpropagation algorithm to reduce the loss value. Repeat the forward propagation, loss calculation, and backpropagation steps until the preset number of iterations is reached. During the training process, use the validation set data to verify the model and evaluate the generalization ability of the model. After the training is completed, use the test set data to test the model and evaluate the accuracy and reliability of the model to obtain a fault diagnosis model. Input the abnormal operating state features in the abnormal feature list into the fault diagnosis model, compare them with various abnormal patterns, and output a confidence score to determine whether there is an abnormal pattern in the intelligent circuit breaker. Set an abnormal classification threshold T, and then analyze the output result to classify the abnormal pattern, which is minor abnormality and fault;

[0071] The calculation process of the confidence score is as follows:

[0072] For each operating state feature, calculate the relative deviation between its actual value and the reference value. The relative deviation reflects the degree of difference between the feature value and the reference value. If the relative deviation is 0, it means the feature value is exactly the same as the reference value. If the relative deviation is large, it means the feature value deviates significantly from the reference value. Then, take the absolute value of the relative deviation for each operating state feature. The absolute value ensures that the magnitude of the deviation is not affected by the positive or negative sign, and only focuses on the amplitude of the deviation. Perform a radical calculation on the absolute value of the relative deviation for each operating state feature. The radical part is actually equal to the absolute value of the relative deviation. Squaring and then taking the square root cancels the influence of the sign and ensures the non-negativity of the deviation. Set an adjustment parameter and apply an exponential decay function to the absolute value of the relative deviation for each operating state feature. Calculate the exponential decay factor, multiply the radical part of each operating state feature by the exponential decay factor, and sum over all operating state features to calculate the weighted deviation sum, comprehensively considering the deviations of all operating state features and their decay effects. Sum the absolute values of the relative deviations for all operating state features and apply the natural logarithm function for adjustment. Non-linearly adjust the total deviation through the natural logarithm function to ensure that the denominator will not be zero and amplify larger total deviations. Then, multiply the total number of operating state features by the natural logarithm adjustment term to calculate the denominator part. Divide the weighted deviation sum as the numerator part by the denominator part to obtain the confidence score for analyzing the degree of deviation between the actual value and the reference value of the operating state feature;

[0073] The calculation expression of the confidence score is:

[0074] ;

[0075] In the formula, is the confidence score, is the actual value of the th operating state feature, is the reference value of the th operating state feature, is the total number of operating state features, is the adjustment parameter used to control the speed of exponential decay, and its value range is , The value range of is When When it is close to 0, it indicates that the deviation between the eigenvalue representing the operating state characteristic and the reference value is large, and the confidence level is low. The numerator part combines a radical and an exponential function to perform a weighted sum of the deviations of each operating state characteristic. The radical part calculates the absolute value of the deviation, and the exponential function part attenuates the deviation, so that the influence of larger deviations on the sum is smaller. The denominator part adjusts the total deviation through the natural logarithm function to ensure that the denominator is not zero, and at the same time non-linearly amplifies the larger total deviation, so that the confidence score decreases as the deviation increases. If , it is classified as a minor anomaly. If , it is classified as a fault;

[0076] The anomaly location module specifically includes:

[0077] Collect the geographical location information and operating data of the intelligent circuit breaker. The geographical location information includes the installation location coordinates of the circuit breaker, and collect the output of the anomaly diagnosis module, including the abnormal operating state characteristics and diagnosis results. Associate and match the geographical location information with the corresponding operating data through a unique identifier (circuit breaker ID) to ensure that the location of each circuit breaker corresponds one-to-one with its operating state information. Analyze the output of the anomaly diagnosis module to judge the intelligent circuit breakers with abnormal operating states, and locate the abnormal circuit breaker points corresponding to each abnormal operating state characteristic by matching the abnormal operating state characteristics in the output of the anomaly diagnosis module with the geographical location information. Then, combine the historical operating data and maintenance records to analyze the frequency and potential causes of the abnormal circuit breaker points, and provide support for maintenance decisions. Use geographic information system (GIS) technology to mark the locations of the intelligent circuit breakers with anomalies on the electronic map, and use different colors to distinguish the anomaly types, with red indicating a fault and yellow indicating a minor anomaly;

[0078] The fault warning module specifically includes:

[0079] Receive the intelligent circuit breaker anomaly pattern information identified by the anomaly diagnosis module, analyze the anomaly pattern, judge whether it reaches the warning condition, determine that there is an anomaly pattern that needs to be warned, and immediately trigger a warning signal. At the same time, extract the key information in the anomaly pattern, including the anomaly type, anomaly location, and severity. Based on the triggered warning signal and the extracted key information, generate a warning report. Among them, the content of the warning report includes the anomaly type, occurrence location, occurrence time point, severity, and recommended maintenance measures, and display the warning report through a visual interface.

[0080] As described above, it is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, and all should be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims described.

Claims

1. A fault warning system for remote monitoring of an intelligent circuit breaker based on the Internet of Things, including a remote monitoring platform, characterized in that: The remote monitoring platform is communicatively connected to a data acquisition and storage module, a cloud data analysis module, an anomaly diagnosis module, an anomaly location module, and a fault warning module. Among them, the modules are electrically connected to each other; The data acquisition and storage module is used to collect the operation data of the intelligent circuit breaker in real time through sensors and store it in the cloud server; The cloud data analysis module is used to perform feature analysis on the operation data of the intelligent circuit breaker, mark the operation state features with anomalies, and obtain an anomaly feature sequence list; The anomaly diagnosis module is used to use the anomaly feature sequence list and combine a fault diagnosis model pre-trained based on a neural network model to identify the anomaly mode of the intelligent circuit breaker; The anomaly location module is used to combine the geographical location information and operation data of the intelligent circuit breaker to locate the anomaly point; The fault warning module is used to combine the identified anomaly mode of the intelligent circuit breaker, issue a warning signal, output a warning report, and then visually display the warning report.

2. The fault warning system for remote monitoring of an intelligent circuit breaker based on the Internet of Things according to claim 1, characterized in that: The data acquisition and storage module includes an intelligent sensor unit, an Internet of Things communication unit, and a cloud storage unit; Among them, the intelligent sensor unit is used to collect various operation data of the intelligent circuit breaker through various types of sensors deployed, including current, voltage, temperature, switch status, load, and power quality; The Internet of Things communication unit is used to transmit the operation data collected by the intelligent sensor unit to the cloud server in real time through Internet of Things technology; The cloud storage unit is used to store the historical and real-time operation data of the intelligent circuit breaker in the cloud database.

3. The fault warning system for remote monitoring of an intelligent circuit breaker based on the Internet of Things according to claim 2, wherein: The intelligent sensor unit specifically includes: In the area to be monitored, according to the layout of the intelligent circuit breaker and the monitoring requirements, deploy various types of sensors, and continuously and synchronously collect the operation data of the intelligent circuit breaker at a preset collection frequency. Among them, the sensors include current sensors, voltage sensors, temperature sensors, switch status sensors, load sensors, and power quality sensors to obtain operation data including current, voltage, temperature, switch status, load, and power quality; Preprocess the collected operation data of the intelligent circuit breaker, including preprocessing operations such as filtering and normalization; Integrate the preprocessed various operation data, arrange them in an orderly manner according to the data type and collection time, and form a structured data packet.

4. The fault warning system for remote monitoring of an intelligent circuit breaker based on the Internet of Things according to claim 2, characterized in that: The Internet of Things communication unit and the cloud storage unit specifically include: The Internet of Things communication unit establishes a communication connection with the intelligent sensor unit, performs preliminary format conversion and encapsulation on the collected operation data according to the preset Internet of Things communication protocol, and converts the operation data of the intelligent sensor into a standardized data frame that meets the requirements of remote transmission; Encrypt the encapsulated operation data through the Internet of Things communication unit, use the AES encryption algorithm, and transmit the encrypted operation data to the cloud server in real time through the selected communication network; The cloud storage unit receives the historical and real-time operation data of the intelligent circuit breaker transmitted by the Internet of Things communication unit and stores it in the cloud database.

5. The fault warning system for remote monitoring of an intelligent circuit breaker based on the Internet of Things according to claim 2, characterized in that: The cloud data analysis module includes a feature analysis unit and an anomaly marking and integration unit; Among them, the feature analysis unit is used to perform feature analysis on the operation data of the intelligent circuit breaker stored in the cloud server, and extract the operation state features related to the abnormal analysis of the circuit breaker. The abnormal mark integration unit is used to combine the historical operation data and the monitoring requirements, set the reference values of the operation state features, distinguish the operation state features with abnormalities, and then integrate the operation state features to obtain an abnormal feature sequence list.

6. The fault warning system for remote monitoring of an intelligent circuit breaker based on the Internet of Things according to claim 5, characterized in that: The feature analysis unit specifically includes: Perform feature analysis on the operation data of the intelligent circuit breaker stored in the cloud server, combine the historical operation data and the remote monitoring requirements of the intelligent circuit breaker, determine the operation data including current, voltage, temperature, switch state, load, and power quality, and then determine the operation state features associated with the abnormal analysis. Analyze the operation state features respectively extracted from the current, voltage, temperature, switch state, load, and power quality data, which are the current mutation rate, voltage deviation rate, temperature rise rate of key parts, abnormal tripping times, load imbalance degree, and harmonic distortion rate. Integrate the extracted operation state features according to a predefined format to form a structured feature data set, and the feature data set contains the time stamp, feature type, and numerical information of each operation state feature.

7. The fault warning system for remote monitoring of an intelligent circuit breaker based on the Internet of Things according to claim 6, characterized in that: The abnormal mark integration unit specifically includes: Combine the historical operation data and the monitoring requirements, analyze various operation state features, determine the normal operation range of each operation state feature by statistically analyzing the historical operation data, and combine the monitoring requirements of the abnormal analysis of the intelligent circuit breaker to set the corresponding reference values for each operation state feature. At the same time, obtain the latest operation state feature data from the cloud server. Compare the extracted operation state feature data with the set reference values, calculate the deviation between the feature data and the reference values, and judge whether the deviation exceeds the normal range according to the preset deviation threshold to identify whether there is an abnormality. If the feature data exceeds the deviation threshold defined by the reference value, it is determined that the operation state feature has an abnormality, and then mark the abnormal operation state feature, and record the type and occurrence time information of the abnormality. Integrate the marked operation state features in chronological order and feature type, arrange each abnormal feature in chronological order of occurrence, and classify them according to the feature type at the same time to generate an abnormal feature sequence list.

8. An intelligent circuit breaker remote monitoring fault warning system based on the Internet of Things according to claim 5, characterized in that: The abnormal diagnosis module specifically includes: Extract and mark the operation state features with abnormalities from the historical operation data, match the abnormal patterns of the intelligent circuit breaker based on the abnormal operation state features, which are respectively minor abnormalities and faults, and then integrate the marked operation state features and the matched abnormal patterns to obtain a data set, and divide the data set into a training set, a validation set, and a test set. Select the neural network model as the basic architecture, determine the number of layers of the neural network, the number of neurons in each layer, the activation function, and the loss function parameters, randomly initialize the weight and bias parameters of the neural network, input the training set data into the neural network model, and use the validation set data to verify the model during the training process. After the training is completed, use the test set data to test the model to obtain a fault diagnosis model. Input the abnormal operation state features in the abnormal feature sequence list into the fault diagnosis model, compare them with various abnormal patterns, and output a confidence score to determine whether there is an abnormal pattern in the intelligent circuit breaker. Set an abnormal classification threshold T, and then analyze the output results to classify the abnormal patterns, namely minor abnormalities and faults.

9. The fault warning system for remote monitoring of an intelligent circuit breaker based on the Internet of Things according to claim 8, characterized in that: The calculation process of the confidence score is as follows: For each operation state feature, calculate the relative deviation between its actual value and the reference value, and then take the absolute value of the relative deviation of each operation state feature; Perform a radical calculation on the absolute value of the relative deviation of each operation state feature, set an adjustment parameter, apply an exponential decay function to the absolute value of the relative deviation of each operation state feature, and calculate the exponential decay factor; Multiply the radical part of each operation state feature by the exponential decay factor, and sum all the operation state features to calculate the weighted deviation sum; Sum the absolute values of the relative deviations of all operation state features, apply the natural logarithm function for adjustment, and then multiply the total number of operation state features by the natural logarithm adjustment term to calculate the denominator part; Divide the weighted deviation sum as the numerator part by the denominator part to obtain the confidence score to analyze the deviation degree between the actual value and the reference value of the operation state features.

10. The fault warning system for remote monitoring of an intelligent circuit breaker based on the Internet of Things according to claim 8, characterized in that: The abnormal location module specifically includes: Collect the geographical location information and operation data of the intelligent circuit breaker. The geographical location information includes the installation position coordinates of the circuit breaker, and collect the output of the abnormal diagnosis module, including abnormal operation state features and diagnosis results, and associate and match the geographical location information with the corresponding operation data through a unique identifier; Analyze the output of the abnormal diagnosis module, judge the intelligent circuit breakers with abnormal motion states, and locate the abnormal circuit breaker points corresponding to each abnormal operation state feature by matching the abnormal operation state features in the output of the abnormal diagnosis module with the geographical location information. Then, combine the historical operation data and maintenance records to analyze the frequency and potential causes of the abnormal circuit breaker points; Use geographic information system technology to mark the locations of the intelligent circuit breakers with abnormalities on the electronic map, and use different colors to distinguish the types of abnormalities. Red indicates a fault, and yellow indicates a minor abnormality.

Images