Power equipment intelligent gateway fault detection system based on Internet of Things

Abstract

The invention discloses a power equipment intelligent gateway fault detection system based on the Internet of Things, relates to the technical field of power equipment intelligent gateways, and is used for solving the problem that an existing power equipment monitoring system is inaccurate in fault detection. Comprising a power equipment access module, a data preprocessing and edge calculation module, a data storage and analysis module and a fault diagnosis and alarm module which are in signal connection. The power equipment access module is used for collecting operation state data of power equipment; the data preprocessing and edge calculation module performs cleaning, format conversion and preliminary calculation on the collected data, so that data redundancy is reduced, and the processing efficiency is improved; the data storage and analysis module stores the processed data and extracts feature information by using a big data analysis method; and the fault diagnosis and alarm module carries out fault identification based on an analysis result and triggers an alarm signal so as to realize accurate detection and efficient maintenance of the intelligent gateway of the power equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent gateways for electric power equipment, and more specifically, to a fault detection system for intelligent gateways for electric power equipment based on the Internet of Things. Background Art

[0002] As the power system develops towards intelligence and automation, a large number of power equipment requires efficient and stable remote monitoring and management. Traditional monitoring systems rely on fixed protocols and centralized data processing methods, and have problems such as poor equipment compatibility, incomplete data collection, and delayed fault detection, making it difficult to meet the needs of modern power systems for efficient operation and maintenance.

[0003] Existing smart gateway products still have deficiencies in multi-protocol compatibility, data processing capabilities, fault diagnosis accuracy, etc. Some devices only support a single communication protocol, which makes it difficult for devices from different manufacturers to interconnect. On the other hand, traditional data analysis methods rely on cloud processing, making it difficult to identify and respond to on-site faults in a timely manner, increasing maintenance costs and operation and maintenance difficulties.

[0004] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an intelligent gateway fault detection system for power equipment based on the Internet of Things to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: In a preferred embodiment, it includes: a power equipment access module, a data preprocessing and edge computing module, a data storage and analysis module, a fault diagnosis and alarm module, and signal connections between the modules; The power equipment access module ensures safe access to power equipment through protocol identification and encryption authentication, collects power equipment operation data, and adopts a hierarchical configuration strategy to achieve automatic access and configuration of power equipment through the priority of power equipment with different protocols; The data preprocessing and edge computing module cleans the power equipment operation data through temporary storage, parsing, interpolation and anomaly detection, applies the decision tree classification model to judge the power equipment status, analyzes the operation mode through K-Means clustering, and uses the IsolationForest algorithm to detect fault signs; The data storage and analysis module uses a hierarchical storage architecture to optimize the management of power equipment operation data, and uses batch processing and stream processing to analyze the operation trend of power equipment, and uses Fourier transform, STL decomposition and wavelet transform to identify fault modes; The fault diagnosis and alarm module determines the cause of the fault through the fault knowledge base and reasoning method, combines random forest and LSTM to identify the fault type and abnormal trend, and adopts a hierarchical alarm mechanism; it also supports SNMP protocol to monitor the status of power equipment in real time, TR-069 to remotely manage power equipment, and automatically generates operation and maintenance reports.

[0007] In a preferred embodiment, when the power equipment is online, the power equipment access module automatically scans the communication port of the power equipment, monitors and captures the power equipment operation data packet, and adopts a protocol recognition engine to analyze the power equipment operation data packet using deep packet inspection technology to identify the communication protocol used. For supported protocols, the power equipment access module directly calls the corresponding parsing module to decode the data. For unknown protocols, the power equipment access module extracts protocol features and tries to match the existing protocol library. If it cannot be identified, the power equipment is marked as "to be manually configured"; When the power equipment is connected for the first time, the power equipment access module adopts TLS / SSL encryption authentication and OAuth2.0 power equipment authentication. After successful authentication, the power equipment access module allocates a unique session token to the power equipment; The power equipment access module uses a remote terminal unit to poll low-frequency power equipment operation data, and an event trigger mechanism for high-frequency abnormal power equipment operation data. The collected raw power equipment operation data is parsed into a structured format through the protocol parsing layer to perform a preliminary power equipment operation data integrity check; The power equipment access module adopts a double-layer cache mechanism, maintaining a short-term cache on the power equipment side based on Redis. When the power equipment network is abnormal, the SQLite-based persistent cache is started. When the power equipment network is normal, the power equipment access module automatically synchronizes and caches the power equipment operation data and marks the power equipment operation data that has been successfully uploaded. The power equipment access module uses the data conversion mapping table to convert the data structure of each protocol into a unified JSON format, and encapsulates the structured power equipment operation data in the standard format of timestamp + power equipment ID + measurement value; The power equipment access module adopts adaptive data compression and layered transmission strategies. In low-speed network environments, it uses lightweight compression algorithms LZ4 and Snappy. In high-speed network environments, it uses batch transmission Batching. In edge computing power equipment, it uses the MQTT protocol. In LPWAN Internet of Things scenarios, it uses the CBOR format. The power equipment access module uses an LSTM-based sequence classification model to automatically identify the power equipment protocol type, and automatically loads the corresponding parsing driver based on the identified protocol type. It also uses pattern matching and neural network structure reasoning to analyze the data frame structure of the power equipment operation data, and automatically maps the data fields through Few-ShotLearning.

[0008] In a preferred embodiment, when the power equipment is connected, the power equipment access module automatically scans the TCP / UDP port or serial port, listens to the power equipment operation data packet sent by the power equipment, and adapts the TCP device and the serial port device: MQTT corresponds to 1883, IEC61850MMS corresponds to 102, ModbusTCP corresponds to 502, ModbusRTU, DL / T645 are read through UART / RS485, and then the power equipment access module listens to the data stream and extracts the protocol feature fields: listens to and extracts the CONNECT, SUBSCRIBE, and PUBLISH fixed message headers for the MQTT protocol; listens to and extracts the message start identifier and function code for the Modbus protocol; listens to and extracts the 68H frame header, the power equipment address field, and the checksum for the DL / T645 protocol; listens to and extracts the IEC61850 protocol: MMS / GOOSE / SV-specific ASN.1 code; finally, the power equipment access module matches the extracted feature fields with the protocol library to determine the protocol type; The power equipment access module loads the corresponding parsing driver according to the protocol type: parses JSON load data for MQTT protocol power equipment, reads register data for Modbus protocol power equipment, decodes meter data frames for DL / T645 protocol power equipment, verifies CRC checksum, parses MMS / GOOSE / SV messages for IEC61850 protocol power equipment, and establishes logical node mapping; finally, initializes communication for MQTT, Modbus, DL / T645, and IEC61850 protocol power equipment; The power equipment access module converts the data structures of different protocols into computable data formats: directly parses the JSON format for MQTT data, reads data from the register address for Modbus protocol data, converts fields according to the mapping table, decodes data frames for DL / T645 protocol data, and parses fields according to the protocol specification, and extracts logical node data in the MMS / GOOSE message for IEC61850 protocol data; The power equipment access module determines the configuration priority of each protocol based on the real-time performance T of the power equipment operation data, the importance I of the power equipment operation data, the complexity C of the power equipment access, the reliability R of the power equipment communication, and the power consumption constraint E of the power equipment. The specific steps are as follows: Step A1: measure the value of the real-time performance T of the power equipment operation data by the power equipment's requirement for the update frequency of the power equipment operation data, measure the value of the importance I of the power equipment operation data by the type of the power equipment, determine the value of the power equipment access complexity C according to the complexity of the protocol, measure the value of the power equipment communication reliability R by the network quality and the support of the power equipment protocol, and measure the value of the power equipment power consumption constraint E by the power consumption mode of the power equipment; Step A2: Determine the comprehensive priority Ptotal of the protocol power equipment according to the quantified values ​​of the real-time performance T of the power equipment operation data, the importance I of the power equipment operation data, the access complexity C of the power equipment, the communication reliability R of the power equipment, and the power consumption constraint E of the power equipment, specifically according to the formula: Ptotal=Qt×T+Qi×I+Qc×C+Qr×R+Qe×E, where Qt represents the weight of the real-time performance T of the power equipment operation data, Qi represents the weight of the importance I of the power equipment operation data, Qc represents the weight of the access complexity C of the power equipment, Qr represents the weight of the communication reliability R of the power equipment, and Qe represents the weight of the power consumption constraint E of the power equipment, indicating the importance of different factors; The power equipment access module sorts all newly connected power equipment according to the comprehensive priority Ptotal, starting from the newly connected power equipment with the highest priority and gradually configuring the newly connected power equipment with lower scores.

[0009] In a preferred embodiment, the data preprocessing and edge computing module receives the power equipment operation data transmitted by the power equipment access module, and the edge computing power equipment temporarily stores the power equipment operation data through the data buffer queues Kafka and Redis. The data preprocessing and edge computing module uses a protocol parser to parse the original power equipment operation data, and standardizes the power equipment operation data of different protocols into a unified format; The data preprocessing and edge computing module uses moving average filling or interpolation method to process the missing power equipment operation data; The data preprocessing and edge computing module uses Z-Score, which is applicable to normally distributed data, to calculate the mean and standard deviation of the power equipment operation data, and uses IQR, which is applicable to non-normally distributed data, to calculate the IQR value of the power equipment operation data. It uses DBSCAN, which is applicable to anomaly detection in complex environments, to identify isolated points through neighboring point density calculation; it determines whether the power equipment operation data is abnormal, and finally standardizes the power equipment operation data format; The data preprocessing and edge computing module trains a decision tree-based power equipment status classification model to classify the power equipment status data and determine whether the power equipment is in normal, warning, or faulty states. K-Means clustering is used to cluster the long-term power equipment operation data to identify normal operating modes and detect abnormal modes. The IsolationForest algorithm is used to analyze the characteristic values ​​of power equipment operation data to detect fault signs in advance.

[0010] In a preferred embodiment, the data storage and intelligent analysis module adopts a column storage format for time series data, a relational database suitable for storing power equipment archives, operating status, maintenance logs and other information for structured data, and an object storage method for unstructured data. Then, a time slicing strategy is adopted to store the power equipment operating data according to time windows. The data storage and intelligent analysis module also establishes a multi-level index and adopts a cache mechanism. The data storage and intelligent analysis module uses an outlier detection algorithm to filter invalid power equipment operation data and scales the power equipment operation data to a uniform range through standardization; The data storage and intelligent analysis module performs batch analysis on historical power equipment operation data through batch processing suitable for offline big data analysis and stream processing suitable for real-time data analysis for anomaly detection. It also uses Fourier transform to analyze the frequency characteristics of signals, uses STL to separate long-term trends, periodic changes and random fluctuations, and uses wavelet transform technology to detect signal mutation points and identify abnormal patterns.

[0011] In a preferred embodiment, the fault diagnosis and alarm module establishes a knowledge base of power equipment faults, stores known fault modes, possible causes and corresponding treatment plans, and uses reasoning RBR to use IF-THEN rules to judge and reason about known faults. CBR infers the cause of faults by matching the similarity of historical fault cases. The fault diagnosis and alarm module uses a multi-classification model random forest to identify fault categories, and uses LSTM to analyze time series data and detect abnormal operation trends; and sets an alarm mechanism according to the scope and urgency of the fault impact; The fault diagnosis and alarm module uses the SNMP protocol to obtain the status of power equipment in real time, remotely upgrades the firmware and fixes software problems through TR-069 remote management that supports remote modification of power equipment parameters, and automatically generates operation and maintenance reports based on NLG that include major fault statistics, power equipment operation trends, and maintenance recommendations.

[0012] The present invention discloses an intelligent gateway fault detection system for electric power equipment based on the Internet of Things, which relates to the technical field of intelligent gateways for electric power equipment and is used to solve the problem of inaccurate fault detection in existing electric power equipment monitoring systems. It includes: an electric power equipment access module, a data preprocessing and edge computing module, a data storage and analysis module, a fault diagnosis and alarm module, and signal connections between the modules. The electric power equipment access module is used to collect the operating status data of the electric power equipment; the data preprocessing and edge computing module cleans, converts the format and performs preliminary calculations on the collected data to reduce data redundancy and improve processing efficiency; the data storage and analysis module stores the processed data and extracts feature information using a big data analysis method; the fault diagnosis and alarm module identifies faults based on the analysis results and triggers an alarm signal to achieve accurate detection and efficient maintenance of the intelligent gateway for electric power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 The figure is a schematic diagram of the structure of the intelligent gateway fault detection system for power equipment based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0015] Example The present invention discloses an intelligent gateway fault detection system for electric power equipment based on the Internet of Things, comprising: an electric power equipment access module, a data preprocessing and edge computing module, a data storage and analysis module, a fault diagnosis and alarm module, and signal connections between the modules.

[0016] The power equipment access module is mainly responsible for connecting to the power equipment intelligent gateway, collecting power equipment operation data, including: current, voltage, temperature, communication status, and transmitting the data to the data preprocessing and edge computing module after standardization.

[0017] Specifically, the power equipment access module is compatible with MQTT, Modbus, DL / T645, IEC61850 and other protocols to adapt to data access of different types of power equipment.

[0018] First, when the power equipment goes online, the power equipment access module automatically scans the communication port of the power equipment, listens to and captures data packets, and uses a protocol identification engine to analyze the power equipment data packets using deep packet inspection (DPI) technology to identify the communication protocols used, such as MQTT, Modbus, DL / T645, and IEC61850; if the protocol is supported, the power equipment access module directly calls the corresponding parsing module to decode the data. If it is an unknown protocol, the power equipment access module extracts protocol features and tries to match the existing protocol library. If it still cannot be identified, the power equipment is marked as "pending manual configuration."

[0019] Furthermore, when the power equipment is first connected, the power equipment access module uses TLS / SSL encryption authentication and OAuth2.0 power equipment authentication to prevent illegal power equipment access. First, the power equipment access module sends an identity authentication request to the power equipment, and the power equipment returns identity information, such as power equipment ID, MAC address, firmware version, etc. At the same time, the service uses public and private key encryption (RSA or ECC) to verify the identity information to ensure that the power equipment is trustworthy. After successful authentication, the power equipment access module assigns a unique session token to the power equipment and establishes a secure communication channel.

[0020] Furthermore, the power equipment access module uses a remote terminal unit (RTU). For low-frequency data (such as temperature and voltage), a polling method is used to request power equipment data at fixed time intervals. For high-frequency abnormal data (such as instantaneous current mutations), an event trigger mechanism is used. When the power equipment detects that the threshold is exceeded, the data is immediately pushed to the collection end. The collected raw data is parsed into a structured format through the protocol parsing layer, and a preliminary data integrity check (such as missing value and duplicate value detection) is performed.

[0021] Furthermore, the power equipment access module adopts a two-layer cache mechanism (memory + local storage), maintaining a short-term cache (based on Redis or EdgeDB) on the power equipment side to store the data of the last few seconds; if the power equipment network is abnormal, the persistent cache (based on SQLite / LevelDB) is started to store data for a longer period of time. After the network is restored, the power equipment access module automatically synchronizes the cached data to the server and marks the successfully uploaded data to avoid repeated transmission.

[0022] Furthermore, the power equipment access module uses a data conversion mapping table (DataMapping) to convert the data structure of each protocol into a unified JSON / Protobuf format, and encapsulates the structured data in a standard format of timestamp + power equipment ID + measurement value.

[0023] Furthermore, the power equipment access module adopts adaptive data compression (AdaptiveDataCompression) and hierarchical transmission strategy (HierarchicalTransmission) to reduce data transmission overhead and improve transmission reliability. Specifically, in a low-speed network environment, a lightweight compression algorithm (such as LZ4, Snappy) is used to reduce the size of the data packet. In a high-speed network environment, batch transmission (Batching) is used to merge multiple data packets before sending them to reduce the request frequency. The MQTT protocol (QoS level 1 or 2) is used in edge computing power equipment to ensure reliable data transmission. In the 5G or LPWAN Internet of Things scenario, the CBOR (CompactBinaryObjectRepresentation) format is used, which is smaller than JSON and improves bandwidth utilization.

[0024] Finally, the power equipment access module uses an LSTM-based sequence classification model to automatically identify the power equipment protocol type, and automatically loads the corresponding parsing driver according to the identified protocol type. It also uses pattern matching and neural network structure reasoning to analyze the data frame structure of the power equipment. Through Few-ShotLearning, it automatically maps data fields such as current, voltage, temperature, etc., instead of relying on fixed field mapping rules, to achieve automatic configuration of newly added power equipment.

[0025] It should be noted that MQTT adopts a publish-subscribe mode. The power equipment actively pushes data. The server only needs to subscribe to the corresponding topic to obtain data without active request. At the same time, MQTT power equipment generally uses JSON or Protobuf format. The data field is dynamic. The data structure of different power equipment may be different, and it needs to be dynamically parsed according to the specific definition of the power equipment. Modbus adopts a master-slave query mode. The server must actively send a request to the power equipment before the power equipment returns the data. Therefore, it is necessary to maintain a polling mechanism on the server side. At the same time, Modbus uses a fixed-length binary format. The data is stored in a fixed register address. The meaning of each register needs to be parsed by looking up the mapping table. DL / T645 is also a request-response mechanism, but it also involves the identity authentication of the power equipment. Only after the authentication is passed can the server read the data. In addition, DL / T645 uses a strict fixed frame format. The byte position of each field is fixed. When parsing, it needs to be disassembled according to the byte position, otherwise it will cause data parsing errors. IEC61850 is more complicated. It not only supports server polling mode (MMS), but also supports active broadcast data (GOOSE / SV) of power equipment. The diversity of this communication mechanism makes it impossible to use a unified method to automatically configure all power equipment. IEC61850 also uses a logical node (LN) structure, and data is stored in a hierarchical manner. When parsing, it is necessary to read data objects at multiple levels and perform logical mapping. As a result, the data formats and parsing methods of different protocols are different, and it is impossible to adapt all power equipment through a universal automatic configuration method.

[0026] Therefore, the power equipment access module adopts a hierarchical configuration strategy to achieve automatic access and configuration of power equipment through steps such as protocol identification, driver loading, and data standardization.

[0027] First, the power equipment access module determines the communication protocol used by the newly connected power equipment to ensure the correct subsequent data parsing. Specifically, when the power equipment is connected, the power equipment access module automatically scans the TCP / UDP port or serial port, listens to the data packets sent by the power equipment, and adapts to TCP power equipment and serial port power equipment, such as: MQTT (default 1883), IEC61850MMS (102), ModbusTCP (502), ModbusRTU, DL / T645 read through UART / RS485, and then the power equipment access module listens to the data stream and extracts the protocol feature fields, for example, listens to and extracts the fixed message headers such as CONNECT, SUBSCRIBE, and PUBLISH for the MQTT protocol. Listens to and extracts the message start identifier and function code (such as 0x03 to read the register) for the Modbus protocol. Listens to and extracts the 68H frame header, power equipment address field, and checksum for the DL / T645 protocol. Listens to and extracts the IEC61850 protocol: MMS / GOOSE / SV-specific ASN.1 encoding. Finally, the power equipment access module matches the extracted feature fields with the protocol library to determine the protocol type. When the match fails, the LSTM sequence classification model is used to infer the protocol. If it still cannot be identified, it is marked as "pending manual configuration" and stored in the exception log.

[0028] After identifying the protocol, the power equipment access module loads the corresponding parsing driver according to the protocol type. For example, the MQTT protocol power equipment parses the JSON / Protobuf load data and registers the subscription topic. The Modbus protocol power equipment reads the register data and maps it to the standard data structure. The DL / T645 protocol power equipment decodes the meter data frame and verifies the CRC checksum. The IEC61850 protocol power equipment parses the MMS / GOOSE / SV message and establishes a logical node mapping. Finally, the communication of the four protocol power equipments, MQTT, Modbus, DL / T645, and IEC61850, is initialized to ensure reliable data transmission.

[0029] Furthermore, the power equipment access module converts the data structures of different protocols into computable data formats. Specifically, the JSON / Protobuf format is directly parsed for MQTT data to extract the power equipment data field. For Modbus protocol data, data is read from the register address and the fields are converted according to the mapping table. For DL / T645 protocol data, the data frame is decoded and the fields are parsed according to the protocol specification. For IEC61850 protocol data, the logical node (LN) data in the MMS / GOOSE message is extracted. Then all data are uniformly converted into timestamp + power equipment ID + data type + data value format. And a data mapping table (DataMapping) is used to convert protocol-specific fields into standard fields, and the converted data is uploaded to the data storage and analysis module.

[0030] Furthermore, the power equipment access module adopts QoS=1 or QoS=2 for MQTT protocol power equipment in the layered data transmission strategy, and the data of Modbus protocol power equipment is preferentially stored locally, and uploaded in batches after the network is restored, while ensuring reliable data transmission.

[0031] When multiple power devices with different protocols are connected at the same time, resources (such as computing power, network bandwidth, and data storage) are limited. Configuring all power devices at the same time may cause computing resource conflicts, communication bottlenecks, and data integrity issues. Therefore, in this embodiment, the power equipment access module comprehensively considers data real-time performance (T), power equipment data importance (I), power equipment access complexity (C), power equipment communication reliability (R), and power equipment power consumption constraints (E) to determine the configuration priority of each protocol, and completes the power equipment configuration in the optimal order to ensure priority processing of key data, stable communication, and rational use of resources.

[0032] First, the power equipment access module defines and quantifies the evaluation criteria for each factor. Specifically, the data real-time (T) value is measured by the power equipment's requirements for data update frequency, for example: high real-time requirements (for example, power equipment that needs to collect data every second) T=3; medium real-time requirements (for example, power equipment that needs to collect data every minute) T=2; low real-time requirements (for example, power equipment that needs to collect data every hour) T=1. The power equipment data importance (I) value is measured by the power equipment category: for example: high importance power equipment (for example, power grid core power equipment): I=3; medium importance power equipment (for example, auxiliary power equipment, general sensors): I=2; low importance power equipment (for example, non-critical detection power equipment): I=1; the power equipment access complexity (C) value is determined according to the complexity of the protocol, for example: high complexity protocol (for example, IE C61850): C=3; medium complexity protocol (e.g., DL / T645): C=2; low complexity protocol (e.g., Modbus, MQTT): C=1. The value of power equipment communication reliability (R) is measured by the network quality and the support of the power equipment protocol. For example: high reliability power equipment (e.g., through TCP / IP protocol, with multi-channel redundant network): R=3; medium reliability power equipment (e.g., Wi-Fi network transmission): R=2; low reliability power equipment (e.g., using relatively unstable wireless transmission technology): R=1. The value of power equipment power consumption constraint (E) is measured by the power consumption mode of the power equipment. For example: high power consumption constraint (e.g., battery-powered, low power consumption power equipment): E=3; medium power consumption constraint (e.g., external power supply power equipment): E=2; low power consumption constraint (e.g., power equipment always connected to the power grid): E=1.

[0033] Furthermore, a comprehensive score is calculated based on the five evaluation factors of data real-time (T), power equipment data importance (I), power equipment access complexity (C), power equipment communication reliability (R) and power equipment power consumption constraint (E) to determine the configuration priority of the power equipment. The specific formula is: Ptotal = Qt × T + Qi × I + Qc × C + Qr × R + Qe × E, where Qt represents the weight of data real-time (T), Qi represents the weight of power equipment data importance (I), Qc represents the weight of power equipment access complexity (C), Qr represents the weight of power equipment communication reliability (R), and Qe represents the weight of power equipment power consumption constraint (E), indicating the importance of different factors. Ptotal represents the comprehensive priority of the power equipment of this protocol. The higher the priority, the higher the priority of the power equipment of this protocol.

[0034] The power equipment access module sorts all newly connected power equipment according to the comprehensive priority Ptotal. The access order will start from the newly connected power equipment with the highest priority and gradually be configured to the newly connected power equipment with lower scores, ensuring that important data that needs to be processed in real time (such as relay status, transformer monitoring data, etc.) are configured first to ensure the efficient operation of the power equipment.

[0035] The data preprocessing and edge computing module mainly cleans and optimizes the power equipment operation data transmitted from the power equipment access module, and uses edge computing power equipment to perform preliminary analysis to improve the quality of power equipment operation data and reduce network transmission pressure.

[0036] First, the data preprocessing and edge computing module receives the power equipment operation data transmitted by the power equipment access module. The edge computing device temporarily stores the data through the data buffer queues Kafka and Redis to prevent data loss when the data traffic suddenly increases. At the same time, the data preprocessing and edge computing module uses the protocol parser (ProtocolParser) to parse the original data and standardize the data of different protocols into a unified format, such as JSON or CSV.

[0037] Furthermore, the data preprocessing and edge computing module uses moving average filling or interpolation method (linear interpolation, Lagrange interpolation) for small-scale missing data (such as missing single data points), determines the data missing ratio, and deletes abnormal records. For example, when the data missing ratio exceeds 30%, the data is judged invalid and deleted.

[0038] At the same time, the data preprocessing and edge computing module uses three anomaly detection algorithms to ensure that anomalies can be effectively detected under different data distribution conditions. Specifically, the Z-Score (standard score detection) for normal distribution data (such as voltage and current) is used to calculate the mean and standard deviation of the data. If the data point deviates from the mean by more than 3 times the standard deviation, it is marked as anomaly; the IQR (interquartile range method) for non-normal distribution data (such as equipment operation time) is used to calculate the IQR value (Q3-Q1) of the data. If the data exceeds [Q1-1.5×IQR,Q3+1.5×IQR], it is marked as anomaly; DBSCAN (density-based clustering anomaly detection) for anomaly detection in complex environments (such as load fluctuation data) is used to identify isolated points through neighboring point density calculation to determine whether it is abnormal. Finally, the data format is standardized, for example, the time format is standardized (such as unified to UTC timestamp), unit conversion (such as kV to V, MW to kW) and field name unification (to avoid inconsistent field naming for different devices).

[0039] Furthermore, the data preprocessing and edge computing module trains a power equipment status classification model based on a decision tree (DecisionTree), classifies the collected voltage, current, temperature and other data, and determines whether the equipment is in normal, warning, or faulty states. K-Means clustering is used to perform cluster analysis on the long-term operation data of the equipment, identify normal operation modes, and detect abnormal modes. The IsolationForest algorithm is used to analyze data feature values ​​to detect possible fault signs in advance. For example, a sudden increase in current may mean that the motor is overloaded, and a continuous increase in equipment temperature may mean a cooling system failure.

[0040] The data storage and intelligent analysis module is mainly used to store and manage data, and conduct in-depth analysis to provide decision-making basis for fault detection.

[0041] First, the data storage and intelligent analysis module adopts different storage architectures according to the time series data, structured data and unstructured data included in the power equipment operation data. Specifically, the column storage format is used for time series data (current, voltage, power, etc.) to optimize the writing and query of high-frequency data; for structured data (equipment status, operation and maintenance records, etc.), a relational database (PostgreSQL / MySQL) suitable for storing equipment archives, operation status, maintenance logs and other information is used; for unstructured data (fault logs, pictures, videos, etc.), object storage is used to support fast access to large files and distributed storage (HDFS / MinIO) suitable for storing large-scale log files and video surveillance data. Then, the time partitioning strategy is adopted to store data according to time windows to improve query efficiency, and a multi-level index (time index + equipment ID index) is established to optimize data retrieval performance. Finally, a cache mechanism (Redis / Memcached) is used to reduce database query load and improve response speed.

[0042] Furthermore, the data storage and intelligent analysis module uses an outlier detection algorithm to filter invalid data and improve data accuracy, and scales the data to a uniform range through standardization (Min-MaxScaling / Z-scoreNormalization) to prevent different dimensions from affecting the analysis results.

[0043] Finally, the data storage and intelligent analysis module uses batch processing (Hadoop+HDFS) for offline big data analysis and stream processing (Apache Spark Streaming / Flink) for real-time data analysis of anomaly detection to analyze historical data in batches and mine equipment operation trends. At the same time, the data storage and intelligent analysis module also uses time series analysis methods to mine equipment operation rules, such as using Fourier transform (FFT) to analyze the frequency characteristics of signals and identify periodic fault modes. Use STL (seasonal-trend decomposition) to separate long-term trends, periodic changes, and random fluctuations to improve prediction accuracy, and use wavelet transform (Wavelet Transform) technology to detect signal mutation points and identify abnormal patterns. Finally, the data storage and intelligent analysis module pushes the fault analysis results to the fault diagnosis and alarm module to achieve rapid response.

[0044] The fault diagnosis and alarm module is mainly used to identify power equipment faults, trigger alarms, and provide remote maintenance support based on the fault analysis results transmitted by the data storage and intelligent analysis module.

[0045] First, the fault diagnosis and alarm module establishes a knowledge base of power equipment faults, stores known fault modes, possible causes and corresponding treatment plans, and uses reasoning RBR to use IF-THEN rules to judge known faults (for example, "If the voltage fluctuation exceeds 10%, it may be a line fault") and reasoning CBR to infer the cause of the fault by matching the similarity of historical fault cases (for example, "The current fault characteristics are similar to the historical records of a certain equipment fault, which may be due to transformer aging"). Then, the fault diagnosis and alarm module uses a multi-classification model Random Forest to identify fault categories (such as short circuit, overload, and line aging), and uses LSTM (Long Short-Term Memory Network) to analyze time series data, detect abnormal operation trends, and warn potential faults in advance.

[0046] Furthermore, the fault diagnosis and alarm module sets an alarm mechanism based on the scope and urgency of the fault, and notifies the staff to handle it. For example, according to the scope and urgency of the fault, a three-level alarm mechanism is set: minor abnormalities that do not affect the operation of the equipment are low-level alarms, which are only stored in the log and reported to the operation and maintenance personnel regularly; equipment performance degradation and faults that may affect operation are intermediate alarms, which are notified to the operation and maintenance personnel via SMS, email, and APP push notifications, and the alarm log is recorded and marked as "pending"; serious faults that affect the safety of equipment or the entire power grid are high-level alarms, which are immediately connected to the SCADA system, linking other equipment to execute emergency plans (such as automatically cutting off the circuit), and using voice calls, WeChat / DingTalk notifications to directly warn the operation and maintenance person in charge.

[0047] Furthermore, the fault diagnosis and alarm module uses the SNMP protocol to obtain the device status (temperature, current, voltage) in real time, and remotely upgrades the firmware and fixes software problems through TR-069 remote management that supports remote modification of device parameters.

[0048] Finally, the fault diagnosis and alarm module automatically generates an operation and maintenance report based on NLG, which includes major fault statistics, equipment operation trends, and maintenance recommendations for decision-making reference.

[0049] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0050] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0051] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0052] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0053] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0054] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. Intelligent gateway fault detection system for power equipment based on the Internet of Things, It is characterized by comprising: power equipment access module, data preprocessing and edge computing module, data storage and analysis module, fault diagnosis and alarm module, and signal connection between modules; The power equipment access module ensures safe access to power equipment through protocol identification and encryption authentication, collects power equipment operation data, and adopts a hierarchical configuration strategy to achieve automatic access and configuration of power equipment through the priority of power equipment with different protocols; The data preprocessing and edge computing module cleans the power equipment operation data through temporary storage, parsing, interpolation and anomaly detection, applies the decision tree classification model to judge the power equipment status, analyzes the operation mode through K-Means clustering, and uses the IsolationForest algorithm to detect fault signs; The data storage and analysis module uses a hierarchical storage architecture to optimize the management of power equipment operation data, and uses batch processing and stream processing to analyze the operation trend of power equipment, and uses Fourier transform, STL decomposition and wavelet transform to identify fault modes; The fault diagnosis and alarm module determines the cause of the fault through the fault knowledge base and reasoning method, combines random forest and LSTM to identify the fault type and abnormal trend, and adopts a hierarchical alarm mechanism; it also supports the SNMP protocol to monitor the status of power equipment in real time, TR-069 to remotely manage power equipment, and automatically generates operation and maintenance reports.

2. According to the Internet of Things-based power equipment intelligent gateway fault detection system according to claim 1, it is characterized in that: When the power equipment is online, the power equipment access module automatically scans the communication port of the power equipment, monitors and captures the power equipment operation data packet, and adopts the protocol identification engine to analyze the power equipment operation data packet using deep packet inspection technology to identify the communication protocol used. For supported protocols, the power equipment access module directly calls the corresponding parsing module to decode the data. For unknown protocols, the power equipment access module extracts protocol features and tries to match the existing protocol library. If it cannot be identified, the power equipment is marked as "pending manual configuration"; When the power equipment is connected for the first time, the power equipment access module adopts TLS / SSL encryption authentication and OAuth2.0 power equipment authentication. After successful authentication, the power equipment access module allocates a unique session token to the power equipment; The power equipment access module uses a remote terminal unit to poll low-frequency power equipment operation data, and an event trigger mechanism for high-frequency abnormal power equipment operation data. The collected raw power equipment operation data is parsed into a structured format through the protocol parsing layer to perform a preliminary power equipment operation data integrity check; The power equipment access module adopts a double-layer cache mechanism, maintaining a short-term cache on the power equipment side based on Redis. When the power equipment network is abnormal, the SQLite-based persistent cache is started. When the power equipment network is normal, the power equipment access module automatically synchronizes and caches the power equipment operation data and marks the power equipment operation data that has been successfully uploaded. The power equipment access module uses the data conversion mapping table to convert the data structure of each protocol into a unified JSON format, and encapsulates the structured power equipment operation data in the standard format of timestamp + power equipment ID + measurement value; The power equipment access module adopts adaptive data compression and layered transmission strategies. In low-speed network environments, it uses lightweight compression algorithms LZ4 and Snappy. In high-speed network environments, it uses batch transmission Batching. In edge computing power equipment, it uses the MQTT protocol. In LPWAN Internet of Things scenarios, it uses the CBOR format. The power equipment access module uses an LSTM-based sequence classification model to automatically identify the power equipment protocol type, and automatically loads the corresponding parsing driver based on the identified protocol type. It also uses pattern matching and neural network structure reasoning to analyze the data frame structure of the power equipment operation data, and automatically maps the data fields through Few-ShotLearning.

3. The power equipment intelligent gateway fault detection system based on the Internet of Things according to claim 2 is characterized in that: When the power equipment is connected, the power equipment access module automatically scans the TCP / UDP port or serial port, listens to the power equipment operation data packet sent by the power equipment, and adapts the TCP device and serial port device: MQTT corresponds to 1883, IEC61850MMS corresponds to 102, ModbusTCP corresponds to 502, ModbusRTU, DL / T645 are read through UART / RS485, and then the power equipment access module listens to the data stream and extracts the protocol feature fields: listens to and extracts the CONNECT, SUBSCRIBE, and PUBLISH fixed message headers for the MQTT protocol; listens to and extracts the message start identifier and function code for the Modbus protocol; listens to and extracts the 68H frame header, power equipment address field, and checksum for the DL / T645 protocol; listens to and extracts the MMS / GOOSE / SV-specific ASN.1 code for the IEC61850 protocol; finally, the power equipment access module matches the extracted feature fields with the protocol library to determine the protocol type; The power equipment access module loads the corresponding parsing driver according to the protocol type: parses JSON load data for MQTT protocol power equipment, reads register data for Modbus protocol power equipment, decodes meter data frames for DL / T645 protocol power equipment, verifies CRC checksum, parses MMS / GOOSE / SV messages for IEC61850 protocol power equipment, and establishes logical node mapping; finally, initializes communication for MQTT, Modbus, DL / T645, and IEC61850 protocol power equipment; The power equipment access module converts the data structures of different protocols into computable data formats: directly parses the JSON format for MQTT data, reads data from the register address for Modbus protocol data, converts fields according to the mapping table, decodes data frames for DL / T645 protocol data, and parses fields according to the protocol specification, and extracts logical node data in the MMS / GOOSE message for IEC61850 protocol data; The power equipment access module determines the configuration priority of each protocol based on the real-time performance T of the power equipment operation data, the importance I of the power equipment operation data, the complexity C of the power equipment access, the reliability R of the power equipment communication, and the power consumption constraint E of the power equipment. The specific steps are as follows: Step A1: measure the value of the real-time performance T of the power equipment operation data by the power equipment's requirement for the update frequency of the power equipment operation data, measure the value of the importance I of the power equipment operation data by the type of the power equipment, determine the value of the power equipment access complexity C according to the complexity of the protocol, measure the value of the power equipment communication reliability R by the network quality and the support of the power equipment protocol, and measure the value of the power equipment power consumption constraint E by the power consumption mode of the power equipment; Step A2: Determine the comprehensive priority Ptotal of the protocol power equipment according to the quantified values ​​of the real-time performance T of the power equipment operation data, the importance I of the power equipment operation data, the access complexity C of the power equipment, the communication reliability R of the power equipment, and the power consumption constraint E of the power equipment, specifically according to the formula: Ptotal=Qt×T+Qi×I+Qc×C+Qr×R+Qe×E, where Qt represents the weight of the real-time performance T of the power equipment operation data, Qi represents the weight of the importance I of the power equipment operation data, Qc represents the weight of the access complexity C of the power equipment, Qr represents the weight of the communication reliability R of the power equipment, and Qe represents the weight of the power consumption constraint E of the power equipment, indicating the importance of different factors; The power equipment access module sorts all newly connected power equipment according to the comprehensive priority Ptotal, starting from the newly connected power equipment with the highest priority and gradually configuring the newly connected power equipment with lower scores.

4. The power equipment intelligent gateway fault detection system based on the Internet of Things according to claim 3 is characterized in that; The data preprocessing and edge computing module receives the power equipment operation data transmitted by the power equipment access module. The edge computing power equipment temporarily stores the power equipment operation data through the data buffer queues Kafka and Redis. The data preprocessing and edge computing module uses a protocol parser to parse the original power equipment operation data and standardize the power equipment operation data of different protocols into a unified format. The data preprocessing and edge computing module uses moving average filling or interpolation method to process the missing power equipment operation data; The data preprocessing and edge computing module uses Z-Score, which is applicable to normally distributed data, to calculate the mean and standard deviation of the power equipment operation data, and uses IQR, which is applicable to non-normally distributed data, to calculate the IQR value of the power equipment operation data. It uses DBSCAN, which is applicable to anomaly detection in complex environments, to identify isolated points through neighboring point density calculation; it determines whether the power equipment operation data is abnormal, and finally standardizes the power equipment operation data format; The data preprocessing and edge computing module trains a power equipment status classification model based on a decision tree, classifies the power equipment status data, and determines whether the power equipment is in normal, warning, or fault status; And K-Means clustering is used to perform cluster analysis on the long-term operation data of power equipment to identify normal operation modes and detect abnormal modes; The IsolationForest algorithm is used to analyze the characteristic values ​​of power equipment operation data to detect fault signs in advance.

5. The power equipment intelligent gateway fault detection system based on the Internet of Things according to claim 4 is characterized in that: The data storage and intelligent analysis module uses column storage format for time series data, and a relational database suitable for storing power equipment archives, operating status, maintenance logs and other information for structured data. Object storage is used for unstructured data, and then a time slicing strategy is adopted to store power equipment operating data according to time windows. The data storage and intelligent analysis module also establishes multi-level indexes and adopts a cache mechanism; The data storage and intelligent analysis module uses an outlier detection algorithm to filter invalid power equipment operation data and scales the power equipment operation data to a uniform range through standardization; The data storage and intelligent analysis module performs batch analysis on historical power equipment operation data through batch processing suitable for offline big data analysis and stream processing suitable for real-time data analysis for anomaly detection. It also uses Fourier transform to analyze the frequency characteristics of signals, uses STL to separate long-term trends, periodic changes and random fluctuations, and uses wavelet transform technology to detect signal mutation points and identify abnormal patterns.

6. The power equipment intelligent gateway fault detection system based on the Internet of Things according to claim 5 is characterized in that: The fault diagnosis and alarm module establishes a knowledge base of power equipment faults, stores known fault modes, possible causes and corresponding treatment plans, and uses reasoning RBR to use IF-THEN rules to judge and reason about known faults. CBR infers the cause of faults through similarity matching of historical fault cases. The fault diagnosis and alarm module uses a multi-classification model random forest to identify fault categories, and uses LSTM to analyze time series data and detect abnormal operation trends; and sets an alarm mechanism based on the scope and urgency of the fault impact; The fault diagnosis and alarm module uses the SNMP protocol to obtain the status of power equipment in real time, remotely upgrades the firmware and fixes software problems through TR-069 remote management that supports remote modification of power equipment parameters, and automatically generates operation and maintenance reports based on NLG that include major fault statistics, power equipment operation trends, and maintenance recommendations.

Images