Intelligent detection system for switch cabinet

By adopting high-precision sensors and advanced data processing technology in the switch cabinet intelligent detection system, large-scale data processing and analysis problems are solved, real-time data acquisition, preprocessing and analysis are realized, and early warning accuracy and timeliness are improved. The stability and safety of the power system.

CN119063790APending Publication Date: 2024-12-03STATE GRID HEBEI ELECTRIC POWER CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411277316.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-12
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing technology is difficult to effectively process and analyze large-scale switch cabinet monitoring data, and cannot meet the needs of real-time analysis and response.

Method used

An intelligent detection system for switch cabinets is designed, including data acquisition and transmission module, data preprocessing module, real-time data storage and management module, data analysis and mining module and real-time response and early warning module, using high-precision sensors, MongoDB databases, mobile Technologies such as average filtering algorithm, median filtering algorithm, K-mean clustering algorithm and ARIMA model realize real-time data acquisition, preprocessing, storage, analysis and early warning.

Benefits of technology

Realize timely processing and analysis of large-scale data, improve the accuracy and reliability of data analysis, reduce the false alarm rate, improve the accuracy and timeliness of early warning, help users to discover and solve potential problems in a timely manner, and improve the The stability and safety of the power system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119063790A_ABST
    Figure CN119063790A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent detection system for a switch cabinet, and the system comprises a data collection and transmission module which collects parameter data in the switch cabinet in real time; the data preprocessing module is used for preprocessing the collected original data, including data cleaning, denoising and abnormal value processing; the real-time data storage and management module is used for storing the preprocessed data in a MongoDB database; the data analysis and mining module is used for grouping or classifying the data and identifying an abnormal or fault mode; and the real-time response and early warning module is used for generating early warning information in real time based on the analysis result, and sending an early warning notification to related personnel when the monitoring data is abnormal. Through intelligent data processing and analysis, efficient processing and mining of large-scale data are realized, more reliable and intelligent switch cabinet monitoring and early warning services are provided for users, and improvement of stability and safety of a power system is facilitated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of switch cabinet detection, and in particular to an intelligent detection system for a switch cabinet. Background Art

[0002] The intelligent detection system of switchgear is a device used to monitor and manage power switchgear. It usually uses various sensors and intelligent algorithms to monitor the current, voltage, temperature and other parameters inside the switchgear in real time, and transmits the data to the monitoring center or cloud platform through a network connection. Such a system can improve the safety, reliability and efficiency of power equipment, prevent potential failures and accidents, and thus reduce downtime and maintenance costs. Although many advances have been made, there are still some technical problems that have not been solved, including: With the continuous increase of monitoring data, how to effectively process and analyze large-scale data and extract useful information and rules is a challenging problem. Current data processing and analysis technologies may not meet the needs of real-time analysis and response to large-scale data. Summary of the invention

[0003] In order to solve the above problems, the present invention provides a switch cabinet intelligent detection system.

[0004] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0005] A switch cabinet intelligent detection system, comprising:

[0006] Data acquisition and transmission module: real-time acquisition of parameter data inside the switch cabinet;

[0007] Data preprocessing module: preprocess the collected raw data, including data cleaning, denoising and outlier processing;

[0008] Real-time data storage and management module: stores the pre-processed data in the MongoDB database;

[0009] Data analysis and mining module: group or classify data and identify abnormalities or failure modes;

[0010] Real-time response and early warning module: Generate early warning information in real time based on the analysis results, and send early warning notifications to relevant personnel when abnormal conditions occur in the monitoring data.

[0011] Further: the data acquisition and transmission module includes:

[0012] Use sensors to collect real-time data on various parameters inside the switch cabinet and transmit them to a cloud server or data center via the network, including:

[0013] Current sensors, voltage sensors and temperature sensors, connect the sensors to the data acquisition equipment and set the sampling frequency to ensure real-time monitoring of the internal parameters of the switch cabinet.

[0014] Further: the data preprocessing module includes:

[0015] Use the deletion method to check the collected data and exclude possible missing values, abnormal values ​​and invalid data;

[0016] Use the moving average filtering algorithm to smooth the data and remove noise interference in the data:

[0017]

[0018] in, is the moving average at the tth moment, N is the window size, x i is the original data at the i-th moment;

[0019] Use the median filter algorithm to process outliers in the data and replace the outliers with the median value near the data point:

[0020]

[0021] in, is the median filtering result at the tth moment, x t-k to x t+k is the 2k+1 data points before and after the tth moment, and k is the window size.

[0022] Further: the real-time data storage and management module includes:

[0023] Deploy MongoDB database in the data center, set MongoDB configuration parameters, and design data models, including the organizational structure and field definitions of data sets;

[0024] Store the preprocessed data in the form of documents in the MongoDB database;

[0025] Design data partitioning strategies based on data volume and access patterns, and partition data by time and region;

[0026] Configure the data sharding function of MongoDB to distribute data to multiple physical nodes.

[0027] Further: the data analysis and mining module includes:

[0028] The data is standardized so that different features have the same scale, and the data is divided into K different clusters according to the feature vector of the data:

[0029]

[0030] Among them, C i represents the i-th cluster, μ i represents the center point of the i-th cluster, ‖x-μ i ‖ represents the distance from sample x to cluster center μ i distance;

[0031] Perform a stationarity test on the time series data and select the orders p, d and q of the ARIMA model based on the autocorrelation diagram and partial autocorrelation diagram of the time series;

[0032] The ARIMA model is used to fit and predict time series data and predict the data trend in the future. The mathematical expression of the ARIMA model is:

[0033]

[0034] Among them, Y t represents time series data, the observed value at time t, c represents the constant term, and θ i represents the parameters of the ARIMA model, ∈ t Represents white noise.

[0035] Further: the real-time response and early warning module includes:

[0036] According to the results of data analysis and mining, early warning rules and models are established to detect abnormal situations in monitoring data. When abnormal situations occur in monitoring data, the early warning generation process is triggered to generate early warning information and identify the abnormal type and severity.

[0037] According to the actual situation of monitoring data, the warning threshold is updated regularly to keep it consistent with the data distribution;

[0038] When the warning information is generated, a warning notification is sent to relevant personnel or systems.

[0039] Compared with the prior art, the present invention has the following technical advances:

[0040] The present invention can collect various parameter data inside the switch cabinet in real time, and realize real-time data storage and management through a high-performance database (such as MongoDB), thereby ensuring timely processing and analysis of large-scale data.

[0041] The present invention uses a preprocessing algorithm to clean, denoise and process outliers on the raw data, improving the accuracy and reliability of subsequent data analysis. At the same time, it uses machine learning and data mining techniques to analyze and mine large-scale data, discovering potential laws and patterns in the data, and providing strong support for subsequent predictions and decisions.

[0042] The present invention designs an intelligent early warning strategy, dynamically adjusts the early warning threshold according to historical data and model prediction results, and makes the early warning mechanism adaptive and flexible. This can effectively reduce the false alarm rate, improve the accuracy and timeliness of early warning, and help users discover and solve potential problems in a timely manner.

[0043] In summary, the present invention realizes efficient processing and mining of large-scale data through intelligent data processing and analysis, provides users with more reliable and intelligent switch cabinet monitoring and early warning services, and helps to improve the stability and safety of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0045] In the attached picture:

[0046] Figure 1 It is a system structure diagram of the present invention. DETAILED DESCRIPTION

[0047] The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0048] like Figure 1 As shown, the present invention discloses a switch cabinet intelligent detection system, comprising:

[0049] Data acquisition and transmission module: real-time acquisition of parameter data inside the switch cabinet.

[0050] In this module, this embodiment uses high-precision sensors to collect various parameter data inside the switch cabinet in real time, and transmits them to the cloud server or data center through the network to ensure the timeliness and reliability of the data. The specific implementation modules are as follows:

[0051] 1. Sensor selection and deployment:

[0052] Select appropriate high-precision sensors, such as current sensors, voltage sensors, and temperature sensors, to ensure data accuracy and stability. According to different parts of the switch cabinet and monitoring needs, deploy sensors reasonably to ensure comprehensive coverage without wasting resources.

[0053] 2. Sensor data collection:

[0054] Design a data acquisition device and connect the sensor to the data acquisition device. Use the sampling theorem to set a suitable sampling frequency to ensure real-time monitoring of the internal parameters of the switch cabinet.

[0055] 3. Data transmission protocol and network connection: Select appropriate data transmission protocols, such as MQTT, HTTP, etc., to ensure the efficiency and stability of data transmission. Connect the switch cabinet detection system with the network of the cloud server or data center to ensure that data can be transmitted smoothly.

[0056] 4. Data encryption and compression:

[0057] During data transmission, encryption algorithms are used to encrypt data to ensure data security and privacy protection. Data is compressed to reduce bandwidth usage and transmission delay, thereby improving transmission efficiency.

[0058] 5. Error handling and fault tolerance mechanism:

[0059] Design error handling and fault tolerance mechanisms for data transmission, including retransmission mechanisms, data verification, etc., to deal with errors and packet loss that may occur during network transmission. Monitor the network connection status in real time during data transmission, detect and handle network anomalies in a timely manner, and ensure the stability and reliability of data transmission.

[0060] Through the above modules, this embodiment can effectively realize the real-time collection and reliable transmission of internal parameter data of the switch cabinet, providing a reliable data basis for subsequent data processing and analysis.

[0061] Data preprocessing module: preprocess the collected raw data, including data cleaning, denoising and outlier processing.

[0062] In this module, this embodiment preprocesses the collected raw data, including data cleaning, denoising and outlier processing, to improve the accuracy of subsequent analysis. The specific implementation modules are as follows:

[0063] 1. Data cleaning:

[0064] First, check the collected raw data to exclude possible missing values, outliers and other invalid data. You can use data cleaning algorithms, such as deletion and interpolation, to clean and fill the data to make it more complete and reliable.

[0065] 2. Denoising: Use the moving average filter (MA) algorithm to smooth the data and remove the noise interference in the data. The formula of moving average filter is:

[0066]

[0067] in, is the moving average at the tth moment, N is the window size, x i is the original data at the ith moment.

[0068] 3. Outlier processing:

[0069] Use the median filter algorithm to process outliers on the data and replace the outliers with the median value near the data point. The formula for median filtering is:

[0070]

[0071] in, is the median filtering result at the tth moment, x t-k to x t+k is the 2k+1 data points before and after the tth moment, and k is the window size.

[0072] Through the above modules, this embodiment can effectively pre-process the collected raw data, improve the quality and accuracy of the data, and provide a reliable data foundation for subsequent data analysis and mining.

[0073] Real-time data storage and management module: stores the preprocessed data in the MongoDB database.

[0074] In this module, this embodiment uses MongoDB as a high-performance NoSQL database to store the preprocessed data, and designs a reasonable data management solution, including data partitioning, index optimization, etc., to quickly retrieve and query large-scale data. The specific implementation modules are as follows:

[0075] 1.MongoDB database deployment: Deploy the MongoDB database in a cloud server or data center and ensure the high availability and reliability of the database. Set MongoDB configuration parameters such as storage engine, memory cache, etc. to optimize the performance of the database.

[0076] 2. Data model design: According to the structure and characteristics of switchgear data, design a suitable data model, including the organizational structure and field definition of the data collection. Consider the hierarchical structure and association relationship of the data, and reasonably design the nesting and indexing of the document.

[0077] 3. Data storage and import: Store the preprocessed data in the form of documents in the MongoDB database to ensure data integrity and consistency. You can use the data import tool or programming interface provided by MongoDB to import data into the database in batches.

[0078] 4. Data partitioning and sharding: Design a reasonable data partitioning strategy based on the data volume and access mode, and partition the data according to time, region, etc. Configure MongoDB's data sharding function to distribute data to multiple physical nodes to improve the scalability and fault tolerance of the database.

[0079] 5. Index optimization: Design appropriate indexes based on the frequency and conditions of data queries to speed up queries and improve retrieval performance. Maintain index updates and reconstructions to ensure index validity and consistency.

[0080] 6. Data backup and recovery: Design a strategy for regular data backup to ensure data security and reliability. Implement regular data backup and emergency recovery to deal with accidental data loss or damage.

[0081] Through the above modules, this embodiment can efficiently store the preprocessed data in the MongoDB database and design a reasonable data management solution to meet the needs of fast retrieval and query of large-scale data.

[0082] Data analysis and mining module: Group or classify data and identify abnormalities or failure patterns.

[0083] In this module, this embodiment uses the K-means clustering algorithm and the ARIMA model to analyze and mine large-scale data to discover potential rules and patterns, and then perform anomaly detection and data prediction. The specific implementation modules are as follows:

[0084] 1. K-means clustering algorithm:

[0085] First, select appropriate data features and standardize the data so that different features have the same scale. Then, according to the feature vector of the data, use the K-means clustering algorithm to divide the data into K different clusters. The objective function of K-means clustering is to minimize the sum of the squared distances between samples in the cluster, and its mathematical expression is:

[0086]

[0087] Among them, C i represents the i-th cluster, μ i represents the center point of the i-th cluster, ‖x-μ i ‖ represents the distance from sample x to cluster center μ i Distance

[0088] 2.ARIMA model building:

[0089] First, the stationarity test of the time series data is performed to ensure that the data meets the basic assumptions of the ARIMA model. Then, according to the autocorrelation diagram (ACF) and partial autocorrelation diagram (PACF) of the time series, the appropriate order p, d and q of the ARIMA model are selected. Finally, the selected ARIMA model is used to fit and predict the time series data to predict the data trend in the future. The mathematical expression of the ARIMA model is:

[0090]

[0091] Among them, Y t represents time series data, the observed value at time t, c represents the constant term, and θ i represents the parameters of the ARIMA model, ∈ t Represents white noise

[0092] Through the above modules, this embodiment can use the K-means clustering algorithm to group or classify data and identify abnormal or fault modes; at the same time, the ARIMA model is used for data prediction and trend analysis to provide more in-depth data analysis and mining capabilities for the switch cabinet intelligent detection system.

[0093] Real-time response and early warning module: Generate early warning information in real time based on the analysis results, and send early warning notifications to relevant personnel when abnormal conditions occur in the monitoring data.

[0094] In this module, this embodiment generates warning information in real time based on the analysis results, designs an intelligent warning strategy, and dynamically adjusts the warning threshold according to historical data and model prediction results to improve the accuracy and timeliness of the warning. The specific implementation modules are as follows:

[0095] 1. Real-time warning generation: Based on the results of previous data analysis and mining, warning rules and models are established to detect abnormalities in monitoring data. When abnormalities occur in monitoring data, the warning generation process is immediately triggered to generate warning information and identify the abnormality type and severity.

[0096] 2. Intelligent early warning strategy design: Design an intelligent early warning strategy to dynamically adjust the early warning threshold based on historical data and model prediction results. Statistical methods or machine learning algorithms can be used to automatically adjust the early warning threshold based on the distribution and pattern of historical data to adapt to data changes and fluctuations.

[0097] 3. Dynamic adjustment of warning thresholds: According to the actual situation of the monitoring data, the warning thresholds are updated regularly to maintain consistency with the data distribution. Methods such as exponentially weighted moving average (EWMA) can be used to perform weighted averaging of historical data and dynamically adjust the warning thresholds.

[0098] 4. Sending of early warning information:

[0099] When warning information is generated, a warning notification is immediately sent to relevant personnel or systems. Warning notifications can be sent via email, SMS, App push, etc. to ensure that relevant personnel are informed in time and take appropriate measures.

[0100] Through the above modules, this embodiment can realize real-time warning generation based on analysis results, and design intelligent warning strategies to dynamically adjust warning thresholds according to historical data and model prediction results to improve the accuracy and timeliness of warnings.

[0101] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein with equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of protection of the claims of the present invention.

Claims

1. A switch cabinet intelligent detection system, It is characterized in that include: Data acquisition and transmission module: real-time acquisition of parameter data inside the switch cabinet; Data preprocessing module: preprocess the collected raw data, including data cleaning, denoising and outlier processing; Real-time data storage and management module: stores the pre-processed data in the MongoDB database; Data analysis and mining module: group or classify data and identify abnormalities or failure modes; Real-time response and early warning module: Generate early warning information in real time based on the analysis results, and send early warning notifications to relevant personnel when abnormal conditions occur in the monitoring data.

2. According to claim 1, a switch cabinet intelligent detection system, It is characterized in that The data acquisition and transmission module includes: Use sensors to collect real-time data on various parameters inside the switch cabinet and transmit them to a cloud server or data center via the network, including: Current sensors, voltage sensors and temperature sensors, connect the sensors to the data acquisition equipment and set the sampling frequency to ensure real-time monitoring of the internal parameters of the switch cabinet.

3. A switch cabinet intelligent detection system according to claim 2, It is characterized in that The data preprocessing module comprises: Use the deletion method to check the collected data and exclude possible missing values, abnormal values ​​and invalid data; Use the moving average filtering algorithm to smooth the data and remove noise interference in the data: in, is the moving average at the tth moment, N is the window size, x i is the original data at the i-th moment; Use the median filter algorithm to process outliers in the data and replace the outliers with the median value near the data point: in, is the median filtering result at the tth moment, x t-k to x t+k is the 2k+1 data points before and after the tth moment, and k is the window size.

4. A switch cabinet intelligent detection system according to claim 3, It is characterized in that The real-time data storage and management module includes: Deploy MongoDB database in the data center, set MongoDB configuration parameters, and design data models, including the organizational structure and field definitions of data sets; Store the preprocessed data in the form of documents in the MongoDB database; Design data partitioning strategies based on data volume and access patterns, and partition data by time and region; Configure the data sharding function of MongoDB to distribute data to multiple physical nodes.

5. A switch cabinet intelligent detection system according to claim 4, It is characterized in that The data analysis and mining module includes: The data is standardized so that different features have the same scale, and the data is divided into K different clusters according to the feature vector of the data: Among them, C i represents the i-th cluster, μ i represents the center point of the i-th cluster, ‖x-μ i ‖ represents the distance from sample x to cluster center μ i distance; Perform a stationarity test on the time series data and select the orders p, d and q of the ARIMA model based on the autocorrelation diagram and partial autocorrelation diagram of the time series; The ARIMA model is used to fit and predict time series data and predict the data trend in the future. The mathematical expression of the ARIMA model is: Among them, Y t represents time series data, the observed value at time t, c represents the constant term, and θ i represents the parameters of the ARIMA model, ∈ t Represents white noise.

6. A switch cabinet intelligent detection system according to claim 5, It is characterized in that The real-time response and early warning module includes: According to the results of data analysis and mining, early warning rules and models are established to detect abnormal situations in monitoring data. When abnormal situations occur in monitoring data, the early warning generation process is triggered to generate early warning information and identify the abnormal type and severity. According to the actual situation of monitoring data, the warning threshold is updated regularly to keep it consistent with the data distribution; When the warning information is generated, a warning notification is sent to relevant personnel or systems.

Citation Information

Cited By

  • Power distribution cabinet operation dynamic safety assessment analysis method and system

    CN119944954A