Power transmission, transformation and distribution equipment safety risk assessment system and method based on Internet of Things

By deploying IoT sensors and edge computing technology on power transmission and distribution equipment, combined with distributed computing and the isolated forest algorithm, the problems of limited data transmission and insufficient accuracy of risk assessment are solved, enabling real-time and accurate equipment safety monitoring and management.

CN118966766AInactive Publication Date: 2024-11-15SHANGHAI XUNJI WHALE TECHNOLOGY CO LTD
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202411022553.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-15
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing safety monitoring technologies for power transmission and distribution equipment suffer from limitations in data transmission, poor real-time processing, and insufficient accuracy in risk assessment.

Method used

IoT sensors are deployed on power transmission and distribution equipment, edge computing technology is used for data preprocessing, and a risk assessment model for the equipment is established based on a distributed computing framework and the isolated forest algorithm. The model is then trained using a sample dataset to assess the safety risks of the equipment in real time.

Benefits of technology

It improves the real-time performance and accuracy of data processing, enabling timely detection of equipment anomalies and potential problems, generating scientific equipment operation reports, and enhancing equipment safety and management efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118966766A_ABST
    Figure CN118966766A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of intelligent monitoring and safety assessment of a power system, and discloses a power transmission, transformation and distribution equipment safety risk assessment system and method based on the Internet of Things, and the method comprises the steps: deploying an Internet of Things sensor on power transmission, transformation and distribution equipment, and collecting historical equipment operation data; performing data preprocessing on equipment operation data acquired by utilizing an edge computing technology to obtain a sample data set; establishing an equipment risk assessment model based on a distributed computing framework and an isolated forest algorithm, and performing learning training on the equipment risk assessment model in combination with the sample data set; inputting the operation data of the to-be-tested equipment into the evaluation model after training is finished to carry out safety risk evaluation on the power transmission, transformation and distribution equipment, and outputting an evaluation result; and according to an evaluation result, generating an equipment safety operation report for auxiliary reference of workers. According to the invention, the operation safety risk of the power transmission, transformation and distribution equipment can be evaluated more efficiently and accurately, and the overall safety and stability of a power system are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring and safety assessment of power systems, and in particular to a system and method for safety risk assessment of power transmission, transformation and distribution equipment based on the Internet of Things. Background Art

[0002] With the development of modern power systems, the number and complexity of power transmission, transformation and distribution equipment are increasing, and the monitoring and risk assessment of equipment operation status are becoming more and more important. The traditional method of power transmission, transformation and distribution equipment operation monitoring mainly relies on manual inspection and regular maintenance. This method not only consumes a lot of manpower and material resources, but also has problems such as untimely monitoring and incomplete data acquisition. With the rapid development of the Internet of Things (IoT), big data and artificial intelligence (AI) technologies, these emerging technologies are gradually applied to power systems in order to improve the operating efficiency and safety of power transmission, transformation and distribution equipment through real-time data collection, intelligent analysis and prediction.

[0003] At present, some research and practice have applied IoT sensors to monitor power transmission and distribution equipment in real time, and transmit data to the cloud or centralized data center for processing through wireless sensor networks (WSN). However, this method still has many shortcomings in practical applications.

[0004] On the one hand, due to the wide distribution of power transmission and distribution equipment and the complex environment, the transmission of sensor data is easily disturbed, resulting in data loss or delay, affecting the real-time and accuracy of monitoring; on the other hand, the centralized data processing mode has problems such as limited data transmission bandwidth and computing resource bottlenecks, which makes it difficult to meet the needs of large-scale data processing and real-time analysis; in addition, most of the existing risk assessment methods are based on traditional statistical analysis or simple machine learning algorithms, which cannot fully explore the potential patterns and abnormal characteristics in complex equipment data, and the accuracy and reliability of the assessment results need to be improved. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract of the specification and the title of the invention of this application to avoid blurring the purpose of this section, the abstract of the specification and the title of the invention, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the above existing problems, the present invention is proposed.

[0007] Therefore, the technical problem solved by the present invention is that the existing safety monitoring technology for power transmission, transformation and distribution equipment has the problems of limited data transmission, poor real-time processing and insufficient risk assessment accuracy.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: deploying IoT sensors on power transmission, transformation and distribution equipment to collect historical equipment operation data;

[0009] The device operation data collected by edge computing technology is preprocessed to obtain a sample data set;

[0010] Establishing an equipment risk assessment model based on a distributed computing framework and an isolation forest algorithm, and training the model based on the sample data set;

[0011] Inputting the operating data of the equipment to be tested into the evaluation model after training to conduct safety risk evaluation on the power transmission, transformation and distribution equipment, and outputting the evaluation result;

[0012] Based on the evaluation results, an equipment safety operation report is generated for auxiliary reference by staff.

[0013] As a preferred scheme of the Internet of Things-based power transmission and distribution equipment safety risk assessment method described in the present invention, the collected historical equipment operation data at least includes voltage, current, active power, reactive power, power factor, equipment surface temperature, ambient temperature and humidity, vibration frequency, vibration amplitude, noise intensity, switch status, and equipment operation time.

[0014] As a preferred solution of the method for safety risk assessment of power transmission, transformation and distribution equipment based on the Internet of Things described in the present invention, the data preprocessing includes:

[0015] Deploy edge computing devices near the power transmission, transformation and distribution equipment, and deploy data preprocessing algorithms on the edge computing devices, the data preprocessing algorithms including but not limited to data cleaning, outlier detection, data filtering, data standardization, feature extraction and data integration algorithms;

[0016] Transmitting the historical device operation data collected by the sensor to the edge computing device through wireless communication;

[0017] The edge computing device processes the received historical equipment operation data in real time, performs data cleaning, noise reduction, and outlier detection on the data, and performs data standardization after marking abnormal data points;

[0018] Separately extract time features and frequency domain features for storage, and add risk level labels to the feature parameters to indicate the device status at the corresponding time point;

[0019] The historical equipment operation data collected by different sensors are then time-aligned and integrated to form a unified sample data set.

[0020] As a preferred solution of the Internet of Things-based power transmission and distribution equipment safety risk assessment method described in the present invention, the sample data set is represented in the form of a structured data table, wherein each row represents data at a time point or a sampling period, and each column represents a characteristic parameter.

[0021] As a preferred solution of the power transmission, transformation and distribution equipment safety risk assessment method based on the Internet of Things described in the present invention, the established equipment risk assessment model is trained, including:

[0022] Using the Apache Spark distributed computing framework, the historical equipment operation data is divided into several small blocks and distributed to multiple computing nodes;

[0023] Randomly select a number of sub-sample sets from them;

[0024] Build an isolation tree for each subsample set, randomly selecting features and split points;

[0025] The anomaly score is calculated based on the path length of the data point in the isolation tree, where the shorter the path, the higher the degree of anomaly;

[0026] Input the preprocessed sample data set into the isolation forest algorithm;

[0027] Parallel training of the isolation forest model on the Apache Spark distributed computing framework to generate multiple isolated trees;

[0028] Adjusting the parameters of the isolation forest to optimize the model performance, wherein the parameter adjustment includes adjusting the number of isolated trees and adjusting the size of the sample data set;

[0029] Deploy the trained isolation forest model to edge computing devices for real-time risk assessment.

[0030] As a preferred solution of the method for safety risk assessment of power transmission, transformation and distribution equipment based on the Internet of Things described in the present invention, the safety risk assessment of the power transmission, transformation and distribution equipment is performed in the assessment model, which can be expressed by the following mathematical expression formula:

[0031]

[0032] Among them, R is the risk assessment value, t0 is the start time of data collection, t1 is the end time of data collection, n is the number of characteristic parameters involved in the assessment, V i is the voltage at the i-th time point, I i is the current at the i-th time point, P a,i is the active power at the i-th time point, P r,i is the reactive power at the i-th time point, α iis the exponential decay coefficient related to the device surface temperature, T s is the surface temperature of the equipment, Norm(H e ) is the normalized value of ambient temperature and humidity, ω i is the vibration frequency, φ i is the vibration phase angle, A v is the vibration amplitude, B v is the noise intensity, C n is the standardized value of the switch state, m is the number of different switch states, A i is the device running time at the i-th time point, Γ i A label that indicates the risk level associated with the device status.

[0033] As a preferred solution of the safety risk assessment method for power transmission, transformation and distribution equipment based on the Internet of Things described in the present invention, the value range of the output R value is a non-negative real number, and the assessment result is obtained according to the value of the R value, wherein:

[0034] When the R value is low, it means that the equipment is at low risk and operating well;

[0035] When the R value is high, it means that the equipment has a higher risk and requires further inspection and maintenance.

[0036] As a preferred solution of the Internet of Things-based power transmission and distribution equipment safety risk assessment method described in the present invention, the generated equipment safety operation report includes but is not limited to equipment information, assessment time, risk assessment value, risk level, abnormal parameters, abnormal trends, low risk suggestions, medium risk suggestions, high risk suggestions, and extremely high risk suggestions.

[0037] As a preferred solution of the power transmission, transformation and distribution equipment safety risk assessment system based on the Internet of Things described in the present invention, it includes:

[0038] one or more processors;

[0039] A memory stores operable instructions, wherein when the instructions are executed by the one or more processors, the one or more processors perform operations, wherein the operations include the process of the above-mentioned method for safety risk assessment of power transmission, transformation and distribution equipment based on the Internet of Things.

[0040] Beneficial effects of the present invention:

[0041] 1. Through real-time data collection, the problems of untimely monitoring and incomplete data acquisition in traditional manual inspection and regular maintenance methods are solved;

[0042] 2. Through data standardization and feature extraction, the data is made more consistent and comparable. The extraction of time features and frequency domain features can better capture changes in the operating status of the equipment;

[0043] 3. Through distributed computing and parallel training, the training efficiency and processing capacity of the model are greatly improved, and high-performance risk assessment models can be quickly built on large-scale data sets;

[0044] 4. Through real-time risk assessment, abnormalities and potential problems in equipment operation can be discovered in time, providing a scientific basis for equipment maintenance and management;

[0045] 5. By generating equipment operation reports, staff can fully understand the operating status and potential risks of the equipment and formulate corresponding maintenance and management measures to improve the management efficiency of the equipment and enhance the operating safety and reliability of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0047] Figure 1 It is a flow chart of a method for safety risk assessment of power transmission, transformation and distribution equipment based on the Internet of Things shown in the present invention;

[0048] Figure 2 It is a schematic diagram of some parameters of the structured data table of the sample data set shown in the present invention. DETAILED DESCRIPTION

[0049] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0050] Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without making any creative work should fall within the scope of protection of the present invention.

[0051] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0052] Example 1

[0053] According to an embodiment of the present invention, Figure 1The flowchart shown is a method for safety risk assessment of power transmission, transformation and distribution equipment based on the Internet of Things, which specifically includes the following steps:

[0054] S1. Deploy IoT sensors on power transmission, transformation and distribution equipment to collect historical equipment operation data;

[0055] S2. Use edge computing technology to collect equipment operation data for data preprocessing to obtain a sample data set;

[0056] S3. Establish an equipment risk assessment model based on a distributed computing framework and the isolation forest algorithm, and train it based on sample data sets;

[0057] S4, inputting the operating data of the equipment to be tested into the evaluation model after training to conduct safety risk assessment on the power transmission, transformation and distribution equipment, and outputting the evaluation results;

[0058] S5. Generate equipment safety operation report based on the evaluation results for reference by staff.

[0059] It should be noted that the present invention deploys IoT sensors on power transmission and distribution equipment to collect equipment operation data in real time, and uses edge computing technology to pre-process the data to improve the real-time and reliability of data processing.

[0060] Furthermore, an equipment risk assessment model is established based on a distributed computing framework and the isolation forest algorithm. The model is trained by combining the preprocessed sample data set, so that potential risks and abnormal conditions in equipment operation can be more accurately identified.

[0061] In addition, the generated equipment safety operation report not only provides detailed risk assessment results, but also provides a scientific decision-making basis for equipment maintenance personnel, which helps to improve the safety and operation efficiency of power transmission, transformation and distribution equipment.

[0062] The following describes in more detail the implementation process and / or effects of certain embodiments of the present invention in conjunction with some preferred or optional examples of the present invention.

[0063] In an optional implementation, the collected historical equipment operation data includes at least voltage, current, active power, reactive power, power factor, equipment surface temperature, ambient temperature and humidity, vibration frequency, vibration amplitude, noise intensity, switch status, and equipment operation time.

[0064] As an example, data preprocessing includes the following steps:

[0065] Deploy edge computing devices near power transmission, transformation and distribution equipment, and deploy data preprocessing algorithms on edge computing devices. The data preprocessing algorithms include but are not limited to data cleaning, outlier detection, data filtering, data standardization, feature extraction and data integration algorithms.

[0066] Transmitting historical equipment operation data collected by sensors to edge computing devices via wireless communications;

[0067] The edge computing device processes the received historical equipment operation data in real time, performs data cleaning, noise reduction, and outlier detection on it, and performs data standardization after marking abnormal data points;

[0068] Separately extract time features and frequency domain features for storage, and add risk level labels to the feature parameters to indicate the device status at the corresponding time point;

[0069] The historical equipment operation data collected by different sensors are then time-aligned and integrated to form a unified sample data set.

[0070] As an example, the risk level label is represented by the values ​​0, 1, 2, 3, and 4. The equipment operation status and registration corresponding to each value are as follows:

[0071] 0 means normal, the device is running normally, no abnormalities or potential risks are detected, all parameters of the device are within the safe range, and the device is running smoothly;

[0072] 1 means slight risk, there is a slight abnormality in the operation of the equipment, but the risk is low, some parameters slightly deviate from the normal range, but it does not affect the overall operation of the equipment;

[0073] 2 indicates moderate risk. Moderate abnormalities occur during equipment operation and attention should be paid. Multiple parameters deviate from the normal range, which may affect equipment performance.

[0074] 3 means high risk, serious abnormalities occur during equipment operation, there is a high risk, multiple parameters seriously deviate from the normal range, and may cause damage to the equipment;

[0075] 4 means extremely high risk. There are serious abnormalities in the operation of the equipment. There is an extremely high risk. The equipment parameters are seriously abnormal and failure may occur at any time.

[0076] Reference Figure 2 ,The sample data set is represented in the form of a structured data table, where ,each row represents the data of a time point or a sampling period, and ,each column represents a characteristic parameter, such as voltage, current, and temperature.

[0077] Preferably, an embodiment of the present invention transmits historical equipment operation data collected by sensors to an edge computing device through wireless communication, processes the data in real time, and removes noise and outliers in the data through data cleaning and noise reduction processing to ensure data quality. Data standardization and feature extraction make the data more consistent and comparable. The extraction of time features and frequency domain features can better capture changes in the equipment's operating status.

[0078] Furthermore, the embodiment of the present invention also needs to explain that the established equipment risk assessment model is trained, specifically including the following steps:

[0079] (1) Using the Apache Spark distributed computing framework, historical equipment operation data is divided into several small blocks and distributed to multiple computing nodes;

[0080] (2) randomly select a number of sub-sample sets;

[0081] (3) Build an isolation tree for each subsample set and randomly select features and split points;

[0082] (4) Calculate the anomaly score based on the path length of the data point in the isolation tree, where the shorter the path, the higher the degree of anomaly;

[0083] (5) Input the preprocessed sample data set into the isolation forest algorithm;

[0084] (6) Parallel training of the isolation forest model on the Apache Spark distributed computing framework to generate multiple isolated trees;

[0085] (7) Adjusting the parameters of the isolation forest to optimize the model performance, wherein the parameter adjustment includes adjusting the number of isolated trees and the size of the sample data set;

[0086] (8) Deploy the trained isolation forest model to edge computing devices for real-time risk assessment.

[0087] Preferably, Apache Spark, as a distributed computing framework, can efficiently process large-scale data, divide historical equipment operation data into several small blocks and distribute them to multiple computing nodes, solving the problem that traditional centralized computing cannot efficiently process large-scale historical data. It improves computing efficiency through distributed computing and adapts to the equipment risk assessment needs in the big data environment.

[0088] In the embodiment of the present invention, an isolation forest algorithm is used for anomaly detection. The algorithm is applicable to high-dimensional data and does not require pre-definition of abnormal samples. It can calculate the anomaly score through the path length, thereby efficiently identifying abnormal data points. It solves the problem of anomaly detection in high-dimensional data, does not require pre-definition of abnormal samples, can adaptively identify abnormal situations, and improves the accuracy and robustness of risk assessment.

[0089] Preferably, the isolation forest model is trained in parallel on the Apache Spark distributed computing framework to generate multiple isolated trees, and the model performance is optimized by adjusting the number of isolated trees and the size of the sample data set, thereby improving the speed and efficiency of model training, accelerating model training through parallel computing, and improving model performance through parameter optimization to ensure the accuracy of risk assessment results.

[0090] As an example, the safety risk assessment of power transmission, transformation and distribution equipment can be performed through the assessment model, which can be expressed by the following mathematical expression formula:

[0091]

[0092] Among them, R is the risk assessment value, t0 is the start time of data collection, t1 is the end time of data collection, n is the number of characteristic parameters involved in the assessment, V i is the voltage at the i-th time point, I i is the current at the i-th time point, P a,i is the active power at the i-th time point, P r,i is the reactive power at the i-th time point, α i is the exponential decay coefficient related to the device surface temperature, T s is the surface temperature of the equipment, Norm(H e ) is the normalized value of ambient temperature and humidity, ω i is the vibration frequency, φ i is the vibration phase angle, A v is the vibration amplitude, B v is the noise intensity, C n is the standardized value of the switch state, m is the number of different switch states, A i is the device running time at the i-th time point, Γ i A label that indicates the risk level associated with the device status.

[0093] As an example, the value range of the output R value is a non-negative real number, and the evaluation result is obtained according to the value of R value, where:

[0094] When the R value is low, it means that the equipment is at low risk and operating well;

[0095] When the R value is high, it means that the equipment has a higher risk and requires further inspection and maintenance.

[0096] It should be noted that the embodiments of the present invention greatly improve the training efficiency and processing power of the model through the above-mentioned distributed computing and parallel training, and can quickly build a high-performance risk assessment model on a large-scale data set. The optimized isolation forest model can accurately identify anomalies and potential risks in equipment operation.

[0097] Preferably, through real-time risk assessment processing, anomalies and potential problems in equipment operation can be discovered in a timely manner, providing a scientific basis for equipment maintenance and management. The assessment results provide strong support for subsequent maintenance decisions and preventive maintenance, thereby improving the operational safety of the equipment.

[0098] In an optional implementation, the generated equipment safety operation report includes but is not limited to equipment information, assessment time, risk assessment value, risk level, abnormal parameters, abnormal trends, low risk recommendations, medium risk recommendations, high risk recommendations, and extremely high risk recommendations.

[0099] As an example, the generated equipment safety operation report is as follows:

[0100] Equipment information: equipment name, model, location, and operating hours;

[0101] Evaluation time: the time when the evaluation report is generated and the period of data collection;

[0102] Risk assessment value: specific R value;

[0103] Risk level: normal, slight risk, moderate risk, high risk, very high risk;

[0104] Abnormal parameters: identified abnormal parameters and their specific values;

[0105] Abnormal trend: abnormal parameter change trend chart over time;

[0106] Low risk recommendation: The equipment is in good operating condition and no special attention is required;

[0107] Moderate risk recommendation: The device has minor abnormalities and regular inspection is recommended;

[0108] High-risk advice: The equipment has obvious abnormalities and needs to be maintained and repaired;

[0109] Very high risk advice: The equipment has serious abnormalities and needs to be shut down for inspection immediately.

[0110] It should be noted again in the embodiments of the present invention that, through the generated equipment safety operation report, the staff can fully understand the operating status and potential risks of the equipment and formulate corresponding maintenance and management measures, which not only improves the management efficiency of the equipment, but also improves the operating safety and reliability of the equipment.

[0111] The data cleaning, outlier detection, data filtering, data standardization, feature extraction and data integration algorithms of the aforementioned data can be performed using methods and means in the prior art and will not be described in detail in this example.

[0112] In accordance with the teachings of the above embodiments, other aspects disclosed in the embodiments of the present invention further provide a power transmission, transformation and distribution equipment safety risk assessment system based on the Internet of Things, including: one or more processors and a memory.

[0113] The memory is used to store operable instructions, which, when executed by the one or more processors, cause the one or more processors to perform operations, including the process of the method for safety risk assessment of power transmission, transformation and distribution equipment based on the Internet of Things in the aforementioned embodiment, especially Figure 1 The process of the method shown.

[0114] The risk assessment system also includes a computer-readable medium storing software, the software including instructions executable by one or more computers, the instructions causing one or more computers to perform operations through such execution, the operations including the process of the power transmission, transformation and distribution equipment safety risk assessment method based on the Internet of Things in the aforementioned embodiment, especially Figure 1 The process of the method shown.

[0115] It should be appreciated that embodiments of the present invention can be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory.

[0116] The method may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with a computer program, wherein the storage medium so configured causes a computer to operate in a specific and predefined manner.

[0117] Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with a computer system, however, the program can be implemented in assembly or machine language if desired.

[0118] In any case, the language may be a compiled or interpreted language.

[0119] Furthermore, the program can be run on an application specific integrated circuit programmed for this purpose.

[0120] The processes described herein (or variations and / or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed collectively on one or more processors, by hardware, or a combination thereof. The computer program includes a plurality of instructions that can be executed by one or more processors.

[0121] Further, the method may be implemented in any type of computing platform operably connected to a suitable computer, including but not limited to a personal computer, a minicomputer, a mainframe, a workstation, a network or distributed computing environment, a separate or integrated computer platform, or in communication with a charged particle tool or other imaging device.

[0122] Various aspects of the present invention may be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optical read and / or write storage media, RAM, ROM, etc., so that it can be read by a programmable computer, which, when the storage medium or device is read by the computer, can be used to configure and operate the computer to perform the processes described herein.

[0123] Additionally, the machine-readable code, or portions thereof, can be transmitted over a wired or wireless network.

[0124] The invention described herein includes these and other various types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor.

[0125] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A safety risk assessment method for power transmission, transformation and distribution equipment based on the Internet of Things. It is characterized in that include: Deploy IoT sensors on power transmission, transformation and distribution equipment to collect historical equipment operation data; The device operation data collected by edge computing technology is preprocessed to obtain a sample data set; Establishing an equipment risk assessment model based on a distributed computing framework and an isolation forest algorithm, and training the model based on the sample data set; Inputting the operating data of the equipment to be tested into the evaluation model after training to conduct safety risk evaluation on the power transmission, transformation and distribution equipment, and outputting the evaluation result; Based on the evaluation results, an equipment safety operation report is generated for auxiliary reference by staff.

2. According to the Internet of Things-based power transmission, transformation and distribution equipment safety risk assessment method of claim 1, It is characterized in that The collected historical equipment operation data at least includes voltage, current, active power, reactive power, power factor, equipment surface temperature, ambient temperature and humidity, vibration frequency, vibration amplitude, noise intensity, switch status, and equipment operation time.

3. According to the Internet of Things-based power transmission, transformation and distribution equipment safety risk assessment method of claim 1, It is characterized in that The data preprocessing includes: Deploy edge computing devices near the power transmission, transformation and distribution equipment, and deploy data preprocessing algorithms on the edge computing devices, the data preprocessing algorithms including but not limited to data cleaning, outlier detection, data filtering, data standardization, feature extraction and data integration algorithms; Transmitting the historical device operation data collected by the sensor to the edge computing device through wireless communication; The edge computing device processes the received historical equipment operation data in real time, performs data cleaning, noise reduction, and outlier detection on the data, and performs data standardization after marking abnormal data points; Separately extract time features and frequency domain features for storage, and add risk level labels to the feature parameters to indicate the device status at the corresponding time point; The historical equipment operation data collected by different sensors are then time-aligned and integrated to form a unified sample data set.

4. According to the method for safety risk assessment of power transmission, transformation and distribution equipment based on the Internet of Things according to claim 1 or 3, It is characterized in that The sample data set is represented in the form of a structured data table, wherein each row represents data of a time point or a sampling period, and each column represents a characteristic parameter.

5. According to the method for safety risk assessment of power transmission, transformation and distribution equipment based on the Internet of Things in claim 1, It is characterized in that The established equipment risk assessment model is trained, including: Using the Apache Spark distributed computing framework, the historical equipment operation data is divided into several small blocks and distributed to multiple computing nodes; Randomly select a number of sub-sample sets from them; Build an isolation tree for each subsample set, randomly selecting features and split points; The anomaly score is calculated based on the path length of the data point in the isolation tree, where the shorter the path, the higher the degree of anomaly; Input the preprocessed sample data set into the isolation forest algorithm; Parallel training of the isolation forest model on the Apache Spark distributed computing framework to generate multiple isolated trees; Adjusting the parameters of the isolation forest to optimize the model performance, wherein the parameter adjustment includes adjusting the number of isolated trees and adjusting the size of the sample data set; Deploy the trained isolation forest model to edge computing devices for real-time risk assessment.

6. According to the Internet of Things-based power transmission, transformation and distribution equipment safety risk assessment method of claim 1, It is characterized in that The safety risk assessment of the power transmission, transformation and distribution equipment is performed through the assessment model and can be expressed by the following mathematical expression formula: Among them, R is the risk assessment value, t 0 is the start time of data collection, t 1 is the end time of data collection, n is the number of characteristic parameters involved in the evaluation, V i is the voltage at the i-th time point, I i is the current at the i-th time point, P a,i is the active power at the i-th time point, P r,i is the reactive power at the i-th time point, α i is the exponential decay coefficient related to the surface temperature of the device, T s is the surface temperature of the equipment, Norm(H e ) is the normalized value of ambient temperature and humidity, ω i is the vibration frequency, φ i is the vibration phase angle, A v is the vibration amplitude, B v is the noise intensity, C n is the standardized value of the switch state, m is the number of different switch states, A i is the equipment running time at the i-th time point, Γ i A label that indicates the risk level associated with the device status.

7. According to the Internet of Things-based power transmission, transformation and distribution equipment safety risk assessment method of claim 6, It is characterized in that The value range of the output R value is a non-negative real number. The evaluation result is obtained according to the value of R, where: When the R value is low, it means that the equipment is at low risk and operating well; When the R value is high, it means that the equipment has a higher risk and requires further inspection and maintenance.

8. According to the Internet of Things-based power transmission, transformation and distribution equipment safety risk assessment method of claim 1, It is characterized in that The generated equipment safety operation report includes but is not limited to equipment information, assessment time, risk assessment value, risk level, abnormal parameters, abnormal trend, low risk recommendation, medium risk recommendation, high risk recommendation, and extremely high risk recommendation.

9. A safety risk assessment system for power transmission, transformation and distribution equipment based on the Internet of Things. It is characterized in that include: one or more processors; A memory storing operable instructions, wherein when the instructions are executed by the one or more processors, the one or more processors perform operations, wherein the operations include the process of the method for safety risk assessment of power transmission, transformation and distribution equipment based on the Internet of Things as described in any one of claims 1 to 8.

Citation Information

Cited By

  • Intelligent control method and system based on operation state of power equipment

    CN119628222A

  • Method, system and device for determining regional risk intensity of smart city and medium

    CN119740857A

  • Home safety control method and system based on big data analysis

    CN119902451A

  • Abnormal data processing method, device and system and storage medium

    CN120048037A