Power transmission and transformation grid power distribution station room monitoring device based on Internet of Things

Abstract

The invention relates to the technical field of power systems, in particular to a power transmission and transformation network power distribution station room monitoring device based on the Internet of Things, which comprises a data acquisition module, a data preprocessing module, a heterogeneous data fusion power grid health assessment module, a fault prediction and alarm module and an intelligent maintenance module, the data acquisition module acquires real-time operation data and environmental data of power grid equipment; the data preprocessing module is used for preprocessing the acquired operation data and environment data; the heterogeneous data fusion power grid health assessment module assesses the health condition of the power grid in real time; the fault prediction and alarm module identifies potential faults of power grid equipment in advance and generates fault early warning signals. And the intelligent maintenance module automatically generates an equipment maintenance plan based on the generated fault early warning signal. According to the invention, quick response can be realized under different operation conditions, false alarms are reduced, and stable operation of a power grid is effectively guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a monitoring device for a power distribution station room in a power transmission and transformation network based on the Internet of Things. Background Art

[0002] In the operation of modern power transmission and transformation power distribution stations, the stability and safety of power grid equipment are crucial to the reliable operation of the power system. With the continuous expansion of the scale of the power grid and the increase in the complexity of equipment, real-time monitoring and fault warning of equipment have become increasingly important. The rapid development of Internet of Things technology has provided new possibilities for the health monitoring of power grid equipment. Through a variety of sensors, the operating status and environmental conditions of the equipment are monitored in real time, providing comprehensive data support for the safe operation of the power grid. However, how to integrate these multi-dimensional data and perform intelligent analysis to accurately evaluate the health status of power grid equipment, predict faults in advance and realize intelligent maintenance is still a problem that needs to be solved in current technology.

[0003] In the prior art, the monitoring system of the distribution station of the power transmission and transformation network usually relies on a single data source or simple rule judgment to realize equipment status monitoring, and it is difficult to effectively integrate multiple data types. When faced with complex equipment failures and changing environmental conditions, the traditional monitoring system cannot accurately judge the health status of the equipment, resulting in delays or misjudgments in fault identification. In addition, the prior art lacks systematic design in data preprocessing, fault prediction and maintenance management, making it difficult to achieve refined fault prediction and automated resource allocation, so that after a failure occurs, it can only respond passively, which increases the equipment downtime and affects the reliability and stability of the power grid.

[0004] In order to address the deficiencies in the prior art, the present invention proposes a monitoring device for a power distribution station room in a transmission and transformation network based on the Internet of Things, which ensures that maintenance tasks are performed in a timely and efficient manner, improves the stability, maintenance efficiency and automation level of the power grid, and ensures the safe and stable operation of the power grid. Summary of the invention

[0005] The present invention provides a monitoring device for a power distribution station room in a power transmission and transformation network based on the Internet of Things, which solves the problems of insufficient multi-dimensional data integration, inaccurate health status assessment, untimely fault prediction and low maintenance management efficiency in the existing power transmission and transformation network distribution station monitoring technology, realizes comprehensive monitoring, accurate assessment, fault prediction and intelligent maintenance of power grid equipment, and improves the reliability and automation level of power grid operation.

[0006] A monitoring device for a power distribution station room of a transmission and transformation network based on the Internet of Things, comprising a data acquisition module, a data preprocessing module, a heterogeneous data fusion power grid health assessment module, a fault prediction and alarm module and an intelligent maintenance module, wherein; The data acquisition module collects real-time operation data and environmental data of power grid equipment through various sensors and meteorological monitoring equipment deployed in the power grid distribution station. The operation data includes current, voltage, frequency, power and vibration data, and the environmental data includes meteorological data (temperature, humidity, wind speed, air pressure) and air quality data; The data preprocessing module preprocesses the collected operation data and environmental data, including denoising, missing value filling, and standardization; The heterogeneous data fusion power grid health assessment module fuses the pre-processed operation data and environmental data to assess the health status of the power grid in real time, specifically including: Feature extraction: Extract features from pre-processed operating data and environmental data to extract relevant features of power grid equipment, including current fluctuation amplitude, voltage deviation, frequency stability, vibration mode, temperature change rate, relative humidity, wind speed change rate, air pressure change rate, and air quality index; Data fusion: Adopt adaptive weighting algorithm to fuse the extracted related features to form multi-dimensional features; Health status assessment: Use the power grid equipment health status assessment model to analyze multi-dimensional features and assess the health status of power grid equipment in real time; The fault prediction and alarm module identifies potential faults of power grid equipment in advance based on the evaluation results of the power grid health status and generates fault warning signals; The intelligent maintenance module automatically generates an equipment maintenance plan based on the generated fault warning signal.

[0007] Optionally, the data acquisition module includes: Deploy sensors and meteorological monitoring equipment: Deploy a variety of sensors in power distribution stations, including current sensors, voltage sensors, frequency sensors, power sensors, and vibration sensors. Deploy meteorological monitoring equipment around distribution stations, including temperature, humidity, wind speed, and air pressure sensors. Operation data collection: Use current sensors to monitor the current data of power grid equipment, use voltage sensors to record the voltage value of the power grid in real time, use frequency sensors to collect the frequency of the power grid, use power sensors to record the power output of power grid equipment, and use vibration sensors to collect the vibration data of power grid equipment; Environmental data collection: Meteorological data of the surrounding environment, including temperature, humidity, wind speed and air pressure, are collected through temperature, humidity, wind speed and air pressure sensors, and air quality data is collected through air quality sensors.

[0008] Optionally, the data preprocessing module includes: De-noising: Use the sliding average filter method to denoise the collected operating data and environmental data; Missing value filling: Linear interpolation is used to fill missing values ​​in the collected operation data and environmental data; Standardization: The Z-score standardization method is used to standardize the operating data and environmental data.

[0009] Optionally, the feature extraction includes: Current fluctuation amplitude calculation: Calculate the current fluctuation amplitude during the operation of the power grid equipment through the maximum and minimum values ​​of the current within a predetermined time window (3 minutes) ; Voltage deviation calculation: Calculate the voltage deviation based on the standard voltage value of the power grid ; Frequency stability calculation: Calculate frequency deviation from standard frequency value , assessing the frequency stability of the power grid; Vibration mode analysis: The vibration signal in the time domain is converted into frequency domain information using discrete Fourier transform, from which the vibration frequency and amplitude are extracted; Temperature change rate calculation: By calculating the temperature change rate of the device , monitor the thermal stability of the equipment; Relative humidity monitoring: directly monitor the relative humidity value in the environment to reflect the impact of environmental humidity on the equipment; Wind speed change detection: by calculating the wind speed change rate , to assess the impact of wind on open-air equipment; Air pressure change monitoring: By monitoring the changes in air pressure, calculate the air pressure change rate , to predict the impact of climate on equipment; Air quality index calculation: directly read the data of the air quality sensor, convert the concentration of each pollutant into the corresponding sub-index, and then take the maximum value as the air quality index .

[0010] Optionally, the data fusion includes: Adaptive weight assignment: Assign adaptive weights to each feature based on its importance to health assessment ; Weighted fusion processing: Adopt adaptive weighted algorithm to weight and fuse each eigenvalue into comprehensive eigenvalue ; Multi-dimensional feature output: The integrated feature value after fusion Output, as multi-dimensional features.

[0011] Optionally, the adaptive weight allocation includes: Feature importance score calculation: Perform importance analysis on each relevant feature to quantify its impact on grid health assessment. Calculate the correlation coefficient between each relevant feature and health assessment results (such as equipment failure rate or health score) to calculate the first Importance score of relevant features ; Calculate adaptive weights: based on the importance score of each relevant feature , calculate the adaptive weight .

[0012] Optionally, the power grid equipment health status assessment model adopts a Bayesian network model, and the Bayesian network model includes: Multi-layer conditional dependency modeling: By constructing a multi-layer Bayesian network, multi-dimensional features and health status are placed at different levels to reflect the dependency relationship between variables; Dynamic update mechanism: Introduce a dynamic update mechanism to update the health status of the device in real time based on time series data; Multi-feature joint probability calculation: Conditional mutual information is introduced to weight the impact of different features and calculate the final health status probability; Final health state calculation: After obtaining the final probability distribution of the health state through multi-feature joint probability calculation, the health state with the highest probability is selected. As an evaluation result.

[0013] Optionally, the fault prediction and alarm module includes: Health status score setting: based on the output of the Bayesian network model As the current moment Health status score ; Change rate calculation: Calculate the change rate of health status score , to identify deteriorating trends in health status; Failure probability prediction: Calculate the probability of potential failure based on the score change rate and the current health status score ; Fault warning generation: When Exceeding the preset threshold When a fault occurs, a fault warning signal is generated.

[0014] Optionally, the intelligent maintenance module includes: Maintenance task scheduling: When a fault warning signal is triggered, a maintenance task is automatically created; Resource allocation: After receiving a maintenance task, determine the manpower, materials, and tools required for maintenance, and automatically allocate the required resources.

[0015] Optionally, the resource configuration includes: Resource requirement analysis: Based on the maintenance tasks created, determine the number of personnel, skill levels, spare parts and tool lists required for the tasks; Resource availability check: Check the current available resource inventory and automatically generate a purchase or deployment request if there is a shortage of resources; Automatic resource allocation: Maintenance personnel are automatically assigned based on their skill matching and resource availability, and the corresponding materials and tools are allocated.

[0016] Beneficial effects of the present invention: The present invention realizes comprehensive collection of real-time operation data and environmental data of power grid equipment through multiple sensors and meteorological monitoring equipment. The coordinated work of the data acquisition module, preprocessing module and feature extraction module makes the data more accurate and consistent, providing high-quality data support for health status assessment and fault prediction of power grid equipment, ensuring comprehensive monitoring of equipment operation status and environmental conditions, improving the monitoring accuracy and real-time performance of the system, and facilitating timely discovery of potential risks and anomalies.

[0017] The present invention, through the heterogeneous data fusion power grid health assessment module and the fault prediction and alarm module, can accurately evaluate the health status of power grid equipment and identify potential faults in advance, adopt an adaptive weighted algorithm for feature fusion, and combine the Bayesian network model to realize dynamic update of health status and multi-feature joint analysis, thereby improving the accuracy and reliability of fault prediction. At the same time, the dynamic threshold set based on the quantile of historical data is combined with real-time environmental change adjustment, so that the early warning system has a high degree of adaptability and sensitivity, can respond quickly and reduce false alarms under different operating conditions, and effectively ensure the stable operation of the power grid.

[0018] The present invention automatically generates maintenance tasks after a fault warning signal is triggered through an intelligent maintenance module, and realizes rapid matching and automatic allocation of maintenance resources through resource configuration, thereby ensuring timely execution of maintenance tasks. The combination of resource demand analysis, availability check and automatic allocation optimizes the utilization efficiency of maintenance resources, reduces human intervention, and improves operation and maintenance efficiency. This automated and intelligent maintenance mechanism can reduce equipment downtime and maintenance costs, improve the reliability and operational stability of the power grid, and fully support the efficient and intelligent management of power grid equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1A schematic diagram of functional modules of a monitoring device according to an embodiment of the present invention; Figure 2 Schematic diagram of a heterogeneous data fusion power grid health assessment module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0022] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0023] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0024] like Figure 1-Figure 2 As shown, a monitoring device for a power distribution station room of a transmission and transformation network based on the Internet of Things includes a data acquisition module, a data preprocessing module, a heterogeneous data fusion power grid health assessment module, a fault prediction and alarm module, and an intelligent maintenance module, wherein; The data acquisition module collects real-time operation data and environmental data of power grid equipment through various sensors and meteorological monitoring equipment deployed in power grid distribution stations. The operation data includes current, voltage, frequency, power and vibration data, and the environmental data includes meteorological data (temperature, humidity, wind speed, air pressure) and air quality data. The data preprocessing module preprocesses the collected operation data and environmental data, including denoising, missing value filling, and standardization; The heterogeneous data fusion power grid health assessment module integrates the pre-processed operation data and environmental data to evaluate the health of the power grid in real time, including: Feature extraction: Extract features from pre-processed operating data and environmental data to extract relevant features of power grid equipment, including current fluctuation amplitude, voltage deviation, frequency stability, vibration mode, temperature change rate, relative humidity, wind speed change rate, air pressure change rate, and air quality index; Data fusion: Adopt adaptive weighting algorithm to fuse the extracted related features to form multi-dimensional features; Health status assessment: Use the power grid equipment health status assessment model to analyze multi-dimensional features and assess the health status of power grid equipment in real time; The fault prediction and alarm module identifies potential faults of power grid equipment in advance based on the evaluation results of the power grid health status and generates fault warning signals; The intelligent maintenance module automatically generates equipment maintenance plans based on the generated fault warning signals; Through the above content, it is possible to monitor the operating status and environmental conditions of power grid equipment in real time, accurately evaluate the health status of power grid equipment, predict potential failures in advance, and automatically generate maintenance plans, thereby improving the reliability and maintenance efficiency of the power grid, reducing manual intervention and equipment downtime. It has strong intelligent and automated characteristics and can effectively ensure the safety and stability of power grid operation.

[0025] The data acquisition module includes: Deploy sensors and meteorological monitoring equipment: Deploy a variety of sensors in power distribution stations, including current sensors, voltage sensors, frequency sensors, power sensors, and vibration sensors. Deploy meteorological monitoring equipment around distribution stations, including temperature, humidity, wind speed, and air pressure sensors. Operation data collection: Use current sensors to monitor the current data of power grid equipment, use voltage sensors to record the voltage value of the power grid in real time, use frequency sensors to collect the frequency of the power grid, use power sensors to record the power output of power grid equipment, and use vibration sensors to collect the vibration data of power grid equipment; Environmental data collection: collects meteorological data of the surrounding environment, including temperature, humidity, wind speed and air pressure, through temperature, humidity, wind speed and air pressure sensors, and collects air quality data through air quality sensors; Through the above content, comprehensive collection of operation data and environmental data of power grid equipment can provide comprehensive and accurate real-time data support for power grid health assessment and fault prediction, help to comprehensively monitor the status of power grid equipment, timely discover potential risks, and optimize power grid operation and maintenance strategies, thereby improving the reliability, stability and operation efficiency of the power grid, reducing the frequency of faults and downtime, and ensuring the safe and efficient operation of the power grid.

[0026] The data preprocessing module includes: Denoising: Use the sliding average filter method to denoise the collected operating data and environmental data to remove high-frequency noise in the data, expressed as: ; in, is the sliding window size, For in time The observed value at is the denoised data; Missing value filling: For the missing values ​​in the collected operation data and environmental data, linear interpolation is used to fill them, which is expressed as: ; in, For in time The interpolation of and are the known time points before and after the missing data point, and is the known data value at the corresponding time point; Standardization: The Z-score standardization method is used to standardize the operation data and environmental data, so that the dimensions of different data sources are unified, expressed as: ; in, is the standardized data, is the original data, is the mean of the data, is the standard deviation of the data; Through the above content, the quality and consistency of collected data are improved. De-noising processing effectively removes noise in the data to ensure the stability of the signal. Missing value filling supplements data gaps through interpolation and other methods to ensure data integrity. Standardization makes each data source have a unified dimension, which is convenient for subsequent fusion and analysis, and provides a more accurate and reliable data basis for power grid health assessment and fault prediction, thereby improving the assessment accuracy and stability of the entire system and helping to achieve more accurate monitoring and decision-making.

[0027] Feature extraction includes: Current fluctuation amplitude calculation: Calculate the current fluctuation amplitude during the operation of the power grid equipment through the maximum and minimum values ​​of the current within a predetermined time window (3 minutes) , expressed as: ; in, , They are the maximum and minimum values ​​of the current within the predetermined time window (3 minutes); Voltage deviation calculation: Calculate the voltage deviation based on the standard voltage value of the power grid , expressed as: ; in, is the real-time voltage value, is the standard voltage value of the power grid; Frequency stability calculation: Calculate frequency deviation from standard frequency value , evaluate the frequency stability of the power grid, expressed as: ; in, is the real-time frequency value, is the standard frequency value; Vibration mode analysis: Discrete Fourier transform is used to convert the vibration signal in the time domain into frequency domain information, from which the vibration frequency and amplitude are extracted, expressed as: ; in, is the first frequency components, including the frequency and amplitude information of the vibration signal, It is the time domain sampling points, is the total number of sampling points of the signal, is the frequency index, corresponding to different frequency components; ; in, is the sampling frequency, is the vibration frequency; Temperature change rate calculation: By calculating the temperature change rate of the device , monitors the thermal stability of the device and is expressed as: ; in, For time The temperature value, is the temperature value at the previous moment; Relative humidity monitoring: directly monitor the relative humidity value in the environment to reflect the impact of environmental humidity on the equipment; Wind speed change detection: by calculating the wind speed change rate , to evaluate the impact of wind on open-air equipment, expressed as: ; in, For time The wind speed at is the wind speed at the previous moment; Air pressure change monitoring: By monitoring the changes in air pressure, calculate the air pressure change rate , to predict the impact of climate on the equipment, expressed as: ; in, For time The air pressure at is the air pressure at the previous moment; Air quality index calculation: directly read the data of the air quality sensor, convert the concentration of each pollutant into the corresponding sub-index, and then take the maximum value as the air quality index , expressed as: ; in, is the sub-index of pollutants, is the actual concentration of the pollutant, and for Adjacent concentration limits in the standard, and For the corresponding The upper and lower limits of the interval; Through the above content, the health status of power grid equipment can be accurately assessed, helping to identify potential risks or failure trends more quickly, providing rich and valuable information for health assessment and fault prediction, thereby significantly improving the intelligence level of the monitoring system and the accuracy of early warning.

[0028] Data fusion includes: Adaptive weight assignment: Assign adaptive weights to each feature based on its importance to health assessment ; Weighted fusion processing: Adopt adaptive weighted algorithm to weight and fuse each eigenvalue into comprehensive eigenvalue , expressed as: ; in, is the comprehensive eigenvalue after fusion, For the The weight of the feature, For the The value of the feature, is the total number of features; Multi-dimensional feature output: The integrated feature value after fusion Output, as multi-dimensional features; Through the above content, the differentiated information of each feature can be effectively utilized, so that the features that contribute more to health assessment occupy a larger proportion in the results, thereby generating more accurate and comprehensive multi-dimensional features. This provides a high-quality data foundation for power grid health assessment and fault prediction, improves the accuracy of the assessment and the intelligent response capability of the system, and helps to achieve more reliable power grid equipment monitoring and risk warning.

[0029] Adaptive weight allocation includes: Feature importance score calculation: Perform importance analysis on each relevant feature to quantify its impact on grid health assessment. Calculate the correlation coefficient between each relevant feature and health assessment results (such as equipment failure rate or health score) to calculate the first Importance score of relevant features , expressed as: ; in, For the Features and health assessment results The correlation coefficient of Calculate adaptive weights: based on the importance score of each relevant feature , calculate the adaptive weight , expressed as: ; in, It is The importance scores of the relevant features, It is The importance scores of the relevant features, is the total number of relevant features; Through the above content, the real health status of power grid equipment can be reflected more accurately, the accuracy and reliability of the evaluation can be improved, the stability of feature fusion can be guaranteed, and the system can still adapt when the contribution of different features to the evaluation changes, thereby enhancing the intelligence level and responsiveness of the monitoring system.

[0030] The power grid equipment health status assessment model adopts the Bayesian network model, which includes: Multi-layer conditional dependency modeling: By constructing a multi-layer Bayesian network, multi-dimensional features and health status are placed at different levels to reflect the dependency relationship between variables, expressed as: ; in, For a given multidimensional feature set In case of health status The conditional probability of is a multidimensional feature set, including Features, namely , is a health status variable, indicating the health status of the device. For a given feature The parent node set Under the conditions, the characteristics The conditional probability of For a given health state The parent node set In case of health status The conditional probability of is the total number of features, that is, the comprehensive feature set The number of features in ; Dynamic update mechanism: A dynamic update mechanism is introduced to update the device health status in real time based on time series data, expressed as: ; in, For a given time from time 1 to time All feature sets In the case of Health status The conditional probability of For the moment The health status of the device indicates the health status of the device at the current moment. From time 1 to time The multidimensional feature set of , For the Features at time The observed value of For the Features at time The observed value of For a given previous moment Eigenvalue Under the condition of No. Features The conditional probability of is the health status at a given moment and the feature set at the current moment Under the condition of Health status The conditional probability of is the total number of features, that is, the number of features contained in the multidimensional feature set; Multi-feature joint probability calculation: Conditional mutual information is introduced to weight the impact of different features and calculate the final health status probability, which is expressed as: ; in, For a given multidimensional feature set In case of health status The conditional probability of For health status The prior probability that no feature is observed In the case The probability of is a multidimensional feature set, including Features, For the features, belonging to the multidimensional feature set One dimension in For a given health state Under the conditions of Features The conditional probability of is the conditional mutual information, which measures the Under the conditions of Features and health status The strength of the association between For the Features Other feature sets besides is the conditional mutual information, which measures the Under the conditions of Features and health status The strength of the association between For the Features Other feature sets besides is the total number of features; Final health state calculation: After obtaining the final probability distribution of the health state through multi-feature joint probability calculation, the health state with the highest probability is selected. As the evaluation result, it is expressed as: ; in, For the moment The final health status of the assessment, To find the conditional probability Maximum health status , For a given time from time 1 to time Multidimensional feature set In case of health status The value is The conditional probability of For the moment The health status of the device indicates the health status of the device at the current moment. From time 1 to time The multidimensional feature set of ; Through the above content, the accuracy and real-time performance of the health status assessment of power grid equipment can be significantly improved. By introducing conditional mutual information weighting, features with higher importance are given greater influence, thereby more accurately reflecting the impact of features on health status in the joint probability calculation of comprehensive features. At the same time, the dynamic update mechanism allows the model to adjust the health assessment results in real time according to time series data, and can quickly respond to changes in equipment status. This multi-level, dynamic and weighted Bayesian network structure provides an efficient and intelligent solution for health monitoring and fault warning of power grid equipment, ensuring the stability and safety of equipment operation.

[0031] The fault prediction and alarm module includes: Health status score setting: based on the output of the Bayesian network model As the current moment Health status score ; Change rate calculation: Calculate the change rate of health status score , to identify the deteriorating trend of health status, expressed as: ; in, and Respectively indicate time and If the health status score A negative value with a large magnitude indicates that health status is deteriorating; Failure probability prediction: Calculate the probability of potential failure based on the score change rate and the current health status score , expressed as: ; in, Represents the sigmoid function, which is used to map the results to The probability interval of and To adjust the parameters; Fault warning generation: When Exceeding the preset threshold When a fault occurs, a fault warning signal is generated; Threshold Dynamic quantile settings based on historical data include: Collect historical health status score data: Collect health status scores from the historical operation data of the device and corresponding fault records; Calculate the quantile of the fault score: For the fault score in the historical data , calculate its quantile (90% quantile) and set it as the initial threshold , expressed as: ; in, Represents the health score data when it was marked as a fault state in history; Dynamically adjust the threshold: Based on the changes in real-time data and the stability of the current operating environment, the initial threshold is dynamically adjusted, expressed as: ; in, Indicates the degree of environmental change (such as wind speed, temperature fluctuations, etc.); Through the above content, it is possible to effectively identify potential failures of power grid equipment in advance and generate early warning signals. The initial threshold is set by the quantile of historical data, and dynamically adjusted in combination with real-time environmental factors. It has good adaptability and sensitivity, which can not only effectively reduce false alarms under different operating conditions, but also ensure timely identification of equipment abnormalities. This adaptive prediction and early warning mechanism provides a reliable guarantee for the stable operation of power grid equipment and improves the safety and operating efficiency of the system.

[0032] The intelligent maintenance module includes: Maintenance task scheduling: When a fault warning signal is triggered, a maintenance task is automatically created; Resource allocation: After receiving the maintenance task, determine the manpower, materials and tools required for maintenance, and automatically allocate the required resources to ensure the smooth implementation of the maintenance task; Through the above content, it is possible to respond quickly after the fault warning signal is triggered, immediately generate maintenance tasks and allocate the required manpower and materials, reduce human intervention, improve fault response speed and maintenance efficiency, ensure that maintenance work can be carried out in a timely and effective manner, and help prevent the fault from further expanding or causing equipment damage. At the same time, automated resource allocation ensures the smooth implementation of maintenance tasks, optimizes the use of maintenance resources, and improves the reliability and operational stability of power grid equipment.

[0033] Resource configuration includes: Resource requirement analysis: Based on the maintenance tasks created, determine the number of personnel, skill levels, spare parts and tool lists required for the tasks; Resource availability check: Check the current available resource inventory to ensure that the required materials and tools can meet the task requirements. If there is a shortage of resources, a purchase or deployment request is automatically generated; Automatic resource allocation: Automatically allocate maintenance personnel based on personnel skill matching and resource availability, and allocate corresponding materials and tools to form a complete resource allocation plan; Through the above content, it can be ensured that maintenance tasks respond quickly and obtain sufficient support after receiving early warnings. Resource demand analysis accurately matches the personnel, skills, spare parts and tools required for the task, avoiding excessive or insufficient resources. Resource availability checks are carried out through real-time inventory verification, and procurement or deployment requests are generated in a timely manner to ensure adequate supply of key materials and tools. The final automated resource allocation is intelligently matched according to personnel skills and available resources to ensure efficient execution of maintenance work, improve maintenance response speed and resource utilization efficiency, reduce human intervention, optimize operation and maintenance costs, and effectively ensure the stable operation of power grid equipment.

[0034] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0035] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A monitoring device for a power distribution station room of a transmission and transformation network based on the Internet of Things, characterized in that: It includes data acquisition module, data preprocessing module, heterogeneous data fusion power grid health assessment module, fault prediction and alarm module and intelligent maintenance module, among which; The data acquisition module collects real-time operation data and environmental data of power grid equipment through various sensors and meteorological monitoring equipment deployed in the power grid distribution station. The operation data includes current, voltage, frequency, power and vibration data, and the environmental data includes meteorological data and air quality data. The data preprocessing module preprocesses the collected operation data and environmental data, including denoising, missing value filling, and standardization; The heterogeneous data fusion power grid health assessment module fuses the pre-processed operation data and environmental data to assess the health status of the power grid in real time, specifically including: Feature extraction: Extract features from pre-processed operating data and environmental data to extract relevant features of power grid equipment, including current fluctuation amplitude, voltage deviation, frequency stability, vibration mode, temperature change rate, relative humidity, wind speed change rate, air pressure change rate, and air quality index; Data fusion: Adopt adaptive weighting algorithm to fuse the extracted related features to form multi-dimensional features; Health status assessment: Use the power grid equipment health status assessment model to analyze multi-dimensional features and assess the health status of power grid equipment in real time; The fault prediction and alarm module identifies potential faults of power grid equipment in advance based on the evaluation results of the power grid health status and generates fault warning signals; The intelligent maintenance module automatically generates an equipment maintenance plan based on the generated fault warning signal.

2. According to the Internet of Things-based power transmission and transformation network distribution station room monitoring device according to claim 1, it is characterized in that: The data acquisition module comprises: Deploy sensors and meteorological monitoring equipment: Deploy a variety of sensors in power distribution stations, including current sensors, voltage sensors, frequency sensors, power sensors, and vibration sensors. Deploy meteorological monitoring equipment around distribution stations, including temperature, humidity, wind speed, and air pressure sensors. Operation data collection: Use current sensors to monitor the current data of power grid equipment, use voltage sensors to record the voltage value of the power grid in real time, use frequency sensors to collect the frequency of the power grid, use power sensors to record the power output of power grid equipment, and use vibration sensors to collect the vibration data of power grid equipment; Environmental data collection: Meteorological data of the surrounding environment, including temperature, humidity, wind speed and air pressure, are collected through temperature, humidity, wind speed and air pressure sensors, and air quality data is collected through air quality sensors.

3. According to the Internet of Things-based power transmission and transformation network distribution station room monitoring device according to claim 1, it is characterized in that: The data preprocessing module comprises: De-noising: Use the sliding average filter method to denoise the collected operating data and environmental data; Missing value filling: Linear interpolation is used to fill missing values ​​in the collected operation data and environmental data; Standardization: The Z-score standardization method is used to standardize the operating data and environmental data.

4. The monitoring device for power distribution station room of a power transmission and transformation network based on the Internet of Things according to claim 1 is characterized in that: The feature extraction comprises: Current fluctuation amplitude calculation: Calculate the current fluctuation amplitude during the operation of the power grid equipment through the maximum and minimum values ​​of the current within a predetermined time window ; Voltage deviation calculation: Calculate the voltage deviation based on the standard voltage value of the power grid ; Frequency stability calculation: Calculate frequency deviation from standard frequency value , assessing the frequency stability of the power grid; Vibration mode analysis: The vibration signal in the time domain is converted into frequency domain information using discrete Fourier transform, from which the vibration frequency and amplitude are extracted; Temperature change rate calculation: By calculating the temperature change rate of the device , monitor the thermal stability of the equipment; Relative humidity monitoring: directly monitor the relative humidity value in the environment to reflect the impact of environmental humidity on the equipment; Wind speed change detection: by calculating the wind speed change rate , to assess the impact of wind on open-air equipment; Air pressure change monitoring: By monitoring the changes in air pressure, calculate the air pressure change rate , to predict the impact of climate on equipment; Air quality index calculation: directly read the data of the air quality sensor, convert the concentration of each pollutant into the corresponding sub-index, and then take the maximum value as the air quality index .

5. The monitoring device for power distribution station room of a power transmission and transformation network based on the Internet of Things according to claim 4 is characterized in that: The data fusion includes: Adaptive weight assignment: Assign adaptive weights to each feature based on its importance to health assessment ; Weighted fusion processing: Adopt adaptive weighted algorithm to weight and fuse each eigenvalue into comprehensive eigenvalue ; Multi-dimensional feature output: The integrated feature value after fusion Output, as multi-dimensional features.

6. The monitoring device for power distribution station room of a power transmission and transformation network based on the Internet of Things according to claim 5 is characterized in that: The adaptive weight allocation comprises: Feature importance score calculation: Perform importance analysis on each relevant feature to quantify its impact on grid health assessment. Calculate the correlation coefficient between each relevant feature and the health assessment result. Importance score of relevant features ; Calculate adaptive weights: based on the importance score of each relevant feature , calculate the adaptive weight .

7. The monitoring device for power distribution station room of a power transmission and transformation network based on the Internet of Things according to claim 6 is characterized in that: The power grid equipment health status assessment model adopts a Bayesian network model, and the Bayesian network model includes: Multi-layer conditional dependency modeling: By constructing a multi-layer Bayesian network, multi-dimensional features and health status are placed at different levels to reflect the dependency relationship between variables; Dynamic update mechanism: Introduce a dynamic update mechanism to update the health status of the device in real time based on time series data; Multi-feature joint probability calculation: Conditional mutual information is introduced to weight the impact of different features and calculate the final health status probability; Final health state calculation: After obtaining the final probability distribution of the health state through multi-feature joint probability calculation, the health state with the highest probability is selected. As an evaluation result.

8. The monitoring device for power distribution station room of a power transmission and transformation network based on the Internet of Things according to claim 7 is characterized in that: The fault prediction and alarm module includes: Health status score setting: based on the output of the Bayesian network model As the current moment Health status score ; Change rate calculation: Calculate the change rate of health status score , to identify deteriorating trends in health status; Failure probability prediction: Calculate the probability of potential failure based on the score change rate and the current health status score ; Fault warning generation: When Exceeding the preset threshold When a fault occurs, a fault warning signal is generated.

9. The monitoring device for power distribution station room of a power transmission and transformation network based on the Internet of Things according to claim 8 is characterized in that: The intelligent maintenance module comprises: Maintenance task scheduling: When a fault warning signal is triggered, a maintenance task is automatically created; Resource allocation: After receiving a maintenance task, determine the manpower, materials, and tools required for maintenance, and automatically allocate the required resources.

10. The monitoring device for power distribution station room of a power transmission and transformation network based on the Internet of Things according to claim 9 is characterized in that: The resource configuration includes: Resource requirement analysis: Based on the maintenance tasks created, determine the number of personnel, skill levels, spare parts and tool lists required for the tasks; Resource availability check: Check the current available resource inventory and automatically generate a purchase or deployment request if there is a shortage of resources; Automatic resource allocation: Maintenance personnel are automatically assigned based on their skill matching and resource availability, and the corresponding materials and tools are allocated.

Images