An edge-computing-based real-time processing method and system for dynamic environment monitoring data
By deploying acquisition and monitoring terminals at the edge of power equipment and using convolutional neural networks to build evaluation models, the problem of high latency and low efficiency in cloud processing is solved, enabling efficient fault diagnosis and data processing of power equipment.
Patent Information
- Application Number
- CN202511503319.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-21
- Publication Date
- 2025-12-26
- Estimated Expiration
- 2045-10-21
AI Technical Summary
In existing technologies, data processing for power equipment relies on cloud processing, resulting in high latency and low efficiency. Furthermore, the deployment of edge terminals remains fixed and cannot be flexibly adjusted.
An edge computing-based environmental monitoring system is adopted. By deploying acquisition terminals and monitoring terminals for power equipment, an equipment monitoring module, a fault assessment module, and a monitoring feedback module are constructed. An evaluation model is built using a convolutional neural network to determine faults and provide feedback in real time.
It enables efficient data processing at the edge of power equipment, reduces the amount of data processing, and improves the accuracy of fault diagnosis and data processing efficiency.
Smart Images
Figure CN120973636B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application relates to the technical field of data processing, and particularly relates to a dynamic environment monitoring data real-time processing method and system based on edge computing. BACKGROUND
[0002] Dynamic environment monitoring, which is also called power and environment monitoring, is a system for monitoring power equipment and environmental parameters of key facilities in real time, and aims to ensure the safe and stable operation of power equipment. In the prior art, the data of power equipment often needs to be sent to the cloud for processing, which inevitably leads to high delay and low efficiency.
[0003] Therefore, real-time processing of the data of power equipment by using edge computing technology has become a new technology direction. In the prior art, the deployment and use of edge terminals are often fixed and unchanged, and cannot be flexibly adjusted according to the states of the edge terminals and the data to be processed, so that the efficiency of data processing is still high. In view of the defects in the prior art, the application provides a dynamic environment monitoring data real-time processing method and system based on edge computing. SUMMARY
[0004] The application aims to provide a dynamic environment monitoring data real-time processing method and system based on edge computing.
[0005] The application can be achieved by the following technical scheme: a dynamic environment monitoring data real-time processing system based on edge computing, comprising the following modules:
[0006] A device monitoring module is configured to deploy a collection terminal for each power equipment to obtain different collection data, and to obtain a plurality of monitoring points in an application scenario to deploy a monitoring terminal.
[0007] A fault evaluation module is configured to obtain an abnormal data set according to a preset filtering range and different collection data, and to obtain corresponding abnormal data features, and to construct a first evaluation model according to abnormal data sets and abnormal data features of different fault types.
[0008] A time consumption evaluation module is configured to obtain processing parameters of different abnormal data sets, and to construct a second evaluation model by combining the processing time consumption of different abnormal data sets by the monitoring terminal under different operation parameters.
[0009] A monitoring feedback module is configured to obtain an optimal monitoring terminal for different abnormal data sets in real time by using the second evaluation model, to determine whether a fault event exists in the abnormal data set of the optimal monitoring terminal by using the first evaluation model in the optimal monitoring terminal, and to feed back.
[0010] Further, the acquisition terminal is respectively arranged for each power equipment to obtain different acquisition data, and in the application scenario, the process of obtaining multiple monitoring points to arrange the monitoring terminal includes:
[0011] The acquisition terminal is respectively arranged for each power equipment in the same application scenario, and different acquisition units are arranged in the acquisition terminal. The corresponding acquisition data, including voltage, current, temperature, humidity, pressure, and amplitude, are obtained in real time through each acquisition unit.
[0012] The deployment positions of each acquisition terminal in the same application scenario are obtained, and a GIS distribution map of all acquisition terminals is constructed according to the obtained deployment positions by using GIS technology. The initial monitoring points are obtained in the GIS distribution map, and the probability values of other deployment positions being selected as the next monitoring points are obtained.
[0013] The next monitoring point is constructed at the deployment position corresponding to the maximum probability value, and this step is repeated until n monitoring points are constructed. The monitoring terminal is arranged at each monitoring point.
[0014] Further, the process of obtaining an abnormal data set according to a preset filtering range and different acquisition data and obtaining corresponding abnormal data features includes:
[0015] The corresponding filtering range is set for different acquisition data, the judgment unit is arranged in each acquisition terminal, and whether each acquisition data of each acquisition terminal is within the filtering range is judged.
[0016] When any acquisition data of a single acquisition terminal is not within the filtering range, the current time is marked as an abnormal time, and the values of the acquisition data obtained by each acquisition terminal in the same application scenario at the abnormal time are included in the first abnormal data set.
[0017] All values of the acquisition data of the acquisition terminal between the current time and the last abnormal time are included in the second abnormal data set. The data features of the first abnormal data set and the second abnormal data set are respectively taken as the first abnormal data feature and the second abnormal data feature. The abnormal data set and the abnormal data feature of each acquisition data of each acquisition terminal are obtained.
[0018] Further, the process of constructing a first evaluation model according to the abnormal data set and the abnormal data feature of different fault types includes:
[0019] Obtain historical fault records of different fault types, the historical fault records including an abnormal data set at a corresponding abnormal moment and an abnormal data feature thereof, generate a first evaluation set according to the abnormal data set, the abnormal data feature and the corresponding fault type of different historical fault records, and divide the first evaluation set into a first training set and a first test set;
[0020] Construct a first convolutional neural network, take the abnormal data set and the abnormal data feature in the first training set as input data of the first convolutional neural network, and take whether a fault event exists and a fault type as output data of the first convolutional neural network;
[0021] Train the first convolutional neural network by using the first training set to obtain an initial first convolutional neural network, perform model verification on the initial first convolutional neural network by using the first test set, and output the initial first convolutional neural network less than or equal to a preset first test error threshold as a first evaluation model.
[0022] Further, the process of constructing a second evaluation model by using processing parameters of different abnormal data sets and combining processing time consumptions of different abnormal data sets by the monitoring terminal under different running parameters includes:
[0023] Deploy the first evaluation model in each monitoring terminal, input a single abnormal data set and an abnormal data feature thereof into the first evaluation model in each monitoring terminal respectively, and output evaluation results respectively, and take a time interval from data input to result output of each first evaluation model as a processing time consumption thereof;
[0024] Obtain processing parameters of the single abnormal data set and running parameters of each monitoring terminal, the processing parameters being data volume and data packet size of the single abnormal data set, and the running parameters being real-time state parameters of a server preset in each monitoring terminal;
[0025] Obtain processing time consumptions of abnormal data sets with different processing parameters in each monitoring terminal and corresponding running parameters, generate a second evaluation set according to the processing time consumptions of the abnormal data sets with different processing parameters in each monitoring terminal and the running parameters, and divide the second evaluation set into a second training set and a second test set;
[0026] Construct a second convolutional neural network, take different processing parameters and running parameters in the second training set as input data of the second convolutional neural network, and take corresponding processing time consumptions in the second training set as output data of the second convolutional neural network;
[0027] The second convolutional neural network is trained by using the second training set to obtain an initial second convolutional neural network, the initial second convolutional neural network is model verified by using the second test set, and the initial second convolutional neural network less than or equal to a preset second test error threshold is output as a second evaluation model.
[0028] Further, the process of acquiring the optimal monitoring terminal of different abnormal data sets in real time by using the second evaluation model comprises:
[0029] The second evaluation model is respectively deployed in each monitoring terminal, when a single abnormal data set is generated in a single collection terminal, the abnormal data features and processing parameters corresponding to the abnormal data set are acquired, and the processing parameters are sent to the monitoring terminal closest to the collection terminal;
[0030] The running parameters of each monitoring terminal are synchronized in real time, the processing parameters of the abnormal data set and the running parameters of each monitoring terminal are respectively input into the second evaluation model in the monitoring terminal closest to the collection terminal, so as to acquire the processing time of each monitoring terminal for the abnormal data set, and the monitoring terminal with the shortest processing time is taken as the optimal monitoring terminal of the abnormal data set.
[0031] Further, the process of judging whether the abnormal data set in the optimal monitoring terminal exists a fault event by using the first evaluation model and feeding back comprises:
[0032] The single abnormal data set of the single collection terminal and the abnormal data features thereof are sent to the optimal monitoring terminal thereof, the received abnormal data set and abnormal data features are input into the first evaluation model in the optimal monitoring terminal, so as to judge whether the abnormal data set exists a fault event, if yes, the fault type is acquired and fed back to the relevant personnel, and if no, no other operation is performed.
[0033] A real-time processing method for dynamic environment monitoring data based on edge computing comprises the following steps:
[0034] Step S1: a collection terminal is respectively deployed for each power equipment to acquire different collection data, and a plurality of monitoring points are acquired in an application scene to deploy a monitoring terminal;
[0035] Step S2: abnormal data sets are acquired according to a preset filtering range combined with different collection data, and corresponding abnormal data features are acquired, and a first evaluation model is constructed according to abnormal data sets and abnormal data features of different fault types;
[0036] Step S3: processing parameters of different abnormal data sets are acquired, and a second evaluation model is constructed combined with processing time of different abnormal data sets by the monitoring terminal under different running parameters;
[0037] Step S4: Real-time acquisition of the optimal monitoring terminal of the different abnormal data sets by using the second evaluation model, and judging whether the abnormal data sets exist fault events by using the first evaluation model in the optimal monitoring terminal and feeding back.
[0038] Compared with the prior art, the beneficial effects of the present application are:
[0039] The present application can realize data processing of the edge of the power equipment by setting corresponding acquisition terminals and a plurality of monitoring terminals for the power equipment, solve the technical problem of high delay and low efficiency of cloud processing in the past, and effectively reduce the data processing amount by filtering the data within the normal range, thereby improving the efficiency of data processing.
[0040] By obtaining two types of abnormal data sets and their abnormal data characteristics of the same acquisition terminal, the data characteristics of the acquisition data of the same power equipment at different times and the data characteristics of different power equipment at the same time can be comprehensively reflected to reflect the data change of the power equipment when it is in failure, and the first evaluation model is constructed, which is beneficial to form an effective fault judgment mechanism for the power equipment. The second evaluation model is constructed according to the processing time of the monitoring terminal under different processing parameters and operating parameters, which can real-time allocate the optimal monitoring terminal for different abnormal data sets to process the data, and improve the efficiency of data processing. BRIEF DESCRIPTION OF DRAWINGS
[0041] Figure 1 The module diagram of the present application. DETAILED DESCRIPTION
[0042] As shown in Figure 1 A real-time processing system for dynamic environmental monitoring data based on edge computing, comprising the following modules:
[0043] The device monitoring module is used for deploying acquisition terminals for each power equipment to obtain different acquisition data, and obtaining a plurality of monitoring points in the application scene to deploy monitoring terminals.
[0044] The fault evaluation module is used for obtaining abnormal data sets according to the preset filtering range combined with different acquisition data, and obtaining corresponding abnormal data characteristics, and constructing a first evaluation model according to abnormal data sets and their abnormal data characteristics of different fault types.
[0045] The time consumption evaluation module is used for obtaining the processing parameters of different abnormal data sets, and constructing a second evaluation model combined with the processing time of the monitoring terminal for different abnormal data sets under different operating parameters.
[0046] The monitoring feedback module is configured to acquire optimal monitoring terminals for different abnormal data sets in real time by using the second evaluation model, and determine whether the abnormal data sets have fault events by using the first evaluation model in the optimal monitoring terminals and feed back.
[0047] It should be further explained that, in the specific implementation process, different acquisition terminals are respectively arranged for the power equipment to acquire different acquisition data, and the process of acquiring a plurality of monitoring points in the application scenario to arrange the monitoring terminals includes:
[0048] The acquisition terminal is arranged for each power equipment in the same application scenario, and different acquisition units are arranged in the acquisition terminal, including a voltage acquisition unit, a current acquisition unit, a temperature acquisition unit, a humidity acquisition unit, a pressure acquisition unit, and an amplitude acquisition unit. The corresponding acquisition data, including voltage, current, temperature, humidity, pressure, and amplitude, are acquired in real time by the acquisition units;
[0049] The deployment positions of the acquisition terminals in the same application scenario are acquired, which are used to reflect the specific coordinates of the acquisition terminals in the application scenario, and a GIS distribution map of all the acquisition terminals is constructed by using GIS technology according to the acquired deployment positions;
[0050] In the GIS distribution map, the deployment position of any acquisition terminal is taken as an initial monitoring point, the shortest distance d between each deployment position and the current monitoring point is acquired i , where i = 1, 2, …, k, k is the number of each deployment position except the current monitoring point in the application scenario, and the probability value P of each deployment position being selected as the next monitoring point is acquired i .
[0051] ;
[0052] The next monitoring point is constructed at the deployment position corresponding to the maximum probability value, and the step is repeated until n monitoring points are constructed. The n constructed monitoring points are uploaded to the GIS distribution map for synchronization, and the monitoring terminals for data processing are arranged at each monitoring point.
[0053] It should be further explained that, in the specific implementation process, the abnormal data sets are acquired according to the preset filtering range and different acquisition data, and the corresponding abnormal data features are acquired, and the process includes:
[0054] The corresponding filtering range is set for different acquisition data, and the filtering range is a fixed numerical range. A judgment unit is arranged in each acquisition terminal to determine whether each acquisition data of each acquisition terminal is in (including equal to) the corresponding filtering range.
[0055] Taking any collection terminal as an example, when each item of collection data is within its filtering range, no other operation is performed thereon, and when there is an item of collection data that is not within its filtering range, the current time is marked as an abnormal time, and the values of the item of collection data acquired by each collection terminal in the same application scenario at the abnormal time are all included in a first abnormal data set;
[0056] All values of the item of collection data of the collection terminal between the current time and the last abnormal time are included in a second abnormal data set, the first abnormal data set and the second abnormal data set are both abnormal data sets of the collection terminal, and the data features of the first abnormal data set and the second abnormal data set are respectively the first abnormal data feature and the second abnormal data feature, both of which are abnormal data features of the corresponding collection terminal;
[0057] Since the first abnormal data set is a plurality of values at the same time, its data features include mean and variance, and since the second abnormal data set is a plurality of values at different times, its data features include mean, variance and change trend, and the method is adopted to acquire the abnormal data set and the abnormal data feature of each item of collection data of each collection terminal.
[0058] It should be further explained that, in the specific implementation process, the process of constructing the first evaluation model according to the abnormal data sets and the abnormal data features of different fault types includes:
[0059] Acquiring historical fault records of different fault types, the historical fault records refer to related records of fault events that have occurred in the past of the power equipment, which include abnormal data sets and abnormal data features at corresponding abnormal times;
[0060] Generating a first evaluation set according to the abnormal data sets, the abnormal data features and the corresponding fault types contained in different historical fault records, and dividing the first evaluation set into a first training set and a first test set;
[0061] Constructing a first convolutional neural network, taking the abnormal data sets and the abnormal data features in the first training set as input data of the first convolutional neural network, and taking whether there is a fault event and the fault type thereof as output data of the first convolutional neural network;
[0062] Training the first convolutional neural network using the first training set to obtain an initial first convolutional neural network, verifying the model of the initial first convolutional neural network using the first test set, and outputting the initial first convolutional neural network less than or equal to a preset first test error threshold as the corresponding first evaluation model.
[0063] It needs to be further explained that in the specific implementation process, the process of obtaining the processing parameters of different abnormal data sets and combining the processing time of different abnormal data sets by the monitoring terminal under different running parameters to build the second evaluation model includes:
[0064] The first evaluation model is respectively deployed in each monitoring terminal, the single abnormal data set and its abnormal data features are respectively input into the first evaluation model in each monitoring terminal, and the corresponding evaluation results are respectively output, and the time interval from data input to result output of each first evaluation model is taken as its processing time;
[0065] The processing parameters of the single abnormal data set and the running parameters of each monitoring terminal in the evaluation process of its first evaluation model are obtained, the processing parameters refer to the data volume and data packet size of the single abnormal data set, and the running parameters refer to the real-time state parameters of the server preset in each monitoring terminal, including CPU usage, CPU core number and frequency, memory usage, memory read / write speed, hard disk usage, hard disk read / write speed, network bandwidth usage, network delay;
[0066] The processing time of abnormal data sets with different processing parameters in each monitoring terminal and its corresponding running parameters are obtained, the second evaluation set is generated according to the processing time of abnormal data sets with different processing parameters in each monitoring terminal and its running parameters, and it is divided into a second training set and a second test set;
[0067] The second convolutional neural network is constructed, the different processing parameters and running parameters in the second training set are taken as the input data of the second convolutional neural network, and the corresponding processing time in the second training set is taken as the output data of the second convolutional neural network;
[0068] The second training set is used to train the second convolutional neural network to obtain an initial second convolutional neural network, the second test set is used to verify the model of the initial second convolutional neural network, and the initial second convolutional neural network less than or equal to the preset second test error threshold is output as the corresponding second evaluation model.
[0069] It needs to be further explained that in the specific implementation process, the process of obtaining the optimal monitoring terminal of different abnormal data sets in real time by using the second evaluation model includes:
[0070] The second evaluation model is respectively deployed in each monitoring terminal, taking a single collection terminal as an example, when the collection terminal generates an abnormal data set, the abnormal data features and processing parameters corresponding to the abnormal data set are obtained, and the processing parameters are sent to the monitoring terminal closest to the collection terminal;
[0071] The running parameters of each monitoring terminal are synchronized in real time, the processing parameters of the abnormal data set and the running parameters of each monitoring terminal are input into the second evaluation model in the monitoring terminal closest to the collection terminal, to obtain the processing time of each monitoring terminal for the abnormal data set, and the monitoring terminal with the shortest processing time is taken as the optimal monitoring terminal for the abnormal data set.
[0072] It needs to be further explained that, in the specific implementation process, the process of using the first evaluation model in the optimal monitoring terminal to judge whether the abnormal data set has a fault event and feeding back includes:
[0073] The abnormal data set of a single collection terminal and its abnormal data features are sent to the corresponding optimal monitoring terminal, and in the optimal monitoring terminal, the received abnormal data set and abnormal data features are input into the first evaluation model to judge whether the abnormal data set has a fault event, if it does, its fault type is obtained and fed back to the relevant personnel to prompt the relevant personnel to timely overhaul the power equipment, and if it does not, no other operation is performed.
[0074] In the embodiments of the present application, a real-time processing method for dynamic environmental monitoring data based on edge computing is also included, which comprises the following steps:
[0075] Step S1: a collection terminal is deployed for each power equipment to obtain different collection data, and in the application scene, multiple monitoring points are obtained to deploy monitoring terminals;
[0076] Step S2: abnormal data sets are obtained according to the preset filtering range combined with different collection data, and corresponding abnormal data features are obtained, and a first evaluation model is constructed according to abnormal data sets and abnormal data features of different fault types;
[0077] Step S3: processing parameters of different abnormal data sets are obtained, and a second evaluation model is constructed combined with the processing time of the monitoring terminal for different abnormal data sets under different running parameters;
[0078] Step S4: the optimal monitoring terminal for different abnormal data sets is obtained in real time by using the second evaluation model, and the first evaluation model in the optimal monitoring terminal is used to judge whether the abnormal data set has a fault event and feed back.
[0079] The above embodiments are only used to illustrate the technical method of the present application and not to limit it, although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical method of the present application.
Claims
1. An edge-computing-based real-time processing system for dynamic environmental monitoring data, characterized in that, The application comprises the following modules: A device monitoring module is configured to deploy collection terminals for respective power devices to obtain different collection data, and to obtain multiple monitoring points in an application scenario to deploy monitoring terminals; A fault evaluation module is configured to obtain an abnormal data set according to a preset filtering range and different collection data, and to obtain corresponding abnormal data features, and to construct a first evaluation model according to abnormal data sets and abnormal data features of different fault types; A time-consuming evaluation module is configured to obtain processing parameters of different abnormal data sets, and to construct a second evaluation model in combination with processing time of different abnormal data sets under different operating parameters of the monitoring terminal; A monitoring feedback module is configured to obtain an optimal monitoring terminal for different abnormal data sets in real time by using the second evaluation model, to determine whether the abnormal data set of the optimal monitoring terminal has a fault event by using the first evaluation model in the optimal monitoring terminal, and to feed back the determination result. The process of obtaining abnormal data sets and abnormal data features comprises: Respective filtering ranges are set for different collection data, and a judgment unit is set in each collection terminal, and it is determined whether each collection data of each collection terminal is within the filtering range thereof; When any collection data of a single collection terminal is not within the filtering range thereof, the current time is marked as an abnormal time, and the values of the collection data obtained by each collection terminal in the same application scenario at the abnormal time are included in a first abnormal data set; All values of the collection data of the collection terminal between the current time and the last abnormal time are included in a second abnormal data set, and the data features of the first abnormal data set and the second abnormal data set are respectively taken as the first abnormal data features and the second abnormal data features, and the abnormal data sets and the abnormal data features of each collection data of each collection terminal are obtained. 2.The real-time processing system for dynamic environment monitoring data based on edge computing according to claim 1, wherein, The process of obtaining collection data and deploying monitoring terminals comprises: Collection terminals are deployed for respective power devices in the same application scenario, and different collection units are arranged in the collection terminals, and corresponding collection data, including voltage, current, temperature, humidity, pressure, and amplitude, are obtained in real time by the collection units; Deployment positions of each collection terminal in the same application scenario are obtained, a GIS distribution map of all collection terminals is constructed by using GIS technology according to the obtained deployment positions, an initial monitoring point is obtained in the GIS distribution map, and a probability value of each deployment position being selected as a next monitoring point is obtained; A next monitoring point is constructed at the deployment position corresponding to the maximum probability value, and the step is repeated until n monitoring points are constructed, and monitoring terminals are deployed at the respective monitoring points. 3.The real-time processing system for dynamic environment monitoring data based on edge computing according to claim 2, wherein, The process of constructing the first evaluation model comprises: Historical fault records of different fault types are obtained, the historical fault records contain abnormal data sets and abnormal data features at corresponding abnormal times, a first evaluation set is generated according to abnormal data sets, abnormal data features, and corresponding fault types of different historical fault records, and the first evaluation set is divided into a first training set and a first test set. The first convolutional neural network is constructed, and the abnormal data set and the abnormal data features in the first training set are used as input data of the first convolutional neural network, and whether the abnormal data set has a fault event and a fault type of the abnormal data set are used as output data of the first convolutional neural network. The first convolutional neural network is trained by using the first training set to obtain an initial first convolutional neural network, and the initial first convolutional neural network is verified by using the first test set, and an initial first convolutional neural network less than or equal to a preset first test error threshold is output as the first evaluation model.
4. The real-time processing system for dynamic environment monitoring data based on edge computing according to claim 3, characterized in that, The process of constructing the second evaluation model comprises: The first evaluation model is deployed in each monitoring terminal, the single abnormal data set and the abnormal data features thereof are input into the first evaluation model in each monitoring terminal, and an evaluation result is output, and a time interval from data input to result output of each first evaluation model is used as processing time consumption; The processing parameters of the single abnormal data set and the running parameters of each monitoring terminal are obtained, the processing parameters are data volume and data packet size of the single abnormal data set, and the running parameters are real-time state parameters of a server preinstalled in each monitoring terminal; The processing time consumption of the abnormal data set with different processing parameters in each monitoring terminal and the corresponding running parameters are obtained, a second evaluation set is generated according to the processing time consumption of the abnormal data set with different processing parameters in each monitoring terminal and the running parameters, and the second evaluation set is divided into a second training set and a second test set; The second convolutional neural network is constructed, and the different processing parameters and the running parameters in the second training set are used as input data of the second convolutional neural network, and the corresponding processing time consumption in the second training set is used as output data of the second convolutional neural network; The second convolutional neural network is trained by using the second training set to obtain an initial second convolutional neural network, and the initial second convolutional neural network is verified by using the second test set, and an initial second convolutional neural network less than or equal to a preset second test error threshold is output as the second evaluation model.
5. The real-time processing system for dynamic environment monitoring data based on edge computing according to claim 4, characterized in that, The process of obtaining the optimal monitoring terminal of different abnormal data sets comprises: The second evaluation model is deployed in each monitoring terminal, and when a single abnormal data set is generated in a single collection terminal, the abnormal data features and the processing parameters corresponding to the abnormal data set are obtained, and the processing parameters are sent to the monitoring terminal closest to the collection terminal; The running parameters of each monitoring terminal are synchronized in real time, the processing parameters of the abnormal data set and the running parameters of each monitoring terminal are input into the second evaluation model in the monitoring terminal closest to the collection terminal, so as to obtain the processing time consumption of each monitoring terminal to the abnormal data set, and the monitoring terminal with the shortest processing time consumption is used as the optimal monitoring terminal of the abnormal data set.
6. The real-time processing system for dynamic environment monitoring data based on edge computing according to claim 5, characterized in that, The process of judging whether the abnormal data set has a fault event comprises: The single abnormal data set of the single collection terminal and the abnormal data features thereof are sent to the optimal monitoring terminal thereof, and in the optimal monitoring terminal, the received abnormal data set and abnormal data features are input into a first evaluation model to determine whether the abnormal data set has a fault event, if yes, the fault type thereof is obtained and fed back to relevant personnel, and if not, no other operation is performed.
7. A real-time processing method for dynamic environmental monitoring data based on edge computing, implemented based on the real-time processing system for dynamic environmental monitoring data based on edge computing in any of claims 1-6, characterized in that, The method comprises: Step S1: deploying a collection terminal for each power equipment to obtain different collection data, and obtaining multiple monitoring points in an application scenario to deploy a monitoring terminal; Step S2: obtaining abnormal data sets according to a preset filtering range in combination with different collection data, and obtaining corresponding abnormal data features, and constructing a first evaluation model according to abnormal data sets and abnormal data features of different fault types; Step S3: obtaining processing parameters of different abnormal data sets, and constructing a second evaluation model in combination with processing time of the monitoring terminal for different abnormal data sets under different operating parameters; Step S4: obtaining the optimal monitoring terminal of different abnormal data sets in real time by using the second evaluation model, and determining whether the abnormal data set has a fault event by using the first evaluation model in the optimal monitoring terminal and feeding back.
Citation Information
Patent Citations
Ultra-high voltage transmission line monitoring method and system based on oil-driven unmanned aerial vehicle
CN117674419A
Cloud internet-of-things security monitoring method and system with fault self-diagnosis function
CN120498974A