CN118075314A - Intelligent security monitoring method and system for power generation enterprises - Google Patents
Intelligent security monitoring method and system for power generation enterprises Download PDFInfo
- Publication number
- CN118075314A CN118075314A CN202410468665.9A CN202410468665A CN118075314A CN 118075314 A CN118075314 A CN 118075314A CN 202410468665 A CN202410468665 A CN 202410468665A CN 118075314 A CN118075314 A CN 118075314A
- Authority
- CN
- China
- Prior art keywords
- inspection
- data packet
- real
- risk
- node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 99
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000010248 power generation Methods 0.000 title claims abstract description 14
- 238000007689 inspection Methods 0.000 claims abstract description 344
- 230000005540 biological transmission Effects 0.000 claims abstract description 73
- 238000012545 processing Methods 0.000 claims abstract description 19
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 11
- 238000004806 packaging method and process Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 8
- 238000003860 storage Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 5
- 230000015556 catabolic process Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 4
- 238000006731 degradation reaction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013144 data compression Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000013140 knowledge distillation Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application provides an intelligent security monitoring method and system for power generation enterprises, and belongs to the technical field of intelligent security. Meanwhile, the equipment monitors the real-time network condition and formulates a transmission strategy. And uploading the data packet and the network condition to the cloud server by the equipment according to the strategy, and analyzing the data packet by the cloud to determine the risk state and the network state. Based on the risk state, the cloud determines a risk processing strategy and optimizes an initial route of the inspection equipment. When facing complex and severe application scenes with poor network environment, the system can meet the inspection requirement, has high equipment safety and saves labor cost.
Description
Technical Field
The application relates to the technical field of intelligent security, in particular to an intelligent security monitoring method and system for power generation enterprises.
Background
Along with the promotion of the intelligent level of society, traditional human eye inspection mode is long in time consuming and low in efficiency, and is difficult to find abnormal events in real time, so that the problems of inaccurate collected data, large subjective influence factors, untimely treatment, frequent problem facing and passive situation and the like are caused, the current inspection requirement cannot be met, the traditional manual inspection is replaced by AI video intelligent inspection, and the intelligent inspection mode is gradually widely applied to power enterprises.
Then, the intelligent inspection equipment is limited by the hardware capability of the equipment, and when facing complex and severe application scenes with poor network environment, the intelligent inspection equipment can have the problems of performance reduction, data loss and the like, so that serious safety accidents are caused.
Disclosure of Invention
The embodiment of the application provides an intelligent security monitoring method and system for power generation enterprises, and the method adopts the following technical scheme:
in a first aspect, a method for monitoring intelligent security of a power generation enterprise is provided, the method comprising:
the inspection equipment acquires a real-time monitoring image of the inspection node, and generates an inspection data packet of the inspection node according to the real-time monitoring image;
the inspection equipment acquires the real-time network condition of the inspection node, and determines the target transmission strategy of the inspection data packet according to the real-time network condition;
the inspection equipment adopts a target transmission strategy to upload the inspection data packet and the real-time network condition of the inspection node to the cloud service end, and the cloud service end analyzes the inspection data packet to determine the risk state and the network state of the inspection node;
and the cloud server determines a corresponding risk processing strategy according to the risk state of the routing inspection node, and dynamically optimizes the initial routing inspection route of the routing inspection equipment according to the risk state and the network state of the routing inspection node.
Optionally, the inspection device is deployed with a first identification model, and generates an inspection data packet of the inspection node according to the real-time monitoring image, including:
inputting the real-time monitoring image into a first recognition model to obtain an initial risk recognition result and risk recognition confidence of the real-time monitoring image;
and generating a patrol data packet according to the comparison result of the risk identification confidence coefficient and the threshold value.
Optionally, the inspection data packet includes a first inspection data packet and a second inspection data packet, and the generating the inspection data packet according to a comparison result between the risk identification confidence and the threshold includes:
under the condition that the risk identification confidence coefficient is larger than or equal to a threshold value, packaging the risk identification confidence coefficient and a risk identification result into a first routing inspection data packet;
And under the condition that the risk identification confidence is smaller than the threshold value, packaging the risk identification confidence, the real-time monitoring image and the initial risk identification result into a second inspection data packet.
Optionally, the real-time network condition includes a normal condition and an abnormal condition, the target transmission policy includes a transmission mode and a transmission node, and determining the target transmission policy of the inspection data packet according to the real-time network condition includes:
under the condition that the real-time network condition is normal, determining that the target transmission mode of the routing inspection data packet is real-time lossless transmission, wherein the transmission node is a routing inspection node;
And under the condition that the real-time network condition is abnormal, determining that the target transmission mode of the routing inspection data packet is delay lossy transmission, wherein the transmission node is a data uploading node.
Optionally, the cloud service end analyzes the inspection data packet to determine a risk state of the inspection node, including:
Under the condition that the received inspection data packet is a first inspection data packet, determining an initial risk identification result of the first inspection data packet as a risk state of an inspection node;
And under the condition that the received inspection data packet is a second inspection data packet, determining the risk state of the inspection node according to the second inspection data packet and the standard scene image.
Optionally, the cloud service end is deployed with a second identification model, and determines a risk state of the inspection node according to the second inspection data packet and the standard scene image, including:
performing image reconstruction on the real-time monitoring image in the second inspection data packet according to the standard scene image;
and inputting the real-time monitoring image subjected to image reconstruction into a second recognition model to obtain a final risk recognition result, and determining the final risk recognition result as the risk state of the inspection node.
Optionally, the method further comprises:
And optimizing the first recognition model according to the corresponding relation between the real-time monitoring image and the final risk recognition result, and issuing the optimized first recognition model to the inspection equipment.
Optionally, before the inspection device acquires the real-time monitoring image of the inspection node, the method further includes:
and determining a routing inspection node corresponding to each routing inspection device, and constructing an initial routing inspection route of each routing inspection device according to the routing inspection node, wherein the initial routing inspection route at least comprises a data uploading node comprising a plurality of redundant communication networks.
In a second aspect, an intelligent public security monitoring system for a power generation enterprise is provided, the system comprising:
The acquisition module is used for acquiring a real-time monitoring image of the inspection node by the inspection equipment and generating an inspection data packet of the inspection node according to the real-time monitoring image;
The transmission strategy determining module is used for acquiring the real-time network condition of the inspection node by the inspection equipment and determining the target transmission strategy of the inspection data packet according to the real-time network condition;
The uploading policy determining module is used for uploading the inspection data packet and the real-time network condition of the inspection node to the cloud server by the inspection equipment by adopting a target transmission policy, and the cloud server analyzes the inspection data packet to determine the risk state and the network state of the inspection node;
the execution module is used for determining a corresponding risk processing strategy by the cloud service end according to the risk state of the inspection node, and dynamically optimizing an initial inspection route of the inspection equipment according to the risk state and the network state of the inspection node.
Optionally, the acquisition module includes:
The identification sub-module is used for inputting the real-time monitoring image into the first identification model so as to obtain an initial risk identification result and risk identification confidence coefficient of the real-time monitoring image;
and the identification sub-module is used for generating a patrol data packet according to the comparison result of the risk identification confidence coefficient and the threshold value.
Optionally, the identifying submodule includes:
the first identification unit is used for packaging the risk identification confidence and the risk identification result into a first routing inspection data packet under the condition that the risk identification confidence is greater than or equal to a threshold value;
And the second identification unit is used for packaging the risk identification confidence coefficient, the real-time monitoring image and the initial risk identification result into a second inspection data packet under the condition that the risk identification confidence coefficient is smaller than a threshold value.
Optionally, the transmission policy determining module includes:
The first strategy determination submodule is used for determining that the target transmission mode of the routing inspection data packet is real-time lossless transmission under the condition that the real-time network condition is normal, and the transmission node is a routing inspection node;
And the second strategy determination submodule is used for determining that the target transmission mode of the routing inspection data packet is delay lossy transmission and the transmission node is a data uploading node under the condition that the real-time network condition is abnormal.
Optionally, the execution module includes:
The first judging sub-module is used for determining an initial risk identification result of the first inspection data packet as a risk state of the inspection node under the condition that the received inspection data packet is the first inspection data packet;
and the second judging sub-module is used for determining the risk state of the inspection node according to the second inspection data packet and the standard scene image under the condition that the received inspection data packet is the second inspection data packet.
Optionally, the second judging sub-module includes:
the reconstruction unit is used for carrying out image reconstruction on the real-time monitoring image in the second inspection data packet according to the standard scene image;
The input unit is used for inputting the real-time monitoring image subjected to image reconstruction into the second recognition model to obtain a final risk recognition result, and determining the final risk recognition result as the risk state of the inspection node.
Optionally, the system further comprises:
And the updating module is used for optimizing the first recognition model according to the corresponding relation between the real-time monitoring image and the final risk recognition result and issuing the optimized first recognition model to the inspection equipment.
In summary, the method and the system have the following technical effects:
According to the security monitoring method provided by the application, the inspection equipment can acquire the monitoring image of the inspection node in real time and convert the monitoring image into the inspection data packet. This enables the device to capture the actual state of the node in time, helping to detect risks and problems that may exist. The inspection equipment not only acquires the real-time monitoring image, but also actively acquires the real-time network condition of the inspection node. The method is beneficial to the equipment to flexibly adjust the transmission strategy according to the network condition, select a proper data transmission mode and reduce the risks of data loss and performance degradation. Through uploading the inspection data packet to the cloud service end, the cloud can carry out more complicated and intelligent risk state judgment. The cloud server can utilize stronger computing power, machine learning algorithm and the like to carry out deep analysis and accurately judge the risk state of the node, so that the reliability of the whole system is improved. And the cloud server determines a corresponding risk processing strategy according to the risk state of the routing inspection node. This helps the device to handle the potential risk more effectively, thereby reducing the likelihood of a security incident. The cloud service end focuses on the risk state and dynamically optimizes an initial inspection route of the inspection equipment according to the network state. In this way, the system can more flexibly adjust the inspection plan, and avoid or reduce performance degradation and data loss problems in situations of limited performance or poor network environment.
In general, by combining the inspection equipment with the cloud service end and utilizing the strong calculation and analysis capabilities of the cloud, the performance, reliability and adaptability of the intelligent inspection equipment can be improved under the condition of limited hardware capabilities, so that potential safety accidents can be effectively prevented.
Drawings
FIG. 1 is a schematic flow chart of an intelligent security monitoring method for a power generation enterprise according to an embodiment of the present application;
Fig. 2 is a schematic diagram of a power generation enterprise intelligent security monitoring system according to an embodiment of the present application.
Detailed Description
Hereinafter, the terms "first," "second," and the like are used for descriptive convenience only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first", "a second", etc. may explicitly or implicitly include one or more such feature. In the description of the present application, unless otherwise indicated, the meaning of "a plurality" is two or more. For example, a plurality of processing units refers to two or more processing units.
Furthermore, in the embodiments of the present application, "upper", "lower", "left" and "right" are not limited to the orientation in which the components in the drawings are schematically disposed, and it should be understood that these directional terms may be relative concepts, which are used for descriptive and clarity with respect thereto, and which may be correspondingly varied according to the variation in orientation in which the components in the drawings are disposed. In the drawings, the thicknesses of layers and regions are exaggerated for clarity, and the dimensional relationships between the parts in the drawings do not reflect actual dimensional relationships.
In embodiments of the present application, unless explicitly specified and limited otherwise, the term "connected" is to be construed broadly, and for example, "connected" may be either fixedly connected, detachably connected, or integrally formed; can be directly connected or indirectly connected through an intermediate medium. Furthermore, the term "electrically connected" may be a direct electrical connection or an indirect electrical connection via an intermediary.
In the embodiment of the present application, the term "module" is generally a functional structure divided according to logic, and the "module" may be implemented by pure hardware or a combination of hardware and software. In the embodiment of the present application, "and/or" describes the association relationship of the association object, which means that three relationships may exist, for example, a and/or B may represent: a alone, B alone, and both A and B.
In embodiments of the application, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g." in an embodiment should not be taken as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.
The technical scheme of the application will be described below with reference to the accompanying drawings.
With the continuous improvement of the level of social intelligence, traditional inspection methods, especially human eye inspection modes, have revealed inherent drawbacks in many fields. The mode is long in time consumption and low in efficiency, and abnormal events are difficult to find in real time. In addition, because the manual inspection mode has limited data acquisition precision and larger subjective influence factors, the problem processing speed is often not fast enough, so that the problem facing situation is often in a passive situation. These problems make the conventional manual inspection method unable to adapt to the current inspection requirements.
Under the background, the application of artificial intelligence technology brings the change of the land covered by the sky for the patrol work. AI video intelligent patrol is becoming an emerging patrol method, and is being widely used in power enterprises. Compared with the traditional manual inspection, the AI video intelligent inspection has obvious advantages. Firstly, the AI video intelligent patrol can realize efficient information processing. By analyzing a large amount of data in real time, the system can quickly find abnormal events and timely send out early warning, so that the inspection efficiency is improved. Secondly, AI video intelligence inspection has higher data acquisition precision. By means of advanced image recognition and data analysis technology, the system can accurately acquire key information, subjective influence factors are reduced, and inspection results are more reliable.
In addition, AI video intelligence is patrolled and examined can also realize timely problem processing. When the system discovers the problem, the related information can be immediately pushed to related personnel, so that the problem is ensured to be treated in time. This helps to improve the stability and safety of the power system, reducing potential risks. Finally, the AI video intelligent patrol can realize active patrol. Through analysis of historical data, the system can predict potential problem areas, so that preventive patrol is realized, and the power enterprise can be actively in a position when facing problems.
However, when the intelligent inspection equipment is adopted to inspect power stations and cables, the following non-negligible problems exist: along with the increasing number of substations and the increasing scale, the types of equipment to be inspected are various and huge, the defect sample library of the substations and the power transmission lines is limited, the generalized intelligent recognition algorithm is difficult to directly use, and the result of inspection is not accurate due to the reason of being limited by a network.
Firstly, describing an application scene of the application, the monitoring system comprises a cloud service end and a plurality of inspection devices, wherein the inspection devices are used for inspecting a power station or a power transmission line, and the inspection time and the inspection place which are responsible for each inspection device can be intersected. The inspection device is generally a device with sensing and monitoring functions for performing inspection tasks and real-time monitoring. These devices may cover a variety of areas including, but not limited to, industrial, security, environmental monitoring, and the like. The main purpose of the inspection equipment is to execute inspection tasks, monitor the state of a specific area or facility, and ensure normal operation or timely find problems. These devices are typically designed to improve efficiency, safety, and reduce the amount of manual inspection effort. Inspection equipment is often equipped with various sensing technologies, such as cameras, sensors, measuring instruments, etc., to gather information about the environment or equipment status. These perceptions enable the device to acquire data in real time and make corresponding decisions. The patrol device is typically provided with the capability to communicate with other devices or a central system.
Referring to fig. 1, an embodiment of the present application provides a method for monitoring intelligent public security of a power generation enterprise, which is applied to a first server, and specifically includes the following steps:
s101: the inspection device acquires a real-time monitoring image of the inspection node, and generates an inspection data packet of the inspection node according to the real-time monitoring image.
In this embodiment, the inspection device collects real-time monitoring images of each inspection node on the route according to a predefined inspection route, where the actual monitoring images may be an image set including a plurality of inspection angles of the inspection node, and after the collection of the real-time monitoring images is completed, the inspection device may generate a corresponding inspection data packet according to the real-time monitoring images, and the specific steps may include:
S1011: and inputting the real-time monitoring image into the first recognition model to obtain an initial risk recognition result and risk recognition confidence of the real-time monitoring image.
In this embodiment, each inspection device is deployed with a first recognition model, where the first recognition model is a neural network model with fewer computing resources and fewer parameters issued by the server. The lightweight model is typically designed for efficient operation in a resource constrained environment, for example, the first recognition model may be a lightweight neural network model. The first recognition model takes a real-time monitoring image as input, and extracts and analyzes various information in the image through deep learning, computer vision and other technologies. The initial risk recognition result and the risk recognition confidence are important indicators for evaluating the risk level. The risk recognition result describes whether preset risk features exist in the monitoring image, and the risk recognition confidence represents the confidence level of the model on the result.
Because the calculation power of the inspection equipment is limited, the recognition accuracy of the inspection equipment cannot be improved by deploying a large model, the inspection equipment has higher recognition accuracy only for standard defect images, and once the real-time monitoring image is different from the standard defect image in time sequence characteristics and space characteristics, the recognition accuracy of the inspection equipment is reduced. For example, the temporal feature of a standard defect image is the morning and the temporal feature of a real-time monitoring image is the evening. This difference may lead to a decrease in the identification accuracy of the inspection equipment, thereby affecting the inspection effect in the production process.
S1012: and generating a patrol data packet according to the comparison result of the risk identification confidence coefficient and the threshold value.
In this embodiment, after the inspection device obtains the initial risk identification result and the risk identification confidence coefficient of the real-time monitoring image, different inspection data packets, that is, different risk identification confidence coefficients, need to be generated according to the comparison result of the risk identification confidence coefficient and the threshold value, and the data fed back to the cloud server are different. In practical applications, the risk identification confidence and the threshold value are set according to the actual condition and production requirement of the equipment. In general, the higher the risk identification confidence, the more true the risk of a detected fault; the setting of the threshold value is related to which risks are considered potential faults, thereby affecting the generation of the inspection data packet. Therefore, when the patrol strategy is formulated, enterprises need to fully consider the relationship between the two, so as to ensure the rationality and the effectiveness of the patrol data packet.
The step of generating the patrol packet may include:
S10121: and under the condition that the risk identification confidence is greater than or equal to the threshold value, packaging the risk identification confidence and the risk identification result into a first routing inspection data packet.
In this embodiment, when the risk identification confidence coefficient is greater than or equal to the threshold value, it is indicated that the accuracy of risk identification by the inspection device is higher, and the risk identification confidence coefficient and the identification result may be directly packaged into the first inspection data packet. And the packaged first routing inspection data packet is used as source data and is sent to a cloud server for further processing and analysis.
S10122: and under the condition that the risk identification confidence is smaller than the threshold value, packaging the risk identification confidence, the real-time monitoring image and the initial risk identification result into a second inspection data packet.
In this embodiment, when the risk identification confidence is smaller than the threshold, it is indicated that the inspection device has low accuracy in risk identification, and further identification and judgment are required. In this case, the risk identification confidence level, the real-time monitoring image and the initial risk identification result are packaged into a second inspection data packet. The real-time monitoring image can provide more visual field information, and is helpful for the cloud service end to more accurately identify and judge risks. And sending the packaged second inspection data packet to the cloud server as source data. The cloud server can further analyze and judge the safety risk in the production environment according to the data and the real-time monitoring image.
S102: the inspection equipment acquires the real-time network condition of the inspection node, and determines the target transmission strategy of the inspection data packet according to the real-time network condition.
In this embodiment, after the routing inspection device generates the routing inspection data packet, the routing inspection device is not limited to acquiring the real-time network condition of the routing inspection node where the routing inspection device is currently located, but also further considers the influence of the geographic position of the routing inspection node on the network condition. Because different patrol nodes are located in different geographic locations, the network environments in which they are located also exhibit differences. In order to ensure timeliness and accuracy of the inspection data, a corresponding uploading mode is required according to different geographic positions and network conditions. This means that the patrol equipment has to flexibly adjust the uploading policy in the face of the diversity of the network topology. The specific steps thereof can include:
S1021: and under the condition that the real-time network condition is normal, determining that the target transmission mode of the routing inspection data packet is real-time lossless transmission, and determining that the transmission node is a routing inspection node.
In this embodiment, when the real-time network condition of the routing inspection node is normal, it is determined that the target transmission mode of the routing inspection data packet is real-time lossless transmission, and it is ensured that no data loss or delay occurs in the transmission process. In addition, the transmission node is a routing node to ensure that data is transferred from the source routing node to the cloud server in a most efficient and reliable manner. The definition of real-time lossless transmission extends to ensuring that high quality data integrity is maintained across each transmission node in the entire transmission path to prevent information loss or distortion.
S1022: and under the condition that the real-time network condition is abnormal, determining that the target transmission mode of the routing inspection data packet is delay lossy transmission, wherein the transmission node is a data uploading node.
In this embodiment, when the real-time network condition of the routing inspection node is an abnormal condition, it is indicated that the current transmission node does not have the capability of uploading data, then the routing inspection data packet corresponding to the current routing inspection node is temporarily stored, and when the next routing inspection node or the data uploading node completes uploading of the routing inspection data packet, a predictive data compression algorithm is required to process the routing inspection data packet, and then the processed routing inspection data packet is uploaded to the cloud server. Predictive data compression refers to a technique of reducing the amount of data transmission by predicting and differentially encoding data. This approach aims to minimize the amount of data that needs to be transmitted over the network while maintaining the accuracy of the data, thereby reducing the reliance on network bandwidth.
By way of example, assume that a patrol packet has a series of digital data: 1,3,5,7, 9. It can be seen by observation that each digit is the previous digit plus 2. If the first number of the inspection data packet is 1, then each number is the previous number plus 2, the inspection data packet can calculate the whole sequence by itself. So only the transmission law (plus 2) and the first digit (1) are required, and not every specific digit.
S103: and uploading the inspection data packet and the real-time network condition of the inspection node to a cloud server by the inspection equipment by adopting a target transmission strategy, and analyzing the inspection data packet by the cloud server to determine the risk state and the network state of the inspection node.
In this embodiment, after receiving the inspection data packets sent by different inspection devices, the cloud service end needs to analyze the inspection data packets to determine the current risk status and the corresponding risk processing policy, and the specific steps include:
S1031: under the condition that the received inspection data packet is a first inspection data packet, determining an initial risk identification result of the first inspection data packet as a risk state of an inspection node;
S1032: and under the condition that the received inspection data packet is a second inspection data packet, determining the risk state of the inspection node according to the second inspection data packet and the standard scene image.
In the embodiments of S1031 to S1032, after the cloud computing server receives the inspection data packets sent from different inspection devices, a series of parsing operations are required to accurately determine the current risk status and formulate a corresponding risk processing policy. This process can be divided into two main steps:
When the received inspection data packet is a first type data packet, the cloud service end needs to determine an initial risk identification result of the first type data packet as a risk state of the inspection node. The purpose of this step is to make a preliminary risk assessment of the patrol nodes in order to understand their basic risk status.
When the received inspection data packet is the second type data packet, the cloud service end needs to combine the data packet and the standard scene image for further analysis. In this way, the risk status of the patrol node can be determined more accurately. The purpose of this step is to make detailed risk assessment of the patrol nodes in order to get a more accurate knowledge of their risk status.
In a possible implementation manner, determining a risk state of the inspection node according to the second inspection data packet and the standard scene image includes:
performing image reconstruction on the real-time monitoring image in the second inspection data packet according to the standard scene image;
and inputting the real-time monitoring image subjected to image reconstruction into a second recognition model to obtain a final risk recognition result, and determining the final risk recognition result as the risk state of the inspection node.
In this embodiment, when the inspection device cannot make accurate determination on the risk state represented by the real-time image, the cloud processing end needs to rely on a strong computing capability to make accurate determination. A standard scene image is first used as a reference. These standard scene images may be predefined, represent images under normal operating conditions, or contain various possible risks and anomalies. These images serve as references for reconstruction and risk recognition of subsequent images. In order to more accurately perform risk identification, the system performs image reconstruction on the real-time monitoring image. This means that the system attempts to restore the live monitoring image by using information of the standard scene image to reduce distortion introduced during transmission or storage. Or the real-time monitoring image lacks some information during acquisition, and is perfected by using the standard scene image. The real-time monitoring image after image reconstruction is input into the second recognition model. This model may be a deep learning model, machine learning model, or other image recognition model. The model is trained to identify specific risks or anomalies in the image. The second recognition model analyzes the input image and outputs a final risk recognition result. This result indicates whether there is some risk or abnormality in the image, and possibly a risk level. And determining the final risk identification result as the risk state of the inspection node.
S104: and the cloud server determines a corresponding risk processing strategy according to the risk state of the routing inspection node, and dynamically optimizes the initial routing inspection route of the routing inspection equipment according to the risk state and the network state of the routing inspection node.
In this embodiment, after determining the risk status of the inspection node, the cloud server needs to formulate a corresponding risk processing policy according to different risk levels. Aiming at the inspection nodes with different risk levels, the following measures can be taken:
1. for the inspection nodes with lower risks, the inspection nodes can be inspected regularly, normal operation of equipment is ensured, and the discovered problems are processed in time.
2. For inspection nodes with medium risks, the inspection frequency needs to be enhanced, and discovered problems are timely processed. In addition, the running condition of the equipment can be known in real time through remote monitoring and data analysis so as to discover potential risks in advance.
3. For the inspection nodes with higher risks, the on-site treatment should be immediately carried out, so that the safe operation of the equipment is ensured. Meanwhile, the equipment can be monitored in real time by combining remote monitoring and data analysis, so that high-risk problems can be found and treated in time.
In one possible embodiment, the method further comprises:
And optimizing the first recognition model according to the corresponding relation between the real-time monitoring image and the final risk recognition result, and issuing the optimized first recognition model to the inspection equipment.
In this embodiment, the cloud server may establish a correspondence between the real-time monitoring image and the final risk recognition result. And then optimizing and parameter adjusting a second recognition model deployed at the cloud server according to the corresponding relation between the monitoring image and the final risk recognition result, and optimizing a first recognition model based on the adjusted second recognition model, wherein the second recognition model can be a teacher model, the first recognition model can be a student model, and the second recognition model can be optimized based on knowledge distillation. Once the first recognition model is optimized, the system issues the updated model to the inspection device. This means that the inspection device will use the improved risk identification model for analysis and risk identification of the real-time monitoring image. Therefore, the system not only can timely cope with the change in the actual scene, but also can continuously improve the performance of the inspection equipment in the aspect of risk identification.
In general, this step creates a closed loop system that enables dynamic optimization of the recognition model by monitoring the relationship between the image and the final risk recognition result in real time. The feedback loop enables the system to be more flexible and intelligent, can be continuously adapted to the continuously-changing actual monitoring environment, and improves the risk identification capability of the inspection equipment.
In a possible embodiment, before the inspection device acquires the real-time monitoring image of the inspection node, the method further includes:
and determining a routing inspection node corresponding to each routing inspection device, and constructing an initial routing inspection route of each routing inspection device according to the routing inspection node, wherein the initial routing inspection route at least comprises a data uploading node comprising a plurality of redundant communication networks.
In this embodiment, in the inspection system, it is first necessary to determine a specific inspection node to be monitored by each inspection device. This may include various devices, facilities or areas where it is desirable to ensure that each device has a well-defined monitoring scope or task.
In order to perform the patrol task efficiently, the system needs to construct an initial patrol route for each patrol apparatus. This is to plan the path and location each device will traverse during the inspection process. The initial tour route may be constructed based on a variety of factors, such as device location, tour task priority, tour history data, etc. When constructing the initial routing, it is ensured that the route of each routing device comprises at least one data uploading node comprising a plurality of redundant communication networks. This means that in the patrol task, each device has a plurality of selectable network paths when uploading patrol data in communication. Such a design helps to improve the stability and reliability of the communication. Through the steps, the system ensures that each inspection device has a clear inspection task range before the actual inspection task starts, has an initial inspection route, and considers the design of a redundant communication network when uploading data in communication so as to reduce the influence caused by communication faults. Such an arrangement helps to ensure stability and efficiency of the overall inspection system.
According to the security monitoring method provided by the application, the inspection equipment can acquire the monitoring image of the inspection node in real time and convert the monitoring image into the inspection data packet. This enables the device to capture the actual state of the node in time, helping to detect risks and problems that may exist. The inspection equipment not only acquires the real-time monitoring image, but also actively acquires the real-time network condition of the inspection node. The method is beneficial to the equipment to flexibly adjust the transmission strategy according to the network condition, select a proper data transmission mode and reduce the risks of data loss and performance degradation. Through uploading the inspection data packet to the cloud service end, the cloud can carry out more complicated and intelligent risk state judgment. The cloud server can utilize stronger computing power, machine learning algorithm and the like to carry out deep analysis and accurately judge the risk state of the node, so that the reliability of the whole system is improved. And the cloud server determines a corresponding risk processing strategy according to the risk state of the routing inspection node. This helps the device to handle the potential risk more effectively, thereby reducing the likelihood of a security incident. The cloud service end focuses on the risk state and dynamically optimizes an initial inspection route of the inspection equipment according to the network state. In this way, the system can more flexibly adjust the inspection plan, and avoid or reduce performance degradation and data loss problems in situations of limited performance or poor network environment.
In general, by combining the inspection equipment with the cloud service end and utilizing the strong calculation and analysis capabilities of the cloud, the performance, reliability and adaptability of the intelligent inspection equipment can be improved under the condition of limited hardware capabilities, so that potential safety accidents can be effectively prevented.
The intelligent security monitoring method for the power generation enterprises provided by the embodiment of the application is described in detail with reference to FIG. 1. Referring to fig. 2, a system for executing the intelligent security monitoring method for the power generation enterprise provided by the embodiment of the application is described in detail below.
The system comprises:
the acquisition module 201 is configured to obtain a real-time monitoring image of the inspection node by using an inspection device, and generate an inspection data packet of the inspection node according to the real-time monitoring image;
The transmission policy determining module 202 is configured to obtain a real-time network condition of the inspection node by the inspection device, and determine a target transmission policy of the inspection data packet according to the real-time network condition;
The uploading policy determining module 203 is configured to upload the inspection data packet and the real-time network condition of the inspection node to the cloud server by using the target transmission policy, where the cloud server analyzes the inspection data packet to determine a risk state and a network state of the inspection node;
the execution module 204 is configured to determine, by using the cloud server, a corresponding risk processing policy according to the risk state of the routing inspection node, and dynamically optimize an initial routing inspection route of the routing inspection device according to the risk state and the network state of the routing inspection node.
Optionally, the acquisition module includes:
The identification sub-module is used for inputting the real-time monitoring image into the first identification model so as to obtain an initial risk identification result and risk identification confidence coefficient of the real-time monitoring image;
and the identification sub-module is used for generating a patrol data packet according to the comparison result of the risk identification confidence coefficient and the threshold value.
Optionally, the identifying submodule includes:
the first identification unit is used for packaging the risk identification confidence and the risk identification result into a first routing inspection data packet under the condition that the risk identification confidence is greater than or equal to a threshold value;
And the second identification unit is used for packaging the risk identification confidence coefficient, the real-time monitoring image and the initial risk identification result into a second inspection data packet under the condition that the risk identification confidence coefficient is smaller than a threshold value.
Optionally, the transmission policy determining module includes:
The first strategy determination submodule is used for determining that the target transmission mode of the routing inspection data packet is real-time lossless transmission under the condition that the real-time network condition is normal, and the transmission node is a routing inspection node;
And the second strategy determination submodule is used for determining that the target transmission mode of the routing inspection data packet is delay lossy transmission and the transmission node is a data uploading node under the condition that the real-time network condition is abnormal.
Optionally, the execution module includes:
The first judging sub-module is used for determining an initial risk identification result of the first inspection data packet as a risk state of the inspection node under the condition that the received inspection data packet is the first inspection data packet;
and the second judging sub-module is used for determining the risk state of the inspection node according to the second inspection data packet and the standard scene image under the condition that the received inspection data packet is the second inspection data packet.
Optionally, the second judging sub-module includes:
the reconstruction unit is used for carrying out image reconstruction on the real-time monitoring image in the second inspection data packet according to the standard scene image;
The input unit is used for inputting the real-time monitoring image subjected to image reconstruction into the second recognition model to obtain a final risk recognition result, and determining the final risk recognition result as the risk state of the inspection node.
Optionally, the system further comprises:
And the updating module is used for optimizing the first recognition model according to the corresponding relation between the real-time monitoring image and the final risk recognition result and issuing the optimized first recognition model to the inspection equipment.
The above embodiments may be implemented in whole or in part by software, hardware (e.g., circuitry), firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable system. The computer program or instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer program or instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by a wired (e.g., infrared, wireless, microwave, etc.) means. Computer readable storage media can be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc. that contain one or more collections of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
It should be understood that the term "and/or" is merely an association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B may mean: there are three cases, a alone, a and B together, and B alone, wherein a, B may be singular or plural. In addition, the character "/" herein generally indicates that the associated object is an "or" relationship, but may also indicate an "and/or" relationship, and may be understood by referring to the context.
In the present application, "at least one" means one or more, and "a plurality" means two or more. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the system, system and unit described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.
In the several embodiments provided by the present application, it should be understood that the disclosed systems, and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative, e.g., the partitioning of elements is merely a logical functional partitioning, and there may be additional partitioning in actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not implemented. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, system or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely illustrative embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present application, and the application should be covered. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (10)
1. An intelligent security monitoring method for a power generation enterprise, which is characterized by comprising the following steps:
The method comprises the steps that a patrol device obtains a real-time monitoring image of a patrol node, and generates a patrol data packet of the patrol node according to the real-time monitoring image;
the inspection equipment acquires the real-time network condition of the inspection node, and determines a target transmission strategy of the inspection data packet according to the real-time network condition;
The inspection equipment adopts the target transmission strategy to upload the inspection data packet and the real-time network condition of the inspection node to a cloud server, and the cloud server analyzes the inspection data packet to determine the risk state and the network state of the inspection node;
and the cloud service end determines a corresponding risk processing strategy according to the risk state of the routing inspection node, and dynamically optimizes an initial routing inspection route of the routing inspection equipment according to the risk state and the network state of the routing inspection node.
2. The method of claim 1, wherein the inspection device is deployed with a first recognition model, and wherein generating the inspection data packet of the inspection node according to the real-time monitoring image comprises:
inputting the real-time monitoring image into the first recognition model to obtain an initial risk recognition result and risk recognition confidence coefficient of the real-time monitoring image;
and generating the inspection data packet according to a comparison result of the risk identification confidence coefficient and a threshold value.
3. The method of claim 2, wherein the patrol data packet comprises a first patrol data packet and a second patrol data packet, wherein the generating the patrol data packet according to the comparison of the risk identification confidence level and a threshold value comprises:
under the condition that the risk identification confidence coefficient is larger than or equal to a threshold value, packaging the risk identification confidence coefficient and the risk identification result into the first routing inspection data packet;
and under the condition that the risk identification confidence is smaller than a threshold value, packaging the risk identification confidence, the real-time monitoring image and the initial risk identification result into the second inspection data packet.
4. The method of claim 1, wherein the real-time network conditions include normal conditions and abnormal conditions, the target transmission policy includes a transmission mode and a transmission node, and the determining the target transmission policy of the patrol packet according to the real-time network conditions includes:
Under the condition that the real-time network condition is the normal condition, determining that the target transmission mode of the routing inspection data packet is real-time lossless transmission, wherein a transmission node is the routing inspection node;
And under the condition that the real-time network condition is the abnormal condition, determining that the target transmission mode of the routing inspection data packet is delay lossy transmission, wherein a transmission node is a data uploading node.
5. The method of claim 3, wherein the cloud server parsing the routing data packet to determine a risk status of the routing node comprises:
Under the condition that the received routing inspection data packet is the first routing inspection data packet, determining an initial risk identification result of the first routing inspection data packet as a risk state of the routing inspection node;
And under the condition that the received inspection data packet is the second inspection data packet, determining the risk state of the inspection node according to the second inspection data packet and the standard scene image.
6. The method of claim 5, wherein the cloud server is deployed with a second identification model, and the determining the risk status of the routing inspection node according to the second routing inspection data packet and the standard scene image includes:
performing image reconstruction on the real-time monitoring image in the second inspection data packet according to the standard scene image;
inputting the real-time monitoring image subjected to image reconstruction into the second recognition model to obtain a final risk recognition result, and determining the final risk recognition result as the risk state of the inspection node.
7. The method of claim 6, wherein the method further comprises:
and optimizing a first recognition model according to the corresponding relation between the real-time monitoring image and the final risk recognition result, and issuing the optimized first recognition model to the inspection equipment.
8. The method of claim 1, wherein prior to the inspection device acquiring real-time monitoring images of inspection nodes, the method further comprises:
Determining a routing inspection node corresponding to each routing inspection device, and constructing an initial routing inspection route of each routing inspection device according to the routing inspection nodes, wherein the initial routing inspection route at least comprises a data uploading node comprising a plurality of redundant communication networks.
9. An intelligent public security monitoring system for a power generation enterprise, the system comprising:
the system comprises an acquisition module, a routing inspection device and a routing inspection module, wherein the acquisition module is used for acquiring a real-time monitoring image of a routing inspection node and generating a routing inspection data packet of the routing inspection node according to the real-time monitoring image;
the transmission strategy determining module is used for acquiring the real-time network condition of the inspection node by the inspection equipment and determining the target transmission strategy of the inspection data packet according to the real-time network condition;
The uploading policy determining module is used for uploading the inspection data packet and the real-time network condition of the inspection node to a cloud service end by adopting the target transmission policy by the inspection equipment, and the cloud service end analyzes the inspection data packet to determine the risk state and the network state of the inspection node;
The execution module is used for determining a corresponding risk processing strategy according to the risk state of the inspection node by the cloud service end, and dynamically optimizing an initial inspection route of the inspection equipment according to the risk state of the inspection node and the network state.
10. The system of claim 9, wherein the acquisition module comprises:
The identification sub-module is used for inputting the real-time monitoring image into a first identification model so as to obtain an initial risk identification result and risk identification confidence coefficient of the real-time monitoring image;
And the identification sub-module is used for generating the inspection data packet according to the comparison result of the risk identification confidence coefficient and the threshold value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410468665.9A CN118075314B (en) | 2024-04-18 | 2024-04-18 | Intelligent security monitoring method and system for power generation enterprises |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410468665.9A CN118075314B (en) | 2024-04-18 | 2024-04-18 | Intelligent security monitoring method and system for power generation enterprises |
Publications (2)
Publication Number | Publication Date |
---|---|
CN118075314A true CN118075314A (en) | 2024-05-24 |
CN118075314B CN118075314B (en) | 2024-07-12 |
Family
ID=91111515
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410468665.9A Active CN118075314B (en) | 2024-04-18 | 2024-04-18 | Intelligent security monitoring method and system for power generation enterprises |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118075314B (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2242307A1 (en) * | 2009-04-14 | 2010-10-20 | Alcatel Lucent | Controlling transmission of encoded data packets |
US20210062954A1 (en) * | 2018-04-02 | 2021-03-04 | Shuyong Paul Du | Intelligent data acquisition system and method for pipelines |
CN113065455A (en) * | 2021-03-30 | 2021-07-02 | 中国水利水电科学研究院 | Landslide risk inspection method and system based on deep learning |
CN113129469A (en) * | 2021-04-08 | 2021-07-16 | 深圳市国汇计量质量检测有限公司 | Inspection monitoring method and system and computer readable storage medium |
CN113724414A (en) * | 2021-08-31 | 2021-11-30 | 浙江江南工程管理股份有限公司 | Intelligent inspection method and system |
CN113985879A (en) * | 2021-10-28 | 2022-01-28 | 安徽安宠宠物用品有限公司 | Intelligent mobile inspection system and method based on dynamic historical data optimization |
CN114373245A (en) * | 2021-12-16 | 2022-04-19 | 南京南自信息技术有限公司 | Intelligent inspection system based on digital power plant |
WO2022095616A1 (en) * | 2020-11-03 | 2022-05-12 | 国网智能科技股份有限公司 | On-line intelligent inspection system and method for transformer substation |
CN116245230A (en) * | 2023-02-03 | 2023-06-09 | 南方电网调峰调频发电有限公司运行分公司 | Operation inspection and trend analysis method and system for power station equipment |
US20230326198A1 (en) * | 2022-04-08 | 2023-10-12 | Huaneng Suzhou Thermal Power Co., Ltd | Intelligent Mobile Patrol Method and System thereof |
CN117270569A (en) * | 2023-10-24 | 2023-12-22 | 国网福建省电力有限公司电力科学研究院 | Mountain fire identification inspection method based on dynamic path planning |
WO2024040566A1 (en) * | 2022-08-26 | 2024-02-29 | 国网浙江省电力有限公司电力科学研究院 | Transformer substation intelligent inspection system and method based on image recognition |
-
2024
- 2024-04-18 CN CN202410468665.9A patent/CN118075314B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2242307A1 (en) * | 2009-04-14 | 2010-10-20 | Alcatel Lucent | Controlling transmission of encoded data packets |
US20210062954A1 (en) * | 2018-04-02 | 2021-03-04 | Shuyong Paul Du | Intelligent data acquisition system and method for pipelines |
WO2022095616A1 (en) * | 2020-11-03 | 2022-05-12 | 国网智能科技股份有限公司 | On-line intelligent inspection system and method for transformer substation |
CN113065455A (en) * | 2021-03-30 | 2021-07-02 | 中国水利水电科学研究院 | Landslide risk inspection method and system based on deep learning |
CN113129469A (en) * | 2021-04-08 | 2021-07-16 | 深圳市国汇计量质量检测有限公司 | Inspection monitoring method and system and computer readable storage medium |
CN113724414A (en) * | 2021-08-31 | 2021-11-30 | 浙江江南工程管理股份有限公司 | Intelligent inspection method and system |
CN113985879A (en) * | 2021-10-28 | 2022-01-28 | 安徽安宠宠物用品有限公司 | Intelligent mobile inspection system and method based on dynamic historical data optimization |
CN114373245A (en) * | 2021-12-16 | 2022-04-19 | 南京南自信息技术有限公司 | Intelligent inspection system based on digital power plant |
US20230326198A1 (en) * | 2022-04-08 | 2023-10-12 | Huaneng Suzhou Thermal Power Co., Ltd | Intelligent Mobile Patrol Method and System thereof |
WO2024040566A1 (en) * | 2022-08-26 | 2024-02-29 | 国网浙江省电力有限公司电力科学研究院 | Transformer substation intelligent inspection system and method based on image recognition |
CN116245230A (en) * | 2023-02-03 | 2023-06-09 | 南方电网调峰调频发电有限公司运行分公司 | Operation inspection and trend analysis method and system for power station equipment |
CN117270569A (en) * | 2023-10-24 | 2023-12-22 | 国网福建省电力有限公司电力科学研究院 | Mountain fire identification inspection method based on dynamic path planning |
Also Published As
Publication number | Publication date |
---|---|
CN118075314B (en) | 2024-07-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109872003B (en) | Object state prediction method, object state prediction system, computer device, and storage medium | |
CN112817280A (en) | Implementation method for intelligent monitoring alarm system of thermal power plant | |
CN113642946A (en) | Perception information integration access system based on city important infrastructure | |
CN111124852A (en) | Fault prediction method and system based on BMC health management module | |
CN112906775B (en) | Equipment fault prediction method and system | |
US20230118175A1 (en) | Event analysis in an electric power system | |
CN113099242B (en) | Power transmission line video monitoring data processing method and system | |
CN116684878B (en) | 5G information transmission data safety monitoring system | |
CN108880706A (en) | A kind of fast diagnosis method of satellite channel link failure | |
CN115471625A (en) | Cloud robot platform big data intelligent decision method and system | |
De Vita et al. | A novel data collection framework for telemetry and anomaly detection in industrial iot systems | |
CN117014471A (en) | Engineering thing networking safety monitoring system based on artificial intelligence | |
CN111932060A (en) | Method and system for performing mobile inspection on cable line based on front-end and back-end fusion data | |
CN118075314B (en) | Intelligent security monitoring method and system for power generation enterprises | |
CN117119496A (en) | LTE wireless network evaluation method and server | |
CN117175803A (en) | Wireless communication method and system for distribution line | |
CN116316233A (en) | Intelligent substation inspection system, method, equipment and storage medium | |
CN116611953A (en) | Electric energy meter production and manufacturing real-time data management method and system based on Internet of things | |
CN116401604B (en) | Method for classifying and detecting cold head state and predicting service life | |
WO2024138968A1 (en) | Base station fault diagnosis method and apparatus | |
CN117336137B (en) | Internet of things data processing method and system based on intelligent edge gateway | |
CN118054845B (en) | Distributed optical network terminal fault monitoring method and system | |
CN115580635B (en) | Intelligent fault diagnosis method and system for Internet of things terminal | |
Cao et al. | Edge-Cloud Intelligence in Self-Diagnostic of Land Mobile Radio Systems | |
CN118306250A (en) | Intelligent edge monitoring device and method for electric automobile charging pile |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant |