CN118175065A - Equipment port safety alarm system - Google Patents
Equipment port safety alarm system Download PDFInfo
- Publication number
- CN118175065A CN118175065A CN202410600727.7A CN202410600727A CN118175065A CN 118175065 A CN118175065 A CN 118175065A CN 202410600727 A CN202410600727 A CN 202410600727A CN 118175065 A CN118175065 A CN 118175065A
- Authority
- CN
- China
- Prior art keywords
- real
- temperature
- time sequence
- mode
- time
- 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.)
- Pending
Links
- 230000002159 abnormal effect Effects 0.000 claims abstract description 35
- 238000001514 detection method Methods 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 11
- 239000013598 vector Substances 0.000 claims description 56
- 230000005856 abnormality Effects 0.000 claims description 28
- 238000010586 diagram Methods 0.000 claims description 27
- 238000006243 chemical reaction Methods 0.000 claims description 20
- 230000009467 reduction Effects 0.000 claims description 19
- 238000013527 convolutional neural network Methods 0.000 claims description 16
- 238000012800 visualization Methods 0.000 claims description 15
- 230000004913 activation Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 8
- 239000003638 chemical reducing agent Substances 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 7
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000004807 localization Effects 0.000 claims 1
- 230000008859 change Effects 0.000 abstract description 16
- 238000012544 monitoring process Methods 0.000 abstract description 11
- 238000004422 calculation algorithm Methods 0.000 abstract description 6
- 238000012300 Sequence Analysis Methods 0.000 abstract description 4
- 238000000034 method Methods 0.000 description 19
- 238000011176 pooling Methods 0.000 description 15
- 230000006870 function Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 5
- 210000002569 neuron Anatomy 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000000737 periodic effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000306 component Substances 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Alarm Systems (AREA)
Abstract
The invention discloses a safety alarm system for a device port, which monitors and collects real-time temperature values of the device port in real time through a temperature sensor, introduces a data processing and analyzing algorithm at the rear end to perform time sequence analysis on the real-time temperature values of the device port, detects abnormal temperature modes of the device port, and sends out early warning prompts when the abnormal temperature modes are detected. In this way, the abnormal detection of the equipment port can be automatically carried out by monitoring the temperature mode and the change condition of the equipment port in real time, so that potential problems can be found in time and early warning can be carried out, by adopting the mode, the problems can be rapidly positioned and corresponding measures can be taken, thereby reducing the time and influence of service interruption and ensuring the safety of the equipment port.
Description
Technical Field
The application relates to the field of intelligent alarms, and more particularly, to a device port safety alarm system.
Background
The device ports in the communication room connect to interfaces of various network devices, including servers, switches, routers, etc., and the security of these device ports is critical to protecting the integrity, confidentiality and availability of data.
Once the device port is abnormal, abnormal interruption of system operation may be caused, which affects the correctness of data in the system or damages the database of the system, so that part or even all of data is lost. Meanwhile, the port abnormality can also cause the safety problem of the equipment port, influence the service continuity of the communication machine room and cause great loss for enterprises.
The temperature of the device port is an important indicator, and may reflect the operating state of the device and the possible risk of failure. Conventional equipment port safety alarm systems typically only monitor the temperature value change of the equipment port and use a fixed threshold to determine if there is an abnormality in the temperature. However, the temperature of the device port is affected by various factors, such as the ambient temperature and the device load, so that the complexity and the change rule of the temperature mode cannot be captured by the conventional monitoring method, and the potential abnormal situation cannot be accurately judged. Meanwhile, the alarm method with fixed threshold cannot adapt to temperature changes under different conditions, and false alarm or missing alarm is easily caused.
In addition, conventional equipment port safety alarm systems lack pattern recognition capability in temperature pattern anomaly detection by monitoring equipment port temperature value changes. That is, the temperature pattern typically has a certain periodicity and regularity, such as a temperature rise process or a periodic load change at start-up of the device. The inability of conventional systems to accurately identify and analyze these patterns results in an inability to distinguish between normal temperature variations and abnormal temperature patterns.
Accordingly, an optimized device port security alarm system is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides a safety alarm system for equipment ports, which monitors and collects real-time temperature values of the equipment ports in real time through a temperature sensor, introduces a data processing and analyzing algorithm at the rear end to perform time sequence analysis on the real-time temperature values of the equipment ports, so as to detect abnormal temperature modes of the equipment ports, and sends out early warning prompts when the abnormal temperature modes are detected. In this way, the abnormal detection of the equipment port can be automatically carried out by monitoring the temperature mode and the change condition of the equipment port in real time, so that potential problems can be found in time and early warning can be carried out, by adopting the mode, the problems can be rapidly positioned and corresponding measures can be taken, thereby reducing the time and influence of service interruption and ensuring the safety of the equipment port.
According to one aspect of the present application, there is provided a device port security alarm system comprising:
The device port real-time temperature acquisition module is used for acquiring a time sequence of real-time temperature values of the monitored device port acquired by the temperature sensor in a preset time period;
the temperature time sequence vector field conversion module is used for arranging the time sequence of the real-time temperature values into real-time temperature time sequence input vectors according to the time dimension and obtaining real-time temperature time sequence conversion images of the equipment port through the vector-image converter;
The temperature time sequence correlation mode feature extraction module is used for extracting features of the equipment port real-time temperature time sequence conversion image through the equipment port temperature time sequence mode feature extractor based on the deep neural network model so as to obtain an equipment port real-time temperature time sequence correlation mode feature map;
The temperature time sequence related mode characteristic noise reduction module is used for obtaining a real-time temperature time sequence related mode characteristic diagram of the equipment port after noise reduction by a noise reducer based on the position mask module;
the receptive field focusing module is used for enabling the noise-reduced equipment port real-time temperature time sequence correlation mode characteristic diagram to pass through the receptive field focusing module so as to obtain local display equipment port real-time temperature time sequence correlation mode characteristics;
And the temperature mode abnormality detection early warning module is used for determining whether the temperature mode of the equipment port is abnormal or not based on the real-time temperature time sequence associated mode characteristics of the local display equipment port and determining whether an early warning information prompt is generated or not.
Compared with the prior art, the equipment port safety alarm system provided by the application has the advantages that the real-time temperature value of the equipment port is monitored and collected in real time through the temperature sensor, the real-time temperature value of the equipment port is subjected to time sequence analysis by introducing a data processing and analyzing algorithm into the rear end, so that the abnormal temperature mode of the equipment port is detected, and an early warning prompt is sent when the abnormal temperature mode is detected. In this way, the abnormal detection of the equipment port can be automatically carried out by monitoring the temperature mode and the change condition of the equipment port in real time, so that potential problems can be found in time and early warning can be carried out, by adopting the mode, the problems can be rapidly positioned and corresponding measures can be taken, thereby reducing the time and influence of service interruption and ensuring the safety of the equipment port.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
FIG. 1 is a block diagram of a device port security alarm system in accordance with an embodiment of the application;
FIG. 2 is a system architecture diagram of a device port security alarm system in accordance with an embodiment of the application;
Fig. 3 is a block diagram of a temperature pattern abnormality detection and early warning module in an equipment port safety alarm system according to an embodiment of the present application.
Detailed Description
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
The temperature of the device port is an important indicator, and may reflect the operating state of the device and the possible risk of failure. Conventional equipment port safety alarm systems typically only monitor the temperature value change of the equipment port and use a fixed threshold to determine if there is an abnormality in the temperature. However, the temperature of the device port is affected by various factors, such as the ambient temperature and the device load, so that the complexity and the change rule of the temperature mode cannot be captured by the conventional monitoring method, and the potential abnormal situation cannot be accurately judged. Meanwhile, the alarm method with fixed threshold cannot adapt to temperature changes under different conditions, and false alarm or missing alarm is easily caused. In addition, conventional equipment port safety alarm systems lack pattern recognition capability in temperature pattern anomaly detection by monitoring equipment port temperature value changes. That is, the temperature pattern typically has a certain periodicity and regularity, such as a temperature rise process or a periodic load change at start-up of the device. The inability of conventional systems to accurately identify and analyze these patterns results in an inability to distinguish between normal temperature variations and abnormal temperature patterns. Accordingly, an optimized device port security alarm system is desired.
In the technical scheme of the application, a device port safety alarm system is provided. Fig. 1 is a block diagram of a device port security alarm system in accordance with an embodiment of the application. Fig. 2 is a system architecture diagram of a device port security alarm system according to an embodiment of the application. As shown in fig. 1 and 2, a device port security alarm system 300 according to an embodiment of the present application includes: a device port real-time temperature acquisition module 310, configured to acquire a time sequence of real-time temperature values of the monitored device port acquired by the temperature sensor during a predetermined period of time; the temperature time sequence vector field conversion module 320 is configured to arrange the time sequence of the real-time temperature values into a real-time temperature time sequence input vector according to a time dimension, and then obtain a real-time temperature time sequence conversion image of the device port through a vector-image converter; the temperature time sequence correlation mode feature extraction module 330 is configured to perform feature extraction on the device port real-time temperature time sequence conversion image by using a device port temperature time sequence mode feature extractor based on a deep neural network model to obtain a device port real-time temperature time sequence correlation mode feature map; the temperature time sequence related mode feature denoising module 340 is configured to obtain a denoised device port real-time temperature time sequence related mode feature map by using the device port real-time temperature time sequence related mode feature map based on the denoiser of the per-position mask module; the receptive field focusing module 350 is configured to pass the noise-reduced real-time temperature time sequence correlation mode feature map of the device port through the receptive field focusing module to obtain real-time temperature time sequence correlation mode features of the local display device port; the temperature mode abnormality detection and early warning module 360 is configured to determine whether an abnormality exists in a temperature mode of the device port based on the real-time temperature time sequence correlation mode feature of the local display device port, and determine whether to generate an early warning information prompt.
In particular, the device port real-time temperature acquisition module 310 is configured to acquire a time sequence of real-time temperature values of the monitored device port acquired by the temperature sensor over a predetermined period of time. It should be appreciated that the temperature value of the device port plays a key role in determining whether there is an abnormality in the temperature pattern of the device port. By monitoring and analyzing the temperature value of the equipment port, abnormal conditions in the temperature mode can be identified, and the operation state and safety of the equipment can be judged. Specifically, in one specific example of the application, a temperature sensor monitors and collects a real-time temperature value of a device port in real time, and a data processing and analyzing algorithm is introduced into the rear end to perform time sequence analysis on the real-time temperature value of the device port, so that abnormal temperature mode detection of the device port is performed, and an early warning prompt is sent when abnormal temperature mode is detected.
It is worth mentioning that a temperature sensor is a device for measuring the temperature of an environment or an object. It may convert the temperature into an electrical signal or other form of output for temperature monitoring, control or data recording.
Specifically, the temperature time sequence vector field conversion module 320 is configured to arrange the time sequence of the real-time temperature values into the real-time temperature time sequence input vector according to a time dimension, and then obtain the real-time temperature time sequence conversion image of the device port through a vector-image converter. It is contemplated that the time series image data may provide more information than a simple time series vector representation, including time series relationships, fluctuations, trend changes, etc. of the temperature data. Therefore, in order to better express and analyze the mode and trend of the temperature change of the equipment port, in the technical scheme of the application, the time sequence of the real-time temperature value is further arranged into the real-time temperature time sequence input vector according to the time dimension, and then the real-time temperature time sequence conversion image of the equipment port is obtained through the vector-image converter, so that the conversion can provide a more visual and visualized mode to understand the time sequence mode and the characteristic of the temperature data and help to detect the abnormal condition of the temperature mode. That is, the real-time temperature time sequence conversion image of the equipment port can more intuitively display the overall trend, the periodic mode, the abnormal point and other information of the temperature change of the equipment port, and is helpful for more comprehensively analyzing the characteristics and the abnormal condition of the temperature mode.
In particular, the temperature time series correlation mode feature extraction module 330 is configured to perform feature extraction on the device port real-time temperature time series transformation image by using a device port temperature time series mode feature extractor based on a deep neural network model to obtain a device port real-time temperature time series correlation mode feature map. Specifically, in one specific example of the present application, the deep neural network model is a convolutional neural network model. That is, the device port real-time temperature time sequence conversion image is subjected to feature extraction by using a device port temperature time sequence mode feature extractor based on a convolutional neural network model, which has excellent performance in the aspect of implicit feature extraction of the image, so as to extract time sequence related mode feature information about the device port temperature in the device port real-time temperature time sequence conversion image, thereby obtaining a device port real-time temperature time sequence related mode feature map. More specifically, each layer using the device port temperature time sequence pattern feature extractor based on the convolutional neural network model performs the following steps on input data in forward transfer of the layer: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature images based on the local feature matrix to obtain pooled feature images; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the equipment port temperature time sequence pattern feature extractor based on the convolutional neural network model is the equipment port real-time temperature time sequence association pattern feature map, and the input of the first layer of the equipment port temperature time sequence pattern feature extractor based on the convolutional neural network model is the equipment port real-time temperature time sequence conversion image.
Notably, convolutional neural networks (Convolutional Neural Network, CNN) are a deep learning model, particularly suited for processing tasks with grid structure data (e.g., images, audio). CNN has achieved great success in the field of computer vision, and is widely used in tasks such as image classification, target detection, image generation, etc. The core idea of CNN is to extract and learn the feature representation of the data through the convolution layer, pooling layer and full connection layer. The following are the main components and working principles of CNN: convolution layer: the convolutional layer is the core component of the CNN. It contains a set of learnable convolution kernels (also called filters), each of which performs a convolution operation on the input data, extracting local features. The convolution operation is performed by multiplying the convolution kernel by a portion of the input data element by element and summing the results to obtain an element of the output signature. The convolution layer can automatically learn features with different sizes, and abstract feature representations are gradually extracted from local to global; activation function: a nonlinear activation function, such as ReLU, is applied to the output of the convolutional layer to introduce nonlinear characteristics. The activation function carries out element-by-element nonlinear transformation on the output of the convolution layer, so that the expression capability of the model is enhanced; pooling layer: the pooling layer is used to reduce the size of the feature map and preserve the most important features. Common pooling operations have a maximum pooling and an average pooling, which take the maximum or average value, respectively, in a local area as the output after pooling. The pooling layer can reduce the space dimension of the features, improve the calculation efficiency of the model and has a certain translation invariance; full tie layer: the fully connected layer flattens the feature map output by the pooling layer into a one-dimensional vector and is connected to one or more fully connected layers. The neurons of the full-connection layer are connected with all neurons of the previous layer, and the characteristics are combined and classified through learning weights and biases, and the Dropout layer is as follows: dropout is a regularization technique used to reduce the overfitting of the model. During the training process, the Dropout layer randomly discards some of the neuron outputs with a certain probability, forcing the model to learn a more robust feature representation. Through the stacking of multiple convolution layers, pooling layers, and fully connected layers, CNNs can extract and combine features layer by layer, enabling advanced representation and classification of complex data. In the training process, the CNN optimizes network parameters through a back propagation algorithm, so that the model can better fit training data.
In particular, the temperature timing related mode feature denoising module 340 is configured to obtain the device port real-time temperature timing related mode feature map after denoising by using the denoising device based on the location mask module. It should be understood that, in order to highlight the semantic part with more important temperature time sequence pattern and change feature in the device port real-time temperature time sequence correlation pattern feature map and reduce noise and irrelevant information interference, in the technical scheme of the application, the device port real-time temperature time sequence correlation pattern feature map is further processed by a noise reducer based on a per-position mask module to obtain a noise-reduced device port real-time temperature time sequence correlation pattern feature map. It should be appreciated that the per-position masking mechanism may mask feature values meeting the conditions for each position in the input feature map according to particular conditions to give greater weight to feature values meeting the conditions. Therefore, the positions with more important semantics are more reserved and highlighted in the noise reduction process, and the unimportant positions are suppressed or filtered, so that the quality and the accuracy of the output characteristic diagram are improved, and the abnormal detection and the early warning of the temperature mode of the equipment port are more accurately facilitated. Specifically, the device port real-time temperature time sequence association mode feature map is obtained through a noise reducer based on a per-position mask module, and the device port real-time temperature time sequence association mode feature map after noise reduction comprises the following steps: processing the equipment port real-time temperature time sequence association mode feature map through a noise reducer based on a per-position mask module according to the following noise reduction formula to obtain the noise-reduced equipment port real-time temperature time sequence association mode feature map;
The noise reduction formula is as follows:
Wherein, A real-time temperature time sequence associated mode characteristic diagram for the equipment port,As a characteristic diagram of the threshold value,A real-time temperature time sequence associated mode characteristic diagram of the equipment port after noise reduction,For the characteristic values of each position in the real-time temperature time sequence associated mode characteristic diagram of the equipment port,For the feature values at each position in the threshold feature map,AndIs the parameter of the ultrasonic wave to be used as the ultrasonic wave,A set of conditions representing a threshold function.
In particular, the receptive field focusing module 350 is configured to pass the noise-reduced real-time temperature timing related pattern feature map of the device port through the receptive field focusing module to obtain real-time temperature timing related pattern features of the local display device port. In particular, in one specific example of the application, the receptive field focusing module 350 comprises: the local temperature time sequence correlation mode visualization unit is used for enabling the noise-reduced equipment port real-time temperature time sequence correlation mode feature map to pass through the receptive field focusing module to obtain a local visualization equipment port real-time temperature time sequence correlation mode feature vector as the local visualization equipment port real-time temperature time sequence correlation mode feature.
Specifically, the local temperature time sequence correlation mode visualization unit is configured to pass the noise-reduced real-time temperature time sequence correlation mode feature map of the device port through the receptive field focusing module to obtain a local visualization device port real-time temperature time sequence correlation mode feature vector as the local visualization device port real-time temperature time sequence correlation mode feature. These local features are particularly important for anomalies in the temperature pattern of the device port, given that there are local time series change patterns and associations in the device port real-time temperature time series conversion image with respect to the device port temperature. However, as the structure of the convolutional neural network model in the traditional sense is a convolutional and pooling layer, the neurons with local receptive fields (such as 3×3 convolutional kernels) can be used for extracting features and pooling to reduce dimensions, and meanwhile, remarkable information on each channel is obtained, but the receptive fields are large in the method, so that the time sequence change mode and trend features of the extracted device port real-time temperature time sequence conversion image about temperature become fuzzy, and the quality detail feature information with resolution in the feature map is easily ignored. Therefore, in order to focus on a specific local area of temperature time sequence distribution, so as to further improve the expression and analysis capability of the temperature time sequence characteristics, in the technical scheme of the application, the real-time temperature time sequence associated mode characteristic diagram of the equipment port after noise reduction is further passed through a receptive field focusing module to obtain the real-time temperature time sequence associated mode characteristic vector of the local display equipment port. It should be appreciated that the receptive field focusing module can add a1×1 convolution kernel and a ReLU activation function after conventional convolution, which is equivalent to implementing cascaded cross-channel weighted pooling on a normal convolution layer from the perspective of cross-channel pooling, so that the model can learn the relationship between channels, model and characterize local time sequence feature information about the device disconnection temperature in the device port real-time temperature time sequence conversion image more efficiently, make the network more sensitive in a specific area, and highlight port temperature local time sequence feature information of the area. By the method, the time sequence key characteristic of the equipment port temperature in the local area can be extracted, other characteristic information which is not related to port temperature abnormality detection is ignored, and therefore the real-time temperature time sequence associated mode characteristic vector of the local display equipment port with more expression capability and distinction degree is obtained. More specifically, the step of passing the noise-reduced device port real-time temperature time sequence association mode feature map through the receptive field focusing module to obtain the local display device port real-time temperature time sequence association mode feature vector as the local display device port real-time temperature time sequence association mode feature comprises the following steps: the noise-reduced equipment port real-time temperature time sequence association mode feature diagram is processed through the receptive field focusing module by the following formula to obtain a local display equipment port real-time temperature time sequence association mode feature vector as the local display equipment port real-time temperature time sequence association mode feature; wherein, the formula is:
Wherein, Is global averaging; () Is the function of the activation and, A one-dimensional convolution is represented,A three-dimensional convolution is represented,Is a real-time temperature time sequence associated mode characteristic diagram of the equipment port after noise reduction,Is the real-time temperature time sequence associated mode characteristic vector of the local display equipment port.
It should be noted that, in other specific examples of the present application, the noise-reduced device port real-time temperature time sequence correlation mode feature map may be further processed by a receptive field focusing module to obtain local display device port real-time temperature time sequence correlation mode features, for example: inputting the real-time temperature time sequence association mode characteristic diagram of the equipment port after noise reduction; the receptive field focusing module is used for focusing a specific receptive field area so as to extract the real-time temperature time sequence associated mode characteristics of the locally displayed equipment port. The following is the procedure for the receptive field focusing module: firstly, applying one-dimensional convolution operation to a real-time temperature time sequence associated mode characteristic diagram of a device port after noise reduction; after the convolution operation, the size of the receptive field can be adjusted by changing the size or step of the convolution kernel, so as to control the specific receptive field area focused by the module; applying a nonlinear activation function, such as ReLU, to introduce nonlinear characteristics; and after the processing of the receptive field focusing module, obtaining the real-time temperature time sequence associated mode characteristic vector of the local display equipment port as the real-time temperature time sequence associated mode characteristic of the local display equipment port.
Specifically, the temperature mode abnormality detection and early warning module 360 is configured to determine whether an abnormality exists in a temperature mode of the device port based on the real-time temperature time sequence associated mode feature of the local display device port, and determine whether to generate an early warning information prompt. In particular, in one specific example of the present application, as shown in fig. 3, the temperature pattern abnormality detection and early warning module 360 includes: the device port temperature mode abnormality detection unit 361 is configured to pass the local visualization device port real-time temperature time sequence association mode feature vector through a classifier to obtain a classification result, where the classification result is used to indicate whether an abnormality exists in a temperature mode of the device port; the early warning prompt unit 362 is configured to generate an early warning information prompt in response to the classification result that the temperature mode of the device port is abnormal, for example, a high temperature abnormality, a low temperature abnormality, a temperature fluctuation abnormality, etc.
Specifically, the device port temperature pattern abnormality detection unit 361 is configured to pass the local visualization device port real-time temperature time sequence association pattern feature vector through a classifier to obtain a classification result, where the classification result is used to indicate whether there is an abnormality in the temperature pattern of the device port. That is, classification processing is performed by using the real-time temperature time sequence associated mode characteristic information about the equipment port after the local characteristic is displayed, so as to detect the abnormal temperature mode of the equipment port, and particularly, in a specific example of the application, an early warning information prompt is generated in response to the classification result that the abnormal temperature mode of the equipment port exists. Therefore, the abnormality detection of the equipment port can be automatically carried out by monitoring the temperature mode and the change condition of the equipment port in real time, so that potential problems can be found in time and early warning can be carried out, and the problems can be rapidly positioned and corresponding measures can be taken to ensure the safety of the equipment port. More specifically, the local display device port real-time temperature time sequence association mode feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the temperature mode of the device port is abnormal or not, and the method comprises the following steps: performing full-connection coding on the local display equipment port real-time temperature time sequence association mode feature vector by using a plurality of full-connection layers of the classifier to obtain a coding classification feature vector; and passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
In the technical scheme of the application, each feature matrix of the device port real-time temperature time sequence association mode feature map expresses time sequence association features of the device port real-time temperature in a local time domain based on a convolution kernel scale, and channel distribution of the convolution neural network model is followed among the feature matrices. And filtering the noise part of the equipment port real-time temperature time sequence correlation mode characteristic diagram based on the comparison between the per-position characteristic value and a preset threshold value by using the noise reducer based on the per-position mask module to obtain the equipment port real-time temperature time sequence correlation mode characteristic diagram after noise reduction. When the real-time temperature time sequence associated mode feature vector of the local display equipment port is obtained through the receptive field focusing module, the distribution integrity of the channel dimension among feature matrixes and the space dimension in the feature matrixes of the real-time temperature time sequence associated mode feature vector of the equipment port after noise reduction is considered to be poor, so that the obtained constraint of the real-time temperature time sequence associated mode feature vector of the local display equipment port relative to the overall distribution regression of the classifier is poor, and the accuracy of the classification result obtained through the classifier is affected.
Specifically, in a preferred embodiment of the present application, the device port temperature pattern abnormality detection unit includes: calculating the sum of the square root of the length of the local display equipment port real-time temperature time sequence correlation mode feature vector and the point of the inverse of the square root of the second norm of the local display equipment port real-time temperature time sequence correlation mode feature vector to obtain a local display equipment port real-time temperature time sequence correlation mode offset feature vector; calculating an exponential function based on a natural constant of the local display equipment port real-time temperature time sequence associated mode offset feature vector to obtain a local display equipment port real-time temperature time sequence associated mode offset prediction feature vector; calculating the product of a dot product of a norm and a weight super parameter of the local display equipment port real-time temperature time sequence correlation mode feature vector and the local display equipment port real-time temperature time sequence correlation mode feature vector to obtain a local display equipment port real-time temperature time sequence correlation mode constraint feature vector; calculating the point addition sum of the local display equipment port real-time temperature time sequence association mode deviation prediction feature vector and the local display equipment port real-time temperature time sequence association mode constraint feature vector to obtain an optimized local display equipment port real-time temperature time sequence association mode feature vector; and enabling the optimized local display equipment port real-time temperature time sequence association mode feature vector to pass through the classifier to obtain the classification result.
Specifically, considering that the local display device port real-time temperature time sequence correlation mode feature vector is based on overall distribution regression constraint of a classifier for data embedding coding time sequence context correlation time sequence propagation aggregation distribution of transaction data, in the above preferred example, the constraint of the local display device port real-time temperature time sequence correlation mode feature vector under overall regression distribution is improved by using a structured norm representation of the local display device port real-time temperature time sequence correlation mode feature vector as local canonical coordinates of each feature value of the local display device port real-time temperature time sequence correlation mode feature vector, so that the training speed of a model and the accuracy of classification of the local display device port real-time temperature correlation mode feature vector by using a class deviation prediction direction of class rotation deviation of the feature value relative to each feature value of the local display device port real-time temperature time sequence correlation mode feature vector as a center are improved. In this way, the abnormal detection of the equipment port can be automatically carried out by monitoring the temperature mode and the change condition of the equipment port in real time, so that potential problems can be found in time and early warning can be carried out, by adopting the mode, the problems can be rapidly positioned and corresponding measures can be taken, thereby reducing the time and influence of service interruption and ensuring the safety of the equipment port.
Specifically, the early warning prompting unit 362 is configured to generate an early warning information prompt in response to the classification result that the temperature mode of the device port is abnormal. In a specific example of the present application, when the classification result is that there is an abnormality in the temperature mode of the device port, an early warning information prompt is generated in response to the abnormality result.
It should be noted that, in other specific examples of the present application, it may also be determined whether the temperature mode of the device port is abnormal based on the real-time temperature time sequence associated mode feature of the local display device port in other manners, and determine whether to generate an early warning information prompt, for example: extracting features from real-time temperature time sequence data of a device port; and carrying out local visualization processing on the extracted feature vector. Local visualization may enhance the relevance and importance between features by methods such as self-attention mechanisms, convolution operations, etc., to capture local information in temperature mode; the features after the local visualization are expressed as feature vectors and are used as input; and performing anomaly detection on the feature vector by using a trained anomaly detection model or a threshold method. The anomaly detection model may be an unsupervised learning model, such as a method based on clustering or outlier detection; and judging whether the temperature mode of the equipment port is abnormal or not according to the abnormal detection result. If the abnormality detection result indicates that abnormality exists, corresponding early warning information is generated.
As described above, the device port security alarm system 300 according to the embodiment of the present application may be implemented in various wireless terminals, such as a server having a device port security alarm algorithm, etc. In one possible implementation, the device port security alarm system 300 according to embodiments of the present application may be integrated into a wireless terminal as a software module and/or hardware module. For example, the device port security alarm system 300 may be a software module in the operating system of the wireless terminal or may be an application developed for the wireless terminal; of course, the device port security alarm system 300 could equally be one of many hardware modules of the wireless terminal.
Alternatively, in another example, the device port security alarm system 300 and the wireless terminal may be separate devices, and the device port security alarm system 300 may be connected to the wireless terminal through a wired and/or wireless network and transmit interactive information in a agreed data format.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (7)
1. A device port security alarm system, comprising:
The device port real-time temperature acquisition module is used for acquiring a time sequence of real-time temperature values of the monitored device port acquired by the temperature sensor in a preset time period;
the temperature time sequence vector field conversion module is used for arranging the time sequence of the real-time temperature values into real-time temperature time sequence input vectors according to the time dimension and obtaining real-time temperature time sequence conversion images of the equipment port through the vector-image converter;
The temperature time sequence correlation mode feature extraction module is used for extracting features of the equipment port real-time temperature time sequence conversion image through the equipment port temperature time sequence mode feature extractor based on the deep neural network model so as to obtain an equipment port real-time temperature time sequence correlation mode feature map;
The temperature time sequence related mode characteristic noise reduction module is used for obtaining a real-time temperature time sequence related mode characteristic diagram of the equipment port after noise reduction by a noise reducer based on the position mask module;
the receptive field focusing module is used for enabling the noise-reduced equipment port real-time temperature time sequence correlation mode characteristic diagram to pass through the receptive field focusing module so as to obtain local display equipment port real-time temperature time sequence correlation mode characteristics;
And the temperature mode abnormality detection early warning module is used for determining whether the temperature mode of the equipment port is abnormal or not based on the real-time temperature time sequence associated mode characteristics of the local display equipment port and determining whether an early warning information prompt is generated or not.
2. The device port security alarm system of claim 1, wherein the deep neural network model is a convolutional neural network model.
3. The equipment port security alarm system of claim 2, wherein the temperature timing related mode feature noise reduction module is configured to: processing the equipment port real-time temperature time sequence association mode feature map through a noise reducer based on a per-position mask module according to the following noise reduction formula to obtain the noise-reduced equipment port real-time temperature time sequence association mode feature map;
The noise reduction formula is as follows:
；
；
Wherein, For the real-time temperature time sequence associated mode characteristic diagram of the equipment port,/>Is a threshold feature map,/>For the real-time temperature time sequence associated mode characteristic diagram of the equipment port after noise reduction,/>For the characteristic values of each position in the real-time temperature time sequence associated mode characteristic diagram of the equipment port,/>For the feature values at each position in the threshold feature map,And/>Is super-parameter,/>A set of conditions representing a threshold function.
4. The device port security alarm system of claim 3, wherein the receptive field focusing module comprises:
The local temperature time sequence correlation mode visualization unit is used for enabling the noise-reduced equipment port real-time temperature time sequence correlation mode feature map to pass through the receptive field focusing module to obtain a local visualization equipment port real-time temperature time sequence correlation mode feature vector as the local visualization equipment port real-time temperature time sequence correlation mode feature.
5. The equipment port security alarm system of claim 4, wherein the temperature timing correlation mode localization unit is configured to: the noise-reduced equipment port real-time temperature time sequence association mode feature diagram is processed through the receptive field focusing module by the following formula to obtain a local display equipment port real-time temperature time sequence association mode feature vector as the local display equipment port real-time temperature time sequence association mode feature;
Wherein, the formula is:
；
Wherein, Is global averaging; /(I)() Is an activation function,/>Representing a one-dimensional convolution,/>Representing a three-dimensional convolution,/>Is a characteristic diagram of the real-time temperature time sequence association mode of the equipment port after noise reduction,/>Is the real-time temperature time sequence associated mode characteristic vector of the local display equipment port.
6. The equipment port security alarm system of claim 5, wherein the temperature mode anomaly detection pre-alarm module comprises:
The device port temperature mode abnormality detection unit is used for enabling the local visualization device port real-time temperature time sequence association mode feature vector to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the temperature mode of the device port is abnormal or not;
and the early warning prompt unit is used for responding to the classification result that the temperature mode of the equipment port is abnormal and generating early warning information prompt.
7. The equipment port security alarm system according to claim 6, wherein the equipment port temperature pattern abnormality detection unit includes:
The full-connection coding subunit is used for carrying out full-connection coding on the real-time temperature time sequence associated mode feature vector of the local display equipment port by using a plurality of full-connection layers of the classifier so as to obtain a coding classification feature vector;
And a classification result generation subunit, configured to pass the encoded classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410600727.7A CN118175065A (en) | 2024-05-15 | 2024-05-15 | Equipment port safety alarm system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410600727.7A CN118175065A (en) | 2024-05-15 | 2024-05-15 | Equipment port safety alarm system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118175065A true CN118175065A (en) | 2024-06-11 |
Family
ID=91348969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410600727.7A Pending CN118175065A (en) | 2024-05-15 | 2024-05-15 | Equipment port safety alarm system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118175065A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210048402A1 (en) * | 2018-12-11 | 2021-02-18 | Dalian University Of Technology | Prediction method for mold breakout based on feature vectors and hierarchical clustering |
| CN115235639A (en) * | 2022-07-11 | 2022-10-25 | 无锡艾立德智能科技有限公司 | Temperature monitoring and early warning system and method of power driving chip |
| CN115729162A (en) * | 2022-11-18 | 2023-03-03 | 中国电信股份有限公司 | Inspection system, temperature alarm method, device, electronic equipment and readable medium |
| CN117393921A (en) * | 2023-10-17 | 2024-01-12 | 浙江博时新能源技术有限公司 | Distributed energy storage device |
| CN117420792A (en) * | 2023-11-06 | 2024-01-19 | 浙江电泰阀业有限公司 | Central control system for composite processing machine tool |
| CN117671396A (en) * | 2024-02-02 | 2024-03-08 | 新疆盛诚工程建设有限责任公司 | Intelligent monitoring and early warning system and method for construction progress |
| CN117884032A (en) * | 2024-03-11 | 2024-04-16 | 山东森杰清洁科技有限公司 | Disinfectant for sewage purification and preparation method thereof |
-
2024
- 2024-05-15 CN CN202410600727.7A patent/CN118175065A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210048402A1 (en) * | 2018-12-11 | 2021-02-18 | Dalian University Of Technology | Prediction method for mold breakout based on feature vectors and hierarchical clustering |
| CN115235639A (en) * | 2022-07-11 | 2022-10-25 | 无锡艾立德智能科技有限公司 | Temperature monitoring and early warning system and method of power driving chip |
| CN115729162A (en) * | 2022-11-18 | 2023-03-03 | 中国电信股份有限公司 | Inspection system, temperature alarm method, device, electronic equipment and readable medium |
| CN117393921A (en) * | 2023-10-17 | 2024-01-12 | 浙江博时新能源技术有限公司 | Distributed energy storage device |
| CN117420792A (en) * | 2023-11-06 | 2024-01-19 | 浙江电泰阀业有限公司 | Central control system for composite processing machine tool |
| CN117671396A (en) * | 2024-02-02 | 2024-03-08 | 新疆盛诚工程建设有限责任公司 | Intelligent monitoring and early warning system and method for construction progress |
| CN117884032A (en) * | 2024-03-11 | 2024-04-16 | 山东森杰清洁科技有限公司 | Disinfectant for sewage purification and preparation method thereof |
Non-Patent Citations (2)
| Title |
|---|
| HONG TANG: ""Research on Transformer Temperature Warning Algorithm Based on Support Vector Machine"", 《2023 INTERNATIONAL CONFERENCE ON INTERNET OF THINGS, ROBOTICS AND DISTRIBUTED COMPUTING (ICIRDC)》, 3 May 2024 (2024-05-03) * |
| 吴蕴蕴;郑彩仙;: "基于主成分分析模型的医疗设备温度监测模型及其应用", 中国医疗设备, no. 04, 25 April 2015 (2015-04-25) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9245235B2 (en) | Integrated approach to model time series dynamics in complex physical systems | |
| US11381583B1 (en) | Systems and methods for detecting anomalous system or network behavior | |
| CN116934304B (en) | Intelligent power distribution room equipment operation maintenance management system and method thereof | |
| KR102300049B1 (en) | Fault diagnosis apparatus and method using frequency analysis based on machine-learning | |
| CN117040917A (en) | Intelligent switch with monitoring and early warning functions | |
| CN112906775B (en) | Equipment fault prediction method and system | |
| CN112085281B (en) | Method and device for detecting safety of business prediction model | |
| CN117671396B (en) | Intelligent monitoring and early warning system and method for construction progress | |
| CN110597235A (en) | Universal intelligent fault diagnosis method | |
| Shajihan et al. | CNN based data anomaly detection using multi-channel imagery for structural health monitoring | |
| CN117269644A (en) | Line fault monitoring system and method for current transformer | |
| CN117392604A (en) | Real-time information monitoring and management system and method for Internet of things | |
| KR20210060157A (en) | Fault diagnosis apparatus and method based on artificial intelligence technology | |
| CN117676099B (en) | Security early warning method and system based on Internet of things | |
| CN115964670A (en) | Frequency spectrum anomaly detection method | |
| CN112947649B (en) | Multivariate process monitoring method based on mutual information matrix projection | |
| CN117856442A (en) | Power equipment remote monitoring system and method based on big data | |
| CN118175065A (en) | Equipment port safety alarm system | |
| Ning et al. | An intelligent device fault diagnosis method in industrial internet of things | |
| Yu et al. | A hybrid learning-based model for on-line monitoring and diagnosis of out-of-control signals in multivariate manufacturing processes | |
| CN114972871A (en) | Image registration-based few-sample image anomaly detection method and system | |
| Barreto et al. | A unifying methodology for the evaluation of neural network models on novelty detection tasks | |
| CN112732519A (en) | Event monitoring method and device | |
| CN117421723B (en) | SERVER MESH-based microservice system | |
| CN117636908B (en) | Digital mine production management and control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |