CN117768235A - Real-time flow monitoring alarm system based on Internet of things - Google Patents
Real-time flow monitoring alarm system based on Internet of things Download PDFInfo
- Publication number
- CN117768235A CN117768235A CN202311855292.2A CN202311855292A CN117768235A CN 117768235 A CN117768235 A CN 117768235A CN 202311855292 A CN202311855292 A CN 202311855292A CN 117768235 A CN117768235 A CN 117768235A
- Authority
- CN
- China
- Prior art keywords
- flow
- index
- subsequence
- data
- monitoring
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 108
- 230000007123 defense Effects 0.000 claims abstract description 39
- 230000007246 mechanism Effects 0.000 claims abstract description 20
- 238000013500 data storage Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 14
- 230000005856 abnormality Effects 0.000 claims abstract description 11
- 238000004891 communication Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 46
- 230000008569 process Effects 0.000 claims description 41
- 230000002159 abnormal effect Effects 0.000 claims description 31
- 238000013528 artificial neural network Methods 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 16
- 230000008859 change Effects 0.000 claims description 13
- 238000009776 industrial production Methods 0.000 claims description 11
- 238000007619 statistical method Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 3
- 238000004806 packaging method and process Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000006872 improvement Effects 0.000 abstract description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 2
- 239000013598 vector Substances 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000002776 aggregation Effects 0.000 description 3
- 238000004220 aggregation Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Alarm Systems (AREA)
Abstract
The real-time flow monitoring alarm system based on the Internet of things relates to the technical field of flow monitoring and comprises a monitoring center, wherein the monitoring center is in communication connection with a data acquisition module, a data storage module, a data processing module, a flow prediction module and a flow monitoring alarm module; the data acquisition module is used for acquiring various types of index data flow of each industrial device; the data storage module is used for storing the historical index data flow; the data processing module is used for acquiring flow risk early warning values of the flow subsequences; the flow prediction module is used for obtaining flow prediction information of the current monitoring period of each flow subsequence; the flow monitoring alarm module is used for generating a flow abnormality alarm signal, simultaneously establishing a joint defense early warning mechanism according to the flow prediction information, generating a joint defense early warning signal according to the joint defense early warning mechanism, and providing targeted improvement measures for weak links in advance to improve the production safety of the industrial network.
Description
Technical Field
The invention relates to the technical field of flow monitoring, in particular to a real-time flow monitoring alarm system based on the Internet of things.
Background
The prior art CN115102790A 'network flow abnormality sensing system and method based on big data' is realized by establishing a network flow normal sensing time model and an abnormality sensing time model; the network flow jump time of the unknown risk state sensing network is further predicted through a network flow normal sensing time model and an abnormal sensing time model; and predicting a risk value of the network flow by combining the predicted normal, abnormal and unknown risk sensing time, judging whether the network flow is normal or not according to the risk value, and simultaneously positioning the specific time at which the network flow abnormality possibly occurs by combining the predicted time model, so as to realize real-time monitoring of the network flow state and provide accurate time preparation for preventing and maintaining for each related responsible person.
The prior art CN111695823a "an anomaly evaluation method and system based on industrial control network traffic", the method comprises the following steps: an abnormality checking step, filtering false-reported abnormal information through known multi-source safety information; an abnormal aggregation step, namely reducing the quantity of abnormal traffic through an aggregation algorithm, and realizing the standardization of industrial network abnormal information; and an anomaly association step, wherein safety events are analyzed, perceived and predicted through anomaly association. The anomaly evaluation system is beneficial to improving the interpretation and predictability of industrial control network flow, improving the network situation awareness capability and timely avoiding the safety risk in the industrial network.
When the industrial control system operates normally, as the condition that all devices are in an incomplete synchronous state exists in the cooperative work of each device, the network flow which is required to be consumed by each device is not completely the same, the flow early warning technology of the existing industrial Internet of things is too passive, the flow threshold monitoring technology is often adopted for each index of the industrial device, and factors affecting the operation of the industrial device are more, such as the operation environment, materials and ages, and the like, the static analysis method cannot embody the advantages of the online Internet of things monitoring system, the early failure of the industrial device before the industrial device is converted from the normal state to the failure state is not easy to detect, and the early failure of the industrial device before the failure state is possibly weak or difficult to identify, so that a three-dimensional tower type and deep security protection system cannot be adopted before the failure is established, the traditional island passive defense system is converted into an active intelligent defense system, the problem that the boundary security protection is needed to be solved, and in order to solve the technical problem, the real-time flow monitoring alarm system based on the Internet of things is provided.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a real-time flow monitoring alarm system based on the Internet of things, which comprises a monitoring center, wherein the monitoring center is in communication connection with a data acquisition module, a data storage module, a data processing module, a flow prediction module and a flow monitoring alarm module;
the data acquisition module is in distributed connection with all industrial equipment in the industrial production process through the nodes of the Internet of things, and is used for acquiring various index data flows of all industrial equipment, marking acquisition time and setting a monitoring period;
the data storage module is used for storing the historical index data flow of each flow subsequence;
the data processing module is used for acquiring flow risk early warning values of the flow subsequences according to the historical index data flow of the flow subsequences;
the flow prediction module is used for constructing a flow prediction model based on the RBF neural network and obtaining flow prediction information of the current monitoring period of each flow subsequence;
the flow monitoring alarm module is used for comparing the total flow of index data of each flow sub-sequence with a corresponding flow risk early warning value, generating a flow abnormality alarm signal according to a comparison result, establishing a joint defense early warning mechanism according to flow prediction information, and generating a joint defense early warning signal according to the joint defense early warning mechanism.
Further, the process of collecting the index data flow corresponding to each type of monitoring index of each industrial equipment by the data collecting module comprises the following steps:
acquiring process flow characteristics of each industrial device, extracting flow information according to the process flow characteristics, splitting an industrial production process according to the flow information, and dividing the industrial production process into a plurality of flow subsequences;
setting flow monitoring nodes in each flow subsequence, and acquiring various monitoring indexes of each Internet of things node by utilizing data retrieval according to the functional characteristics in the process flow characteristics of the corresponding flow subsequence;
the node of the Internet of things obtains index data flow corresponding to each type of monitoring index according to each type of monitoring index, marks monitoring time and sets a monitoring period.
Further, the process of the data processing module obtaining the flow risk early warning value of each flow subsequence according to the flow of the historical index data of each flow subsequence includes:
data packaging is carried out on index data flow corresponding to various types of monitoring indexes collected by the nodes of the Internet of things of each flow subsequence, and index flow characteristics of each flow subsequence are generated;
extracting index types related to index flow characteristics of each flow subsequence, acquiring historical occurrence data of the flow subsequence when the flow subsequence suddenly fails from a data storage module, carrying out statistical analysis on the historical occurrence data of the flow subsequence when the flow subsequence suddenly fails through the index types, acquiring abnormal times corresponding to the index types, and setting weight labels for the index types according to the sudden times;
and obtaining the average data flow of each index type when each flow subsequence normally operates from the data storage module, and setting the flow risk early warning value of each flow subsequence according to the average data flow corresponding to each index type in the index flow characteristics of each flow subsequence and the weight label corresponding to each index type.
Further, the process of the data processing module obtaining the abnormal times corresponding to each index type by performing statistical analysis on the historical occurrence data of the index type during the sudden fault includes:
acquiring data flow of each index type when the flow subsequence suddenly fails, setting a deviation threshold value, acquiring flow deviation values of the data flow of each index type and average data flow of corresponding index types when the flow subsequence suddenly fails, and comparing the flow deviation values of each index type with the deviation threshold value;
if the flow deviation value of the index type is larger than the deviation threshold value, marking the index type as abnormal when the flow subsequence suddenly fails.
Further, the flow prediction module builds a flow prediction model based on the RBF neural network, and the process of obtaining flow prediction information of the current monitoring period of each flow subsequence comprises the following steps:
acquiring index flow characteristics of the nodes of the Internet of things, which are acquired by each flow subsequence, respectively extracting time characteristics and space characteristics of the index flow characteristics, and generating an index flow characteristic space-time sequence;
constructing a flow prediction model based on the RBF neural network, taking the historical index flow characteristics of each flow subsequence as historical training data, and training the flow prediction model;
and inputting the index flow characteristic space-time sequence and the index flow characteristic into a trained flow prediction model, and acquiring flow prediction information according to an output layer of the flow prediction model.
Further, the flow prediction module extracts time features and space features of the index flow features respectively, and the process of generating the space-time sequence of the index flow features comprises the following steps:
acquiring flow risk early warning values corresponding to flow subsequences, acquiring differences between index data flow at different moments corresponding to various monitoring indexes in flow characteristics of flow subsequences in a plurality of historical monitoring periods, constructing a time convolution network, and training the time convolution network by taking the differences as training data;
acquiring index data flow time sequence corresponding to each type of monitoring index in index flow characteristics of each flow subsequence in a current monitoring period, inputting the index data flow time sequence and flow risk early warning values corresponding to each flow subsequence into a time convolution network, and acquiring flow change trend characteristics of each type of monitoring index of each flow subsequence;
acquiring an assembly sequence and an assembly relation among the flow subsequences, constructing a topological directed graph through the assembly sequence and the assembly relation, taking the flow subsequences as nodes of the topological directed graph, taking the assembly sequence and the assembly relation among the flow subsequences as connection relation among the nodes, learning the topological directed graph through a BP neural network, and importing flow change trend characteristics of various monitoring indexes of the flow subsequences into the BP neural network;
and performing iterative training on each node in the topological directed graph through the BP neural network to obtain the influence weight among each node, and then generating an index flow characteristic space-time sequence of each node according to the influence degree among each node and the flow change trend characteristic of each node.
Further, the flow monitoring alarm module compares the total flow of index data of each flow sub-sequence with a corresponding flow risk early warning value, generates a flow abnormality alarm signal according to a comparison result, and establishes a joint defense early warning mechanism according to the flow prediction information, wherein the process comprises the following steps:
acquiring the total flow of index data of each flow subsequence in the current monitoring period, and comparing the total flow of index data of each flow subsequence with a corresponding flow risk early warning value;
if a flow sub-sequence with the total flow of the index data being larger than the flow risk early warning value exists, generating a flow abnormal warning signal of the flow sub-sequence and sending the flow abnormal warning signal to a monitoring center, acquiring a deviation value of the total flow of the index data and the flow risk early warning value, presetting a deviation threshold interval, selecting a threshold point in the deviation threshold interval to divide sub-intervals with different risk levels, judging the sub-interval with the deviation value, generating a risk level corresponding to the current flow sub-sequence, acquiring flow prediction information of the flow sub-sequence, and establishing a joint defense early warning mechanism according to the flow prediction information.
Further, the process of generating the joint defense early warning signal by the flow monitoring alarm module according to the joint defense early warning mechanism comprises the following steps:
acquiring flow prediction information of a target flow subsequence, acquiring total flow of index data in different time stamps remained in a current monitoring period of the target flow subsequence and influence weights of the target flow subsequence and other flow subsequences according to the flow prediction information, and acquiring risk levels in different time stamps in the current monitoring period of the target flow subsequence according to the total flow of the index data;
acquiring risk propagation grades of the target flow subsequence to other flow subsequences in different time stamps in the current monitoring period according to the risk grades in the different time stamps in the current monitoring period of the target flow subsequence and the influence weights of the target flow subsequence and the other flow subsequences;
and presetting a risk propagation level threshold, screening out other flow subsequences with risk propagation levels larger than the risk propagation level threshold, generating joint defense early warning signals according to the risk propagation levels of the other flow subsequences in different time stamps in the current monitoring period, and sending the joint defense early warning signals to a monitoring center.
Compared with the prior art, the invention has the beneficial effects that: the invention constructs a flow prediction model based on RBF neural network, obtains flow prediction information of the current monitoring period of each flow sub-sequence, compares the index data total flow of each flow sub-sequence with a corresponding flow risk early warning value, generates a flow abnormal alarm signal according to a comparison result, establishes a joint defense early warning mechanism according to the flow prediction information, generates a joint defense early warning signal according to the joint defense early warning mechanism, drives other flow sub-sequences with connection relation with the flow sub-sequence generating the flow abnormal event through the flow abnormal event, and prevents the flow abnormal event in advance for the other flow sub-sequences, namely, performs network defense improvement operation in advance on the influence relation of the flow sub-sequence generating the flow abnormal event on the other flow sub-sequences through the flow sub-sequence generating the flow abnormal event, and provides targeted improvement measures for weak links in advance so as to improve the industrial network production safety.
Drawings
Fig. 1 is a schematic diagram of a real-time flow monitoring alarm system based on the internet of things according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application, taken in conjunction with the accompanying drawings, clearly and completely describes the technical solutions of the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
As shown in fig. 1, the real-time flow monitoring alarm system based on the internet of things comprises a monitoring center, wherein the monitoring center is in communication connection with a data acquisition module, a data storage module, a data processing module, a flow prediction module and a flow monitoring alarm module;
the data acquisition module is in distributed connection with all industrial equipment in the industrial production process through the nodes of the Internet of things, and is used for acquiring various index data flows of all industrial equipment, marking acquisition time and setting a monitoring period;
the data storage module is used for storing the historical index data flow of each flow subsequence;
the data processing module is used for acquiring flow risk early warning values of the flow subsequences according to the historical index data flow of the flow subsequences;
the flow prediction module is used for constructing a flow prediction model based on the RBF neural network and obtaining flow prediction information of the current monitoring period of each flow subsequence;
the flow monitoring alarm module is used for comparing the total flow of index data of each flow sub-sequence with a corresponding flow risk early warning value, generating a flow abnormality alarm signal according to a comparison result, establishing a joint defense early warning mechanism according to flow prediction information, and generating a joint defense early warning signal according to the joint defense early warning mechanism.
It should be further noted that, in the specific implementation process, the process of collecting the index data flow corresponding to each type of monitoring index of each industrial device by the data collection module includes:
acquiring process flow characteristics of each industrial device, extracting flow information according to the process flow characteristics, splitting an industrial production process according to the flow information, and dividing the industrial production process into a plurality of flow subsequences;
setting flow monitoring nodes in each flow subsequence, and acquiring various monitoring indexes of each Internet of things node by utilizing data retrieval according to the functional characteristics in the process flow characteristics of the corresponding flow subsequence;
the node of the Internet of things obtains index data flow corresponding to each type of monitoring index according to each type of monitoring index, marks monitoring time and sets a monitoring period.
It should be further noted that, in the implementation process, the process of the data processing module obtaining the flow risk early warning value of each flow subsequence according to the historical index data flow of each flow subsequence includes:
data packaging is carried out on index data flow corresponding to various types of monitoring indexes collected by the nodes of the Internet of things of each flow subsequence, and index flow characteristics of each flow subsequence are generated;
extracting index types related to index flow characteristics of each flow subsequence, acquiring historical occurrence data of the flow subsequence when the flow subsequence suddenly fails from a data storage module, carrying out statistical analysis on the historical occurrence data of the flow subsequence when the flow subsequence suddenly fails through the index types, acquiring abnormal times corresponding to the index types, and setting weight labels for the index types according to the sudden times;
and obtaining the average data flow of each index type when each flow subsequence normally operates from the data storage module, and setting the flow risk early warning value of each flow subsequence according to the average data flow corresponding to each index type in the index flow characteristics of each flow subsequence and the weight label corresponding to each index type.
It should be further noted that, in the implementation process, a calculation formula for setting a weight tag for each index type according to the burstiness times is as follows:
Zi＝δ*Ki；
wherein Zi is a weight label of the i-th index type; ki is the number of anomalies of the i-th class index type; delta is a weight factor.
It should be further noted that, in the specific implementation process, a calculation formula of the flow early warning value of each flow subsequence is set according to the average data flow corresponding to each index type in the index flow characteristics of each flow subsequence and the weight label corresponding to each index type, where the calculation formula is as follows:
wherein Wj is the flow early warning value of the jth flow subsequence; rjq is the average data flow corresponding to the q index type in the j-th flow subsequence; zjq is a weight label corresponding to the q index type in the j-th flow subsequence; nj is the total number of index types in the j-th flow subsequence.
It should be further noted that, in the implementation process, the process of obtaining the number of abnormal times corresponding to each index type by the data processing module performing statistical analysis on the historical occurrence data of the index type during the sudden fault includes:
acquiring data flow of each index type when the flow subsequence suddenly fails, setting a deviation threshold value, acquiring flow deviation values of the data flow of each index type and average data flow of corresponding index types when the flow subsequence suddenly fails, and comparing the flow deviation values of each index type with the deviation threshold value;
if the flow deviation value of the index type is larger than the deviation threshold value, marking the index type as abnormal when the flow subsequence suddenly fails.
It should be further noted that, in the implementation process, the flow prediction module builds a flow prediction model based on the RBF neural network, and the process of obtaining the flow prediction information of the current monitoring period of each flow subsequence includes:
acquiring index flow characteristics of the nodes of the Internet of things, which are acquired by each flow subsequence, respectively extracting time characteristics and space characteristics of the index flow characteristics, and generating an index flow characteristic space-time sequence;
constructing a flow prediction model based on the RBF neural network, taking the historical index flow characteristics of each flow subsequence as historical training data, and training the flow prediction model;
and inputting the index flow characteristic space-time sequence and the index flow characteristic into a trained flow prediction model, and acquiring flow prediction information according to an output layer of the flow prediction model.
It should be further noted that, in the implementation process, the flow prediction module extracts the temporal feature and the spatial feature of the index flow feature, and the process of generating the space-time sequence of the index flow feature includes:
acquiring flow risk early warning values corresponding to flow subsequences, acquiring differences between index data flow at different moments corresponding to various monitoring indexes in flow characteristics of flow subsequences in a plurality of historical monitoring periods, constructing a time convolution network, and training the time convolution network by taking the differences as training data;
acquiring index data flow time sequence corresponding to each type of monitoring index in index flow characteristics of each flow subsequence in a current monitoring period, inputting the index data flow time sequence and flow risk early warning values corresponding to each flow subsequence into a time convolution network, and acquiring flow change trend characteristics of each type of monitoring index of each flow subsequence;
the time convolution neural network is used for extracting the characteristics of the time sequence of the monitoring data corresponding to each sensor, mining the time characteristics of the time sequence of the monitoring data, and has stable gradient, so that the problems of gradient disappearance and gradient explosion are avoided, and the stability of characteristic extraction is ensured;
acquiring an assembly sequence and an assembly relation among the flow subsequences, constructing a topological directed graph through the assembly sequence and the assembly relation, taking the flow subsequences as nodes of the topological directed graph, taking the assembly sequence and the assembly relation among the flow subsequences as connection relation among the nodes, learning the topological directed graph through a BP neural network, and importing flow change trend characteristics of various monitoring indexes of the flow subsequences into the BP neural network;
and performing iterative training on each node in the topological directed graph through the BP neural network to obtain the influence weight among each node, and then generating an index flow characteristic space-time sequence of each node according to the influence degree among each node and the flow change trend characteristic of each node.
It should be further described that, a calculation formula for obtaining the influence weight between each node by performing iterative training on each node in the topological directed graph through the BP neural network is as follows:
wherein B is (i+1) ，B (i) Respectively representing the influence weights of a certain flow subsequence to other flow subsequences after i+1th iteration; b= (B) 1 ，B 2 ，...，B n ) T The concrete numerical value is obtained through a node adjacency matrix; θ represents a damping factor; (Y) T ) Representing a state transition matrix; e represents an N x 1 matrix with all elements being 1; n represents the number of flow subsequences;
the specific process of generating the index flow characteristic space-time sequence of each node according to the influence degree among the nodes and the flow change trend characteristic of each node comprises the following steps:
the topology directed graph is subjected to representation learning through a BP neural network, and e is taken as an example by a pair of flow subsequence nodes (x, y) connected with the topology directed graph x ，e y The initial flow change trend vector is made, the flow subsequence node x is represented by a neighbor node aggregation mechanism, and node x vector representation e is obtained x The degree is specifically as follows:
e x °＝ReLU(Oe x +∑B xy (Oe y ))；
wherein R iseLU denotes an activation function; o represents a parameter matrix of the feature transformation; b (B) xy The influence weight of the node y on the node x is represented;
generating a vector representation e of the node y according to the above formula y And after the degree, carrying out vector representation of the next connected node, and so on, carrying out vector representation on all nodes in the topological directed graph, and generating index flow characteristic space-time sequences of the nodes according to the vectors of the nodes.
It should be further noted that, in the implementation process, the flow monitoring alarm module compares the total flow of the index data of each flow subsequence with the corresponding flow risk early-warning value, generates a flow abnormality alarm signal according to the comparison result, and establishes a joint defense early-warning mechanism according to the flow prediction information, where the process includes:
acquiring the total flow of index data of each flow subsequence in the current monitoring period, and comparing the total flow of index data of each flow subsequence with a corresponding flow risk early warning value;
if a flow sub-sequence with the total flow of the index data being larger than the flow risk early warning value exists, generating a flow abnormal warning signal of the flow sub-sequence and sending the flow abnormal warning signal to a monitoring center, acquiring a deviation value of the total flow of the index data and the flow risk early warning value, presetting a deviation threshold interval, selecting a threshold point in the deviation threshold interval to divide sub-intervals with different risk levels, judging the sub-interval with the deviation value, generating a risk level corresponding to the current flow sub-sequence, acquiring flow prediction information of the flow sub-sequence, and establishing a joint defense early warning mechanism according to the flow prediction information.
It should be further noted that, in the specific implementation process, the process of generating the joint defense early warning signal by the flow monitoring alarm module according to the joint defense early warning mechanism includes:
acquiring flow prediction information of a target flow subsequence, acquiring total flow of index data in different time stamps remained in a current monitoring period of the target flow subsequence and influence weights of the target flow subsequence and other flow subsequences according to the flow prediction information, and acquiring risk levels in different time stamps in the current monitoring period of the target flow subsequence according to the total flow of the index data;
acquiring risk propagation grades of the target flow subsequence to other flow subsequences in different time stamps in the current monitoring period according to the risk grades in the different time stamps in the current monitoring period of the target flow subsequence and the influence weights of the target flow subsequence and the other flow subsequences;
and presetting a risk propagation level threshold, screening out other flow subsequences with risk propagation levels larger than the risk propagation level threshold, generating joint defense early warning signals according to the risk propagation levels of the other flow subsequences in different time stamps in the current monitoring period, and sending the joint defense early warning signals to a monitoring center.
It is further to be noted that, in the specific implementation process, after the monitoring center receives the abnormal flow alarm signal and the joint defense early warning signal, a virtual space is constructed, physical entities of industrial equipment in the physical space in the current industrial production process are obtained, index data flows corresponding to each physical entity and each node of the internet of things in the current industrial production process are obtained, and data format preprocessing is performed;
mapping the physical entity of the industrial equipment to a virtual space through three-dimensional modeling treatment, converting the preprocessed index data flow into twin data, and matching the twin data with a corresponding three-dimensional model to obtain a digital twin model;
acquiring assembly sequence and assembly relation between three-dimensional models of each flow subsequence, constructing a topological directed graph through the assembly sequence and the assembly relation, matching a digital twin model with the topological directed graph to acquire a full-flow visual model,
and acquiring flow abnormal change trend characteristics of the flow subsequences according to the flow abnormal alarm signals and the joint defense early warning signals, searching in a data storage module according to the flow abnormal change characteristic trend, acquiring historical data with similarity meeting a preset standard in a data space, and extracting emergency measures and joint defense early warning measures in the historical data for implementation.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (8)
1. The real-time flow monitoring alarm system based on the Internet of things comprises a monitoring center, and is characterized in that the monitoring center is in communication connection with a data acquisition module, a data storage module, a data processing module, a flow prediction module and a flow monitoring alarm module;
the data acquisition module is in distributed connection with all industrial equipment in the industrial production process through the nodes of the Internet of things, and is used for acquiring various index data flows of all industrial equipment, marking acquisition time and setting a monitoring period;
the data storage module is used for storing the historical index data flow of each flow subsequence;
the data processing module is used for acquiring flow risk early warning values of the flow subsequences according to the historical index data flow of the flow subsequences;
the flow prediction module is used for constructing a flow prediction model based on the RBF neural network and obtaining flow prediction information of the current monitoring period of each flow subsequence;
the flow monitoring alarm module is used for comparing the total flow of index data of each flow sub-sequence with a corresponding flow risk early warning value, generating a flow abnormality alarm signal according to a comparison result, establishing a joint defense early warning mechanism according to flow prediction information, and generating a joint defense early warning signal according to the joint defense early warning mechanism.
2. The real-time flow monitoring alarm system based on the internet of things according to claim 1, wherein the process of collecting the index data flow corresponding to each type of monitoring index of each industrial device by the data collecting module comprises the following steps:
acquiring process flow characteristics of each industrial device, extracting flow information according to the process flow characteristics, splitting an industrial production process according to the flow information, and dividing the industrial production process into a plurality of flow subsequences;
setting flow monitoring nodes in each flow subsequence, and acquiring various monitoring indexes of each Internet of things node by utilizing data retrieval according to the functional characteristics in the process flow characteristics of the corresponding flow subsequence;
the node of the Internet of things obtains index data flow corresponding to each type of monitoring index according to each type of monitoring index, marks monitoring time and sets a monitoring period.
3. The real-time flow monitoring alarm system based on the internet of things according to claim 2, wherein the process of the data processing module obtaining the flow risk early warning value of each flow subsequence according to the flow of each flow subsequence history index data comprises:
data packaging is carried out on index data flow corresponding to various types of monitoring indexes collected by the nodes of the Internet of things of each flow subsequence, and index flow characteristics of each flow subsequence are generated;
extracting index types related to index flow characteristics of each flow subsequence, acquiring historical occurrence data of the flow subsequence when the flow subsequence suddenly fails from a data storage module, carrying out statistical analysis on the historical occurrence data of the flow subsequence when the flow subsequence suddenly fails through the index types, acquiring abnormal times corresponding to the index types, and setting weight labels for the index types according to the sudden times;
and obtaining the average data flow of each index type when each flow subsequence normally operates from the data storage module, and setting the flow risk early warning value of each flow subsequence according to the average data flow corresponding to each index type in the index flow characteristics of each flow subsequence and the weight label corresponding to each index type.
4. The real-time traffic monitoring and alarming system based on the internet of things according to claim 3, wherein the process of the data processing module obtaining the abnormal times corresponding to each index type by performing statistical analysis on the historical occurrence data of the index type during the sudden fault comprises:
acquiring data flow of each index type when the flow subsequence suddenly fails, setting a deviation threshold value, acquiring flow deviation values of the data flow of each index type and average data flow of corresponding index types when the flow subsequence suddenly fails, and comparing the flow deviation values of each index type with the deviation threshold value;
if the flow deviation value of the index type is larger than the deviation threshold value, marking the index type as abnormal when the flow subsequence suddenly fails.
5. The real-time traffic monitoring and alarming system based on the internet of things according to claim 4, wherein the process of the traffic prediction module constructing a traffic prediction model based on the RBF neural network and obtaining traffic prediction information of a current monitoring period of each flow subsequence comprises:
acquiring index flow characteristics of the nodes of the Internet of things, which are acquired by each flow subsequence, respectively extracting time characteristics and space characteristics of the index flow characteristics, and generating an index flow characteristic space-time sequence;
constructing a flow prediction model based on the RBF neural network, taking the historical index flow characteristics of each flow subsequence as historical training data, and training the flow prediction model;
and inputting the index flow characteristic space-time sequence and the index flow characteristic into a trained flow prediction model, and acquiring flow prediction information according to an output layer of the flow prediction model.
6. The real-time flow monitoring and alarming system based on the internet of things according to claim 5, wherein the flow prediction module extracts time features and space features of the index flow features respectively, and the process of generating the space-time sequence of the index flow features comprises:
acquiring flow risk early warning values corresponding to flow subsequences, acquiring differences between index data flow at different moments corresponding to various monitoring indexes in flow characteristics of flow subsequences in a plurality of historical monitoring periods, constructing a time convolution network, and training the time convolution network by taking the differences as training data;
acquiring index data flow time sequence corresponding to each type of monitoring index in index flow characteristics of each flow subsequence in a current monitoring period, inputting the index data flow time sequence and flow risk early warning values corresponding to each flow subsequence into a time convolution network, and acquiring flow change trend characteristics of each type of monitoring index of each flow subsequence;
acquiring an assembly sequence and an assembly relation among the flow subsequences, constructing a topological directed graph through the assembly sequence and the assembly relation, taking the flow subsequences as nodes of the topological directed graph, taking the assembly sequence and the assembly relation among the flow subsequences as connection relation among the nodes, learning the topological directed graph through a BP neural network, and importing flow change trend characteristics of various monitoring indexes of the flow subsequences into the BP neural network;
and performing iterative training on each node in the topological directed graph through the BP neural network to obtain the influence weight among each node, and then generating an index flow characteristic space-time sequence of each node according to the influence degree among each node and the flow change trend characteristic of each node.
7. The real-time flow monitoring alarm system based on the internet of things according to claim 6, wherein the flow monitoring alarm module compares the total flow of the index data of each flow sub-sequence with the corresponding flow risk early warning value, generates a flow abnormality alarm signal according to the comparison result, and establishes a joint defense early warning mechanism according to the flow prediction information, wherein the process comprises:
acquiring the total flow of index data of each flow subsequence in the current monitoring period, and comparing the total flow of index data of each flow subsequence with a corresponding flow risk early warning value;
if a flow sub-sequence with the total flow of the index data being larger than the flow risk early warning value exists, generating a flow abnormal warning signal of the flow sub-sequence and sending the flow abnormal warning signal to a monitoring center, acquiring a deviation value of the total flow of the index data and the flow risk early warning value, presetting a deviation threshold interval, selecting a threshold point in the deviation threshold interval to divide sub-intervals with different risk levels, judging the sub-interval with the deviation value, generating a risk level corresponding to the current flow sub-sequence, acquiring flow prediction information of the flow sub-sequence, and establishing a joint defense early warning mechanism according to the flow prediction information.
8. The real-time flow monitoring alarm system based on the internet of things of claim 7, wherein the process of generating the joint defense early warning signal by the flow monitoring alarm module according to the joint defense early warning mechanism comprises:
acquiring flow prediction information of a target flow subsequence, acquiring total flow of index data in different time stamps remained in a current monitoring period of the target flow subsequence and influence weights of the target flow subsequence and other flow subsequences according to the flow prediction information, and acquiring risk levels in different time stamps in the current monitoring period of the target flow subsequence according to the total flow of the index data;
acquiring risk propagation grades of the target flow subsequence to other flow subsequences in different time stamps in the current monitoring period according to the risk grades in the different time stamps in the current monitoring period of the target flow subsequence and the influence weights of the target flow subsequence and the other flow subsequences;
and presetting a risk propagation level threshold, screening out other flow subsequences with risk propagation levels larger than the risk propagation level threshold, generating joint defense early warning signals according to the risk propagation levels of the other flow subsequences in different time stamps in the current monitoring period, and sending the joint defense early warning signals to a monitoring center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311855292.2A CN117768235A (en) | 2023-12-29 | 2023-12-29 | Real-time flow monitoring alarm system based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311855292.2A CN117768235A (en) | 2023-12-29 | 2023-12-29 | Real-time flow monitoring alarm system based on Internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117768235A true CN117768235A (en) | 2024-03-26 |
Family
ID=90322162
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311855292.2A Pending CN117768235A (en) | 2023-12-29 | 2023-12-29 | Real-time flow monitoring alarm system based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117768235A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118197650A (en) * | 2024-05-17 | 2024-06-14 | 长春中医药大学 | Intelligent monitoring system for evaluating safety of gynecological minimally invasive surgery |
-
2023
- 2023-12-29 CN CN202311855292.2A patent/CN117768235A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118197650A (en) * | 2024-05-17 | 2024-06-14 | 长春中医药大学 | Intelligent monitoring system for evaluating safety of gynecological minimally invasive surgery |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111596604B (en) | Intelligent fault diagnosis and self-healing control system and method for engineering equipment based on digital twinning | |
| CN112202736B (en) | Communication network anomaly classification method based on statistical learning and deep learning | |
| CN115857447B (en) | Digital twinning-based complex industrial system operation monitoring method and system | |
| US11840998B2 (en) | Hydraulic turbine cavitation acoustic signal identification method based on big data machine learning | |
| CN108418841A (en) | Next-generation key message infrastructure network Security Situation Awareness Systems based on AI | |
| CN109581871B (en) | Industrial control system intrusion detection method of immune countermeasure sample | |
| CN117768235A (en) | Real-time flow monitoring alarm system based on Internet of things | |
| CN115063020B (en) | Multi-dimensional safety scheduling device and method for cascade hydropower station based on risk monitoring fusion | |
| CN108921230A (en) | Method for diagnosing faults based on class mean value core pivot element analysis and BP neural network | |
| CN116205265A (en) | Power grid fault diagnosis method and device based on deep neural network | |
| CN113177646B (en) | Power distribution equipment online monitoring method and system based on self-adaptive edge proxy | |
| CN117421684B (en) | Abnormal data monitoring and analyzing method based on data mining and neural network | |
| CN107862324A (en) | A kind of CBR forecast model intellectuality method for early warning based on MWSPCA | |
| CN113760670A (en) | Cable joint abnormity early warning method and device, electronic equipment and storage medium | |
| CN113484749A (en) | Generator fault diagnosis and prediction method | |
| CN117560300B (en) | Intelligent internet of things flow prediction and optimization system | |
| CN116112283A (en) | CNN-LSTM-based power system network security situation prediction method and system | |
| CN113722140B (en) | Industrial alarm flooding source diagnosis method based on small sample learning and storage medium | |
| CN113780432A (en) | Intelligent detection method for operation and maintenance abnormity of network information system based on reinforcement learning | |
| CN116259161B (en) | Power failure early warning system | |
| CN117200060A (en) | Intelligent inspection method and system based on new energy power plant | |
| CN112036496A (en) | Nuclear power device fault diagnosis method and system | |
| Li et al. | Meteorological radar fault diagnosis based on deep learning | |
| CN116909788A (en) | Multi-mode fault diagnosis method and system with unchanged task direction and visual angle | |
| CN115560962A (en) | Fan abnormal state detection method based on multi-level space-time diagram neural network |
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 |