CN118400299B - Vehicle-mounted network intelligent monitoring system based on cloud computing - Google Patents
Vehicle-mounted network intelligent monitoring system based on cloud computing Download PDFInfo
- Publication number
- CN118400299B CN118400299B CN202410841602.3A CN202410841602A CN118400299B CN 118400299 B CN118400299 B CN 118400299B CN 202410841602 A CN202410841602 A CN 202410841602A CN 118400299 B CN118400299 B CN 118400299B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- mounted network
- flow data
- network flow
- data segment
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims abstract description 198
- 238000001514 detection method Methods 0.000 claims abstract description 30
- 238000012216 screening Methods 0.000 claims abstract description 4
- 230000005856 abnormality Effects 0.000 claims description 53
- 238000005070 sampling Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 9
- 238000000034 method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 abstract description 16
- 230000011218 segmentation Effects 0.000 abstract description 6
- 230000005540 biological transmission Effects 0.000 description 8
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012935 Averaging Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 101000935117 Homo sapiens Voltage-dependent P/Q-type calcium channel subunit alpha-1A Proteins 0.000 description 1
- 208000036758 Postinfectious cerebellitis Diseases 0.000 description 1
- 102100025330 Voltage-dependent P/Q-type calcium channel subunit alpha-1A Human genes 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0823—Errors, e.g. transmission errors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of abnormal data screening, in particular to a cloud computing-based vehicle-mounted network intelligent monitoring system, which comprises a vehicle-mounted network flow data acquisition module, an abnormal detection module, a data abnormal index acquisition module, a fault possibility acquisition module and a data uploading module, wherein the fault detection accuracy can be ensured by carrying out targeted analysis through segmentation, then a preliminary abnormal vehicle-mounted network flow data section is obtained through network flow data fluctuation conditions, the data abnormal index of each abnormal vehicle-mounted network flow data section is obtained according to the abnormal conditions of network flow, the fault possibility of a vehicle-mounted network node is obtained, finally the fault information of the vehicle-mounted network node is obtained according to the fault possibility of the vehicle-mounted network node and is uploaded to a cloud server, the fault detection accuracy of the vehicle-mounted network node is improved, and the misjudgment condition caused by communication conflicts or signal interference conditions existing in a vehicle-mounted network is greatly reduced.
Description
Technical Field
The invention relates to the technical field of abnormal data screening, in particular to a vehicle-mounted network intelligent monitoring system based on cloud computing.
Background
In the internet of vehicles, the vehicle-mounted network is required to be connected with each vehicle-mounted network node, and the vehicle-mounted network node comprises each intelligent device in the vehicle system, for example: an engine control system, a brake system, a driving assistance system, and the like. The normal operation of the internet of vehicles depends on coordination work among various vehicle-mounted network nodes, and the vehicle-mounted network nodes communicate in real time through a vehicle-mounted network (such as a CAN bus network) to determine cooperative driving among vehicles and between vehicles and systems. And abnormal on-board network conditions may cause delays, loss or errors in data transmission, thereby affecting the stability and reliability of the vehicle system.
By detecting the traffic situation of the vehicle-mounted network, the problem that the vehicle performance is possibly affected can be timely found and solved, and the stable operation of the vehicle system is ensured. When the vehicle-mounted network node fails, abnormal vehicle-mounted network consumption is caused. However, in addition to the above reasons, when a communication collision or signal interference situation occurs in the vehicle-mounted network, an increase in the vehicle-mounted data flow rate is also caused, causing abnormal network consumption, which does not affect the vehicle performance. However, the existing detection mode only detects the flow data consumed by the network to judge whether the vehicle-mounted network node fails or not, and uploads the detection result to the cloud server. Because the vehicle-mounted network may have communication conflict or signal interference, the detection method cannot accurately acquire whether the vehicle-mounted network node fails.
Disclosure of Invention
In view of the above, the invention provides a vehicle-mounted network intelligent monitoring system based on cloud computing in order to solve the technical problem that whether a vehicle-mounted network node fails or not cannot be accurately obtained by the existing detection mode.
The adopted technical scheme is as follows:
An on-vehicle network intelligent monitoring system based on cloud computing, comprising:
the vehicle-mounted network flow data acquisition module is used for acquiring at least two vehicle-mounted network flow data segments obtained by segmenting a vehicle-mounted network flow data sequence, wherein the vehicle-mounted network flow data sequence comprises vehicle-mounted network flow data with a plurality of sampling periods;
the abnormality detection module is used for acquiring abnormal vehicle-mounted network flow data segments from the vehicle-mounted network flow data segments according to the fluctuation condition of the network flow data;
The data anomaly index acquisition module is used for acquiring data anomaly indexes of each abnormal vehicle-mounted network flow data segment according to the network flow data fluctuation condition of each abnormal vehicle-mounted network flow data segment and two vehicle-mounted network flow data segments adjacent to the abnormal vehicle-mounted network flow data segment;
the fault possibility acquisition module is used for acquiring the fault possibility of the vehicle-mounted network nodes of each abnormal vehicle-mounted network flow data segment according to the difference condition of the flow data of each vehicle-mounted network node in the corresponding time period, the number of the abnormal vehicle-mounted network nodes and the data abnormal index;
the data uploading module is used for obtaining the failure information of the vehicle-mounted network node according to the failure possibility of the vehicle-mounted network node and uploading the failure information of the vehicle-mounted network node to the cloud server.
In one embodiment, the anomaly detection module includes:
the system comprises a first anomaly detection unit, a second anomaly detection unit and a first anomaly detection unit, wherein the first anomaly detection unit is used for acquiring network flow data fluctuation indexes of vehicle-mounted network flow data in each vehicle-mounted network flow data segment, and the network flow data fluctuation indexes are used for representing the fluctuation degree of the network flow data of the vehicle-mounted network flow data in the vehicle-mounted network flow data segment;
And the second abnormality detection unit is used for determining the vehicle-mounted network flow data segment which is larger than or equal to the preset fluctuation index threshold value as an abnormal vehicle-mounted network flow data segment.
In a specific embodiment, the calculation formula of the network traffic data fluctuation index is as follows:
Wherein, A network traffic data fluctuation index representing a v-th in-vehicle network traffic data segment,Representing the number of in-vehicle network traffic data in the v-th in-vehicle network traffic data segment,A value representing the i-th in-vehicle network traffic data in the v-th in-vehicle network traffic data segment,An average value of the values of the in-vehicle network flow data representing the v-th in-vehicle network flow data segment,AndThe maximum value and the minimum value of the vehicle-mounted network flow data of the v-th vehicle-mounted network flow data segment are respectively represented,Representing the average of the values of all the vehicle network flow data in the vehicle network flow data sequence, exp representing an exponential function based on a natural constant e,Representing the normalization function.
In a specific embodiment, the data anomaly index acquisition module includes:
A first abnormality index obtaining unit configured to obtain a first network traffic data fluctuation degree of a last vehicle-mounted network traffic data segment adjacent to the candidate abnormal vehicle-mounted network traffic data segment, and a second network traffic data fluctuation degree of a next vehicle-mounted network traffic data segment adjacent to the candidate abnormal vehicle-mounted network traffic data segment, respectively; the candidate abnormal vehicle-mounted network flow data segment is any abnormal vehicle-mounted network flow data segment;
The second abnormal index obtaining unit is configured to obtain a data abnormal index of the candidate abnormal vehicle-mounted network traffic data segment according to the network traffic data fluctuation index of the candidate abnormal vehicle-mounted network traffic data segment, the quantity of vehicle-mounted network traffic data in the candidate abnormal vehicle-mounted network traffic data segment, the first network traffic data fluctuation degree and the second network traffic data fluctuation degree, where the data abnormal index is in a positive correlation with the network traffic data fluctuation index of the candidate abnormal vehicle-mounted network traffic data segment and the quantity of vehicle-mounted network traffic data in the candidate abnormal vehicle-mounted network traffic data segment, and is in an inverse correlation with the first network traffic data fluctuation degree and the second network traffic data fluctuation degree.
In a specific embodiment, the process for obtaining the fluctuation degree of the first network traffic data includes:
Acquiring the absolute value of the difference value of the numerical value of any two adjacent vehicle-mounted network flow data in the last vehicle-mounted network flow data segment, and calculating the average value of all the absolute values of the difference values corresponding to the last vehicle-mounted network flow data segment to obtain the fluctuation degree of the first network flow data;
the process for acquiring the fluctuation degree of the second network flow data comprises the following steps:
And obtaining the absolute value of the difference value of the numerical value of any two adjacent vehicle-mounted network flow data in the next vehicle-mounted network flow data segment, and calculating the average value of all the absolute values of the difference values corresponding to the next vehicle-mounted network flow data segment to obtain the fluctuation degree of the second network flow data.
In a specific embodiment, the failure likelihood obtaining module includes:
The first data feature acquisition unit is used for acquiring local network flow data features of each vehicle-mounted network node in a corresponding period of the candidate abnormal vehicle-mounted network flow data segment, and acquiring overall network flow data features of each vehicle-mounted network node in an overall period corresponding to the vehicle-mounted network flow data sequence, wherein the local network flow data features are used for representing overall conditions of network flow data of the vehicle-mounted network node in the corresponding period of the candidate abnormal vehicle-mounted network flow data segment, and the overall network flow data features are used for representing overall conditions of network flow data of the vehicle-mounted network node in the overall period corresponding to the vehicle-mounted network flow data sequence; the candidate abnormal vehicle-mounted network flow data segment is any abnormal vehicle-mounted network flow data segment;
The second data characteristic acquisition unit is used for screening and obtaining the number of the vehicle-mounted network nodes with abnormal possibility corresponding to the candidate abnormal vehicle-mounted network flow data segments according to the difference degree between the local network flow data characteristic and the whole network flow data characteristic of each vehicle-mounted network node in the corresponding time period of the candidate abnormal vehicle-mounted network flow data segments;
The third data characteristic obtaining unit is used for obtaining the failure possibility of the vehicle-mounted network node of the candidate abnormal vehicle-mounted network flow data segment according to the data abnormality index of the candidate abnormal vehicle-mounted network flow data segment, the number of vehicle-mounted network nodes with the abnormality possibility and the fluctuation index of the difference degree, wherein the failure possibility of the vehicle-mounted network node is in positive correlation with the data abnormality index of the candidate abnormal vehicle-mounted network flow data segment, the number of the vehicle-mounted network nodes with the abnormality possibility and the overall difference degree; the fluctuation index of the difference degree is used for representing the fluctuation degree of the difference degree of all vehicle-mounted network nodes corresponding to the candidate abnormal vehicle-mounted network flow data segment.
In a specific embodiment, the second data feature acquisition unit includes:
The quantity acquisition subunit is used for determining the vehicle-mounted network nodes with the difference degrees larger than a preset threshold value as vehicle-mounted network nodes with the possibility of abnormality, and acquiring the quantity of the vehicle-mounted network nodes with the possibility of abnormality corresponding to the candidate abnormal vehicle-mounted network flow data segments.
In a specific embodiment, the calculation formula of the failure probability of the vehicle network node is:
Wherein, Representing the possibility of failure of the vehicle network node of the v-th abnormal vehicle network traffic data segment,Representing the number of in-vehicle network nodes for which there is a possibility of abnormality corresponding to the v-th abnormal in-vehicle network traffic data segment, N representing the number of in-vehicle network nodes,A data abnormality index indicating a v-th abnormal in-vehicle network flow data segment,A degree of difference fluctuation index indicating a v-th abnormal vehicle-mounted network flow data segment,Representing the normalization function.
In one embodiment, the calculation formula of the variation degree fluctuation index is as follows:
Wherein, A degree of difference fluctuation index indicating a v-th abnormal vehicle-mounted network flow data segment,Represents the degree of difference of the kth on-vehicle network node in the corresponding period of the kth abnormal on-vehicle network flow data segment, N represents the number of on-vehicle network nodes,And the average value of the difference degree of all vehicle-mounted network nodes in the corresponding time period of the v-th abnormal vehicle-mounted network flow data segment is represented.
In a specific embodiment, obtaining the failure information of the on-board network node according to the failure possibility of the on-board network node includes:
Determining an abnormal vehicle-mounted network flow data segment with the possibility of the vehicle-mounted network node fault being larger than a preset fault threshold value as a fault vehicle-mounted network flow data segment, and determining a time period corresponding to the fault vehicle-mounted network flow data segment as a fault time period, wherein the vehicle-mounted network node fault information comprises the fault vehicle-mounted network flow data segment and the fault time period.
The invention has at least the following beneficial effects: in the vehicle-mounted network intelligent monitoring system based on cloud computing, the vehicle-mounted network flow data sequence is segmented, and the fault detection accuracy of the follow-up vehicle-mounted network nodes can be ensured by carrying out targeted analysis on each vehicle-mounted network flow data segment obtained by segmentation; and obtaining preliminary abnormal vehicle-mounted network flow data segments through network flow data fluctuation conditions, taking each abnormal vehicle-mounted network flow data segment as an analysis object, obtaining data abnormality indexes of each abnormal vehicle-mounted network flow data segment according to the network flow data fluctuation conditions of two adjacent vehicle-mounted network flow data segments, and determining abnormal vehicle-mounted network node fault information according to the traffic change of each vehicle-mounted network node and the overall abnormal data network consumption condition of each vehicle-mounted network node, wherein the abnormal conditions are caused by the vehicle-mounted network node fault, so that the accurate data abnormality indexes can be obtained through analyzing the network flow fluctuation conditions of the adjacent vehicle-mounted network flow data segments, and then the vehicle-mounted network node fault probability of each abnormal vehicle-mounted network flow data segment is obtained by combining the difference condition of the flow data of each vehicle-mounted network node in a corresponding time period and the number of the abnormal vehicle-mounted network nodes.
Drawings
Fig. 1 is a schematic structural diagram of an intelligent monitoring system of a vehicle-mounted network based on cloud computing;
Fig. 2 is a schematic flow diagram corresponding to an intelligent monitoring system of a vehicle-mounted network based on cloud computing;
FIG. 3 is a data graph of network traffic data;
fig. 4 is a schematic structural view of the abnormality detection module;
FIG. 5 is a schematic diagram of a data anomaly index acquisition module;
fig. 6 is a schematic structural diagram of the failure possibility acquisition module.
Detailed Description
The technical scheme of the application will be clearly and thoroughly described below with reference to the accompanying drawings.
In this embodiment, the vehicle is connected to each vehicle-mounted network node in the vehicle through a vehicle-mounted network (such as a CAN bus network), where the vehicle-mounted network node is each intelligent device in the vehicle system, for example: an engine control system, a brake system, a driving assistance system, and the like. In order to monitor the network traffic of the vehicle-mounted network, a network traffic detector is usually provided in the vehicle system for detecting the vehicle-mounted network traffic data, so that not only the overall vehicle-mounted network traffic data of the vehicle-mounted network can be detected, but also the network traffic condition of each vehicle-mounted network node can be detected. The vehicle-mounted network intelligent monitoring system based on cloud computing is used for determining whether the vehicle-mounted network abnormal condition is caused by the vehicle-mounted network node fault according to the detected specific condition of the vehicle-mounted network flow.
It should be understood that the vehicle-mounted network intelligent monitoring system based on cloud computing provided in this embodiment may be implemented as a hardware system by a related data processor (such as a CPU), and disposed in a vehicle, or may be implemented as a software system in a vehicle controller in a vehicle system by the vehicle controller.
As shown in fig. 1, the vehicle-mounted network intelligent monitoring system includes a vehicle-mounted network flow data acquisition module 101, an abnormality detection module 102, a data abnormality index acquisition module 103, a failure possibility acquisition module 104, and a data uploading module 105. Fig. 2 is a flowchart of steps of an intelligent monitoring method of the vehicle-mounted network corresponding to the intelligent monitoring system of the vehicle-mounted network.
The vehicle-mounted network flow data acquisition module 101 is configured to acquire at least two vehicle-mounted network flow data segments obtained by segmenting a vehicle-mounted network flow data sequence, where the vehicle-mounted network flow data sequence includes vehicle-mounted network flow data of a plurality of sampling periods.
In this embodiment, a sampling period, that is, a sampling period of the vehicle-mounted network traffic is preset, and vehicle-mounted network traffic data of each sampling period is obtained according to the sampling period, where the sampling period is set according to actual needs, for example, 1s. And, a time period is set, and the vehicle-mounted network flow data acquired in the time period is analyzed, wherein the length of the time period is set according to actual needs, such as 1 day. The vehicle-mounted network flow data of the vehicle-mounted network acquired in the time period form a vehicle-mounted network flow data sequence according to the time sequence, wherein the vehicle-mounted network flow data sequence comprises vehicle-mounted network flow data of a plurality of sampling periods. The vehicle-mounted network flow data is specifically the flow consumed for data transmission, namely the flow consumed for data transmission in each sampling period. It should be appreciated that network traffic data for each sampling period of each on-board network node is also acquired.
As a specific embodiment, the vehicle network traffic may be obtained by: calculating the data size of each signal: from the length of the signals (in bits), the size of the data transmitted by each signal in each sampling period can be calculated; determining a transmission frequency of a signal: the DBC file generally contains transmission period information of each signal, that is, the frequency of the signal transmitted in the vehicle-mounted network; calculating the bandwidth consumption of each signal: multiplying the data size of each signal by the transmission frequency of the signal to obtain the bandwidth occupied by each signal in the sampling period; calculating the total flow consumption: and adding the bandwidth consumption of all the signals to obtain the total flow consumption of the whole vehicle-mounted network in the sampling period.
As an example, fig. 3 shows a waveform diagram corresponding to the in-vehicle network flow data sequence. Wherein, the abscissa represents time series, namely each sampling period, and the ordinate is the numerical value of the vehicle-mounted network flow.
When the vehicle network node is in a normal condition, the vehicle network flow of the vehicle network is generally relatively stable, and no large data fluctuation occurs. However, when the on-vehicle network node is subjected to signal interference, communication collision or damage of the on-vehicle network node, a large energy consumption change may occur in network consumption, and on-vehicle network traffic data is higher than normal. These conditions may cause the vehicle network traffic to exhibit the same data fluctuation law over a period of time. Therefore, the vehicle-mounted network flow data sequence is required to be segmented to obtain at least two vehicle-mounted network flow data segments, and abnormal data segments are determined and obtained according to the data condition of each vehicle-mounted network flow data segment and the correlation among each vehicle-mounted network flow data segment.
In this embodiment, the on-vehicle network traffic data sequence is segmented by a segmentation constant approximation segmentation algorithm (APCA). The piecewise constant approximation piecewise algorithm can divide the time-series numerical approximation data into pieces, and as other embodiments, other data piecewise algorithms can be used, such as: and acquiring the absolute difference values of every two adjacent vehicle-mounted network flow data, and if the absolute difference values of the continuous preset number of vehicle-mounted network flow data exceed a preset threshold value, taking the preset number of intermediate positions as segmentation points, thereby realizing segmentation of the vehicle-mounted network flow data sequence. It should be appreciated that the various vehicle network traffic data segments are arranged in a time sequence, with each vehicle network traffic data segment corresponding to a time period (i.e., time period) in which it is located.
The anomaly detection module 102 is configured to obtain an anomaly vehicle-mounted network traffic data segment from each vehicle-mounted network traffic data segment according to the fluctuation condition of the network traffic data. Because the vehicle-mounted network is under normal conditions, namely when each vehicle-mounted network node is under normal conditions, the vehicle-mounted network flow data is generally in a relatively stable state, and meanwhile, the difference between each vehicle-mounted network flow data segment and the whole vehicle-mounted network flow data sequence is not too large. When the vehicle-mounted network node in the vehicle networking is abnormal, the network is interfered and the communication conflict occurs, the vehicle-mounted network flow data can be increased or reduced, and meanwhile, the overall fluctuation condition of the vehicle-mounted network flow data is severe. The abnormal data segment is also larger in difference from the vehicle-mounted network traffic data sequence than the vehicle-mounted network traffic data sequence. Therefore, according to the fluctuation condition of the network flow data, abnormal vehicle-mounted network flow data segments can be obtained from the vehicle-mounted network flow data segments, and the abnormal vehicle-mounted network flow data segments are data segments with more severe fluctuation.
In a specific embodiment, as shown in fig. 4, the anomaly detection module 102 includes a first anomaly detection unit 201 and a second anomaly detection unit 202, where the first anomaly detection unit 201 is configured to obtain a network traffic data fluctuation indicator of the vehicle network traffic data in each vehicle network traffic data segment, and the second anomaly detection unit 202 is configured to determine a vehicle network traffic data segment greater than or equal to a preset fluctuation indicator threshold as an anomaly vehicle network traffic data segment. The network flow data fluctuation index is used for representing the fluctuation degree of network flow data of the vehicle-mounted network flow data in the vehicle-mounted network flow data segments, and then each vehicle-mounted network flow data segment corresponds to one network flow data fluctuation index, and the larger the network flow data fluctuation index is, the more severe the vehicle-mounted network flow data in the corresponding vehicle-mounted network flow data segment is, so that a preset fluctuation index threshold value is set, and the specific value of the preset fluctuation index threshold value is set according to actual needs, and can be set to be 0.7 in the embodiment. The network flow data fluctuation index of each vehicle-mounted network flow data segment is compared with a preset fluctuation index threshold, vehicle-mounted network flow data segments which are larger than or equal to the preset fluctuation index threshold are selected, the selected vehicle-mounted network flow data segments are data comparison fluctuation data segments, and then the vehicle-mounted network flow data segments are determined to be abnormal vehicle-mounted network flow data segments.
In a specific embodiment, the calculation formula of the network traffic data fluctuation index is as follows:
Wherein, A network traffic data fluctuation index representing a v-th in-vehicle network traffic data segment,Representing the number of in-vehicle network traffic data in the v-th in-vehicle network traffic data segment,A value representing the i-th in-vehicle network traffic data in the v-th in-vehicle network traffic data segment,An average value of the values of the in-vehicle network flow data representing the v-th in-vehicle network flow data segment,AndThe maximum value and the minimum value of the vehicle-mounted network flow data of the v-th vehicle-mounted network flow data segment are respectively represented,Representing the average of the values of all the vehicle network flow data in the vehicle network flow data sequence, exp representing an exponential function based on a natural constant e,Representing the normalization function.
The vehicle-mounted network flow data fluctuation condition in the v-th vehicle-mounted network flow data section is represented, and the larger the value is, the more serious the fluctuation condition is; The larger the value representing the data difference between the v-th vehicle-mounted network traffic data segment and the vehicle-mounted network traffic data sequence, the greater the likelihood that the v-th vehicle-mounted network traffic data segment is an abnormal vehicle-mounted network traffic data segment, The data range of the v-th vehicle-mounted network flow data segment is represented, and the larger the data range is, the worse the data stability is, and the greater the possibility that the v-th vehicle-mounted network flow data segment is an abnormal vehicle-mounted network flow data segment is. By aligningNormalization is performed so that the normalized numerical interval is [0,1].
It should be understood that, in the case of satisfying the corresponding logic, the specific calculation manner in the calculation formula may be modified correspondingly, and as other embodiments, the network traffic data fluctuation index may be represented by other indexes capable of characterizing the data fluctuation condition, for example: variance, or average of absolute values of differences of all adjacent two on-vehicle network traffic data, etc.
In addition, the normalization method in the present embodiment may be a maximum value minimum value normalization method, or may be the following normalization method: Where y is the output, x is the input, and e is a natural constant.
The data anomaly index obtaining module 103 is configured to obtain a data anomaly index of each abnormal vehicle-mounted network traffic data segment according to the network traffic data fluctuation condition of each abnormal vehicle-mounted network traffic data segment and two vehicle-mounted network traffic data segments adjacent to the abnormal vehicle-mounted network traffic data segment.
In general, signal interference or communication collisions are only temporary, so the duration of the changes in network traffic data caused by such interference and communication collisions is not long. Since disturbances or collisions suddenly occur, the on-board network will typically change the flow data rapidly; and the interference and collision suddenly disappear, the on-board network is usually quickly restored to a normal state, and the network traffic data is not kept at a high level for a long time. Moreover, on-board communication in the internet of vehicles uses a CAN bus for data transmission, on which an on-board network node CAN send a data packet and to which other corresponding on-board network nodes are expected to respond. Because of the timing communication condition in the internet of vehicles, if the vehicle-mounted network node is damaged and cannot respond to the requests of other vehicle-mounted network nodes, communication interruption or abnormality may be caused, and other vehicle-mounted network nodes may attempt to resend the requests to ensure that communication is performed normally, which may result in an increase in communication burden. The network change caused by the abnormality of the vehicle-mounted network node gradually increases along with the time until the data reach stable, and the network energy consumption of the abnormal vehicle-mounted network flow data segment is larger. Therefore, the data abnormality index of each abnormal vehicle-mounted network flow data segment can be obtained according to the network flow data fluctuation condition of each abnormal vehicle-mounted network flow data segment and two vehicle-mounted network flow data segments adjacent to the abnormal vehicle-mounted network flow data segment.
In a specific embodiment, as shown in fig. 5, the data abnormality index acquisition module 103 includes a first abnormality index acquisition unit 301 and a second abnormality index acquisition unit 302.
The first abnormality index obtaining unit 301 is configured to obtain a first network traffic data fluctuation degree of a last vehicle-mounted network traffic data segment adjacent to the candidate abnormal vehicle-mounted network traffic data segment, and a second network traffic data fluctuation degree of a next vehicle-mounted network traffic data segment adjacent to the candidate abnormal vehicle-mounted network traffic data segment, respectively. In this embodiment, the candidate abnormal vehicle-mounted network traffic data segment is any one abnormal vehicle-mounted network traffic data segment. Then, the previous and next vehicle-mounted network traffic data segments adjacent to the candidate abnormal vehicle-mounted network traffic data segment are acquired, and in general, the previous or next vehicle-mounted network traffic data segment adjacent to the abnormal vehicle-mounted network traffic data segment has the possibility of being or not being the abnormal vehicle-mounted network traffic data segment, and since the aforementioned segments are divided based on the vehicle-mounted network traffic data, in general, neither the previous or next vehicle-mounted network traffic data segment adjacent to the abnormal vehicle-mounted network traffic data segment is the abnormal vehicle-mounted network traffic data segment, nor excluding, of course: the previous and/or the next vehicle-mounted network traffic data segment adjacent to the abnormal vehicle-mounted network traffic data segment is also an abnormal vehicle-mounted network traffic data segment. The last vehicle-mounted network flow data segment adjacent to the candidate abnormal vehicle-mounted network flow data segment is defined as a first vehicle-mounted network flow data segment, and the next vehicle-mounted network flow data segment adjacent to the candidate abnormal vehicle-mounted network flow data segment is defined as a second vehicle-mounted network flow data segment.
The method comprises the steps of obtaining first network flow data fluctuation degrees of first vehicle-mounted network flow data segments, wherein the first network flow data fluctuation degrees represent fluctuation conditions of vehicle-mounted network flow data of the first vehicle-mounted network flow data segments, and the larger the first network flow data fluctuation degrees are, the more serious the vehicle-mounted network flow data of the first vehicle-mounted network flow data segments are. In a specific embodiment, the absolute value of the difference value of the numerical value of any two adjacent vehicle-mounted network flow data in the first vehicle-mounted network flow data segment is obtained, so that a plurality of absolute value of the difference value are obtained, and then the average value of all the obtained absolute value of the difference value is calculated, wherein the average value is the fluctuation degree of the first network flow data.
Similarly, a second network flow data fluctuation degree of the second vehicle-mounted network flow data section is obtained, the second network flow data fluctuation degree represents the fluctuation condition of the vehicle-mounted network flow data of the second vehicle-mounted network flow data section, and the larger the second network flow data fluctuation degree is, the more serious the vehicle-mounted network flow data of the second vehicle-mounted network flow data section is. In a specific embodiment, the absolute value of the difference value of the numerical value of any two adjacent vehicle-mounted network flow data in the second vehicle-mounted network flow data segment is obtained, so that a plurality of absolute value of the difference value are obtained, and then the average value of all the obtained absolute value of the difference value is calculated, wherein the average value is the fluctuation degree of the second network flow data.
It should be understood that, as other embodiments, the first network traffic data fluctuation degree and the second network traffic data fluctuation degree may also be represented by other indexes for representing the data fluctuation situation, such as the variance of the vehicle-mounted network traffic data in the corresponding data segment, or the calculation manner of the network traffic data fluctuation indexes.
The second anomaly index obtaining unit 302 is configured to obtain a data anomaly index of the candidate anomaly vehicle-mounted network traffic data segment according to the network traffic data fluctuation index of the candidate anomaly vehicle-mounted network traffic data segment, the quantity of vehicle-mounted network traffic data in the candidate anomaly vehicle-mounted network traffic data segment, the first network traffic data fluctuation degree and the second network traffic data fluctuation degree.
From the above analysis, it can be known that the network traffic data fluctuation index of the candidate abnormal vehicle-mounted network traffic data segment characterizes the fluctuation condition of the network traffic data of the candidate abnormal vehicle-mounted network traffic data segment, and the more serious the fluctuation is, the more abnormal the network traffic data in the candidate abnormal vehicle-mounted network traffic data segment is, therefore, the data abnormality index of the candidate abnormal vehicle-mounted network traffic data segment and the network traffic data fluctuation index of the candidate abnormal vehicle-mounted network traffic data segment are in positive correlation. Because the number of the vehicle-mounted network traffic data in the candidate abnormal vehicle-mounted network traffic data segment reflects the data length, namely the data duration, of the candidate abnormal vehicle-mounted network traffic data segment, and the data abnormal duration is shorter when the data is interfered by signals or in communication conflict, the more the number of the vehicle-mounted network traffic data in the candidate abnormal vehicle-mounted network traffic data segment is, the more abnormal the network traffic data in the candidate abnormal vehicle-mounted network traffic data segment is, and the less the influence of the signal interference or the communication conflict is possible; accordingly, the smaller the number of the vehicle-mounted network traffic data in the candidate abnormal vehicle-mounted network traffic data segment is, the more normal the network traffic data in the candidate abnormal vehicle-mounted network traffic data segment is, and the greater the possibility of signal interference or communication conflict is, so that the data abnormal index and the number of the vehicle-mounted network traffic data in the candidate abnormal vehicle-mounted network traffic data segment are in positive correlation.
Since the fluctuation degree of the first network traffic data and the fluctuation degree of the second network traffic data respectively represent the fluctuation condition of the network traffic data of the last vehicle-mounted network traffic data section and the next vehicle-mounted network traffic data section adjacent to the candidate abnormal vehicle-mounted network traffic data section, the larger the fluctuation degree of the first network traffic data and the fluctuation degree of the second network traffic data are, the smaller the fluctuation condition of the first network traffic data section and the fluctuation condition of the candidate abnormal vehicle-mounted network traffic data section are, the higher the possibility that the network traffic data of the last vehicle-mounted network traffic data section and the next vehicle-mounted network traffic data section are interfered by signals or collide with each other is, and the more the last vehicle-mounted network traffic data section and the next vehicle-mounted network traffic data section are relatively not abnormal, so that the data abnormal indexes are in an anti-correlation relation with the fluctuation degree of the first network traffic data and the fluctuation degree of the second network traffic data.
The specific calculation mode for realizing the positive correlation and the negative correlation is set according to the actual needs, for example: the positive correlation may be addition, multiplication, etc., and the inverse correlation may be subtraction, division, etc. In a specific embodiment, calculating a product of a network traffic data fluctuation index of the candidate abnormal vehicle-mounted network traffic data segment and the number of vehicle-mounted network traffic data in the candidate abnormal vehicle-mounted network traffic data segment as a first product; calculating the product of the fluctuation degree of the first network flow data and the fluctuation degree of the second network flow data as a second product; and finally, calculating and normalizing the ratio of the first product to the second product, wherein the obtained result is a data anomaly index of the candidate abnormal vehicle-mounted network flow data segment.
Through the process, the data abnormality index of each abnormal vehicle-mounted network flow data segment can be obtained.
The failure probability obtaining module 104 is configured to obtain the failure probability of the vehicle-mounted network node of each abnormal vehicle-mounted network flow data segment according to the difference condition of the flow data of each vehicle-mounted network node in the corresponding period of time, the number of abnormal vehicle-mounted network nodes and the data abnormality index. The difference condition of the flow data of each vehicle-mounted network node in each abnormal vehicle-mounted network flow data segment in the corresponding time period, the number of the abnormal vehicle-mounted network nodes and the corresponding data abnormality indexes are all related to the abnormality condition of each corresponding abnormal vehicle-mounted network flow data segment, and the more abnormal is the higher the possibility of the vehicle-mounted network node fault of the corresponding abnormal vehicle-mounted network flow data segment, the three parameters can be fused, so that the possibility of the vehicle-mounted network node fault of the abnormal vehicle-mounted network flow data segment can be obtained.
In a specific embodiment, as shown in fig. 6, the failure possibility acquiring module 104 includes a first data feature acquiring unit 401, a second data feature acquiring unit 402, and a third data feature acquiring unit 403.
The first data feature obtaining unit 401 is configured to obtain local network traffic data features of each vehicle-mounted network node in a corresponding period of the candidate abnormal vehicle-mounted network traffic data segment, where the local network traffic data features are used to characterize an overall situation of network traffic data of the vehicle-mounted network node in the corresponding period of the candidate abnormal vehicle-mounted network traffic data segment. It should be understood that the corresponding period of the candidate abnormal vehicle network traffic data segment includes a plurality of sampling periods, each vehicle-mounted network node corresponds to one network traffic data in each sampling period of the corresponding period of the candidate abnormal vehicle network traffic data segment, and the plurality of sampling periods correspond to the plurality of network traffic data, so that for any vehicle-mounted network node, an average value of all network traffic data of the vehicle-mounted network node in the corresponding period of the candidate abnormal vehicle network traffic data segment is obtained as a local network traffic data feature of the vehicle-mounted network node in the corresponding period of the candidate abnormal vehicle network traffic data segment, thereby obtaining a local network traffic data feature of each vehicle-mounted network node in the corresponding period of the candidate abnormal vehicle network traffic data segment. As another embodiment, the median, mode, and the like in the plurality of network traffic data may be used as the local network traffic data feature for characterizing the overall condition of the network traffic data of the vehicle-mounted network node in the corresponding period of the candidate abnormal vehicle-mounted network traffic data segment.
The first data feature obtaining unit 401 is further configured to obtain overall network traffic data features of each vehicle-mounted network node in an overall period corresponding to the vehicle-mounted network traffic data sequence, where the overall network traffic data features are used to characterize overall conditions of network traffic data of the vehicle-mounted network node in the overall period corresponding to the vehicle-mounted network traffic data sequence. It should be understood that the period corresponding to the vehicle-mounted network flow data sequence is defined as an overall period, each vehicle-mounted network node corresponds to one network flow data in each sampling period in the overall period, and a plurality of sampling periods correspond to a plurality of network flow data. As another embodiment, the median, mode, and the like in the plurality of network traffic data may be used as the overall network traffic data feature for characterizing the overall situation of the network traffic data of the vehicle-mounted network node in the overall period corresponding to the vehicle-mounted network traffic data sequence.
The second data feature obtaining unit 402 is configured to screen and obtain, according to the degree of difference between the local network traffic data feature and the overall network traffic data feature of each vehicle-mounted network node in the corresponding period of the candidate abnormal vehicle-mounted network traffic data segment, the number of vehicle-mounted network nodes with possibility of abnormality corresponding to the candidate abnormal vehicle-mounted network traffic data segment. The local network flow data characteristics reflect the overall situation of network flow data of the vehicle-mounted network node in the corresponding time period of the candidate abnormal vehicle-mounted network flow data section, the overall network flow data characteristics reflect the overall situation of network flow data of the vehicle-mounted network node in the corresponding overall time period of the vehicle-mounted network flow data sequence, and normally, the two characteristics are not greatly different, the more abnormal the greater the degree of difference between the two characteristics, so that the number of the vehicle-mounted network nodes with abnormal possibility can be obtained according to the degree of difference between the two characteristics.
In a specific embodiment, the second data characteristic acquisition unit 402 comprises a quantity acquisition subunit. The quantity acquisition subunit is used for determining the vehicle-mounted network nodes with the difference degree larger than a preset threshold value as the vehicle-mounted network nodes with the possibility of abnormality, and acquiring the quantity of the vehicle-mounted network nodes with the possibility of abnormality corresponding to the candidate abnormal vehicle-mounted network flow data segments. Wherein the degree of difference is the absolute value of the difference between the local network traffic data characteristic and the global network traffic data characteristic. The preset threshold is set by actual needs, and as a specific implementation manner, the preset threshold is set to be 0.1 times of the overall network traffic data characteristic. The difference degree is larger than a preset threshold value, the difference degree is larger, the vehicle-mounted network nodes with the difference degree larger than the preset threshold value are determined to be the vehicle-mounted network nodes with the possibility of abnormality, and therefore the number of the vehicle-mounted network nodes with the possibility of abnormality corresponding to the candidate abnormal vehicle-mounted network flow data segments is obtained. It should be appreciated that the preset threshold may also be a fixed set value.
The third data feature obtaining unit 403 is configured to obtain a failure probability of the vehicle-mounted network node of the candidate abnormal vehicle-mounted network traffic data segment according to the data abnormality index of the candidate abnormal vehicle-mounted network traffic data segment, the number of vehicle-mounted network nodes with possibility of abnormality, and the fluctuation index of the degree of difference. The higher the data abnormality index of the candidate abnormal vehicle-mounted network flow data segment is, the more abnormal the network flow data is, and the higher the possibility of vehicle-mounted network node faults is, so that the possibility of vehicle-mounted network node faults and the data abnormality index of the candidate abnormal vehicle-mounted network flow data segment are in positive correlation. The greater the number of in-vehicle network nodes for which there is a possibility of abnormality, the more abnormal the network traffic data, and the higher the possibility of in-vehicle network node failure, and therefore the in-vehicle network node failure possibility has a positive correlation with the number of in-vehicle network nodes for which there is a possibility of abnormality.
And setting a fluctuation index of the difference degree, wherein the fluctuation index is used for representing the fluctuation degree of the difference degree of all vehicle-mounted network nodes corresponding to the candidate abnormal vehicle-mounted network flow data segment, and the difference degree is the difference degree between the local network flow data characteristic and the whole network flow data characteristic. The greater the fluctuation degree of the difference degree is, the more unstable the difference degree of all vehicle-mounted network nodes corresponding to the candidate abnormal vehicle-mounted network flow data segments is, the more abnormal the network flow data is, the greater the possibility that the candidate abnormal vehicle-mounted network flow data segments are influenced by the damage of the vehicle-mounted network nodes is, and the higher the possibility of the failure of the vehicle-mounted network nodes is, so that the possibility of the failure of the vehicle-mounted network nodes is in positive correlation with the fluctuation index of the difference degree.
In one embodiment, the calculation formula of the variation degree fluctuation index is as follows:
Wherein, A degree of difference fluctuation index indicating a v-th abnormal vehicle-mounted network flow data segment,Represents the degree of difference of the kth on-vehicle network node in the corresponding period of the kth abnormal on-vehicle network flow data segment, N represents the number of on-vehicle network nodes,And the average value of the difference degree of all vehicle-mounted network nodes in the corresponding time period of the v-th abnormal vehicle-mounted network flow data segment is represented.The absolute value of the difference between the difference degree of each vehicle-mounted network node in the v-th abnormal vehicle-mounted network flow data segment and the average value of the difference degrees is represented, and the larger the absolute value is, the larger the difference of the change degree of each vehicle-mounted network node is, and the greater the possibility that the v-th abnormal vehicle-mounted network flow data segment is affected by the damage of the vehicle-mounted network node is. The difference degree fluctuation index can be obtained by means of the absolute value of the difference between the difference degree of each vehicle-mounted network node and the average value of the difference degree and then averaging.
As other embodiments, other manners may be used, such as: and (5) obtaining the absolute value of the difference value of each two adjacent difference degrees, and then averaging to obtain the fluctuation index of the difference degrees.
In a specific embodiment, the calculation formula of the failure probability of the vehicle network node is:
Wherein, Representing the possibility of failure of the vehicle network node of the v-th abnormal vehicle network traffic data segment,Representing the number of on-board network nodes corresponding to the v-th abnormal on-board network traffic data segment for which there is a possibility of abnormality,The number of on-board network nodes representing the possibility of an abnormality,A data abnormality index indicating a v-th abnormal in-vehicle network flow data segment,The normalized function is represented, and the normalized data interval is [0,1].
By the method, the possibility of failure of the vehicle-mounted network node of each abnormal vehicle-mounted network flow data segment can be obtained.
The data uploading module 105 is configured to obtain failure information of the vehicle-mounted network node according to the failure probability of the vehicle-mounted network node, and upload the failure information of the vehicle-mounted network node to the cloud server. After the failure probability of the vehicle-mounted network node of each abnormal vehicle-mounted network flow data segment is obtained, the vehicle-mounted network node failure information can be determined and obtained according to the failure probability of the vehicle-mounted network node, and the vehicle-mounted network node failure information is uploaded to the cloud server.
In a specific embodiment, obtaining the failure information of the on-board network node according to the failure possibility of the on-board network node includes: a preset fault threshold is set, the magnitude of the preset fault threshold is set by the actual judgment, the more strict the judgment is, the smaller the preset fault threshold can be set, and the embodiment sets the preset fault threshold to 0.7.
Determining an abnormal vehicle-mounted network flow data segment with the possibility of the vehicle-mounted network node fault being greater than a preset fault threshold value as a fault vehicle-mounted network flow data segment, and determining a period corresponding to the determined fault vehicle-mounted network flow data segment as a fault period, so as to obtain vehicle-mounted network node fault information, wherein the vehicle-mounted network node fault information comprises the fault vehicle-mounted network flow data segment and the fault period. It should be appreciated that when a faulty on-board network traffic data segment is obtained, it is also determined that the cause of the abnormal network traffic is caused by the on-board network node fault.
The vehicle-mounted network node fault information forms a DBC file, and the embodiment can be uploaded to a cloud server through a data transmission module (such as LTE connection) on a vehicle.
In the following, after the cloud server receives the DBC file, the corresponding parsing tool or algorithm may be used to parse the network information in the file. According to the analyzed network information, the cloud server can analyze the vehicle-mounted network nodes, the messages and the signals related to the abnormal data, and is helpful for determining problems of the vehicle-mounted network nodes, such as communication faults, hardware faults and the like. Once the problem of the vehicle-mounted network node is determined, an alarm can be triggered to inform related personnel or systems, and corresponding measures are taken to repair or adjust so as to ensure the normal operation of the vehicle networking.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application and are intended to be included within the scope of the application.
Claims (8)
1. An on-vehicle network intelligent monitoring system based on cloud computing, which is characterized by comprising:
the vehicle-mounted network flow data acquisition module is used for acquiring at least two vehicle-mounted network flow data segments obtained by segmenting a vehicle-mounted network flow data sequence, wherein the vehicle-mounted network flow data sequence comprises vehicle-mounted network flow data with a plurality of sampling periods;
the abnormality detection module is used for acquiring abnormal vehicle-mounted network flow data segments from the vehicle-mounted network flow data segments according to the fluctuation condition of the network flow data;
The data anomaly index acquisition module is used for acquiring data anomaly indexes of each abnormal vehicle-mounted network flow data segment according to the network flow data fluctuation condition of each abnormal vehicle-mounted network flow data segment and two vehicle-mounted network flow data segments adjacent to the abnormal vehicle-mounted network flow data segment;
the fault possibility acquisition module is used for acquiring the fault possibility of the vehicle-mounted network nodes of each abnormal vehicle-mounted network flow data segment according to the difference condition of the flow data of each vehicle-mounted network node in the corresponding time period, the number of the abnormal vehicle-mounted network nodes and the data abnormal index;
The data uploading module is used for obtaining the failure information of the vehicle-mounted network node according to the failure possibility of the vehicle-mounted network node and uploading the failure information of the vehicle-mounted network node to the cloud server;
The failure possibility acquisition module includes:
The first data feature acquisition unit is used for acquiring local network flow data features of each vehicle-mounted network node in a corresponding period of the candidate abnormal vehicle-mounted network flow data segment, and acquiring overall network flow data features of each vehicle-mounted network node in an overall period corresponding to the vehicle-mounted network flow data sequence, wherein the local network flow data features are used for representing overall conditions of network flow data of the vehicle-mounted network node in the corresponding period of the candidate abnormal vehicle-mounted network flow data segment, and the overall network flow data features are used for representing overall conditions of network flow data of the vehicle-mounted network node in the overall period corresponding to the vehicle-mounted network flow data sequence; the candidate abnormal vehicle-mounted network flow data segment is any abnormal vehicle-mounted network flow data segment;
The second data characteristic acquisition unit is used for screening and obtaining the number of the vehicle-mounted network nodes with abnormal possibility corresponding to the candidate abnormal vehicle-mounted network flow data segments according to the difference degree between the local network flow data characteristic and the whole network flow data characteristic of each vehicle-mounted network node in the corresponding time period of the candidate abnormal vehicle-mounted network flow data segments;
The third data characteristic obtaining unit is used for obtaining the failure possibility of the vehicle-mounted network node of the candidate abnormal vehicle-mounted network flow data segment according to the data abnormality index of the candidate abnormal vehicle-mounted network flow data segment, the number of vehicle-mounted network nodes with the abnormality possibility and the fluctuation index of the difference degree, wherein the failure possibility of the vehicle-mounted network node is in positive correlation with the data abnormality index of the candidate abnormal vehicle-mounted network flow data segment, the number of the vehicle-mounted network nodes with the abnormality possibility and the overall difference degree; the difference degree fluctuation index is used for representing fluctuation degrees of the difference degrees of all vehicle-mounted network nodes corresponding to the candidate abnormal vehicle-mounted network flow data segments;
The calculation formula of the failure possibility of the vehicle-mounted network node is as follows:
Wherein P v represents the possibility of failure of the vehicle-mounted network node of the v-th abnormal vehicle-mounted network traffic data segment, C v represents the number of vehicle-mounted network nodes with possibility of abnormality corresponding to the v-th abnormal vehicle-mounted network traffic data segment, N represents the number of vehicle-mounted network nodes, Z v represents the data abnormality index of the v-th abnormal vehicle-mounted network traffic data segment, a v represents the fluctuation index of the degree of difference of the v-th abnormal vehicle-mounted network traffic data segment, and softmax represents the normalization function.
2. The cloud computing-based on-vehicle network intelligent monitoring system of claim 1, wherein the anomaly detection module comprises:
the system comprises a first anomaly detection unit, a second anomaly detection unit and a first anomaly detection unit, wherein the first anomaly detection unit is used for acquiring network flow data fluctuation indexes of vehicle-mounted network flow data in each vehicle-mounted network flow data segment, and the network flow data fluctuation indexes are used for representing the fluctuation degree of the network flow data of the vehicle-mounted network flow data in the vehicle-mounted network flow data segment;
And the second abnormality detection unit is used for determining the vehicle-mounted network flow data segment which is larger than or equal to the preset fluctuation index threshold value as an abnormal vehicle-mounted network flow data segment.
3. The cloud computing-based vehicle-mounted network intelligent monitoring system according to claim 2, wherein a calculation formula of the network flow data fluctuation index is as follows:
Wherein B v represents a network flow data fluctuation index of a v-th vehicle-mounted network flow data segment, N v represents the number of vehicle-mounted network flow data in the v-th vehicle-mounted network flow data segment, Q v,i represents the number of i-th vehicle-mounted network flow data in the v-th vehicle-mounted network flow data segment, Average values of the in-vehicle network flow data representing the v-th in-vehicle network flow data segment, Q v,max and Q v,min represent maximum and minimum values of the in-vehicle network flow data of the v-th in-vehicle network flow data segment,The average value of the numerical values of all the vehicle-mounted network flow data in the vehicle-mounted network flow data sequence is represented, exp represents an exponential function based on a natural constant e, and norm represents a normalization function.
4. The cloud computing-based on-vehicle network intelligent monitoring system according to claim 1, wherein the data anomaly index acquisition module comprises:
A first abnormality index obtaining unit configured to obtain a first network traffic data fluctuation degree of a last vehicle-mounted network traffic data segment adjacent to the candidate abnormal vehicle-mounted network traffic data segment, and a second network traffic data fluctuation degree of a next vehicle-mounted network traffic data segment adjacent to the candidate abnormal vehicle-mounted network traffic data segment, respectively; the candidate abnormal vehicle-mounted network flow data segment is any abnormal vehicle-mounted network flow data segment;
The second abnormal index obtaining unit is configured to obtain a data abnormal index of the candidate abnormal vehicle-mounted network traffic data segment according to the network traffic data fluctuation index of the candidate abnormal vehicle-mounted network traffic data segment, the quantity of vehicle-mounted network traffic data in the candidate abnormal vehicle-mounted network traffic data segment, the first network traffic data fluctuation degree and the second network traffic data fluctuation degree, where the data abnormal index is in a positive correlation with the network traffic data fluctuation index of the candidate abnormal vehicle-mounted network traffic data segment and the quantity of vehicle-mounted network traffic data in the candidate abnormal vehicle-mounted network traffic data segment, and is in an inverse correlation with the first network traffic data fluctuation degree and the second network traffic data fluctuation degree.
5. The cloud computing-based on-vehicle network intelligent monitoring system of claim 4, wherein the process of obtaining the fluctuation degree of the first network traffic data comprises:
Acquiring the absolute value of the difference value of the numerical value of any two adjacent vehicle-mounted network flow data in the last vehicle-mounted network flow data segment, and calculating the average value of all the absolute values of the difference values corresponding to the last vehicle-mounted network flow data segment to obtain the fluctuation degree of the first network flow data;
the process for acquiring the fluctuation degree of the second network flow data comprises the following steps:
And obtaining the absolute value of the difference value of the numerical value of any two adjacent vehicle-mounted network flow data in the next vehicle-mounted network flow data segment, and calculating the average value of all the absolute values of the difference values corresponding to the next vehicle-mounted network flow data segment to obtain the fluctuation degree of the second network flow data.
6. The cloud computing-based on-vehicle network intelligent monitoring system according to claim 1, wherein the second data feature acquisition unit includes:
The quantity acquisition subunit is used for determining the vehicle-mounted network nodes with the difference degrees larger than a preset threshold value as vehicle-mounted network nodes with the possibility of abnormality, and acquiring the quantity of the vehicle-mounted network nodes with the possibility of abnormality corresponding to the candidate abnormal vehicle-mounted network flow data segments.
7. The cloud computing-based vehicle-mounted network intelligent monitoring system according to claim 1, wherein a calculation formula of the difference degree fluctuation index is as follows:
Wherein a v represents a variation index of the degree of difference of the v-th abnormal vehicle-mounted network flow data segment, D v (k) represents the degree of difference of the k-th vehicle-mounted network node in the corresponding period of the v-th abnormal vehicle-mounted network flow data segment, N represents the number of vehicle-mounted network nodes, and D v represents an average value of the degrees of difference of all vehicle-mounted network nodes in the corresponding period of the v-th abnormal vehicle-mounted network flow data segment.
8. The cloud computing-based on-vehicle network intelligent monitoring system of claim 1, wherein obtaining on-vehicle network node failure information from a likelihood of on-vehicle network node failure comprises:
Determining an abnormal vehicle-mounted network flow data segment with the possibility of the vehicle-mounted network node fault being larger than a preset fault threshold value as a fault vehicle-mounted network flow data segment, and determining a time period corresponding to the fault vehicle-mounted network flow data segment as a fault time period, wherein the vehicle-mounted network node fault information comprises the fault vehicle-mounted network flow data segment and the fault time period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410841602.3A CN118400299B (en) | 2024-06-27 | 2024-06-27 | Vehicle-mounted network intelligent monitoring system based on cloud computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410841602.3A CN118400299B (en) | 2024-06-27 | 2024-06-27 | Vehicle-mounted network intelligent monitoring system based on cloud computing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118400299A CN118400299A (en) | 2024-07-26 |
| CN118400299B true CN118400299B (en) | 2024-09-06 |
Family
ID=92001640
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410841602.3A Active CN118400299B (en) | 2024-06-27 | 2024-06-27 | Vehicle-mounted network intelligent monitoring system based on cloud computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118400299B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119363615A (en) * | 2024-12-24 | 2025-01-24 | 睿思网盾(北京)科技有限公司 | Network flow real-time monitoring method and system based on artificial intelligence |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115454778A (en) * | 2022-09-27 | 2022-12-09 | 浙江大学 | Intelligent monitoring system for abnormal time sequence indexes in large-scale cloud network environment |
| CN117349778A (en) * | 2023-12-04 | 2024-01-05 | 湖南蓝绿光电科技有限公司 | Online real-time monitoring system of consumer based on thing networking |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117411811B (en) * | 2023-12-15 | 2024-02-23 | 山西思极科技有限公司 | Intelligent fault monitoring method for power communication equipment |
| CN117439827B (en) * | 2023-12-22 | 2024-03-08 | 中国人民解放军陆军步兵学院 | Network flow big data analysis method |
| CN117805542B (en) * | 2024-03-01 | 2024-05-14 | 张家港市升恒机械设备制造有限公司 | Mining flameproof intrinsically safe frequency converter operation monitoring system |
| CN118051858B (en) * | 2024-04-15 | 2024-07-12 | 山东兰蝶节能环保科技有限公司 | Intelligent electricity saving method and system based on abnormal electricity consumption data |
-
2024
- 2024-06-27 CN CN202410841602.3A patent/CN118400299B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115454778A (en) * | 2022-09-27 | 2022-12-09 | 浙江大学 | Intelligent monitoring system for abnormal time sequence indexes in large-scale cloud network environment |
| CN117349778A (en) * | 2023-12-04 | 2024-01-05 | 湖南蓝绿光电科技有限公司 | Online real-time monitoring system of consumer based on thing networking |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118400299A (en) | 2024-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP4037286B1 (en) | Method and apparatus for predicting fault of optical module | |
| CN118400299B (en) | Vehicle-mounted network intelligent monitoring system based on cloud computing | |
| US11038587B2 (en) | Method and apparatus for locating fault cause, and storage medium | |
| US9524223B2 (en) | Performance metrics of a computer system | |
| EP3575960B1 (en) | System upgrade assessment method based on system parameter correlation coefficients | |
| EP4131094A1 (en) | Prediction method and apparatus, readable medium, and electronic device | |
| CN113438110B (en) | Cluster performance evaluation method, device, equipment and storage medium | |
| CN114095965A (en) | Index detection model obtaining and fault positioning method, device, equipment and storage medium | |
| EP4096232B1 (en) | Attack detection method, attack detection system and program | |
| CN114244751B (en) | Wireless sensor network anomaly detection method and system | |
| CN113341813A (en) | Urban gas medium-low pressure pipe network detection method and system | |
| US9589394B2 (en) | Determining the source of a ground offset in a controller area network | |
| US20130325203A1 (en) | Methods and systems for monitoring a vehicle for faults | |
| CN114356621A (en) | Method and device for bus exit based on information entropy analysis | |
| CN112799911A (en) | Node health state detection method, device, equipment and storage medium | |
| CN115114124A (en) | Host risk assessment method and assessment device | |
| CN114157486B (en) | Communication flow data abnormity detection method and device, electronic equipment and storage medium | |
| US11228606B2 (en) | Graph-based sensor ranking | |
| CN114429240A (en) | Method and device for monitoring running state of highway equipment | |
| CN115372915B (en) | Method for estimating maximum detection distance blind area on line caused by radar performance degradation | |
| US20240388552A1 (en) | Detection apparatus, detection method, and detection program | |
| CN117527545A (en) | Abnormality monitoring method and device for vehicle-mounted Ethernet, electronic equipment and storage medium | |
| CN118980833A (en) | Fault detection and recovery method, system, device and medium for speed sensor | |
| CN112448942A (en) | Method for identifying a deterioration in a network | |
| CN115630265A (en) | Track anomaly detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |