Anomaly prediction method and system for automobile domain control system

Abstract

The present application relates to the field of data processing, and in particular to an abnormality prediction method and system for automobile domain control systems, including: obtaining a collection strategy in the current monitoring cycle based on the running state of the automobile and the use state of the domain control system in the current monitoring cycle; collecting control parameters of the domain control system in the current monitoring cycle according to the acquired collection strategy; obtaining the interaction relationship in the domain control system from the active directory based on the acquired control parameters; calculating the abnormality prediction index in the current monitoring cycle based on the control parameters of the domain control system collected in the current monitoring cycle and the interaction relationship in the domain control system; obtaining the abnormality prediction comprehensive index in the current monitoring cycle through the abnormality prediction index in the current monitoring cycle and the abnormality prediction index in the previous monitoring cycle to indicate the abnormal situation. The present application can predict the abnormality of the automobile domain control system, avoid various data leakages of the automobile, and ensure the safety of the automobile.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to an abnormality prediction method and system for an automobile domain control system. Background Art

[0002] Under the trend of the new four modernizations in the automotive industry, the electronic and electrical architecture of vehicles has changed from decentralized to centralized in the process of automotive intelligence, which has given rise to the development of automotive domain control systems. The intelligent networking of automobiles has brought about a large increase in information flow, and the number of electronic control units (ECUs) has also increased. The automotive electronic and electrical (EE) architecture has also been continuously upgraded, gradually evolving from a distributed architecture-domain centralized architecture-central computing architecture, and control functions have also been rapidly centralized to the automotive domain control system, resulting in a large amount of data and a variety of data processed by the domain controller (DCU) of the automotive domain control system.

[0003] As more and more data is exchanged between cars and the outside world, the possibility of external attacks on the car domain control system is rapidly increasing. Once the car domain control system is attacked, the car domain control system will be abnormal, which may cause various car data leakages and even lead to the leakage of privacy data. In addition, since the control function is concentrated in the domain controller (DCU) of the car domain control system, once the car domain control system is attacked, it is very easy to affect the domain controller (DCU) to control the electronic control unit (ECU) of each subsystem of the car, thereby affecting the normal operation of each subsystem of the car (for example: powertrain system, auxiliary driving system, etc.), thus affecting the safety of the car.

[0004] Therefore, how to predict the anomalies of the automobile domain control system, avoid various data leakages of the automobile, and ensure the safety of the automobile is a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0005] The present application provides an abnormality prediction method and system for an automobile domain control system, so as to predict abnormalities of the automobile domain control system, avoid leakage of various automobile data, and ensure the safety of the automobile.

[0006] In order to solve the above technical problems, this application provides the following technical solutions:

[0007] A method for predicting anomalies in a domain control system of an automobile comprises the following steps: step S110, obtaining a collection strategy in the current monitoring cycle according to the running state of the automobile and the use state of the domain control system in the current monitoring cycle; step S120, collecting control parameters of the domain control system in the current monitoring cycle according to the obtained collection strategy; step S130, obtaining interaction relationships in the domain control system from an active directory according to the obtained control parameters; step S140, calculating anomaly prediction indicators in the current monitoring cycle according to the control parameters of the domain control system collected in the current monitoring cycle and the interaction relationships in the domain control system; step S150, obtaining anomaly prediction comprehensive indicators in the current monitoring cycle through the anomaly prediction indicators in the current monitoring cycle and the anomaly prediction indicators in the previous monitoring cycle to indicate an abnormal situation.

[0008] In the above-mentioned abnormality prediction method for automobile domain control system, preferably, step S110 includes the following sub-steps: after the current monitoring cycle starts, the running status of the automobile, the usage status of the domain controller of the domain control system, and the usage status of each electronic control unit of each group of electronic control systems of the domain control system are collected; according to the running status of the automobile, the usage status of the domain control system, and the usage status of each electronic control unit of each group of electronic control systems of the domain control system, the collection strategy acquisition index within the current monitoring cycle is calculated; according to the collection strategy acquisition index within the current monitoring cycle, the collection strategy database is traversed, and the collection strategy whose collection strategy identifier is closest to the collection strategy acquisition index within the current monitoring cycle is used as the collection strategy within the current monitoring cycle.

[0009] In the abnormality prediction method for an automobile domain control system as described above, preferably, step S120 includes the following sub-steps: collecting control parameters of the domain controller according to the collection method for the domain controller specified in the collection strategy, and integrating the control parameters of the domain controller obtained in the current monitoring cycle into the domain controller control parameter set; collecting control parameters of the electronic control units in the corresponding electronic control systems according to the collection method for each group of electronic control systems specified in the collection strategy, and integrating the control parameters of the electronic control units in each group of electronic control systems obtained in the current monitoring cycle into the electronic control unit control parameter set.

[0010] As described above, the abnormality prediction method for the automobile domain control system, wherein preferably, step S130 includes the following sub-steps: obtaining from the active directory based on the obtained control parameters the interaction relationship between the domain controller that generates the control parameters and each group of electronic control systems and the interaction relationship between each group of electronic control systems and other groups of electronic control systems, and integrating the interaction relationships into an interaction relationship set.

[0011] As described above, in the abnormality prediction method for the automobile domain control system, preferably, step S140 includes the following sub-steps: calculating the abnormality prediction index within the current monitoring period based on the domain controller control parameter set, the electronic control unit control parameter set and the interaction relationship set.

[0012] An abnormality prediction system for a domain control system of an automobile comprises: a collection strategy acquisition unit, a control parameter collection unit, an interaction relationship acquisition unit, a prediction index calculation unit and a prediction index synthesis unit; the collection strategy acquisition unit acquires the collection strategy in the current monitoring cycle according to the running state of the automobile and the use state of the domain control system in the current monitoring cycle; the control parameter collection unit collects the control parameters of the domain control system in the current monitoring cycle according to the acquired collection strategy; the interaction relationship acquisition unit acquires the interaction relationship in the domain control system from an active directory according to the acquired control parameters; the prediction index calculation unit calculates the abnormality prediction index in the current monitoring cycle according to the control parameters of the domain control system collected in the current monitoring cycle and the interaction relationship in the domain control system; the prediction index synthesis unit obtains the abnormality prediction synthesis index in the current monitoring cycle through the abnormality prediction index in the current monitoring cycle and the abnormality prediction index in the previous monitoring cycle to indicate the abnormal situation.

[0013] The abnormality prediction system for automobile domain control system as described above, wherein, preferably, after the start of the current monitoring cycle, the collection strategy acquisition unit collects the operating status of the automobile, the usage status of the domain controller of the domain control system, and the usage status of each electronic control unit of each group of electronic control systems of the domain control system, and calculates the collection strategy acquisition index within the current monitoring cycle according to the operating status of the automobile, the usage status of the domain control system, and the usage status of each electronic control unit of each group of electronic control systems of the domain control system; the collection strategy acquisition unit traverses the collection strategy database according to the collection strategy acquisition index within the current monitoring cycle, and uses the collection strategy whose collection strategy identifier is closest to the collection strategy acquisition index within the current monitoring cycle as the collection strategy within the current monitoring cycle.

[0014] In the abnormality prediction system for automobile domain control system as described above, preferably, the control parameter acquisition unit acquires the control parameters of the domain controller according to the acquisition method for the domain controller specified in the acquisition strategy, and integrates the control parameters of the domain controller obtained in the current monitoring cycle into the domain controller control parameter set; the control parameter acquisition unit acquires the control parameters of the electronic control units in the corresponding electronic control systems according to the acquisition method for each group of electronic control systems specified in the acquisition strategy, and integrates the control parameters of the electronic control units in each group of electronic control systems obtained in the current monitoring cycle into the electronic control unit control parameter set.

[0015] As described above, in the abnormality prediction system for automobile domain control systems, preferably, the interaction relationship acquisition unit obtains from the active directory based on the obtained control parameters the interaction relationship between the domain controller that generates the control parameters and each group of electronic control systems, as well as the interaction relationship between each group of electronic control systems and other groups of electronic control systems, and integrates the interaction relationships into an interaction relationship set.

[0016] As described above, in the abnormality prediction system for automobile domain control system, preferably, the prediction index calculation unit calculates the abnormality prediction index in the current monitoring period based on the domain controller control parameter set, the electronic control unit control parameter set and the interaction relationship set.

[0017] Compared with the above background technology, the present application can predict abnormalities of the automobile domain control system, prevent the domain controller (DCU) of the automobile domain control system from being attacked, prevent the leakage of various automobile data (even private data), and ensure the safety of the automobile. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0019] Figure 1 is a flow chart of an abnormality prediction method for an automobile domain control system provided in an embodiment of the present application;

[0020] Figure 2 is a schematic diagram of a vehicle domain control system provided by an embodiment of the present application;

[0021] Figure 3 It is a schematic diagram of an abnormality prediction system for an automobile domain control system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. In addition, spatial relationship terms such as "upper", "lower", "front", "back", "left" and "right" are used to facilitate the description to explain the positional relationship between two components. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.

[0023] Embodiment 1

[0024] like Figure 1As shown, the present application provides an abnormality prediction method for an automobile domain control system, comprising the following steps:

[0025] Step S110: obtaining a collection strategy in the current monitoring period according to the running state of the vehicle and the use state of the domain control system in the current monitoring period;

[0026] like Figure 2 As shown, the automobile domain control system 200 includes: a domain controller (DCU) 210 and multiple electronic control systems 220, each electronic control system 220 includes multiple electronic control units (ECU) 221, and the electronic control unit (ECU) 221 of each electronic control system 220 is used to control a subsystem of the automobile, such as: power transmission system, monitoring system, auxiliary driving system, etc.

[0027] The domain controller (DCU) 210 of the automobile domain control system 200 has different usage states, and in different usage states, the busyness of the domain controller (DCU) 210 is different; the electronic control unit (ECU) 221 of the automobile domain control system 200 also has different usage states, and in different usage states, the busyness of the electronic control unit (ECU) 221 is also different. The busyness of the domain controller (DCU) 210 and the electronic control unit (ECU) 221 will affect the number of control parameters generated by the domain controller (DCU) 210 and the electronic control unit (ECU) 221.

[0028] A car has different operating states, such as high-speed driving state, low-speed driving state, parked state with the engine not turned off, parked state with the engine turned off, etc.; and in different operating states, after the car domain control system 200 is attacked, the degree of impact on the car safety is different, for example: in the high-speed driving state, the impact of the car domain control system 200 being attacked on the car safety is greater, and in the parked state with the engine turned off, the impact of the car domain control system 200 being attacked on the car safety is less.

[0029] Therefore, after the current monitoring cycle begins, the operating status of the vehicle, the usage status of the domain controller (DCU) 210 of the domain control system 200, and the usage status of each electronic control unit (ECU) 221 of each group of electronic control systems 220 of the domain control system 200 are collected, and based on the operating status of the vehicle, the usage status of the domain controller (DCU) 210 of the domain control system 200, and the usage status of each electronic control unit (ECU) 221 of each group of electronic control systems 220 of the domain control system 200, the collection strategy acquisition indicators within the current monitoring cycle are calculated, for example: the collection strategy is the time interval for collecting control parameters, the number of collected control parameters, etc.

[0030] Specifically, according to the following formula:

[0031]

[0032] Calculate the acquisition strategy index Z within the current monitoring period t clt ; Among them, Y t is the running status of the car in the current monitoring period t; W1 is the index Z obtained by the car running status for the collection strategy clt The impact weight of SD t is the usage status of the domain controller (DCU) 210 in the current monitoring period t; α1 is the weight corresponding to the usage status of the domain controller (DCU) 210; SE ijt is the usage status of the jth electronic control unit (ECU) 221 of the i-th group of electronic control systems 220 in the current monitoring period t; μj is the weight corresponding to the use state of the j-th electronic control unit (ECU) 221; J is the number of electronic control units (ECUs) 221 in the i-th group of electronic control systems 220; β i is the weight corresponding to the use status of the i-th group of electronic control systems 220; I is the number of electronic control systems 220; α2 is the total weight corresponding to the use status of all electronic control systems 220; W2 is the acquisition index Z of the domain control system use status for the collection strategy clt The influence weight of .

[0033] Obtain indicator Z according to the collection strategy within the current monitoring period t clt Traverse the collection strategy database, compare its collection strategy identifier with the collection strategy acquisition index Z in the current monitoring period t clt The closest collection strategy is used as the collection strategy in the current monitoring cycle. The collection strategy database is pre-stored in the memory of the car. At this time, it is necessary to obtain the indicator Z according to the collection strategy. clt The acquisition strategy for the current monitoring cycle is obtained from the vehicle's memory.

[0034] Step S120: collecting control parameters of the domain control system in the current monitoring period according to the acquired collection strategy;

[0035] The control parameters of the domain controller (DCU) 210 are collected according to the collection method of the domain controller (DCU) 210 specified in the collection strategy. For example, the control parameters of the domain controller (DCU) 210 are collected according to the time interval T1, and the control parameters of the domain controller (DCU) 210 obtained in the current monitoring period t are integrated into the domain controller (DCU) control parameter set A = {A t1 , A t2 , …, A tN}, where A t1 is the first control parameter of the domain controller (DCU) 210 collected in the current monitoring period t, At2 is the second control parameter of the domain controller (DCU) 210 collected in the current monitoring period t, A tN is the Nth control parameter of the domain controller (DCU) 210 collected in the current monitoring period t, and N is the number of control parameters in the domain controller (DCU) control parameter set A. For example: memory occupancy, hard disk occupancy, CPU occupancy, temperature, memory change rate, hard disk change rate, CPU change rate, temperature change rate, etc.

[0036] The control parameters of the electronic control unit (ECU) 221 in the corresponding electronic control system 220 are collected according to the collection method for each group of electronic control systems 220 specified in the collection strategy, for example: according to the time interval T 2i Collect the control parameters of the electronic control unit (ECU) 221 in the i-th group of electronic control systems 220, and integrate the control parameters of the electronic control unit (ECU) 221 in each group of electronic control systems 220 obtained in the current monitoring period t into the electronic control unit (ECU) control parameter set B = {(B t11 , B t12 ,…)、(B t21 , B t22 ,…)、…、(B ti1 , B ti2 , …)}, where B t11 is the control parameter of the first electronic control unit (ECU) 221 in the first group of electronic control systems 220 collected in the current monitoring period t, B t12 is the control parameter of the second electronic control unit (ECU) 221 in the first group of electronic control systems 220 collected in the current monitoring period t, B t21 is the control parameter of the first electronic control unit (ECU) 221 in the second group of electronic control systems 220 collected in the current monitoring period t, B t22 is the control parameter of the second electronic control unit (ECU) 221 in the second group of electronic control systems 220 collected in the current monitoring period t, B ti1 is the control parameter of the first electronic control unit (ECU) 221 in the i-th group of electronic control systems 220 collected in the current monitoring period t, B ti2 It is the control parameter of the second electronic control unit (ECU) 221 in the i-th group of electronic control systems 220 collected in the current monitoring period t. For example: cruise control parameters, lighting control parameters, airbag control parameters, suspension control parameters, fuel heating control parameters, exhaust control parameters, brake control parameters, etc.

[0037] Step S130, obtaining the interaction relationship in the domain control system from the active directory according to the obtained control parameters;

[0038] The domain controller (DCU) 210 stores an active directory, which is a small database that records the attributes of various objects in the domain and the interaction relationships between the objects, so as to facilitate the unified management of the domain controller (DCU) 210. After obtaining the control parameters of the domain control system 200 in the current monitoring period, the interaction relationship between the domain controller (DCU) 210 that generates the above control parameters and each group of electronic control systems 220 and the interaction relationship between each group of electronic control systems 220 and other groups of electronic control systems 220 are obtained from the active directory according to the obtained control parameters, and these interaction relationships are integrated into an interaction relationship set JH = {JH i , JH (i，i‘)}, where JH i is the interaction relationship between the domain controller (DCU) 210 and the i-th group of electronic control systems 220, JH (i、i‘) is the interaction relationship between the i-th group of electronic control systems 220 and the i′-th group of electronic control systems 220 , and i≠i′.

[0039] Step S140: Calculate the abnormal prediction index in the current monitoring period according to the control parameters of the domain control system collected in the current monitoring period and the interaction relationship in the domain control system;

[0040] After obtaining the domain controller (DCU) control parameter set A, the electronic control unit (ECU) control parameter set B and the interaction relationship set JH, the abnormality prediction index within the current monitoring period t is calculated based on the domain controller (DCU) control parameter set A, the electronic control unit (ECU) control parameter set B and the interaction relationship set JH.

[0041] Specifically, according to the following formula:

[0042]

[0043] Calculate the abnormal prediction index YC within the current monitoring period t t Among them, B tij is the control parameter of the jth electronic control unit (ECU) 221 in the i-th group of electronic control systems 220 collected in the current monitoring period t; A is the weight corresponding to the control parameter of the jth electronic control unit (ECU) 221; tn is the nth control parameter of the domain controller (DCU) 210 collected within the current monitoring period t.

[0044] Step S150, obtaining an abnormal prediction comprehensive index in the current monitoring period through the abnormal prediction index in the current monitoring period and the abnormal prediction index in the previous monitoring period to indicate an abnormal situation;

[0045] After obtaining the abnormal prediction index YC within the current monitoring period t t After that, according to the abnormal prediction indicator YC in the current monitoring period t and the abnormal prediction index YC in the previous monitoring period (t-1) (t-1) Get the comprehensive abnormal prediction index YC within the current monitoring period zt .

[0046] Specifically, according to the following formula:

[0047]

[0048] Calculate the comprehensive abnormal prediction index YC within the current monitoring period zt ; Among them, Q1 is YC t Corresponding weights; Q2 is YC (t-1) The corresponding weight is Q1=ωQ2, where ω is the adjustment constant and takes the value as 4.587.

[0049] Get the abnormal prediction comprehensive index YC in the current monitoring period zt After that, the abnormal prediction comprehensive index YC in the current monitoring period is zt Compared with the preset abnormal judgment indicator YC pd For comparison, if the abnormal prediction comprehensive index YC in the current monitoring period zt Greater than the abnormality judgment indicator YC pd , it indicates that the vehicle domain control system is abnormal. If the abnormal prediction comprehensive index YC in the current monitoring period is zt Not greater than the abnormality judgment index YC pd , it indicates that the car domain control system is normal.

[0050] Embodiment 2

[0051] like Figure 3 As shown, the present application provides an abnormality prediction system 300 for an automobile domain control system, including: a collection strategy acquisition unit 310, a control parameter collection unit 320, an interaction relationship acquisition unit 330, a prediction index calculation unit 340 and a prediction index synthesis unit 350.

[0052] The collection strategy acquisition unit 310 acquires the collection strategy in the current monitoring period according to the running status of the vehicle and the use status of the domain control system in the current monitoring period.

[0053] like Figure 2As shown, the automobile domain control system 200 includes: a domain controller (DCU) 210 and multiple electronic control systems 220; the acquisition strategy acquisition unit 310, the control parameter acquisition unit 320, the interaction relationship acquisition unit 330, the prediction index calculation unit 340 and the prediction index synthesis unit 350 all run in the domain controller (DCU) 210; each electronic control system 220 includes multiple electronic control units (ECU) 221, and the electronic control unit (ECU) 221 of each electronic control system 220 is used to control a subsystem of the automobile, such as: power transmission system, monitoring system, auxiliary driving system, etc.

[0054] The domain controller (DCU) 210 of the automobile domain control system 200 has different usage states, and in different usage states, the busyness of the domain controller (DCU) 210 is different; the electronic control unit (ECU) 221 of the automobile domain control system 200 also has different usage states, and in different usage states, the busyness of the electronic control unit (ECU) 221 is also different. The busyness of the domain controller (DCU) 210 and the electronic control unit (ECU) 221 will affect the number of control parameters generated by the domain controller (DCU) 210 and the electronic control unit (ECU) 221.

[0055] A car has different operating states, such as high-speed driving state, low-speed driving state, parked state with the engine not turned off, parked state with the engine turned off, etc.; and in different operating states, after the car domain control system 200 is attacked, the degree of impact on the car safety is different, for example: in the high-speed driving state, the impact of the car domain control system 200 being attacked on the car safety is greater, and in the parked state with the engine turned off, the impact of the car domain control system 200 being attacked on the car safety is less.

[0056] Therefore, after the current monitoring cycle begins, the collection strategy acquisition unit 310 collects the operating status of the vehicle, the usage status of the domain controller (DCU) 210 of the domain control system 200, and the usage status of each electronic control unit (ECU) 221 of each group of electronic control systems 220 of the domain control system 200, and calculates the collection strategy acquisition indicators within the current monitoring cycle based on the operating status of the vehicle, the usage status of the domain controller (DCU) 210 of the domain control system 200, and the usage status of each electronic control unit (ECU) 221 of each group of electronic control systems 220 of the domain control system 200, for example: the collection strategy is the time interval for collecting control parameters, the number of collected control parameters, etc.

[0057] Specifically, according to the following formula:

[0058]

[0059] Calculate the acquisition strategy index Z within the current monitoring period t clt ; Among them, Y t is the running status of the car in the current monitoring period t; W1 is the index Z obtained by the car running status for the collection strategy clt The impact weight of SD t is the usage status of the domain controller (DCU) 210 in the current monitoring period t; α1 is the weight corresponding to the usage status of the domain controller (DCU) 210; SE ijt is the usage status of the jth electronic control unit (ECU) 221 of the i-th group of electronic control systems 220 in the current monitoring period t; μ j is the weight corresponding to the use state of the j-th electronic control unit (ECU) 221; J is the number of electronic control units (ECUs) 221 in the i-th group of electronic control systems 220; β i is the weight corresponding to the use status of the i-th group of electronic control systems 220; I is the number of electronic control systems 220; α2 is the total weight corresponding to the use status of all electronic control systems 220; W2 is the acquisition index Z of the domain control system use status for the collection strategy clt The influence weight of .

[0060] The acquisition strategy acquisition unit 310 acquires the index Z according to the acquisition strategy in the current monitoring period t. clt Traverse the collection strategy database, compare its collection strategy identifier with the collection strategy acquisition index Z in the current monitoring period t clt The closest collection strategy is used as the collection strategy in the current monitoring cycle. The collection strategy database is pre-stored in the memory of the car. At this time, it is necessary to obtain the indicator Z according to the collection strategy. clt The acquisition strategy for the current monitoring cycle is obtained from the vehicle's memory.

[0061] The control parameter collection unit 320 collects the control parameters of the domain control system in the current monitoring period according to the acquired collection strategy.

[0062] The control parameter collection unit 320 collects the control parameters of the domain controller (DCU) 210 according to the collection method of the domain controller (DCU) 210 specified in the collection strategy, for example: collects the control parameters of the domain controller (DCU) 210 according to the time interval T1, and integrates the control parameters of the domain controller (DCU) 210 obtained in the current monitoring period t into the domain controller (DCU) control parameter set A = {A t1 , A t2 , …, A tN}, where A t1 is the first control parameter of the domain controller (DCU) 210 collected in the current monitoring period t, A t2is the second control parameter of the domain controller (DCU) 210 collected in the current monitoring period t, A tN is the Nth control parameter of the domain controller (DCU) 210 collected in the current monitoring period t, and N is the number of control parameters in the domain controller (DCU) control parameter set A. For example: memory occupancy, hard disk occupancy, CPU occupancy, temperature, memory change rate, hard disk change rate, CPU change rate, temperature change rate, etc.

[0063] The control parameter acquisition unit 320 acquires the control parameters of the electronic control unit (ECU) 221 in the corresponding electronic control system 220 according to the acquisition method for each group of electronic control systems 220 specified in the acquisition strategy, for example: according to the time interval T 2i Collect the control parameters of the electronic control unit (ECU) 221 in the i-th group of electronic control systems 220, and integrate the control parameters of the electronic control unit (ECU) 221 in each group of electronic control systems 220 obtained in the current monitoring period t into the electronic control unit (ECU) control parameter set B = {(B t11 , B t12 ,…)、(B t21 , B t22 ,…)、…、(B ti1 , B ti2 , …)}, where B t11 is the control parameter of the first electronic control unit (ECU) 221 in the first group of electronic control systems 220 collected in the current monitoring period t, B t12 is the control parameter of the second electronic control unit (ECU) 221 in the first group of electronic control systems 220 collected in the current monitoring period t, B t21 is the control parameter of the first electronic control unit (ECU) 221 in the second group of electronic control systems 220 collected in the current monitoring period t, B t22 is the control parameter of the second electronic control unit (ECU) 221 in the second group of electronic control systems 220 collected in the current monitoring period t, B ti1 is the control parameter of the first electronic control unit (ECU) 221 in the i-th group of electronic control systems 220 collected in the current monitoring period t, B ti2 It is the control parameter of the second electronic control unit (ECU) 221 in the i-th group of electronic control systems 220 collected in the current monitoring period t. For example: cruise control parameters, lighting control parameters, airbag control parameters, suspension control parameters, fuel heating control parameters, exhaust control parameters, brake control parameters, etc.

[0064] The interaction relationship acquisition unit 330 acquires the interaction relationship in the domain control system from the active directory according to the obtained control parameters.

[0065] The domain controller (DCU) 210 stores an active directory, which is a small database that records the attributes of various objects in the domain and the interaction relationships between the objects, so as to facilitate the unified management of the domain controller (DCU) 210. After obtaining the control parameters of the domain control system 200 in the current monitoring period, the interaction relationship acquisition unit 330 obtains the interaction relationship between the domain controller (DCU) 210 that generates the above control parameters and each group of electronic control systems 220 and the interaction relationship between each group of electronic control systems 220 and other groups of electronic control systems 220 from the active directory according to the obtained control parameters, and integrates these interaction relationships into an interaction relationship set JH={JH i , JH (i，i‘)}, where JH i is the interaction relationship between the domain controller (DCU) 210 and the i-th group of electronic control systems 220, JH (i、i‘) is the interaction relationship between the i-th group of electronic control systems 220 and the i′-th group of electronic control systems 220 , and i≠i′.

[0066] The prediction index calculation unit 340 calculates the abnormal prediction index in the current monitoring period according to the control parameters of the domain control system collected in the current monitoring period and the interaction relationship in the domain control system.

[0067] After obtaining the domain controller (DCU) control parameter set A, the electronic control unit (ECU) control parameter set B and the interaction relationship set JH, the prediction index calculation unit 340 calculates the abnormal prediction index within the current monitoring period t based on the domain controller (DCU) control parameter set A, the electronic control unit (ECU) control parameter set B and the interaction relationship set JH.

[0068] Specifically, according to the following formula:

[0069]

[0070] Calculate the abnormal prediction index YC within the current monitoring period t t Among them, B tij is the control parameter of the jth electronic control unit (ECU) 221 in the i-th group of electronic control systems 220 collected in the current monitoring period t; A is the weight corresponding to the control parameter of the jth electronic control unit (ECU) 221; tn is the nth control parameter of the domain controller (DCU) 210 collected within the current monitoring period t.

[0071] The prediction index synthesis unit 350 obtains the abnormal prediction synthesis index in the current monitoring period through the abnormal prediction index in the current monitoring period and the abnormal prediction index in the previous monitoring period to indicate the abnormal situation.

[0072] After obtaining the abnormal prediction index YC within the current monitoring period t t After that, the prediction index synthesis unit 350 generates an abnormal prediction index YC according to the abnormal prediction index YC in the current monitoring period. t and the abnormal prediction index YC in the previous monitoring period (t-1) (t-1) Get the comprehensive abnormal prediction index YC within the current monitoring period zt .

[0073] Specifically, according to the following formula:

[0074]

[0075] Calculate the comprehensive abnormal prediction index YC within the current monitoring period zt ; Among them, Q1 is YC t Corresponding weights; Q2 is YC (t-1) The corresponding weight is Q1=ωQ2, where ω is the adjustment constant and takes the value as 4.587.

[0076] Get the abnormal prediction comprehensive index YC in the current monitoring period zt After that, the prediction index synthesis unit 350 converts the abnormal prediction comprehensive index YC in the current monitoring period into zt Compared with the preset abnormal judgment indicator YC pd For comparison, if the abnormal prediction comprehensive index YC in the current monitoring period zt Greater than the abnormality judgment indicator YC pd , it indicates that the vehicle domain control system is abnormal. If the abnormal prediction comprehensive index YC in the current monitoring period is zt Not greater than the abnormality judgment index YC pd , it indicates that the car domain control system is normal.

[0077] This application can predict abnormalities in the automobile domain control system, prevent the domain controller (DCU) of the automobile domain control system from being attacked, prevent the leakage of various automobile data (even private data), and ensure the safety of the automobile.

[0078] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0079] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. An abnormality prediction method for an automobile domain control system, characterized in that: The steps include: Step S110: obtaining a collection strategy in the current monitoring period according to the running state of the vehicle and the use state of the domain control system in the current monitoring period; Step S110 includes the following sub-steps: After the current monitoring cycle starts, the running status of the vehicle, the usage status of the domain controller of the domain control system, and the usage status of each electronic control unit of each group of electronic control systems of the domain control system are collected; According to the running state of the vehicle, the use state of the domain control system and the use state of each electronic control unit of each group of electronic control systems of the domain control system, the acquisition index of the collection strategy in the current monitoring cycle is calculated; According to the following formula: Calculate the acquisition strategy index Z within the current monitoring period t clt ; Among them, Y t is the running status of the car in the current monitoring period t; W1 is the index Z obtained by the car running status for the collection strategy clt The impact weight of SD t is the usage status of the domain controller in the current monitoring period t; α1 is the weight corresponding to the usage status of the domain controller; SE ijt is the usage status of the jth electronic control unit of the i-th group of electronic control systems in the current monitoring period t; μ j is the weight corresponding to the jth electronic control unit usage state; J is the number of electronic control units in the i-th group of electronic control systems; β i is the weight corresponding to the usage status of the i-th group of electronic control systems; I is the number of electronic control systems; α2 is the total weight corresponding to the usage status of all electronic control systems; W2 is the acquisition index Z of the domain control system usage status for the collection strategy clt The weight of influence; The collection strategy database is traversed according to the collection strategy acquisition index in the current monitoring cycle, and the collection strategy whose collection strategy identifier is closest to the collection strategy acquisition index in the current monitoring cycle is used as the collection strategy in the current monitoring cycle; Step S120, collecting control parameters of the domain control system in the current monitoring period according to the acquired collection strategy, integrating the domain controller control parameter set and the electronic control unit control parameter set; Step S130, obtaining the interaction relationship in the domain control system from the active directory according to the obtained control parameters, and integrating the interaction relationship set; Step S140: Calculate the abnormal prediction index in the current monitoring period according to the control parameters of the domain control system collected in the current monitoring period and the interaction relationship in the domain control system; Step S140 includes the following sub-steps: According to the domain controller control parameter set, the electronic control unit control parameter set and the interaction relationship set, the abnormal prediction index in the current monitoring period is calculated; According to the following formula: Calculate the abnormal prediction index YC within the current monitoring period t t Among them, B tij is the control parameter of the jth electronic control unit in the i-th group of electronic control systems collected in the current monitoring period t; is the weight corresponding to the control parameter of the jth electronic control unit; A tn is the nth control parameter of the domain controller collected in the current monitoring period t; JH i is the interaction relationship between the domain controller and the i-th group of electronic control systems, JH (i、i‘) is the interaction relationship between the i-th group of electronic control systems and the i'th group of electronic control systems, and i≠i'; Step S150, obtaining an abnormal prediction comprehensive index in the current monitoring period through the abnormal prediction index in the current monitoring period and the abnormal prediction index in the previous monitoring period to indicate the abnormal situation.

2. The abnormality prediction method for automobile domain control system according to claim 1, characterized in that: Step S120 includes the following sub-steps: Collect the control parameters of the domain controller according to the collection method for the domain controller specified in the collection strategy, and integrate the control parameters of the domain controller obtained in the current monitoring cycle into the domain controller control parameter set; The control parameters of the electronic control units in the corresponding electronic control systems are collected according to the collection method for each group of electronic control systems specified in the collection strategy, and the control parameters of the electronic control units in each group of electronic control systems obtained in the current monitoring cycle are integrated into an electronic control unit control parameter set.

3. The abnormality prediction method for automobile domain control system according to claim 2, characterized in that: Step S130 includes the following sub-steps: According to the obtained control parameters, the interaction relationship between the domain controller generating the control parameters and each group of electronic control systems and the interaction relationship between each group of electronic control systems and other groups of electronic control systems are obtained from the active directory, and the interaction relationships are integrated into an interaction relationship set.

4. An abnormality prediction system for an automobile domain control system, characterized in that: include: An acquisition strategy acquisition unit, a control parameter acquisition unit, an interaction relationship acquisition unit, a prediction index calculation unit, and a prediction index synthesis unit; The collection strategy acquisition unit acquires the collection strategy in the current monitoring period according to the running state of the vehicle and the use state of the domain control system in the current monitoring period; After the current monitoring cycle starts, the collection strategy acquisition unit collects the running state of the vehicle, the use state of the domain controller of the domain control system, and the use state of each electronic control unit of each group of electronic control systems of the domain control system, and calculates the collection strategy acquisition index in the current monitoring cycle according to the running state of the vehicle, the use state of the domain control system, and the use state of each electronic control unit of each group of electronic control systems of the domain control system; According to the following formula: Calculate the acquisition strategy index Z within the current monitoring period t clt ; Among them, Y t is the running status of the car in the current monitoring period t; W1 is the index Z obtained by the car running status for the collection strategy clt The impact weight of SD t is the usage status of the domain controller in the current monitoring period t; α1 is the weight corresponding to the usage status of the domain controller; SE ijt is the usage status of the jth electronic control unit of the i-th group of electronic control systems in the current monitoring period t; μ j is the weight corresponding to the jth electronic control unit usage state; J is the number of electronic control units in the i-th group of electronic control systems; β i is the weight corresponding to the usage status of the i-th group of electronic control systems; I is the number of electronic control systems; α2 is the total weight corresponding to the usage status of all electronic control systems; W2 is the acquisition index Z of the domain control system usage status for the collection strategy clt The weight of influence; The collection strategy acquisition unit traverses the collection strategy database according to the collection strategy acquisition index in the current monitoring cycle, and uses the collection strategy whose collection strategy identifier is closest to the collection strategy acquisition index in the current monitoring cycle as the collection strategy in the current monitoring cycle; The control parameter collection unit collects the control parameters of the domain control system in the current monitoring period according to the acquired collection strategy, and integrates the control parameter set of the domain controller and the control parameter set of the electronic control unit; The interaction relationship acquisition unit acquires the interaction relationship in the domain control system from the active directory according to the acquired control parameters, and integrates the interaction relationship set; The prediction index calculation unit calculates the abnormal prediction index in the current monitoring period according to the control parameters of the domain control system collected in the current monitoring period and the interaction relationship in the domain control system; The prediction index calculation unit calculates the abnormal prediction index in the current monitoring period according to the domain controller control parameter set, the electronic control unit control parameter set and the interaction relationship set; According to the following formula: Calculate the abnormal prediction index YC within the current monitoring period t t Among them, B tij is the control parameter of the jth electronic control unit in the i-th group of electronic control systems collected in the current monitoring period t; is the weight corresponding to the control parameter of the jth electronic control unit; A tn is the nth control parameter of the domain controller collected in the current monitoring period t; JH i is the interaction relationship between the domain controller and the i-th group of electronic control systems, JH (i、i‘) is the interaction relationship between the i-th group of electronic control systems and the i'th group of electronic control systems, and i≠i'; The prediction index synthesis unit obtains the abnormal prediction synthesis index in the current monitoring cycle through the abnormal prediction index in the current monitoring cycle and the abnormal prediction index in the previous monitoring cycle to indicate the abnormal situation.

5. The abnormality prediction system for automobile domain control system according to claim 4, characterized in that: The control parameter collection unit collects the control parameters of the domain controller according to the collection method of the domain controller specified in the collection strategy, and integrates the control parameters of the domain controller obtained in the current monitoring cycle into the domain controller control parameter set; The control parameter acquisition unit acquires the control parameters of the electronic control units in the corresponding electronic control systems according to the acquisition method for each group of electronic control systems specified in the acquisition strategy, and integrates the control parameters of the electronic control units in each group of electronic control systems obtained in the current monitoring cycle into an electronic control unit control parameter set.

6. The abnormality prediction system for automobile domain control system according to claim 5, characterized in that: The interaction relationship acquisition unit acquires the interaction relationship between the domain controller generating the control parameters and each group of electronic control systems and the interaction relationship between each group of electronic control systems and other groups of electronic control systems from the active directory according to the obtained control parameters, and integrates the interaction relationships into an interaction relationship set.

Images