CN110633905B - Intelligent Che Yun platform reliability calculation method and system - Google Patents
Intelligent Che Yun platform reliability calculation method and system Download PDFInfo
- Publication number
- CN110633905B CN110633905B CN201910843092.2A CN201910843092A CN110633905B CN 110633905 B CN110633905 B CN 110633905B CN 201910843092 A CN201910843092 A CN 201910843092A CN 110633905 B CN110633905 B CN 110633905B
- Authority
- CN
- China
- Prior art keywords
- cloud platform
- intelligent vehicle
- reliability
- time
- fault
- 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
- 238000004364 calculation method Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 40
- 230000004044 response Effects 0.000 claims abstract description 40
- 230000008569 process Effects 0.000 claims abstract description 23
- 230000001133 acceleration Effects 0.000 claims abstract description 10
- 230000006855 networking Effects 0.000 claims abstract description 7
- 238000012360 testing method Methods 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 26
- 238000002347 injection Methods 0.000 claims description 20
- 239000007924 injection Substances 0.000 claims description 20
- 230000008439 repair process Effects 0.000 claims description 18
- 230000005540 biological transmission Effects 0.000 claims description 17
- 230000008859 change Effects 0.000 claims description 17
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 10
- 238000012423 maintenance Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 4
- 239000000243 solution Substances 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 3
- 238000011835 investigation Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000001149 cognitive effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Game Theory and Decision Science (AREA)
- Debugging And Monitoring (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a reliability calculation method of an intelligent vehicle cloud platform, which comprises the following steps: simulating the number of networking intelligent vehicle users in a certain area through dynamic pressure test software, and generating the total data amount and the circulation data amount during running; acquiring the speed and the acceleration of each path node in the whole running process of the intelligent vehicle and the response data of different driving paths to various road condition information through an intelligent vehicle path recording system; acquiring the occurrence time and the duration of the fault of the cloud platform, the type of the fault of the cloud platform and the influence on the running process of the intelligent vehicle through a cloud platform fault automatic recording system; acquiring operation parameters of each system of the intelligent vehicle through an intelligent vehicle fault automatic recording system; establishing a database according to all the acquired data; calculating reliability indexes of the intelligent vehicle cloud platform by utilizing data in the database, wherein the reliability indexes comprise primary indexes and secondary indexes; and calculating the reliability of the intelligent vehicle cloud platform according to the weight of the preset reliability index.
Description
Technical Field
The invention relates to the technical fields of cloud platform reliability and the like, in particular to a calculation method and a system based on an intelligent vehicle cloud platform reliability index.
Background
Under the promotion of China manufacturing 2025, the vehicle industry rapidly develops, intelligent Internet-connected vehicles gradually enter the field of view of the masses, and the intellectualization and Internet-connected vehicles become a great trend of vehicle development. The intelligent vehicle cloud platform is used as an important component in automatic driving, and has functions of navigation, positioning, early warning and the like, and the accuracy and the inefficacy of the data are more related to the safety problem of vehicles and personnel. Therefore, the research on the reliability index of the cloud platform is not slow.
Under the current technical conditions, the design and the manufacture of intelligent vehicles are in a vigorous development stage, but no large-scale automatic driving fleet exists, the intelligent vehicle cloud platform is not widely used, and the functions which can be achieved by the network connected with the vehicle-mounted terminal are difficult to meet the automatic driving requirement, so that most of modules of the cloud platform for the T4-level automatic driving are in an exploration stage. The development direction of the automobile technology is intelligent and networking, the era of internet of things has come, and new requirements and targets will also need to exist for intelligent internet-connected automobiles.
The cloud platform of the intelligent vehicle is not inferior to books for people, and although judgment on conditions of vehicles, roads and environments and control on driving behaviors of vehicles are carried out by the vehicles, the cloud platform provides a large amount of traffic, weather and other data for normal operation of the intelligent vehicle, and the data are very important for the intelligent vehicle. The intelligent vehicle cloud platform is taken as a complex system of software and hardware combination, the service and the function of the intelligent vehicle cloud platform are unreliable, and the reliability evaluation index of the cloud platform is designed and is indistinct. Because the cloud platform is not formally used, a plurality of dynamic pressure tests are needed to simulate the data flow in the actual situation, and the reliability evaluation index design can be performed after necessary data are collected.
Disclosure of Invention
The invention aims to provide a calculation method of reliability indexes of an intelligent vehicle cloud platform, which is used for effectively evaluating the cloud platform and continuously improving the functions of the cloud platform.
The technical scheme adopted for solving the technical problems is as follows:
the utility model provides a reliability calculation method of an intelligent vehicle cloud platform, which comprises the following steps:
simulating the number of networking intelligent vehicle users in a certain area through dynamic pressure test software, and generating the total data amount and the circulation data amount during running;
acquiring the speed and the acceleration of each path node of the intelligent vehicle in the whole running process and the response data of each intelligent vehicle to the same starting point and end point, for the selection of different driving paths and for various road condition information through an intelligent vehicle path recording system;
acquiring the occurrence time and the duration of the fault of the cloud platform, the type of the fault of the cloud platform and the influence on the running process of the intelligent vehicle through a cloud platform fault automatic recording system;
acquiring operation parameters of each system of the intelligent vehicle through an intelligent vehicle fault automatic recording system, wherein the operation parameters comprise accuracy of the intelligent vehicle on data transmission of a cloud platform and time for recovering to be normal after the intelligent vehicle is in fault;
establishing a database according to all the acquired data, and recording the types, types and times of failure and error data;
calculating reliability indexes of the intelligent vehicle cloud platform by utilizing data in a database, wherein the reliability indexes comprise primary indexes and secondary indexes, the primary indexes comprise failure indexes, repairability indexes and comprehensive indexes, the failure indexes comprise the reliability of the secondary index cloud platform, the average time before failure and failure rate of the cloud platform, the repairability indexes comprise the repairability of the secondary indexes, the average time before repair and availability, and the comprehensive indexes comprise the response time of the secondary index cloud platform, the accuracy, confidentiality, overtaking property and fault tolerance of response data;
and calculating the reliability of the intelligent vehicle cloud platform according to the weight of the preset reliability index.
By adopting the technical scheme, the method further comprises the following steps:
generating a specific reliability parameter table of each fault by using fault data and fault modes recorded in a database, and recording the actual condition of cloud platform service: and when the cloud platform normally operates, the simulated fault is injected into the cloud platform, and the reliability parameter change during the fault is simulated.
The technical scheme is that the method further comprises the steps of: designing a path, simulating the number of test users, and testing the intelligent vehicle in the path by using one or more actually-existing intelligent vehicle users, wherein the test is divided into an emergency test and a normal driving condition test, and the driving condition of the intelligent vehicle and the reliability index change condition of the cloud platform are recorded when the intelligent vehicle normally runs; during emergency test, fault injection is carried out on part of path nodes, parameter changes of an intelligent vehicle running path and change trend of reliability indexes of a cloud platform are observed, if the reliability indexes start to be reduced from high reliability to low reliability during fault injection, the indexes are reasonably selected, and the calculation weight of the total indexes is reasonable; if the two are not matched, the weights of the various indexes in the total indexes are readjusted.
By adopting the technical scheme, the method further comprises the following steps: automatically identifying failure modes by utilizing a neural network technology; training corresponding fault parameters and records of fault modes by acquiring historical data and reliability parameters of cloud platform operation, and training to obtain a fault automatic identification model; when the cloud platform runs abnormally or fault injection is simulated, the changed reliability parameters are input into a neural network to perform fault mode identification and judge the accuracy of the identification, and if the identification result is accurate, the neural network and the reliability parameters are effective; if the identification is inaccurate, training the neural network again and verifying again; and finally, obtaining the neural network for accurately identifying the fault mode of the cloud platform.
By adopting the technical scheme, the reliability index is specifically as follows:
cloud platform response time: and sending communication data from the intelligent vehicle terminal equipment, and transmitting the communication data back to the intelligent vehicle-mounted terminal after the cloud platform processes the data:
response time = presentation time + network transmission time + application delay time
Presentation time: refers to the time required by the browser of the client to render the page when receiving the response data;
network transmission time: the method comprises the steps of requesting data and responding to time for data transmission between a client and an intelligent vehicle cloud platform;
delay time is applied: refer to time t required by cloud platform to actually process request f ＝t a +t b +t c
Wherein: t is t f Refers to response time; t is t a Refers to presentation time; t is t b Refers to network transmission time; t is t c Refers to applying a delay time;
accuracy of response data: after the intelligent vehicle uploads the information, whether the information required by the intelligent vehicle is consistent with the information transmitted back by the cloud platform or how much the information has correlation, the data can be obtained from the automatic driving record without calculation.
Cloud platform reliability: the probability that the cloud platform and the intelligent vehicle can normally operate in the period from zero time to t time of a system is indicated;
average time before failure of the cloud platform; : the current time reaches the time before the next failure of the cloud platform and the vehicle running total system;
failure rate: the failure rate refers to the probability of failure occurring in unit time after a product which is not failed at a certain moment;
at time interval t 1 ，t 2 ]In, the failure rate function is:
wherein: h (t) a failure rate function; r (t) 1 )t 1 Time reliability; r (t) 2 )t 2 Time reliability;
maintainability: refers to the probability of isolating and repairing a fault in a system in a given time;
average pre-repair time: mean repair time required for fault maintenance;
availability of: the probability or the time occupancy expected value of the cloud platform capable of operating normally in a certain investigation time by the automatic driving system;
confidentiality: each information of the cloud platform has confidentiality and is set through authority setting and hardware encryption;
traceability: recording the running condition, running track and speed acceleration of the intelligent vehicle, and knowing the running track and the speed acceleration through the storage condition of a database;
fault tolerance capability: when a certain function of the cloud platform fails, other functions can still normally operate, and the parameter is determined by the standby link and the standby server.
By adopting the technical scheme, the weights of the fault index and the maintainability index are 0.4, and the comprehensive index weight is 0.2.
The invention also provides a reliability calculation system of the intelligent vehicle cloud platform, which comprises the following steps:
dynamic pressure test module: simulating the number of networking intelligent vehicle users in a certain area through dynamic pressure test software, and generating the total data amount and the circulation data amount during running;
the original data processing module: acquiring data of a dynamic pressure test module, an intelligent vehicle path recording system, a cloud platform fault automatic recording system and an intelligent vehicle fault automatic recording system, establishing a database, and recording types, types and times of failure and error data;
the reliability index calculation module is used for: calculating and summarizing the data in the data processing module to obtain a plurality of groups of reliability indexes, and carrying out weighted normalization processing on the reliability indexes to obtain a reliability total index; the reliability indexes comprise primary indexes and secondary indexes, wherein the primary indexes comprise failure indexes, repairability indexes and comprehensive indexes, the failure indexes comprise the reliability of a secondary index cloud platform, the average time before failure and failure rate of the cloud platform, the repairability indexes comprise the repairability of the secondary indexes, the average time before repair and the availability, and the comprehensive indexes comprise the response time of the secondary index cloud platform, the accuracy, confidentiality, overtaking property and fault tolerance of response data.
By adopting the technical scheme, the system further comprises:
and a fault injection module: the corresponding parameters under the condition of multiple failures of the cloud platform in the database are derived, faults are injected when the cloud platform and the vehicle normally run, and the change of the reliability parameters is recorded;
and (3) a verification module: verifying whether the total reliability index meets the actual condition requirement and whether the intelligent vehicle and the reliability index trend can carry out relevant change after fault injection;
the automatic fault identification module: the operation of the cloud platform is identified and monitored by utilizing the neural network, when the cloud platform works abnormally, the fault type of the cloud platform service is judged according to the change of the reliability parameter, and the consequences caused by the fault are calculated at the same time, and the corresponding solution method is adopted.
The invention has the beneficial effects that: the intelligent vehicle cloud platform real-time monitoring system can monitor the running states of all parts of the intelligent vehicle cloud platform in real time, automatically process the obtained parameters, calculate the real-time reliability index of the cloud platform, ensure that the cloud platform can be in a good running state to the greatest extent, improve the running safety performance, quantify the experience of experts, reduce the threshold of running and maintenance of the cloud platform, and have low popularization cost and strong repeatability of a strategy method.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a flow chart of a method for calculating reliability of an intelligent vehicle cloud platform according to an embodiment of the invention;
fig. 2 is a functional schematic diagram of a reliability calculation system of a cloud platform of an intelligent vehicle according to an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, the method for calculating the reliability of the intelligent vehicle cloud platform according to the embodiment of the invention comprises the following steps:
s1, simulating the number of networking intelligent vehicle users in a certain area through dynamic pressure test software, wherein the total data amount and the circulation data amount generated during operation are calculated;
s2, acquiring the speed and the acceleration of each path node in the whole running process of the intelligent vehicle and the response data of each intelligent vehicle to various road condition information aiming at the same starting point and end point and selecting different driving paths through an intelligent vehicle path recording system;
s3, acquiring the occurrence time and the duration of the fault of the cloud platform, the type of the fault of the cloud platform and the influence on the running process of the intelligent vehicle through a cloud platform fault automatic recording system;
s4, acquiring operation parameters of each system of the intelligent vehicle through an intelligent vehicle fault automatic recording system, wherein the operation parameters comprise accuracy of the intelligent vehicle on data transmission of the cloud platform and time for recovering to be normal after the intelligent vehicle is in fault;
s5, establishing a database according to all the acquired data, and recording the types, types and times of failure and error data;
s6, calculating reliability indexes of the intelligent vehicle cloud platform by utilizing data in a database, wherein the reliability indexes comprise primary indexes and secondary indexes, the primary indexes comprise failure indexes, repairability indexes and comprehensive indexes, the failure indexes comprise the reliability of the secondary index cloud platform, the average time before failure and failure rate of the cloud platform, the repairability indexes comprise the repairability of the secondary indexes, the average time before repair and the availability, and the comprehensive indexes comprise the response time of the secondary index cloud platform, the accuracy, the confidentiality, the hastenability and the fault tolerance of response data;
and S7, calculating the reliability of the intelligent vehicle cloud platform according to the weight of the preset reliability index.
In step S1, data generated by interaction between a vehicle-mounted terminal and a cloud platform generated by one vehicle and a plurality of vehicles may be recorded for comparison research. And predicting the circulation data quantity and the total data quantity of the cloud platform generated by a large number of vehicles by comparing the results of the research, so that the data circulation quantity and the total data quantity of the cloud platform between the cloud platform and the vehicle-mounted equipment in unit time can be calculated. The data traffic can be used to test whether the terminal and cloud platform communication links are reliable or not, and the total data amount of the cloud platform represents the total data amount stored by the cloud platform and the searching and calling capability of the data.
According to the method, system users in a certain area are simulated by using loadrunner test software, standard basic data and circulation data quantity are set, and the test result is maximum response time, average response time and the like of the intelligent vehicle cloud platform for completing a certain service.
The data can be directly obtained, excluding the abnormal data, and stored in the database by collecting and sorting in step S5. The data which can be directly obtained mainly comprise data obtained by a loadrunner test software test, unmanned vehicle running path data, cloud platform fault automatic recording data, automatic driving vehicle fault data and the like. After the data is obtained, an invalid knowledge database is established by utilizing SQL language, and software faults, hardware faults, network faults and the like in the cloud platform are recorded.
Further, the method may further comprise the steps of: acquiring failure data and error data of the cloud platform and reliability parameters in normal operation, calculating respective reliability parameters, determining weights of the parameters by using a regression statistical method, multiplying and adding each reliability index with the weights, and calculating a reliability total index; in addition, when confidentiality and fault tolerance are achieved and the overtaking property fails, the intelligent vehicle can still continue to drive normally. When a serious fault occurs, the intelligent vehicle should stop driving and receive maintenance.
Further, the method may further comprise the steps of: and generating a specific reliability parameter table of each fault by using fault data and fault modes recorded in the database, and recording the actual condition of cloud platform service. When the cloud platform normally operates, simulated faults can be injected into the system, functions corresponding to some cloud services are reduced or eliminated at the same time, reliability parameter changes during fault simulation are observed and recorded, relevant data are recorded, effective measures are developed to ensure benefits of clients, multiple fault injection exercises are performed, corresponding measures are formulated for different fault modes to perform post-improvement work, cognitive and processing work of practitioners on sudden faults is cultivated, and loss caused by the sudden faults can be effectively reduced.
The intelligent vehicle cloud platform reliability computing system is used for implementing the method, as shown in fig. 2, and mainly comprises the following steps: the system comprises a dynamic pressure test module, an original data processing module, a reliability index calculation module, a fault injection module, a verification module and a fault automatic identification module.
Dynamic pressure test module: and simulating a system user in a certain area by using loadrunner test software, setting standard basic data after data extraction and estimation are performed on the vehicle-mounted terminal equipment, wherein the test result is the maximum response time, average response time and the like of the intelligent vehicle cloud platform for completing a certain service. The selection of the test calculation example is based on simulating the number of intelligent network vehicle-mounted equipment stopped or running in a certain area, and the total data amount and the circulation data amount generated during running. The computing example is mainly used for testing the front end and the functions of the cloud platform.
The original data processing module: the module is used for collecting and arranging some data which can be obtained directly without calculation, and storing the data into a database after removing part of abnormal data. The data which can be directly obtained mainly comprise data obtained by a loadrunner test software test, unmanned vehicle running path data, cloud platform fault automatic recording data, automatic driving vehicle fault data and the like.
The reliability index calculation module is used for: and calculating and summarizing the data in the data processing module to obtain a plurality of groups of reliability indexes, and carrying out weighted normalization processing on the reliability indexes to obtain a reliability total index. The reliability indexes of the cloud platform under different working conditions can be finally obtained by calculating the operation data of the cloud platform and the intelligent vehicle under various working conditions, and the reliability indexes are divided by the driving conditions of the intelligent vehicle. The cloud platform can be monitored in real time, and meanwhile, the reliability index of the cloud platform is calculated.
And a fault injection module: and (3) deriving corresponding parameters under various failure conditions of the cloud platform in the database, injecting faults when the cloud platform and the vehicle normally run, and observing and recording the change of the reliability parameters.
And (3) a verification module: and verifying whether the total reliability index meets the actual condition requirement and whether the intelligent vehicle and the reliability index trend can be subjected to relevant change after fault injection.
The automatic fault identification module: the operation of the cloud platform is identified and monitored by utilizing the neural network, when the cloud platform works abnormally, the fault type of the cloud platform service is judged according to the change of the reliability parameter, and the consequences caused by the fault are calculated at the same time, and the corresponding solution method is adopted.
The test software can obtain data:
(1) Service average response time, including presentation time t a : refers to the time required by the browser of the client to render the page when receiving the response data; network transmission time t b : refers to the time when data (including request data and response data) is transmitted between the client and server; application delayDelay time t c : refers to the time required by the cloud platform to actually process the request.
(2) The success rate of the service, namely simply the probability that the cloud platform responds correctly to the data request sent by the test software and the service is completed satisfactorily.
(3) The total amount of circulation data comprises statistics of concurrency after scene execution, total throughput, average throughput per second, total request number and average request number per second.
(4) Scenario execution conditions, including time of simulated scenario execution, total number of users, etc.
The intelligent vehicle path recording system can obtain data:
the same starting point and end point, for selection of different driving paths
Acceleration a m/s of each path node in the whole travel process of intelligent vehicle
Speed v m/s of each path node in the whole running process of intelligent vehicle
Reaction condition of intelligent vehicle to various road condition information
The cloud platform fault automatic recording system can obtain data:
time of failure occurrence of cloud platform and duration of failure
Type of cloud platform failure
Influence on the running process of an intelligent vehicle
The intelligent vehicle fault automatic recording system can obtain data:
operating parameters of each system of intelligent vehicle
Accuracy of intelligent vehicle to cloud platform transmission data
Time for recovering from failure of intelligent vehicle
The reliability index types are mainly divided into three main categories, and the primary indexes are fault, repairability and comprehensive indexes, and the classification and solving processes are shown in the following table 1.
TABLE 1 reliability index Classification Table
1) Cloud platform response time: and sending out communication data from the intelligent vehicle terminal equipment, and transmitting the communication data back to the intelligent vehicle-mounted terminal after the cloud platform processes the data.
Response time = presentation time + network transmission time + application delay time
Presentation time: refers to the time required by the browser of the client to render the page when receiving the response data; the "presentation time" is related to the in-vehicle terminal device, but has no great relation to the developed cloud platform.
Network transmission time: refers to the time when data (including request data and response data) is transmitted between the client and server; which is related to the network bandwidth.
Delay time is applied: refers to the time required by the cloud platform to actually process the request. If the system uses a database, we can separate the "database latency" and if the system uses middleware, we can also separate the "middleware latency".
t f ＝t a +t b +t c
Wherein: t is t f Refers to response time; t is t a Refers to presentation time; t is t b Refers to network transmission time; t is t c Refers to applying a delay time.
2) Accuracy of response data: after the intelligent vehicle uploads the information, whether the information required by the intelligent vehicle is consistent with the information transmitted back by the cloud platform or how much the information has correlation, the data can be obtained from the automatic driving record without calculation.
3) Cloud platform reliability: the probability of a cloud platform successfully executing a specific function under a specified design scope.
In brief, reliability R t Refers to a system which can normally run during the period from zero time to t timeThe rate is as follows:
R(t)＝P(T＞t)，t≥0
wherein: t is a random variable representing the time before or during which the system fails.
If the density function representing the time-before-failure random variable T is f (T)
Equivalently
4) Cloud platform Mean Time To Failure (MTTF): the current time is the time before the next failure of the cloud platform and the vehicle running total system.
Will be
Substituting into MTTF form to obtain
Since the system must fail within a limited time, it is available
5) Failure rate: failure rate refers to the probability of failure occurring in a unit time after a certain time when a product that has not failed yet is operated.
At time interval t 1 ，t 2 ]In, the failure rate function is:
wherein: h (t) a failure rate function; r (t) 1 )t 1 Time reliability; r (t) 2 )t 2 Time reliability
6) Maintainability: in a prescribed time, maintenance is performed according to prescribed procedures and resources, so that the failed system has a probability of recovering its function, in other words, maintainability refers to a probability of isolating and repairing a failure in the system in a given time.
Let T denote the random variable of time before repair or total downtime, if the repair time density function of T is g (T), then maintainability V (T) is defined as the probability that the failed system can be re-operated at time T, namely:
the repair time density function is related to the repair rate, and if the repair rate is μ > 0 and constant, the repair time density function is:
g(t)＝μe -μt
7) Mean time before repair (MTTR): generally refers to the average repair time required for the fault maintenance of a product, and is used as a measure of the maintainability of the product. It includes the time necessary to confirm that the failure occurred, as well as the time required for maintenance.
8) Availability of: and the probability or the time occupancy expected value of the cloud platform capable of operating normally is determined at a certain investigation time.
9) Confidentiality: the cloud platform has confidentiality of various information, a person without authority cannot obtain data, the parameters are set through authority setting and hardware encryption, and specific parameters are not available.
10 Traceability): and recording the running condition, running track, speed acceleration and the like of the intelligent vehicle, wherein the parameters can be known through the storage condition of a database.
11 Fault tolerance capability): when a certain function of the cloud platform fails, other functions can still operate normally, and the parameter can be determined through a standby link and a standby server.
The specific functions of the cloud platform and the interaction information between the cloud platform and the vehicle are shown in the following table 2:
table 2 detailed interaction data of cloud platform and intelligent vehicle
Through knowing the interactive data between cloud platform and the vehicle, be favorable to judging when these faults appear in the intelligent vehicle whether with the cloud platform, with which data module of cloud platform is relevant, or whether there is delay or mistake in the communication link between cloud platform and the intelligent vehicle, the practitioner can be convenient and fast overhauls and maintains the cloud platform.
In one embodiment of the invention, a reliability evaluation total index calculation formula is established:
reliability total index=0.4×failure index+0.4×maintenance index+0.2×comprehensive index
According to the AHP analytic hierarchy process, the correlation among the three primary indexes is analyzed, so that the failure index and the maintainability index are definitely more important than the comprehensive index as the primary indexes directly related to the intelligent car driving behavior, and the primary indexes have larger proportion, so that the weight of the failure index and the maintainability index is determined to be 0.4, and the weight of the comprehensive index is determined to be 0.2.
The other indexes are subjected to proper range division according to the result of multiple analysis, the indexes in a certain range are of a fixed score, normalization processing is performed, and if the score of one index is smaller than 70, the condition that the intelligent vehicle is in a dangerous condition during driving is indicated, and the intelligent vehicle should be stopped and overhauled as soon as possible. The specific numerical ranges and weights for the secondary indicators are shown in table 3 below.
TABLE 3 reliability index value Range and weights
And generating a specific reliability parameter table of each fault by using fault data and fault modes recorded in the database, and recording the actual condition of cloud platform service. When the cloud platform normally operates, simulated faults can be injected into the system, functions corresponding to some cloud services are reduced or eliminated at the same time, reliability parameter changes during fault simulation are observed and recorded, relevant data are recorded, effective measures are developed to ensure benefits of clients, multiple fault injection exercises are performed, corresponding measures are formulated for different fault modes to perform post-improvement work, cognitive and processing work of practitioners on sudden faults is cultivated, and loss caused by the sudden faults can be effectively reduced.
A section of path can be designed, except for the number of simulated test users, one or more intelligent vehicle users actually exist in the process, namely the intelligent vehicle needs to be tested in the section of path actually existing, and the test is divided into an emergency test and a normal driving condition test; when the intelligent vehicle normally runs, recording the driving condition of the intelligent vehicle and the change condition of the reliability index of the cloud platform, wherein the reliability index value of the intelligent vehicle is larger than 80; and during emergency test, fault injection is carried out on part of path nodes, and parameters of the intelligent vehicle running path and the change condition of the cloud platform reliability index before and after the path nodes are observed and recorded. If the reliability total indicator gradually decreases during fault injection. When the intelligent vehicle cannot operate due to injection of some serious faults, the reliability total index score is lower than 70, so that the selection of the index is reasonable and effective, and the weight configuration of each first-level index is reasonable. Otherwise, when the reliability index rises or is unchanged along with the injection of the fault, or the reliability index score is lower than 70, and the intelligent vehicle can still normally run, the selection of the reliability total index is unreasonable, and the weight of each first-level index needs to be readjusted.
According to the method, the historical data and the reliability parameters of the cloud platform operation can be obtained, records of a plurality of different fault modes in a database are firstly extracted, meanwhile, reliability indexes corresponding to the fault modes are extracted, and the historical data and the reliability parameters are combined and then trained by using a neural network to obtain a fault automatic identification model; when the cloud platform runs abnormally or fault injection is simulated, the changed reliability parameters are input into the neural network to identify the fault mode, so that the fault mode of the cloud platform is accurately obtained, and the repair and analysis of related personnel on the cloud platform are facilitated.
It will be understood that modifications and variations will be apparent to those skilled in the art from the foregoing description, and it is intended that all such modifications and variations be included within the scope of the following claims.
Claims (8)
1. The intelligent vehicle cloud platform reliability calculation method is characterized by comprising the following steps of:
simulating the number of networking intelligent vehicle users in a certain area through dynamic pressure test software, and generating the total data amount and the circulation data amount during running;
acquiring the speed and the acceleration of each path node of the intelligent vehicle in the whole running process and the response data of each intelligent vehicle to the same starting point and end point, for the selection of different driving paths and for various road condition information through an intelligent vehicle path recording system;
acquiring the occurrence time and the duration of the fault of the cloud platform, the type of the fault of the cloud platform and the influence on the running process of the intelligent vehicle through a cloud platform fault automatic recording system;
acquiring operation parameters of each system of the intelligent vehicle through an intelligent vehicle fault automatic recording system, wherein the operation parameters comprise accuracy of the intelligent vehicle on data transmission of a cloud platform and time for recovering to be normal after the intelligent vehicle is in fault;
establishing a database according to all the acquired data, and recording the types, types and times of failure and error data;
calculating reliability indexes of the intelligent vehicle cloud platform by utilizing data in a database, wherein the reliability indexes comprise primary indexes and secondary indexes, the primary indexes comprise failure indexes, repairability indexes and comprehensive indexes, the failure indexes comprise the reliability of the secondary index cloud platform, the average time before failure and failure rate of the cloud platform, the repairability indexes comprise the repairability of the secondary indexes, the average time before repair and availability, and the comprehensive indexes comprise the response time of the secondary index cloud platform, the accuracy, confidentiality, overtaking property and fault tolerance of response data; the reliability of the cloud platform specifically refers to the probability that the cloud platform and the intelligent vehicle can normally operate in the period from zero time to t time of a system; the cloud platform response time is specifically the time from sending communication data from the intelligent vehicle terminal equipment to transmitting the communication data back to the intelligent vehicle-mounted terminal after the cloud platform processes the data: response time = presentation time + network transmission time + application delay time; after the information is uploaded by the intelligent vehicle, whether the required information is consistent with the information transmitted back by the cloud platform or not, or how much correlation exists, the accuracy of the response data is obtained from the automatic driving record without calculation;
and calculating the reliability of the intelligent vehicle cloud platform according to the weight of the preset reliability index.
2. The intelligent vehicle cloud platform reliability calculation method of claim 1, further comprising the steps of:
generating a specific reliability parameter table of each fault by using fault data and fault modes recorded in a database, and recording the actual condition of cloud platform service: and when the cloud platform normally operates, the simulated fault is injected into the cloud platform, and the reliability parameter change during the fault is simulated.
3. The intelligent vehicle cloud platform reliability calculation method of claim 1, further comprising the steps of: designing a path, simulating the number of test users, and testing the intelligent vehicle in the path by using one or more actually-existing intelligent vehicle users, wherein the test is divided into an emergency test and a normal driving condition test, and the driving condition of the intelligent vehicle and the reliability index change condition of the cloud platform are recorded when the intelligent vehicle normally runs; during emergency test, fault injection is carried out on part of path nodes, parameter changes of an intelligent vehicle running path and change trend of reliability indexes of a cloud platform are observed, if the reliability indexes start to be reduced from high reliability to low reliability during fault injection, the indexes are reasonably selected, and the calculation weight of the total indexes is reasonable; if the two are not matched, the weights of the various indexes in the total indexes are readjusted.
4. The intelligent vehicle cloud platform reliability calculation method of claim 1, further comprising the steps of: automatically identifying failure modes by utilizing a neural network technology; training corresponding fault parameters and records of fault modes by acquiring historical data and reliability parameters of cloud platform operation, and training to obtain a fault automatic identification model; when the cloud platform runs abnormally or fault injection is simulated, the changed reliability parameters are input into a neural network to perform fault mode identification and judge the accuracy of the identification, and if the identification result is accurate, the neural network and the reliability parameters are effective; if the identification is inaccurate, training the neural network again and verifying again; and finally, obtaining the neural network for accurately identifying the fault mode of the cloud platform.
5. The intelligent vehicle cloud platform reliability calculation method according to claim 1, wherein the reliability index is specifically:
presentation time: refers to the time required by the browser of the client to render the page when receiving the response data;
network transmission time: the method comprises the steps of requesting data and responding to time for data transmission between a client and an intelligent vehicle cloud platform;
delay time is applied: refer to time t required by cloud platform to actually process request f ＝ a + b + c
Wherein: t is t f Refers to response time; t is t a Refers to presentation time; t is t b Refers to network transmission time; t is t c Refers to applying a delay time;
average time before failure of cloud platform: the current time reaches the time before the next failure of the cloud platform and the vehicle running total system;
failure rate: the failure rate refers to the probability of failure occurring in unit time after a product which is not failed at a certain moment;
at time interval t 1 ,t 2 ]In, the failure rate function is:
wherein: h (t) is a failure rate function; r (t) 1 ) At t 1 Time reliability; r (t) 2 ) At t 2 Time reliability;
maintainability: refers to the probability of isolating and repairing a fault in a system in a given time;
average pre-repair time: mean repair time required for fault maintenance;
availability of: the probability or the time occupancy expected value of the cloud platform capable of operating normally in a certain investigation time by the automatic driving system;
confidentiality: each information of the cloud platform has confidentiality and is set through authority setting and hardware encryption;
traceability: recording the running condition, running track and speed acceleration of the intelligent vehicle, and knowing the running track and the speed acceleration through the storage condition of a database;
fault tolerance capability: when a certain function of the cloud platform fails, other functions can still normally operate, and the parameter is determined by the standby link and the standby server.
6. The intelligent vehicle cloud platform reliability calculation method of claim 1, wherein the weight of the failure index and the maintenance index is 0.4, and the weight of the comprehensive index is 0.2.
7. An intelligent vehicle cloud platform reliability computing system, comprising:
dynamic pressure test module: simulating the number of networking intelligent vehicle users in a certain area through dynamic pressure test software, and generating the total data amount and the circulation data amount during running;
the original data processing module: acquiring data of a dynamic pressure test module, an intelligent vehicle path recording system, a cloud platform fault automatic recording system and an intelligent vehicle fault automatic recording system, establishing a database, and recording types, types and times of failure and error data;
the reliability index calculation module is used for: calculating and summarizing the data in the data processing module to obtain a plurality of groups of reliability indexes, and carrying out weighted normalization processing on the reliability indexes to obtain a reliability total index; the reliability indexes comprise primary indexes and secondary indexes, wherein the primary indexes comprise failure indexes, repairability indexes and comprehensive indexes, the failure indexes comprise the reliability of a secondary index cloud platform, the average time before failure and failure rate of the cloud platform, the repairability indexes comprise the repairability of the secondary indexes, the average time before repair and the availability, and the comprehensive indexes comprise the response time of the secondary index cloud platform, the accuracy, confidentiality, overtaking property and fault tolerance of response data; the reliability of the cloud platform specifically refers to the probability that the cloud platform and the intelligent vehicle can normally operate in the period from zero time to t time of a system; the cloud platform response time is specifically the time from sending communication data from the intelligent vehicle terminal equipment to transmitting the communication data back to the intelligent vehicle-mounted terminal after the cloud platform processes the data: response time = presentation time + network transmission time + application delay time; the accuracy of the response data is specifically that whether the information required by the intelligent vehicle is consistent with the information transmitted back by the cloud platform or how much correlation exists after the intelligent vehicle uploads the information, and the information is obtained from the automatic driving record without calculation.
8. The smart car cloud platform reliability computing system of claim 7, further comprising:
and a fault injection module: the corresponding parameters under the condition of multiple failures of the cloud platform in the database are derived, faults are injected when the cloud platform and the vehicle normally run, and the change of the reliability parameters is recorded;
and (3) a verification module: verifying whether the total reliability index meets the actual condition requirement and whether the intelligent vehicle and the reliability index trend can carry out relevant change after fault injection;
the automatic fault identification module: the operation of the cloud platform is identified and monitored by utilizing the neural network, when the cloud platform works abnormally, the fault type of the cloud platform service is judged according to the change of the reliability parameter, and the consequences caused by the fault are calculated at the same time, and the corresponding solution method is adopted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910843092.2A CN110633905B (en) | 2019-09-06 | 2019-09-06 | Intelligent Che Yun platform reliability calculation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910843092.2A CN110633905B (en) | 2019-09-06 | 2019-09-06 | Intelligent Che Yun platform reliability calculation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110633905A CN110633905A (en) | 2019-12-31 |
| CN110633905B true CN110633905B (en) | 2023-05-02 |
Family
ID=68971489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910843092.2A Active CN110633905B (en) | 2019-09-06 | 2019-09-06 | Intelligent Che Yun platform reliability calculation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110633905B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110932932A (en) * | 2019-11-13 | 2020-03-27 | 上海博泰悦臻电子设备制造有限公司 | Reliability determination method for automatic driving cloud service platform and related device |
| CN111753261B (en) * | 2020-06-29 | 2023-07-04 | 北京百度网讯科技有限公司 | Vehicle safety detection method, device, equipment and storage medium |
| CN112202639B (en) * | 2020-09-30 | 2022-08-09 | 重庆长安汽车股份有限公司 | Performance test method for realizing Internet of vehicles remote control service through LoadRunner tool |
| CN113221096A (en) * | 2021-06-04 | 2021-08-06 | 北银金融科技有限责任公司 | Method and system for analyzing correlation of random events in chaotic engineering |
| CN113438318B (en) * | 2021-07-13 | 2023-04-07 | 阿波罗智联(北京)科技有限公司 | Performance test system and method of cloud control platform, electronic equipment and storage medium |
| CN114500349B (en) * | 2021-12-27 | 2023-08-08 | 天翼云科技有限公司 | Cloud platform chaos testing method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678101A (en) * | 2012-09-10 | 2014-03-26 | 中国科学院软件研究所 | Method for detecting software reliability of high-speed train network control system |
| CN106644503A (en) * | 2016-10-24 | 2017-05-10 | 中国科学院合肥物质科学研究院 | Intelligent vehicle planning capacity testing platform |
| KR20170051591A (en) * | 2015-10-29 | 2017-05-12 | 현대오토에버 주식회사 | Telematics service quality inspection system |
| CN107871418A (en) * | 2017-12-27 | 2018-04-03 | 吉林大学 | It is a kind of to be used to evaluate the man-machine experiment porch for driving reliability altogether |
| CN108430069A (en) * | 2018-02-11 | 2018-08-21 | 重庆邮电大学 | A kind of V2X applied in network performance test and comprehensive evaluation analysis method |
| CN108897693A (en) * | 2018-07-09 | 2018-11-27 | 北京首汽智行科技有限公司 | The software reliability test system and method for shared automobile intelligent vehicle-mounted terminal equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6272347B2 (en) * | 2013-11-08 | 2018-01-31 | 株式会社日立製作所 | Autonomous traveling vehicle and autonomous traveling system |
-
2019
- 2019-09-06 CN CN201910843092.2A patent/CN110633905B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678101A (en) * | 2012-09-10 | 2014-03-26 | 中国科学院软件研究所 | Method for detecting software reliability of high-speed train network control system |
| KR20170051591A (en) * | 2015-10-29 | 2017-05-12 | 현대오토에버 주식회사 | Telematics service quality inspection system |
| CN106644503A (en) * | 2016-10-24 | 2017-05-10 | 中国科学院合肥物质科学研究院 | Intelligent vehicle planning capacity testing platform |
| CN107871418A (en) * | 2017-12-27 | 2018-04-03 | 吉林大学 | It is a kind of to be used to evaluate the man-machine experiment porch for driving reliability altogether |
| CN108430069A (en) * | 2018-02-11 | 2018-08-21 | 重庆邮电大学 | A kind of V2X applied in network performance test and comprehensive evaluation analysis method |
| CN108897693A (en) * | 2018-07-09 | 2018-11-27 | 北京首汽智行科技有限公司 | The software reliability test system and method for shared automobile intelligent vehicle-mounted terminal equipment |
Non-Patent Citations (2)
| Title |
|---|
| 基于Fuzzy-EAHP的无人驾驶车辆智能行为评价;孙扬等;《汽车工程》;20140125(第01期);全文 * |
| 自动气象站监测运行能力可靠性评估;裴等;《气象科技》;20130615(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110633905A (en) | 2019-12-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110633905B (en) | Intelligent Che Yun platform reliability calculation method and system | |
| CN108563214B (en) | Vehicle diagnosis method, device and equipment | |
| CN102568053B (en) | Vehicle-mounted end of comprehensive vehicle fault detection system and data processing method of same | |
| CN109800127A (en) | A kind of system fault diagnosis intelligence O&M method and system based on machine learning | |
| CN108375974A (en) | It is a kind of to be used to remotely record, analysis, diagnose, the method and system of maintenance vehicle failure | |
| CN108268023B (en) | Remote fault diagnosis method and system for rail transit platform door | |
| CN101272580B (en) | Self-adapting mobile base station system reliability estimation method based on feedback | |
| CN106528975A (en) | Fault prognostics and health management method applied to circuits and systems | |
| CN108614539A (en) | AEF airborne equipment failure diagnosis and prediction model verification method | |
| CN114239734B (en) | Distributed vehicle-mounted health management system | |
| CN103049379B (en) | A kind of method of system testing | |
| CN109270921A (en) | A kind of method for diagnosing faults and device | |
| CN115576738B (en) | Method and system for realizing equipment fault determination based on chip analysis | |
| CN112286771A (en) | Alarm method for monitoring global resources | |
| CN111157245B (en) | Supervision method and system for rail transit running gear bearing | |
| CN110471395A (en) | A kind of fault detection method, device, equipment and storage medium | |
| CN108377209A (en) | Equipment fault detecting system based on SCADA and detection method | |
| CN115114124A (en) | Host risk assessment method and device | |
| CN112699490B (en) | Vehicle maintenance result verification method and device | |
| CN110991673B (en) | Fault isolation and localization method for complex systems | |
| CN114398940A (en) | Equipment fault diagnosis method and system for Internet of vehicles | |
| CN116068437A (en) | BMS thermal management and SOX test method | |
| CN109960238B (en) | Automatic test system and method for vehicle diagnostic instrument | |
| CN111965609A (en) | Radar reliability evaluation method and device, electronic equipment and readable storage medium | |
| CN112214912A (en) | External automatic test system and airborne equipment test 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 |