CN104536435A - Online diagnosis method for linear control system network - Google Patents
Online diagnosis method for linear control system network Download PDFInfo
- Publication number
- CN104536435A CN104536435A CN201410795268.9A CN201410795268A CN104536435A CN 104536435 A CN104536435 A CN 104536435A CN 201410795268 A CN201410795268 A CN 201410795268A CN 104536435 A CN104536435 A CN 104536435A
- Authority
- CN
- China
- Prior art keywords
- network
- control system
- fuzzy
- fuzzy inference
- function
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0208—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the configuration of the monitoring system
- G05B23/0213—Modular or universal configuration of the monitoring system, e.g. monitoring system having modules that may be combined to build monitoring program; monitoring system that can be applied to legacy systems; adaptable monitoring system; using different communication protocols
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Small-Scale Networks (AREA)
- Maintenance And Management Of Digital Transmission (AREA)
Abstract
The invention relates to an online diagnosis method for a linear control system network. The method comprises the steps that first, a model including two adaptive neural fuzzy inference systems is established, linear control system network state parameters obtained in a fault environment are used as sample data input, a mixed learning algorithm is used for conducting offline training on the two adaptive neural fuzzy inference systems, fuzzy control rules are extracted respectively, then the fuzzy control rules are converted into a loop-up table, a network health degree calculation function and a network fault reason judging function are generated and are added into a controller node of a linear control system, an linear control system online diagnosis algorithm based on the adaptive neural fuzzy inference systems is formed, and online diagnosis is conducted on the network health degree and the fault reason of the linear control system.
Description
Technical field
The present invention relates to a kind of line control system network inline diagnosis method based on Adaptive Neuro-fuzzy Inference.
Background technology
Along with the development of modern electronic technology, the future development of automotive electronics forward intelligentized control method, and adopt bus that various Vehicle Electronic Control model calling is become In-vehicle networking, traditional mechanical mechanism transfer control signal can not be needed, but utilize electronically to drive a car, this electronically is exactly wire control technology.The automotive interior communication that is constantly applied as of wire control technology offers convenience with the while of intelligentized, brings new challenge also to the development of automotive electronics.Owing to being directly connected to the security of automobile, it requires high for the reliability of comprised each parts, especially comprise the bus communication technology playing critical transmissions effect, in wire control technology, the more employing of bus communication technology is based on the FlexRay bus of time triggered.
The inline diagnosis of network is exactly carry out real-time diagnosis from the angle of bus communication to the ruuning situation of bus, for line control system network, a rational inline diagnosis strategy is for the normal communication process of retention wire Ore-controlling Role, and the reliability of system and security are all necessary.In-circuit diagnostic system (OBD) has been integrated with at present on vehicle, the mistake detected is stored with the form of diagnostic trouble code (DTC), but only have obviously network failure just can be detected, the situations such as such as bus short circuit open circuit, communication stopping.Just may there is a kind of situation in this, even if wrong existence in bus, as long as but these mistakes do not affect normal communication, number of errors is exactly in tolerance interval, traditional in-circuit diagnostic system just cannot find these implicit faults, these problems are progressively accumulated, and probably cause system cannot proper communication.
For the insurmountable problem of traditional in-circuit diagnostic system, Chinese scholars is launched to study from data fusion, network management and the multiple angles such as diagnosing protocol, diagnosis algorithm, as document " research of the network management of CAN_FlexRay bus system and diagnosing protocol " (is opened and joined, Master's thesis, HeFei University of Technology) devise CAN-FlexRay gateway network operating strategy, can to node time-out, message is overtime etc. diagnoses, but this Diagnostic Strategy only rests on monitoring aspect, further process is not done to fault data, can not analyzing failure cause.Document " Diagnostic Fusion for Time-Triggered AutomotiveNetworks " (Utsav Drolia etc., Carnegie Mellon University, 2012IEEE 14th InternationalSymposium on High-Assurance Systems Engineering) in devise FlexRay bus system diagnostic method based on neural network, classification diagnosis can be carried out to the error situation of FlexRay bus, but the neural network algorithm designed by the method only obtains network failure reason, a qualitative judgement can not be provided to current network running status, as current network exists potential danger, or although current network is wrong, but still can run, thus provide foundation for fault processing module.Also do not see at present according to historical data and the current data monitored, also can provide the inline diagnosis method of network operation state and network failure reason efficiently simultaneously.
Summary of the invention
The object of the invention is, for the FlexRay line control system adopting time triggered bus, to propose a kind of inline diagnosis method based on adaptive neural network fuzzy system, the real time execution situation of supervisory network, and judge failure cause.The method can find problem potential in line control system network timely, judges line control system network operation state, for improving the reliability of the line control system network communications technology and real-time for playing a positive role.
The present invention judges from network operation state and failure cause judges that comprehensive real-time diagnosis is carried out to FlexRay network system in two aspects.Introduce the running status that " network health degree " this concept represents network, but " health " or " unhealthy " is a fuzzy concept, failure cause judges it is also a fuzzy concept in addition, because the display form of fault has similarity, no matter as " internal error " or " external disturbance " erroneous frame all likely increases, determining " internal error " or " external disturbance " is also a fuzzy concept.If will finally obtain fuzzy concept from concrete data, just must by fuzzy inference system.Fuzzy inference system does not rely on accurate mathematical analysis, proposes If-Then rule and sets up fuzzy model, design Fuzzy control system based on this from the experimental knowledge and reasoning process of human expert.But, only rely on human knowledge, be difficult to shape and the number of selecting suitable membership function.If utilize Adaptive Neuro-fuzzy Inference, historical data is carried out the training of off-line, then training the fuzzy control rule obtained to be embedded in fuzzy control model, just can reduce training error to greatest extent, improving the accuracy and reliability of system.
The technical scheme realizing above-mentioned purpose is:
Based on the line control system network inline diagnosis method of Adaptive Neuro-fuzzy Inference, comprise the following steps:
Step one: the line control system network building FlexRay bus communication, is extracted in the network operation state parameter under failure environment;
Step 2: build two Adaptive Neuro-fuzzy Inference in Matlab/Simulink, the sample data obtained using network operation state parameter is as input, use hybrid learning algorithm to carry out off-line training to two Adaptive Neuro-fuzzy Inference, extract the fuzzy control rule of network health degree and network failure reason respectively;
Step 3: fuzzy control rule is converted to question blank, generating network inline diagnosis function, comprise network health degree computing function and network failure reason decision function, be embedded in line control system Network Controller nodes, finally obtain line control system network inline diagnosis result.
Described step one comprises following steps further:
Steps A: the communication mode selecting two nodes, its interior joint one implants μ C/OS-II operating system, and the basis of FlexRay bottom communication is carried out the process of multitask, and node two utilizes query method to carry out the statistics of state parameter;
Step B: by adding random signal interference in FlexRay bus, electromagnetic interference (EMI), the failure environment that manufacture physical fault etc. are different, extracts the state and the network state parameters that occur each time slot in FlexRay communication process.
Described step 2 comprises following steps further:
Steps A: in the network state parameters extracted, selects the index of three inlinees diagnosis, the cycle of signal in network, and the number of packet loss and the situation of mistake are the index of inline diagnosis.To these three selecting index multi-group datas, and standardization is carried out to selected data, make its eigenwert be mapped on [0,1] interval;
Step B: the input quantity of the fuzzy neural network that selected two Adaptive Neuro-fuzzy Inference (ANFIS) construct is the cycle, and packet loss number and error situation, output quantity is respectively network health degree and network failure reason.Two Adaptive Neuro-fuzzy Inference input quantity dimensions are 3, and the fuzzy partition number of input quantity is 5, and the membership function of each input component is Gaussian function;
Step C: in two Adaptive Neuro-fuzzy Inference, be multiplied by membership function, calculates the relevance grade of each rule, relevance grade is after normalization computing, calculate the output of each fuzzy rule, and obtain the output of system, be respectively network health degree and network failure reason;
Step D: adopt hybrid learning algorithm, carry out off-line training using the sample data that the state parameter of network obtains as input, determine consequent parameter, extract the fuzzy control rule of two Adaptive Neuro-fuzzy Inference respectively;
Step e: the network health degree of generation and network failure reason fuzzy control rule are directly embedded in the Fuzzy Logic controller control module in Matlab/Simulink, obtain two fuzzy inference systems.
Described step 3 comprises following steps further:
Steps A: two fuzzy inference systems are regarded as a black box respectively, input-output mappings transformation is question blank, in recycling Matlab/Simulink for the automatic Code Generation of Freescale series monolithic question blank generating network health degree computing function and network failure reason decision function.This mode is higher than directly fuzzy inference system being carried out real time workshop efficiency, and more saving resource;
Step B: the inline diagnosis function of generation is comprised network health degree computing function and network failure reason decision function, be directly embedded in line control system Network Controller nodes, by function call, the result of line control system inline diagnosis just can be obtained when abnormal conditions appear in network.
Beneficial effect of the present invention:
The present invention is based on the line control system network inline diagnosis algorithm of Adaptive Neuro-fuzzy Inference, by parameter during collection network malfunction as sample, hybrid learning algorithm is adopted to carry out off-line training, inline diagnosis is carried out in embedded network controller node again after obtaining network inline diagnosis algorithm, health degree and the failure cause of network effectively can be obtained according to the state parameter in network operation process, the running status at real-time monitoring networking, thus problem potential in network was found timely before ceased communication, the reliability of effective raising line control system network service.
Accompanying drawing explanation
Fig. 1 is the main flow chart of line control system network inline diagnosis method of the present invention;
Fig. 2 is line control system network failure data sample of the present invention citing;
Fig. 3 is the process flow diagram of Adaptive Neuro-fuzzy Inference of the present invention;
Fig. 4 is the Adaptive Neuro-fuzzy Inference structural drawing that the present invention is directed to network health degree;
Fig. 5 is Adaptive Neuro-fuzzy Inference off-line training error change figure of the present invention;
Fig. 6 is line control system network health degree variation diagram of the present invention;
Fig. 7 is line control system complete period network inline diagnosis figure of the present invention.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention will be further described.
Fig. 1 is the line control system network inline diagnosis method that the present invention is based on Adaptive Neuro-fuzzy Inference, first by gather FlexRay network failure state time parameter as sample, off-line builds two Adaptive Neural-fuzzy Inference models, and generates corresponding network health degree and network failure reason fuzzy control rule.Further, fuzzy control rule is converted to question blank, generating network inline diagnosis function, comprise network health degree computing function and network failure reason decision function, network inline diagnosis function is embedded in network controller, just can carry out inline diagnosis, obtain health degree and the network failure reason of network according to the state parameter in network operation process, the running status of real-time monitor network.
For wire-controlled steering system, the line control system network comprising two nodes is built based on FlexRay bus, its interior joint one is the steering wheel controller node of wire-controlled steering system, what node two was wire-controlled steering system turns to actuator controller node, is communicated between two nodes by FlexRay bus.In this embodiment, adopt Freescale MC9S12XF512 series monolithic as FlexRay communication node.
Line control system network inline diagnosis method based on Adaptive Neuro-fuzzy Inference mainly comprises three steps:
Step one: to steering wheel controller node and turn to the FlexRay protocol register in actuator controller node to carry out reasonable disposition in line control system network, network operation state parameter is extracted by self-defining function under failure environment, as signal period, packet loss number, error situation etc., for Adaptive Neuro-fuzzy Inference off-line training provides sample.
Concrete steps are as follows:
Steps A: select two nodes to communicate mutually, its interior joint one steering wheel controller node implants μ C/OS-II operating system, according to the file structure of μ C/OS-II, to OS_CPU.H, OS_CPU_A.ASM, OS_CPU_C.C file is modified, and the basis of FlexRay bottom communication utilizes interrupt mode to realize multi-task scheduling; Node two turns to actuator controller node to utilize query method to read the data of relevant status register, and the state of each time slot in analyzing communication process, extracts the cycle of signal, the number of packet loss, the network state parameters such as the situation of mistake.
Step B: by adding random signal interference in FlexRay bus, electromagnetic interference (EMI), the failure environment that manufacture physical fault etc. are different, extracts each time slot state and network state parameters in FlexRay communication process, as historical data, for next step off-line training provides sample.Fig. 2 is the citing of line control system network failure data sample, reflects message cycle and error situation situation over time.
Step 2: as shown in Figure 3, in the process flow diagram of Adaptive Neuro-fuzzy Inference, two Adaptive Neuro-fuzzy Inference are built in Matlab/Simulink environment, use hybrid learning algorithm, off-line training is carried out as historical data input using the network state parameters that the first step obtains, two Adaptive Neuro-fuzzy Inference are trained separately, extracts the fuzzy control rule of Adaptive Neuro-fuzzy Inference.
Concrete steps are as follows:
Steps A: in the network state parameters extracted, selects the cycle of signal in network, and the number of packet loss and the situation of mistake are three inline diagnosis indexs.Standardization is carried out to these three achievement datas, makes its eigenwert be mapped on [0,1] interval;
Step B: the input quantity of the fuzzy neural network that selected two Adaptive Neuro-fuzzy Inference (ANFIS) construct is the cycle, packet loss number and error situation, two Adaptive Neuro-fuzzy Inference input quantity dimensions are 3, and the fuzzy partition number of input quantity is 5.Output quantity is respectively network health degree and network failure reason, wherein the basic domain of network health degree [0,0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1], when network service is normal, network health degree is 1, when network service stops, network health degree is 0, and during other network service abnormality, network health degree is corresponding value within the scope of 0-1.The basic domain [0 of network failure reason, 1,2,3], when network service is normal, network failure reason is 0, and when network service is extremely because the internal errors such as controller software cause, network failure reason is 1, when network service is extremely because external electromagnetic interference etc. causes, network failure reason is 2, and when network service is extremely because physical fault etc. causes, network failure reason is 3.It is the Adaptive Neuro-fuzzy Inference structural drawing that the present invention is directed to network health degree shown in Fig. 4.
The membership function of each input component is Gaussian function:
Wherein, i=1,2,3; J=1,2,3,4,5; a
ijand c
ijfor width and the center of membership function, x
ifor the given parameters of network.This Adaptive Neuro-fuzzy Inference comprises 125 fuzzy control rules altogether, and its fuzzy control collection is as follows:
Rule 1:if (x
1is A
11) and (x
2is A
21) and (x
3is A
31) then f
1=p
10+ p
11x
1+ p
12x
2+ p
13x
3
Rule 2:if (x
1is A
12) and (x
2is A
22) and (x
3is A
32) then f
2=p
20+ p
21x
1+ p
22x
2+ p
23x
3
Rule 3:if (x
1is A
12) and (x
2is A
22) and (x
3is A
33) then f
3=p
30+ p
31x
1+ p
32x
2+ p
33x
3
……
Rule 125:
if(x
1is A
15)and(x
2is A
25)and(x
3is A
35)then f
125＝p
125，0+p
125，1x
1+p
125，2x
2+p
125，3x
3
Wherein p
kmfor consequent parameter (k=1,2,3 ... 125, m=0,1,2,3), f
k(k=1,2,3 ... 125) for corresponding to the output of every bar fuzzy rule.
Step C: in two Adaptive Neuro-fuzzy Inference, be multiplied by membership function, calculates the relevance grade w of each rule
k, relevance grade obtains after normalization computing
the output of final system is f:
w
k＝A
k1(x
1)×A
k2(x
2)×A
k3(x
3)
Make x
0=1, k=1,2,3 ... 125, m=0,1,2,3.Given parameters a
ijand c
ij, in whole network, need the parameter learnt just to only have consequent parameter p
km;
The output of two Adaptive Neuro-fuzzy Inference is respectively network health degree and network failure reason.
Step D: utilize hybrid learning algorithm to train separately two Adaptive Neuro-fuzzy Inference, to determine consequent parameter p
km, extract the fuzzy control rule of two Adaptive Neuro-fuzzy Inference.Hybrid learning algorithm comprises least square method and back-propagation algorithm.First the output of system can be expressed as:
f＝B·X
Wherein, column vector X is conclusion vector, and application least square method can obtain the optimum estimate X of the conclusion vector under square error minimum (min||BX-f||) meaning
*:
X
*＝(B
TB)
-1B
Tf
Then, when there being N group to input data, if the error function of system is:
T=1 in formula, 2,3 ... N, f
tfor reality exports, f
dtfor desired output.When conclusion vector is fixing time, adopt the BP algorithm in feedforward neural network, error is oppositely passed to input end by output terminal, with gradient descent method, upgrade premise parameter c
ijand a
ij, thus change the shape of subordinate function, until training error value is less than the threshold value preset.Training error as shown in Figure 5;
In formula, i=1,2,3, j=1,2,3,4,5, β >0 is learning efficiency.
Step e: the network health degree of generation and network failure reason fuzzy control rule are directly embedded in the Fuzzy Logic controller control module in Matlab/Simulink, obtain two fuzzy inference systems.
Step 3: after two fuzzy inference systems are all trained, fuzzy inference rule in system is converted to question blank, and be created on radiodiagnosis x function by automatic Code Generation, comprise network health degree computing function and network failure reason decision function, these two functions can be directly embedded in line control system nodes controller, carry out the inline diagnosis of line control system network.
Concrete steps are as follows:
Steps A: two fuzzy inference systems are regarded as a black box respectively, input-output mappings transformation is question blank, automatic Code Generation for Freescale series monolithic in recycling Matlab/Simulink is created on radiodiagnosis x function question blank, comprises network health degree computing function and network failure reason decision function.This mode is higher than directly fuzzy inference system being carried out real time workshop efficiency, and more saving resource;
Step B: by the inline diagnosis function generated, comprise network health degree computing function and network failure reason decision function, be directly embedded in line control system Network Controller nodes, by function call, just can obtain the result of line control system inline diagnosis when abnormal conditions appear in network.As shown in Figure 6, when line control system FlexRay network does not have additional any external influences, bus running status is normal, and the health degree of network also remains on 1, but when system adds external disturbance, the health degree of network is also along with declining.Known, when network health degree lower than 1 time, just there is the situation of some mistakes in network internal, the error number of just accumulation is not enough to make ceased communication.
Figure 7 shows that one more fully based on FlexRay network complete period inline diagnosis figure, when occurring message frame decreased number or increasing, and erroneous frame number more time, the erroneous frame number of the cycle according to current message, Network Packet Loss number, network is carried out network health degree judgement by network inline diagnosis algorithm, when abnormal conditions appear in network, appearance declines by network health degree, and can determine current network abnormal cause is internal error, external disturbance or physical fault simultaneously.
The present invention carries out online diagnosis to the network of line control system, the state of bus communication is judged by the health degree of network, thus find problem potential in network timely, analyze abnormal network cause, and carry out correction and make network get back to normal state, effectively raise the reliability of line control system network service.
Claims (4)
1. a line control system network inline diagnosis method, is characterized in that, described line control system network inline diagnosis method comprises the following steps:
Step one: the line control system network building FlexRay bus communication, is extracted in the network operation state parameter under failure environment;
Step 2: build two Adaptive Neuro-fuzzy Inference in Matlab/Simulink, the sample data obtained using network operation state parameter is as input, use hybrid learning algorithm to carry out off-line training to two Adaptive Neuro-fuzzy Inference, extract the fuzzy control rule of network health degree and network failure reason respectively;
Step 3: fuzzy control rule is converted to question blank, generating network inline diagnosis function, comprise network health degree computing function and network failure reason decision function, be embedded in line control system Network Controller nodes, finally obtain line control system network inline diagnosis result.
2. line control system network inline diagnosis method according to claim 1, it is characterized in that, described step one comprises following steps:
Steps A: the communication mode selecting two nodes, its interior joint one implants μ C/OS-II operating system, and the basis of FlexRay bottom communication is carried out the process of multitask, and node two utilizes query method to carry out the statistics of state parameter;
Step B: by adding random signal interference in FlexRay bus, electromagnetic interference (EMI), the failure environment that manufacture physical fault etc. are different, extracts the state and the network state parameters that occur each time slot in FlexRay communication process.
3. line control system network inline diagnosis method according to claim 1, it is characterized in that, described step 2 comprises following steps:
Steps A: in the network state parameters extracted, selects the index of three inlinees diagnosis, the cycle of signal in network, and the number of packet loss and the situation of mistake are the index of inline diagnosis; To these three selecting index multi-group datas, and standardization is carried out to selected data, make its eigenwert be mapped on [0,1] interval;
Step B: the input quantity of the fuzzy neural network that selected two Adaptive Neuro-fuzzy Inference (ANFIS) construct is the cycle, packet loss number and error situation, and output quantity is respectively network health degree and network failure reason; Two Adaptive Neuro-fuzzy Inference input quantity dimensions are 3, and the fuzzy partition number of input quantity is 5, and the membership function of each input component is Gaussian function;
Step C: in two Adaptive Neuro-fuzzy Inference, be multiplied by membership function, calculates the relevance grade of each rule, described relevance grade is after normalization computing, calculate the output of each fuzzy rule, and obtain the output of system, be respectively network health degree and network failure reason;
Step D: adopt hybrid learning algorithm, carry out off-line training using the sample data that the state parameter of network obtains as input, determine consequent parameter, extract the fuzzy control rule of two Adaptive Neuro-fuzzy Inference respectively;
Step e: the network health degree of generation and network failure reason fuzzy control rule are directly embedded in the Fuzzy Logic controller control module in Matlab/Simulink, obtain two fuzzy inference systems.
4. line control system network inline diagnosis method according to claim 1, it is characterized in that, described step 3 comprises following steps:
Steps A: two fuzzy inference systems are regarded as a black box respectively, input-output mappings transformation is question blank, in recycling Matlab/Simulink for the automatic Code Generation of Freescale series monolithic question blank generating network health degree computing function and network failure reason decision function;
Step B: by the inline diagnosis function generated, comprise network health degree computing function and network failure reason decision function, be directly embedded in line control system Network Controller nodes, by function call, just can obtain the result of line control system inline diagnosis when abnormal conditions appear in network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410795268.9A CN104536435B (en) | 2014-12-18 | 2014-12-18 | A kind of line control system network inline diagnosis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410795268.9A CN104536435B (en) | 2014-12-18 | 2014-12-18 | A kind of line control system network inline diagnosis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104536435A true CN104536435A (en) | 2015-04-22 |
| CN104536435B CN104536435B (en) | 2017-06-30 |
Family
ID=52851977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410795268.9A Active CN104536435B (en) | 2014-12-18 | 2014-12-18 | A kind of line control system network inline diagnosis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104536435B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105721199A (en) * | 2016-01-18 | 2016-06-29 | 中国石油大学(华东) | Real-time cloud service bottleneck detection method based on kernel density estimation and fuzzy inference system |
| CN106597178A (en) * | 2017-01-18 | 2017-04-26 | 重庆水利电力职业技术学院 | ANFIS digital pre-distorting method of relay protection test device LPA |
| CN109088754A (en) * | 2018-07-31 | 2018-12-25 | 北京航空航天大学 | A kind of COMMUNICATION NETWORK PERFORMANCES failure reason and characteristic parameter association relationship analysis method |
| CN109101010A (en) * | 2018-09-30 | 2018-12-28 | 深圳市元征科技股份有限公司 | A kind of Diagnosis method of automobile faults and relevant device |
| CN109154811A (en) * | 2016-06-13 | 2019-01-04 | Abb瑞士股份有限公司 | Method for assessing the health status of industrial equipment |
| CN110149265A (en) * | 2018-03-14 | 2019-08-20 | 腾讯科技（深圳）有限公司 | Message shows method, apparatus and computer equipment |
| CN113269952A (en) * | 2020-02-14 | 2021-08-17 | 美光科技公司 | Drive-by-wire sensor monitoring in a vehicle |
| CN113780592A (en) * | 2021-08-28 | 2021-12-10 | 特斯联科技集团有限公司 | Smart city air data link management system, method and computer program product |
| US11498388B2 (en) | 2019-08-21 | 2022-11-15 | Micron Technology, Inc. | Intelligent climate control in vehicles |
| US11586194B2 (en) | 2019-08-12 | 2023-02-21 | Micron Technology, Inc. | Storage and access of neural network models of automotive predictive maintenance |
| US11586943B2 (en) | 2019-08-12 | 2023-02-21 | Micron Technology, Inc. | Storage and access of neural network inputs in automotive predictive maintenance |
| US11635893B2 (en) | 2019-08-12 | 2023-04-25 | Micron Technology, Inc. | Communications between processors and storage devices in automotive predictive maintenance implemented via artificial neural networks |
| US11650746B2 (en) | 2019-09-05 | 2023-05-16 | Micron Technology, Inc. | Intelligent write-amplification reduction for data storage devices configured on autonomous vehicles |
| US11693562B2 (en) | 2019-09-05 | 2023-07-04 | Micron Technology, Inc. | Bandwidth optimization for different types of operations scheduled in a data storage device |
| US11702086B2 (en) | 2019-08-21 | 2023-07-18 | Micron Technology, Inc. | Intelligent recording of errant vehicle behaviors |
| US11709625B2 (en) | 2020-02-14 | 2023-07-25 | Micron Technology, Inc. | Optimization of power usage of data storage devices |
| US11748626B2 (en) | 2019-08-12 | 2023-09-05 | Micron Technology, Inc. | Storage devices with neural network accelerators for automotive predictive maintenance |
| US11775816B2 (en) | 2019-08-12 | 2023-10-03 | Micron Technology, Inc. | Storage and access of neural network outputs in automotive predictive maintenance |
| US11830296B2 (en) | 2019-12-18 | 2023-11-28 | Lodestar Licensing Group Llc | Predictive maintenance of automotive transmission |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11853863B2 (en) | 2019-08-12 | 2023-12-26 | Micron Technology, Inc. | Predictive maintenance of automotive tires |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007120960A (en) * | 2005-10-25 | 2007-05-17 | Honda Motor Co Ltd | Failure diagnosis device of sub-power supply |
| CN102868583A (en) * | 2012-06-06 | 2013-01-09 | 浙江吉利汽车研究院有限公司杭州分公司 | FlexRay bus joint with fault diagnosis function |
| CN104155574A (en) * | 2014-07-31 | 2014-11-19 | 国网湖北省电力公司武汉供电公司 | Power distribution network fault classification method based on adaptive neuro-fuzzy inference system |
| CN104202200A (en) * | 2014-09-15 | 2014-12-10 | 中国科学院电工研究所 | FlexRay bus-based online network diagnosis device |
-
2014
- 2014-12-18 CN CN201410795268.9A patent/CN104536435B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007120960A (en) * | 2005-10-25 | 2007-05-17 | Honda Motor Co Ltd | Failure diagnosis device of sub-power supply |
| CN102868583A (en) * | 2012-06-06 | 2013-01-09 | 浙江吉利汽车研究院有限公司杭州分公司 | FlexRay bus joint with fault diagnosis function |
| CN104155574A (en) * | 2014-07-31 | 2014-11-19 | 国网湖北省电力公司武汉供电公司 | Power distribution network fault classification method based on adaptive neuro-fuzzy inference system |
| CN104202200A (en) * | 2014-09-15 | 2014-12-10 | 中国科学院电工研究所 | FlexRay bus-based online network diagnosis device |
Non-Patent Citations (2)
| Title |
|---|
| 师黎: "基于自适应模糊神经网络的多模型在线故障诊断", 《自动化仪表》 * |
| 段建民，朱亮，于涌川: "基于FlexRay总线的线控转向***通信网络", 《仪表技术与传感器》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105721199B (en) * | 2016-01-18 | 2019-06-07 | 中国石油大学(华东) | A kind of real-time cloud service bottleneck detection method based on Density Estimator and fuzzy inference system |
| CN105721199A (en) * | 2016-01-18 | 2016-06-29 | 中国石油大学(华东) | Real-time cloud service bottleneck detection method based on kernel density estimation and fuzzy inference system |
| CN109154811A (en) * | 2016-06-13 | 2019-01-04 | Abb瑞士股份有限公司 | Method for assessing the health status of industrial equipment |
| CN106597178A (en) * | 2017-01-18 | 2017-04-26 | 重庆水利电力职业技术学院 | ANFIS digital pre-distorting method of relay protection test device LPA |
| CN110149265A (en) * | 2018-03-14 | 2019-08-20 | 腾讯科技（深圳）有限公司 | Message shows method, apparatus and computer equipment |
| CN109088754A (en) * | 2018-07-31 | 2018-12-25 | 北京航空航天大学 | A kind of COMMUNICATION NETWORK PERFORMANCES failure reason and characteristic parameter association relationship analysis method |
| CN109101010A (en) * | 2018-09-30 | 2018-12-28 | 深圳市元征科技股份有限公司 | A kind of Diagnosis method of automobile faults and relevant device |
| US11586194B2 (en) | 2019-08-12 | 2023-02-21 | Micron Technology, Inc. | Storage and access of neural network models of automotive predictive maintenance |
| US11775816B2 (en) | 2019-08-12 | 2023-10-03 | Micron Technology, Inc. | Storage and access of neural network outputs in automotive predictive maintenance |
| US11748626B2 (en) | 2019-08-12 | 2023-09-05 | Micron Technology, Inc. | Storage devices with neural network accelerators for automotive predictive maintenance |
| US11635893B2 (en) | 2019-08-12 | 2023-04-25 | Micron Technology, Inc. | Communications between processors and storage devices in automotive predictive maintenance implemented via artificial neural networks |
| US11586943B2 (en) | 2019-08-12 | 2023-02-21 | Micron Technology, Inc. | Storage and access of neural network inputs in automotive predictive maintenance |
| US11498388B2 (en) | 2019-08-21 | 2022-11-15 | Micron Technology, Inc. | Intelligent climate control in vehicles |
| US11702086B2 (en) | 2019-08-21 | 2023-07-18 | Micron Technology, Inc. | Intelligent recording of errant vehicle behaviors |
| US11650746B2 (en) | 2019-09-05 | 2023-05-16 | Micron Technology, Inc. | Intelligent write-amplification reduction for data storage devices configured on autonomous vehicles |
| US11693562B2 (en) | 2019-09-05 | 2023-07-04 | Micron Technology, Inc. | Bandwidth optimization for different types of operations scheduled in a data storage device |
| US11830296B2 (en) | 2019-12-18 | 2023-11-28 | Lodestar Licensing Group Llc | Predictive maintenance of automotive transmission |
| US11531339B2 (en) | 2020-02-14 | 2022-12-20 | Micron Technology, Inc. | Monitoring of drive by wire sensors in vehicles |
| US11709625B2 (en) | 2020-02-14 | 2023-07-25 | Micron Technology, Inc. | Optimization of power usage of data storage devices |
| CN113269952A (en) * | 2020-02-14 | 2021-08-17 | 美光科技公司 | Drive-by-wire sensor monitoring in a vehicle |
| CN113269952B (en) * | 2020-02-14 | 2023-10-10 | 美光科技公司 | Method for predictive maintenance of a vehicle, data storage device and vehicle |
| CN113780592B (en) * | 2021-08-28 | 2022-05-03 | 特斯联科技集团有限公司 | Smart city air data link management system, method and computer program product |
| CN113780592A (en) * | 2021-08-28 | 2021-12-10 | 特斯联科技集团有限公司 | Smart city air data link management system, method and computer program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104536435B (en) | 2017-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104536435A (en) | Online diagnosis method for linear control system network | |
| Cai et al. | Bayesian networks in fault diagnosis | |
| CN102208028B (en) | Fault predicting and diagnosing method suitable for dynamic complex system | |
| CN102879680B (en) | The general detection of rail transit vehicle equipment and method for diagnosing faults and system | |
| CN104512422B (en) | Hybrid electric vehicle fault handling method and its fault processing system | |
| CN102520697B (en) | Onsite information preprocessing method of remote cooperative diagnosis | |
| KR20190107080A (en) | Cloud-based vehicle fault diagnosis method, apparatus and system | |
| CN103195727B (en) | A kind of blower fan on-line condition monitoring apparatus for evaluating | |
| CN114585983B (en) | Method, device and system for detecting abnormal operation state of equipment | |
| Cheng et al. | A BRB-based effective fault diagnosis model for high-speed trains running gear systems | |
| Sankavaram et al. | An integrated health management process for automotive cyber-physical systems | |
| CN101793928A (en) | Phase-shifting full-bridge convertor real-time fault diagnosis method and system | |
| CN105955233A (en) | Vehicle fault diagnosis method and system based on data excavation | |
| Suwatthikul et al. | In-vehicle network level fault diagnostics using fuzzy inference systems | |
| CN104318485A (en) | Power transmission line fault identification method based on nerve network and fuzzy logic | |
| CN110188837A (en) | A kind of MVB network fault diagnosis method based on fuzzy neural | |
| CN113256096A (en) | Power grid fault diagnosis method considering false data injection attack | |
| CN101807314A (en) | Method for processing embedded vehicle working condition hybrid heterogeneous data information in real time | |
| Jin et al. | A human error quantitative analysis of the railway ATO system based upon improved CREAM | |
| Zhang | Model-Based Fault Diagnosis For Automotive Functional Safety | |
| Fan et al. | A Bayesian framework to integrate knowledge-based and data-driven inference tools for reliable yield diagnoses | |
| Schwall et al. | Multi-modal diagnostics for vehicle fault detection | |
| Taha et al. | Online failure analysis and autonomous risk control scheme for electric buses | |
| Wu et al. | Semigroup of fuzzy automata and its application for fast accurate fault diagnosis on machine and anti-fatigue control | |
| Yang | Framework of Electric Vehicle Fault Diagnosis System Based on Diagnostic Communication |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |