CN108494626A - Physical installation improperly Profibus DP industrial field bus communication failure intelligent diagnosing method - Google Patents
Physical installation improperly Profibus DP industrial field bus communication failure intelligent diagnosing method Download PDFInfo
- Publication number
- CN108494626A CN108494626A CN201810245649.8A CN201810245649A CN108494626A CN 108494626 A CN108494626 A CN 108494626A CN 201810245649 A CN201810245649 A CN 201810245649A CN 108494626 A CN108494626 A CN 108494626A
- Authority
- CN
- China
- Prior art keywords
- profibus
- physical
- value
- signal
- improperly
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
- H04L43/0817—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking functioning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/40—Bus networks
- H04L12/40006—Architecture of a communication node
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/06—Generation of reports
- H04L43/065—Generation of reports related to network devices
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/50—Testing arrangements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/40—Bus networks
- H04L2012/40208—Bus networks characterized by the use of a particular bus standard
- H04L2012/40221—Profibus
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Small-Scale Networks (AREA)
- Maintenance And Management Of Digital Transmission (AREA)
Abstract
The invention discloses physical installation improperly Profibus DP industrial field bus communication failure intelligent diagnosing methods.The method includes 1) obtaining all physical layer signals, other physical layer signals input ANN of EMI signal will filter out；2) physical layer signal is analyzed by ANN, is diagnosed to be the physical installation problem for leading to these abnormal signals；3) Profibus frame analysis and diagnosis are carried out to data link layer signals using ES；4) completely new fuzzy system is built to calculate target circulation time TTRValue, utilizes the best TTRValue carries out analysis and diagnosis to user's layer signal.The present invention carries out analyzing and diagnosing to the signal of physical layer, data link layer and client layer in network respectively using ANN, ES and fuzzy system, suitable for all industrial networks communicated using 485 patterns of RS, it can also be applied in corresponding computer system, help to improve the fault diagnosis intelligent level of industrial network system.
Description
Technical field
The present invention relates to industrial field bus technical field, more particularly to physical installation improperly Profibus DP industry
Field bus communication intelligent fault diagnosis method.
Background technology
Industrial automation is most important to the competitiveness and efficiency that improve industrial department, and the industry that it promotes every profession and trade is existing
The development of field bus network (industrial digital communication network) technology.In current field bus protocol widely used in the world, have
Profibus agreements, such as Profibus PA, Profibus DP and PROFINET.
Although industrial communication network has many merits, but they have the quick of height for failure caused by physical installation
Perception, such as using long wiring (influencing traffic rate), cable ground connection or shielding processing are improper, overload or are not used active total
Line terminal organ etc. may all influence network performance.These can change the electrical characteristic of Transmission system, to reduce transmission signal
Performance.
In order to analyze physical layer failure, can use multimeter, bus tester, oscillograph and network monitoring tool and
Physical layer signal is observed using ProfiTrace or Profibus testers and they are passed in data link layer or client layer
Defeated data frame.When analyzing data link layer and user's layer data, the type sequence to break down and statistical data are needed；
When analyzing physical layer data, need to analyze the signal in terms of digital waveform.The communication and installation being likely encountered in network
Improper problem etc. is presented all in the form of digital waveform.And in the prior art, the improper communication network failure that causes of physical installation
Problem is often difficult to carry out intelligent analysis and diagnosis with the digitized form of expression.
Invention content
In order to overcome the deficiencies of the prior art, the present invention is asked for the improper caused failure of industrial communication network physical installation
Topic proposes the Profibus DP industrial field bus communication failure intelligent diagnosing methods of physics Rig up error.The method utilizes
Artificial neural network (Artificial Neural Network；ANN), expert system (Expert System；ES) and fuzzy
System carries out analyzing and diagnosing to the signal of physical layer, data link layer and client layer in network respectively, helps to improve industrial net
The fault diagnosis intelligent level of network system.
The present invention is achieved by the following technical programs.
Physical installation improperly Profibus DP industrial field bus communication failure intelligent diagnosing method, including following step
Suddenly：
Step 1：The variance yields of all physical layer signal types is obtained, the reference threshold of a variance yields is defined, according to not
Same variance yields separates EMI signal from the physical layer signal, will filter out other physical layer signals of EMI signal
Input ANN；
Step 2：Physical layer signal is analyzed by ANN, when analyze for the first time, all physical layer signals
Sample all be used for train ANN, carry out a series of training and test after, detect which signal waveform affect as a result, and by these
Signal is classified, and then is diagnosed to be the physical installation problem for leading to these abnormal signals；
Step 3：Profibus frame analysis and diagnosis, the number of data link layer are carried out to data link layer signals using ES
It is transmitted by Profibus DP agreements according to frame, the operation of the Profibus DP agreements is based on master-slave communication model；
Step 4：Completely new fuzzy system is built to calculate target circulation time TTRValue, according to activation rule, application
Mamdani inferences are exported by centroid method deblurring, obtain best TTRValue, utilizes the best TTRValue believes client layer
Number carry out analysis and diagnosis.
The present invention is based on the improper caused industrial field bus communication failures of Profibus DP protocol realization physical installations
Intelligent diagnostics, physical layer, data link layer and user of the relied on data of the diagnosis respectively from Profibus DP agreements
Layer analyzes the sample of signal transmitted by industrial network using ANN, and being diagnosed to be causes Profibus DP protocol physical layers to be sent out
Then the installation question of raw signal waveform interference is analyzed the data frame of data-link layer transfer using ES and is diagnosed, most
Afterwards, completely new fuzzy system is built to calculate best target circulation time value TTR, to solve the complexity problem calculated and carry
For good network performance, the inaccuracy in needing to handle mathematics or conceptual model, ambiguity, abstractness and paradox
When, the fuzzy system can be used.The present invention helps to improve the fault diagnosis intelligent level of industrial network system.
Preferably, in step 3, for the master-slave communication model, main equipment is sent to the slave station based on context responded
Data frame, there are one network address for each slave station, and in some cases, network configuration mistake may result in protocol failure,
At this moment, corresponding frame sequence, which is shown, has had submitted which type of mistake, and the historical analysis based on transmission frame, ES would indicate that can
The configuration error that can occur.
Preferably, according to Profibus FMS, DP and PA (1998) specification, T in step 4TRCalculation expression be：
minTTR=NA* (TTC+highTMC)+k*lowTMC+MT*retTMC (1)
Wherein, NA indicates the quantity of main website；TTCIndicate the token cycle time；TMCIt indicates the message cycle time, depends on frame
Length；K indicates the estimative figure in low priority message period in the token circulation period；MT indicates the message weight in the token circulation period
Try periodicity；retTMCIndicate that message retries the period.
Specifically, it is contemplated that correct setting target circulation time value TTRImportance and determine this parameter when difficulty
Good network performance is provided in order to solve the complexity problem calculated with the error of generation, needs to develop a fuzzy system
To calculate TTRValue, whenever system needs to handle the inaccuracy in mathematics or conceptual model, ambiguity, abstractness and paradox
When, the fuzzy system can be used.
Preferably, following simplified formula is used in step 4：
Tmc≈(380+300*S+11*D)*Tbit+75μs (2)
Wherein, S indicates that the quantity of slave station, D indicate the I/O data word joint numbers of all slave stations, TbitValue depends on network transmission
Baud rate.The advantage of doing so is that：Can ignore or some parameters that rough estimate is unrelated with final result because point
When analysing equation (1), it is difficult to the value of certain parameters is accurately estimated, for example, determining that the message in the token circulation period retries the period
Several MT depends on network quality etc..Pass through centroid method deblurring using Mamdani inferences using the result of calculation of equation (2)
Output, best T is provided for networkTRValue.
Preferably, according to T set by the user in off-line arrangementTRValue creates three fuzzy systems, two of which fuzzy set
Conjunction represents input variable, and the input variable is to send the time T of aperiodic informationAWith the time T of sending cycle informationC, another
A fuzzy set represents output variable, i.e., the T of the described fuzzy system suggestionTRValue, using Mamdani inferences, is gone by centroid method
Fuzzy output obtains best TTRValue.
Preferably, TCValue than configuration TTRLow 30% is acceptable, TAValue than configuration TTRLow 60% is that can connect
It receives.
Preferably, when the baud rate of network transmission is 1.5MBit/s, TbitValue is 0.667 μ s.
Preferably, the data transmission between the physical layer of the Profibus DP agreements, data link layer and client layer is adopted
With RS-485 patterns.
Preferably, the profibus fault detection systems connect profibus simulators by ICP/IP protocol, receive
The data frame of sample of signal and the data link layer and client layer transmitted by Profibus agreements from physical layer, provides
Frame is Profibus frames.
Further, the Profibus simulators pass through the sample of signal from ProfiTrace tools and oscillograph importing
Obtain transmission frame information.The Profibus frames are sent to the Profibus fault detection systems after being created.
Preferably, the profibus fault detection systems include ANN modules, ES modules and fuzzy system module.
The beneficial effects of the present invention are 1) present invention introduces ANN to be used for Modulation recognition, effectively increase Modulation recognition essence
Degree, method has versatility and robustness, and can be better diagnosed out using ANN and be transmitted caused by physical installation is improper
The distortion of signal waveform；2) present invention constructs completely new fuzzy system, can obtain optimal TTR values, rationally weighs
Profibus token passing network delay performances；3) all industrial nets that the present invention is suitable for being communicated using RS-485 patterns
Network can also be applied in corresponding computer system, help to improve the fault diagnosis intelligent level of industrial network system.
Description of the drawings
Fig. 1 is the structural schematic diagram of Profibus fault detection systems according to the embodiment；
Fig. 2 is the workflow schematic diagram of ANN systems according to the embodiment.
Specific implementation mode
Clear, complete description is carried out to the technical solution of various embodiments of the present invention below with reference to attached drawing, it is clear that retouched
A part of the embodiment that hair embodiment is only the present invention is stated, instead of all the embodiments.Based on the embodiment of the present invention, originally
Field those of ordinary skill obtained all other embodiment without making creative work, belongs to this hair
Bright protected range.
It is described in further detail below by specific embodiment and in conjunction with attached drawing to the present invention.
Improperly Profibus DP industrial field bus communication failure intelligent diagnosing method includes following step to physical installation
Suddenly：
(1) variance yields for obtaining physical layer whole sample of signal, defines the reference threshold of a variance yields, by EMI signal
It is separated from the sample of signal, as shown in Figure 1, the reference threshold is defined as 0.4, sample variance is more than 0.4
EMI signal separated from the sample of signal, then will filter out EMI signal other physical layer signals input ANN；
(2) physical layer signal is analyzed by ANN, when analyze for the first time, the sample of all physical layer signals
This is all used to train ANN, after carrying out a series of training and test, detects which signal waveform affects as a result, and believing these
Number classify, and then is diagnosed to be the physical installation problem for leading to these abnormal signals, ANN working-flows figure such as Fig. 1 institutes
Show, the system is with three layers of feedforward architecture and uses backpropagation training algorithm, here three layers be respectively input layer, it is hidden
Hide layer and output layer, multilayer perceptron (Multi-Layer Perceptron；MLP) by 20 input neurons, hidden layers
15 neurons and two output neurons composition, finally, using S-shaped activation primitive, the system is divided into three parts, the
A part is made of the single ANN for being responsible for detection EMI signal and long cable signal, and second part is made of three ANN, is born respectively
Duty detects the idle signal correctly installed, without short-circuit between power terminal and data line A, B, and Part III is by four ANN groups
At being each responsible for detecting correct installation signal, interrupted without effective bus terminal or data line, network line overload and being had
Source bus terminal is overloaded, and is analyzed the physical layer signal of Profibus DP by ANN, when analyze for the first time, institute
There is the sample of signal to be all used to train ANN, then repeatedly trained and tested, to detect which waveform influence result and incite somebody to action
These signals are classified；
(3) Profibus frame analysis and diagnosis, the data of data link layer are carried out to data link layer signals using ES
Frame is transmitted by Profibus DP agreements, and the operation of the Profibus DP agreements is based on master-slave communication model, wherein ES systems
System has the user interface based on Java, is an effective scheme for diagnosing Profibus network problems, logical in the principal and subordinate
Believe in model, main equipment is to the slave station transmission data frame based on context responded, and there are one network address for each slave station, at certain
In the case of a little, network configuration mistake may result in protocol failure, corresponding frame sequence show had submitted it is which type of
Mistake, after carrying out historical analysis to transmission frame, ES would indicate that the configuration error that may occur；
(4) completely new fuzzy system is built to calculate target circulation time TTRValue, according to activation rule, using Mamdani
Inference is exported by centroid method deblurring, obtains best TTRValue, utilizes the best TTRValue carries out user's layer signal
Analysis and diagnosis, in specific implementation, in order to solve to calculate TTRComplexity problem, good network performance is provided, structure is needed
A completely new fuzzy system is built to calculate TTRValue is obscured whenever system needs to handle the inaccuracy in mathematics or conceptual model
Property, when being abstracted with paradox, the fuzzy system can be used, here, according to T set by the user in off-line arrangementTRValue wound
Three fuzzy systems are built, two of which fuzzy set represents input variable, and the input variable is when sending aperiodic information
Between TAWith the time T of sending cycle informationC, another fuzzy set represents output variable, i.e., the T of the described fuzzy system suggestionTR
Value, wherein TCValue than configuration TTRLow 30% is acceptable, TAValue than configuration TTRLow 60% is acceptable,
In specific implementation, after creating these fuzzy sets, the failure that Intelligent fault diagnosis is carried out using method provided by the present invention is examined
Examining system obtains real-time cycle information time and aperiodic information time (T from operational networkC/TA) value, these values are input to
After in fault detection system, it is converted into VERY LOW, LOW, GOOD, then the linguistic variable of HIGH and VERY HIGH selects
The rule of activation provides new TTRLinguistic variable classification, for example can be：IF(TCFor height) AND (TAIt is very low) THEN (TTR
For height), in this model, using Mamdani algorithm inferences, finally, according to activation rule, deblurring is obtained by centroid method
Output, as network provides best TTRValue, here,
According to Profibus FMS, DP and PA (1998) specification, TTRCalculation formula be：
minTTR=NA* (TTC+highTMC)+k*lowTMC+MT*retTMC (1)
Wherein, NA is the quantity of main website；K is the estimative figure in low priority message period in the token circulation period；TTCIt is to enable
Board cycle time；TMCIt is the message cycle time, depends on frame length；MT is that the message in the token circulation period retries periodicity；
retTMCIt is that message retries the period,
Because certain parameters in equation (1) are difficult to accurately obtain, simplified formula is：
Tmc≈(380+300*S+11*D)*Tbit+75μs (2)
In such a case, it is possible to ignore or some parameters that rough estimate is unrelated with final result, parameter S is slave station
Quantity, D is the I/O data word joint numbers of all slave stations, TbitBaud rate of the value depending on network transmission, in specific implementation, net
When the baud rate of network transmission is 1.5MBit/s, TbitValue, which is 0.667 μ s, so far can obtain an optimal TTRValue utilizes institute
State optimal TTRValue carries out analysis and diagnosis to user's layer signal.
Data transmission between the physical layers of heretofore described Profibus DP agreements, data link layer and client layer
Using RS-485 patterns, for all industrial networks communicated using this pattern, it is contemplated that using the present invention, help
In the fault diagnosis intelligent level for improving industrial network system.
Embodiment
As shown in Fig. 2, diagnostic method provided by the invention is applied in computer system, Profibus DP nets are obtained
The diagnosis of network exports.Referring to Fig.2, profibus fault detection systems connect profibus simulators by Ethernet, receives and
From the data sample of physical layer and the data frame of the data link layer and client layer transmitted by Profibus agreements, the data
Sample and data frame transmit in the form of data packet, and the frame provided is Profibus frames.The Profibus simulators are logical
It crosses the sample of signal imported from ProfiTrace tools and oscillograph and obtains transmission frame information.When use ProfiTrace tools
When, text file is exported to from Profibus network collection software packages, and with hexadecimal format, then, software module parsing
All information are simultaneously imported its memory by this file.Using waveform sample of the same step process from oscillograph.It is described
Profibus frames are sent to the Profibus fault detection systems after being created.It is described in order to handle these information
Profibus fault detection systems are divided into three software modules, and the analysis and diagnosis of physical layer signal is carried out using ANN, utilizes ES
The analysis and diagnosis for carrying out data link layer signal carries out the analysis and diagnosis of user's layer signal using fuzzy system.This implementation
The Profibus fault detection systems that example is provided assisting user diagnostic network can ask during network installation and monitoring
Topic, the failure in energy efficient diagnosis network installation and operational process.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, it will be understood by those of ordinary skill in the art that：It still may be used
To modify to the technical solution recorded in previous embodiment, either which part or all technical features are equal
It replaces；And these modifications or replacements, technical solution of the embodiment of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. physical installation improperly Profibus DP industrial field bus communication failure intelligent diagnosing method, which is characterized in that packet
Include following steps：
Step 1：The variance yields of all physical layer signal types is obtained, the reference threshold of a variance yields is defined, according to different
Variance yields separates EMI signal from the physical layer signal, will filter out other physical layer signals input of EMI signal
ANN；
Step 2：Physical layer signal is analyzed by ANN, when analyze for the first time, the sample of all physical layer signals
It is all used to train ANN, after carrying out a series of training and test, detects which signal waveform affects as a result, and by these signals
Classify, and then is diagnosed to be the physical installation problem for leading to these abnormal signals；
Step 3：Profibus frame analysis and diagnosis, the data frame of data link layer are carried out to data link layer signals using ES
It is transmitted by Profibus DP agreements, the operation of the Profibus DP agreements is based on master-slave communication model；
Step 4：Completely new fuzzy system is built to calculate target circulation time TTRValue is pushed away according to activation rule using Mamdani
By being exported by centroid method deblurring, obtain best TTRValue, utilizes the best TTRValue divides user's layer signal
Analysis and diagnosis.
2. physical installation as described in claim 1 improperly Profibus DP industrial field bus communication failure intelligent diagnostics
Method, which is characterized in that in step 3, for the master-slave communication model, main equipment is sent to the slave station based on context responded
Data frame, there are one network address for each slave station, and in some cases, network configuration mistake may result in protocol failure,
At this moment, corresponding frame sequence, which is shown, has had submitted which type of mistake, and the historical analysis based on transmission frame, ES would indicate that can
The configuration error that can occur.
3. physical installation as described in claim 1 improperly Profibus DP industrial field bus communication failure intelligent diagnostics
Method, which is characterized in that according to Profibus FMS, DP and PA (1998) specification, T in step 4TRCalculation expression be：
minTTR=NA* (TTC+highTMC)+k*lowTMC+MT*retTMC (1)
Wherein, NA indicates the quantity of main website；TTCIndicate the token cycle time；TMCIt indicates the message cycle time, depends on frame length；
K indicates the estimative figure in low priority message period in the token circulation period；MT indicates that the message in the token circulation period retries week
Issue；retTMCIndicate that message retries the period.
4. physical installation as claimed in claim 3 improperly Profibus DP industrial field bus communication failure intelligent diagnostics
Method, which is characterized in that following simplified formula is used in step 4：
Tmc≈(380+300*S+11*D)*Tbit+75μs (2)
Wherein, S indicates that the quantity of slave station, D indicate the I/O data word joint numbers of all slave stations, TbitWave of the value depending on network transmission
Special rate.
5. physical installation as described in claim 3 or 4 improperly intelligently examine by Profibus DP industrial field bus communication failure
Disconnected method, which is characterized in that according to T set by the user in off-line arrangementTRValue creates three fuzzy systems, and two of which is fuzzy
Set represents input variable, and the input variable is to send the time T of aperiodic informationAWith the time T of sending cycle informationC, separately
One fuzzy set represents output variable, i.e., the T of the described fuzzy system suggestionTRValue, using Mamdani inferences, passes through centroid method
Deblurring exports, and obtains best TTRValue.
6. physical installation as claimed in claim 5 improperly Profibus DP industrial field bus communication failure intelligent diagnostics
Method, which is characterized in that TCValue than configuration TTRLow 30% is acceptable, TAValue than configuration TTRLow 60% is that can connect
It receives.
7. physical installation as claimed in claim 4 improperly Profibus DP industrial field bus communication failure intelligent diagnostics
Method, which is characterized in that when the baud rate of network transmission is 1.5MBit/s, TbitValue is 0.667 μ s.
8. physical installation as described in claim 1 improperly Profibus DP industrial field bus communication failure intelligent diagnostics
Method, which is characterized in that the data transmission between the physical layers of the Profibus DP agreements, data link layer and client layer
Using RS-485 patterns.
9. a kind of profibus fault detection systems of method according to claim 11 structure, which is characterized in that described
Profibus fault detection systems connect profibus simulators by ICP/IP protocol, receive the sample of signal from physical layer
And the data frame for the data link layer and client layer transmitted by Profibus agreements, the frame provided are Profibus frames.
10. profibus fault detection systems as claimed in claim 9, which is characterized in that the profibus fault detects
System includes ANN modules, ES modules and fuzzy system module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810245649.8A CN108494626B (en) | 2018-03-23 | 2018-03-23 | Intelligent diagnosis method for communication faults of Profibus DP industrial field bus with improper physical installation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810245649.8A CN108494626B (en) | 2018-03-23 | 2018-03-23 | Intelligent diagnosis method for communication faults of Profibus DP industrial field bus with improper physical installation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108494626A true CN108494626A (en) | 2018-09-04 |
| CN108494626B CN108494626B (en) | 2021-08-27 |
Family
ID=63319450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810245649.8A Active CN108494626B (en) | 2018-03-23 | 2018-03-23 | Intelligent diagnosis method for communication faults of Profibus DP industrial field bus with improper physical installation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108494626B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784318A (en) * | 2019-03-13 | 2019-05-21 | 西北工业大学 | The recognition methods of Link16 data-link signal neural network based |
| CN114978858A (en) * | 2021-02-22 | 2022-08-30 | Abb瑞士股份有限公司 | Determining diagnostic information based on non-real time data |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6108616A (en) * | 1997-07-25 | 2000-08-22 | Abb Patent Gmbh | Process diagnosis system and method for the diagnosis of processes and states in an technical process |
| CN1419170A (en) * | 2002-12-17 | 2003-05-21 | 白凤双 | Universal intelligent automatic system |
| US20100064297A1 (en) * | 2008-09-05 | 2010-03-11 | Invensys Systems, Inc. | Configuring And Providing Enhanced Access To Profibus Device Diagnostic Data |
| CN101753486A (en) * | 2008-12-19 | 2010-06-23 | 中国科学院沈阳自动化研究所 | Industrial automation field bus gateway equipment |
| CN102736617A (en) * | 2012-06-18 | 2012-10-17 | 北京首钢自动化信息技术有限公司 | Method for diagnosing PROFIBUS-DP bus |
| CN103973677A (en) * | 2014-06-04 | 2014-08-06 | 周原 | Protocol conversion device from IPv6 to PROFIBUS |
| CN104506338A (en) * | 2014-11-21 | 2015-04-08 | 河南中烟工业有限责任公司 | Fault diagnosis expert system based on decision tree for industrial Ethernet network |
| CN107145546A (en) * | 2017-04-26 | 2017-09-08 | 北京环境特性研究所 | Monitor video personnel's fuzzy retrieval method based on deep learning |
-
2018
- 2018-03-23 CN CN201810245649.8A patent/CN108494626B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6108616A (en) * | 1997-07-25 | 2000-08-22 | Abb Patent Gmbh | Process diagnosis system and method for the diagnosis of processes and states in an technical process |
| CN1419170A (en) * | 2002-12-17 | 2003-05-21 | 白凤双 | Universal intelligent automatic system |
| US20100064297A1 (en) * | 2008-09-05 | 2010-03-11 | Invensys Systems, Inc. | Configuring And Providing Enhanced Access To Profibus Device Diagnostic Data |
| CN101753486A (en) * | 2008-12-19 | 2010-06-23 | 中国科学院沈阳自动化研究所 | Industrial automation field bus gateway equipment |
| CN102736617A (en) * | 2012-06-18 | 2012-10-17 | 北京首钢自动化信息技术有限公司 | Method for diagnosing PROFIBUS-DP bus |
| CN103973677A (en) * | 2014-06-04 | 2014-08-06 | 周原 | Protocol conversion device from IPv6 to PROFIBUS |
| CN104506338A (en) * | 2014-11-21 | 2015-04-08 | 河南中烟工业有限责任公司 | Fault diagnosis expert system based on decision tree for industrial Ethernet network |
| CN107145546A (en) * | 2017-04-26 | 2017-09-08 | 北京环境特性研究所 | Monitor video personnel's fuzzy retrieval method based on deep learning |
Non-Patent Citations (2)
| Title |
|---|
| GUILHERME SERPA SESTITO，: ""Artificial neural networks and signal clipping for Profibus DP diagnostics"", 《2014 12TH IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL INFORMATICS (INDIN)》 * |
| 李世红，: ""基于PROFIBUS-DP的PID控制器的研制"", 《中国优秀硕士学位论文全文数据库-工程科技Ⅱ辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784318A (en) * | 2019-03-13 | 2019-05-21 | 西北工业大学 | The recognition methods of Link16 data-link signal neural network based |
| CN114978858A (en) * | 2021-02-22 | 2022-08-30 | Abb瑞士股份有限公司 | Determining diagnostic information based on non-real time data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108494626B (en) | 2021-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3557819B1 (en) | Server failure detection method and system | |
| CN109102189B (en) | Electrical equipment health management system and method | |
| WO2020077672A1 (en) | Method and device for training service quality evaluation model | |
| CN107370732B (en) | Abnormal behavior discovery system of industrial control system based on neural network and optimal recommendation | |
| CN108989136A (en) | Business end to end performance monitoring method and device | |
| CN114039819B (en) | Edge intelligent gateway based on 5G | |
| CN110188837A (en) | A kind of MVB network fault diagnosis method based on fuzzy neural | |
| CN108494626A (en) | Physical installation improperly Profibus DP industrial field bus communication failure intelligent diagnosing method | |
| CN110597235A (en) | Universal intelligent fault diagnosis method | |
| CN111124852A (en) | Fault prediction method and system based on BMC health management module | |
| CN111795819B (en) | Gear box fault diagnosis method integrating vibration and current signal collaborative learning | |
| CN113484693B (en) | Transformer substation secondary circuit fault positioning method and system based on graph neural network | |
| CN104022907A (en) | Failure detection system and method of campus network | |
| CN116662184B (en) | Industrial control protocol fuzzy test case screening method and system based on Bert | |
| Mossin et al. | Automatic diagnosis for profibus networks | |
| Lei et al. | DeviceNet network health monitoring using physical layer parameters | |
| CN113204332B (en) | Intelligent household equipment control program generation system and method | |
| CN101710161A (en) | Rotor ground on-line monitoring device and method based on adaptive frequency square-wave voltage | |
| Sestito et al. | Artificial neural networks and signal clipping for Profibus DP diagnostics | |
| CN113327741A (en) | Front end structure for monitoring oil-filled transformer in real time | |
| Du et al. | Ground Fault Diagnostics for Automotive Electronic Control Units | |
| Mossin et al. | Intelligent diagnostic for PROFIBUS DP networks | |
| Cui | Design and research on automotive controller area network bus analyzer | |
| Aguilar et al. | Situation assessment in autonomous systems | |
| Shang et al. | Fault diagnosis of computer network based on rough sets and BP neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |