CN101135601A - Rotating machinery vibrating failure diagnosis device and method - Google Patents
Rotating machinery vibrating failure diagnosis device and method Download PDFInfo
- Publication number
- CN101135601A CN101135601A CNA2007101760524A CN200710176052A CN101135601A CN 101135601 A CN101135601 A CN 101135601A CN A2007101760524 A CNA2007101760524 A CN A2007101760524A CN 200710176052 A CN200710176052 A CN 200710176052A CN 101135601 A CN101135601 A CN 101135601A
- Authority
- CN
- China
- Prior art keywords
- data
- knowledge
- sign
- module
- diagnostic
- 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.)
- Pending
Links
Images
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The method comprises: using a sensor to collect the characteristic signals; the collected signals about each kind of running state are sent to the data processing module; after processed, the signals are sent to the computer system; said computer system comprises a device database, a symptom event database, a diagnosis knowledge database; a device database and signal analysis module, a symptom acquiring module, a diagnostic reasoning module, and a diagnosis explaining module; the software of the data processing module makes data exchange; the symptom event database exchanges data with the diagnostic module, data processing module; the diagnostic knowledge exchanges the data with the failure processing module, knowledge acquiring module and data processing module.
Description
Technical field
The present invention relates to the equipment fault diagnosis field, particularly adopt the system diagnostics technology of computer software the rotating machinery vibrating fault.
Background technology
Since the eighties, development along with artificial intelligence technology, expert system technology obtains practical application in the rotating machinery vibrating failure diagnosis field, the Turbo-generator Set artificial intelligence diagnosis system based on PDS that develops, released in 1984, several times expands again later on since nineteen eighty-two as U.S. WHEC company (comprises steam turbine, generator and three artificial intelligent online diagnostic systems of water chemistry processing, be TurbinAID, GenAID, ChemAID), Bentley company is in slip-stick artist's backup system (Engineer Assist) of release in 1993.Some colleges and universities of China and research institute have also carried out the development of fault diagnosis expert system, and wherein some system puts into operation.At present, the diagnostic knowledge storage capacity of domestic most of diagnostic systems is little, and feature extraction lacks in ability, and mainly uses conversational mode to obtain failure symptom, and the accuracy of fault diagnosis and real-time are descended.
Summary of the invention
The objective of the invention is to overcome the deficiency of present rotating machinery vibrating failure diagnosis expert system, develop the method that a kind of participation that does not need the expert can be fit to multiple rotating machinery vibrating failure diagnosis, make this system can the common rotating machinery vibrating fault of automatic diagnosis, improve the accuracy rate of fault diagnosis result, reduce requirement user's operant level.
For achieving the above object, technical scheme of the present invention is to adopt a kind of rotating machinery vibrating failure diagnosis device, comprising:
Signal acquisition module, described signal acquisition module are used for the signal of the various operation characteristics of rotating machinery is gathered, and the described signal output that will collect;
Data management module, described data management module are used to receive the signal that described signal acquisition module is exported, and the described signal that receives is carried out data pre-service and temporary, with pretreated data output;
Memory module, described memory module are used for storage facilities database, sign variable storehouse, diagnostic knowledge database;
Interface module, described interface module comprises input end and output terminal, input termination data management module, output termination memory module;
Signal analyse block is used for the slave unit database and reads the various operation characteristic data of rotating machinery, and described data are carried out exporting after the Treatment Analysis;
The sign acquisition module is used for the sign variable that the fetch equipment database is exported, to described data computation confidence value, with the confidence value output after calculating;
The diagnostic reasoning module is used for the data of fetch equipment database, and according to the data in the data in the diagnostic knowledge database, the sign factual database judge, reasoning handles, result is exported;
The diagnostic interpretation module is used for the data of fetch equipment database and according to the data in the diagnostic knowledge database, the fault diagnosis conclusion is outputed in the sign factbase and with data according to data be sent to output device after treatment;
Knowledge acquisition module is used for reading the data of diagnostic knowledge base, read the back to the data management, safeguard, output;
Fault processing module is used for the diagnostic result data according to the output of diagnostic reasoning module, and according to the countermeasure knowledge data in the knowledge acquisition module, draws after treatment for specific fault handling suggestion data and export;
Data processing module is used to read, controls, exports with upper module and data of database, and described module can be carried out exchanges data with peripherals.
The present invention stores various operation characteristics of rotating machinery and structured data in described device databases; described data are divided into current data, historical data, start and stop data and alert data; described data from data management module, by signal analyse block; sign acquisition module, diagnostic interpretation module read, and the input and output of described data are controlled by data processing module.
The present invention stores data, sign numerical values recited data, the sign obtain manner data of rotating machinery fault symptom attribute in described sign factual database, described data from the diagnostic interpretation module, read by fault processing module, the input and output of described data are controlled by data processing module.
The present invention stores the knowledge data relevant with rotating machinery vibrating failure diagnosis in described diagnostic knowledge base, described knowledge data comprises background knowledge data, experimental knowledge data, procedural knowledge data, DECISION KNOWLEDGE and control knowledge data, described data from knowledge acquisition module, read by fault processing module, the input and output of described data are controlled by data processing module.
The Treatment Analysis that signal analyse block of the present invention is carried out data is the Treatment Analysis to master data in the device databases, described master data comprises time domain, frequency domain and the trend analysis to data, analyze back output amplitude and the sizes values of various frequency contents and the data of variation tendency, the input and output of described data are controlled by data processing module.
Sign acquisition module computational data confidence value of the present invention is described module is converted to sign factual data in the sign factual database with the master data in the device databases, and the input and output of described data are controlled by data processing module.
The reasoning diagnosis of diagnostic reasoning module of the present invention is, described module reads the diagnostic knowledge database data and carries out the metalevel reasoning processing, determine candidate's fault collection, utilize the Failure Diagnostic Code knowledge data to carry out the failure level reasoning again, the input and output of described data are controlled by data processing module.
The present invention includes dictionary management module, knowledge management module and knowledge maintenance module again in described knowledge acquisition module;
Described dictionary management module is used for the knowledge of knowledge diagnosis database being deposited into database with the agreement code and dictionary being translated, edited and exports, and described dictionary comprises fault dictionary, sign dictionary, figure dictionary;
Described knowledge management module is used for meta-knoeledge, diagnostic rule and countermeasure knowledge are edited, exported, described editor comprise to the foundation of knowledge base with cancel, input, deletion, insertion, the modification of knowledge, retrieve and browse;
Described knowledge maintenance module is used for the grammar mistake inspection to knowledge, and with check result output, described inspection comprises consistance, redundancy inspection, points out the type and the position of knowledge mistake;
The input and output of dictionary management module, knowledge management module and knowledge maintenance module data are controlled by data processing module in the described knowledge acquisition module.
Data processing module of the present invention is that central processing unit is used to read and handles each module, each data of database, and described central processing unit also carries out exchanges data with peripheral system.
Data management module of the present invention is a single card microcomputer, is provided with microprocessor, preprocessed signal memory module, signal input port and signal output port in described single card microcomputer.
The present invention inserts signal acquisition module at the input port of described single card microcomputer, in output port access, the interface module stores module of described single card microcomputer.
Signal acquisition module of the present invention comprises key phase module, vibration acquisition module, analogue collection module, switching value module;
Described key phase module is used for handling and transmission rotating machinery rotary speed data, and an end of described key phase module is connected the other end and is connected with sensor with single card microcomputer;
Described vibration acquisition module is used for handling the displacement of transmission rotating machinery, speed, acceleration information, and an end of described vibration acquisition module is connected the other end and is connected with sensor with single card microcomputer;
Described analogue collection module is used for handling transmission rotating machinery temperature, pressure, flow, flow speed data, is connected the other end with single card microcomputer at an end of described analogue collection module and is connected with sensor;
Described switching value module is used for the analog to digital conversion of signal and data, and an end of described switching value module is connected the other end and is connected with microprocessor in the single card microcomputer with analog quantity input signal on the single card microcomputer.
A kind of rotating machinery vibrating failure diagnosis method comprises:
The signals collecting step, described signals collecting step is used for the signal of the various operation characteristics of rotating machinery is gathered, and the described signal output that will collect;
Data management step, described data management step are used to receive the signal that described signals collecting step is exported, and the described signal that receives is carried out data pre-service and temporary, with pretreated data output;
Storing step, described storing step are used for data storing to device databases, sign variable storehouse, diagnostic knowledge database;
Input and output step, described input and output step comprise input step and output step, and input step connects the data management process, the output step connects storing step;
Signal analysis step is used for the slave unit database and reads the various operation characteristic data of rotating machinery, and described data are carried out exporting after the Treatment Analysis;
The sign obtaining step is used for the sign variable that the fetch equipment database is exported, to described data computation confidence value, with the confidence value output after calculating;
The diagnostic reasoning step is used for the data of fetch equipment database, and according to the data in the data in the diagnostic knowledge database, the sign factual database judge, reasoning handles, result is exported;
The diagnostic interpretation step is used for the data of fetch equipment database and according to the data in the diagnostic knowledge database, the fault diagnosis conclusion is outputed in the sign factbase and with data according to data be sent to output device after treatment;
The knowledge acquisition step is used for reading the data of diagnostic knowledge base, read the back to the data management, safeguard, output;
The fault handling step is used for the diagnostic result data according to the output of diagnostic reasoning step, and according to the countermeasure knowledge data in the knowledge acquisition step, draws after treatment for specific fault handling suggestion data and export;
Data processing step is used to read, controls, exports above step and data of database, and described step can be carried out exchanges data with peripherals.
The present invention stores various operation characteristics of rotating machinery and structured data in described device databases; described data are divided into current data, historical data, start and stop data and alert data; described data from the data management step, by signal analysis step; sign obtaining step, diagnostic interpretation step read, and the input and output of described data are controlled by data processing step.
The present invention stores data, sign numerical values recited data, the sign obtain manner data of rotating machinery fault symptom attribute in described sign factual database, described data from the diagnostic interpretation step, read by the fault handling step, the input and output of described data are controlled by data processing step.
The present invention stores the knowledge data relevant with rotating machinery vibrating failure diagnosis in described diagnostic knowledge base, described knowledge data comprises background knowledge data, experimental knowledge data, procedural knowledge data, DECISION KNOWLEDGE and control knowledge data, described data from the knowledge acquisition step, read by the fault handling step, the input and output of described data are controlled by data processing step.
The Treatment Analysis that signal analysis step of the present invention is carried out data is the Treatment Analysis to master data in the device databases, described master data comprises time domain, frequency domain and the trend analysis to data, analyze back output amplitude and the sizes values of various frequency contents and the data of variation tendency, the input and output of described data are controlled by data processing step.
Sign obtaining step computational data confidence value of the present invention is described step is converted to sign factual data in the sign factual database with the master data in the device databases, and the input and output of described data are controlled by data processing step.
The reasoning diagnosis of diagnostic reasoning step of the present invention is, described step reads the diagnostic knowledge database data and carries out the metalevel reasoning processing, determine candidate's fault collection, utilize the Failure Diagnostic Code knowledge data to carry out the failure level reasoning again, the input and output of described data are controlled by data processing step.
The present invention includes dictionary management step, information management step and knowledge maintenance step again in described knowledge acquisition step;
Described dictionary management step is used for the knowledge of knowledge diagnosis database being deposited into database with the agreement code and dictionary being translated, edited and exports, and described dictionary comprises fault dictionary, sign dictionary, figure dictionary;
Described information management step is used for meta-knoeledge, diagnostic rule and countermeasure knowledge are edited, exported, described editor comprise to the foundation of knowledge base with cancel, input, deletion, insertion, the modification of knowledge, retrieve and browse;
Described knowledge maintenance step is used for the grammar mistake inspection to knowledge, and with check result output, described inspection comprises consistance, redundancy inspection, points out the type and the position of knowledge mistake;
The input and output of dictionary management step, information management step and knowledge maintenance step data are controlled by data processing step in the described knowledge acquisition step.
Data processing step of the present invention is that central treatment step is used to read and handles each step, each data of database, and described central treatment step also carries out exchanges data with peripheral system.
Data management step of the present invention is to be used on the single card microcomputer, is provided with little treatment step, preprocessed signal storer, signal input step and signal output step in described single card microcomputer.
The input step that the present invention is used on the described single card microcomputer inserts the signals collecting step, is used in output step, access storing step, interface step on the described single card microcomputer.
Signals collecting step of the present invention comprises key phase step, vibration acquisition step, analog acquisition step, switching value step;
Described key phase step is used for handling and transmission rotating machinery rotary speed data, and described key phase step is used for to going into single card microcomputer transmission data and receiving sensor data;
Described vibration acquisition step is used for handling the displacement of transmission rotating machinery, speed, acceleration information, and described vibration acquisition step is used for to going into single card microcomputer transmission data and receiving sensor data;
Described analog acquisition step is used for handling transmission rotating machinery temperature, pressure, flow, flow speed data, and described analog acquisition step is used for to going into single card microcomputer transmission data and receiving sensor data;
Described switching value step is used for the analog to digital conversion of signal and data, and described switching value step is to pass little treatment step to single card microcomputer with importing analog quantity on the single card microcomputer into after digital-to-analog conversion.
The present invention to the workflow of described rotating machinery vibrating failure diagnosis is,
Described workflow starts diagnostic system as required at any time, the various motion state data of rotating machinery are constantly gathered, analyzed to signals collecting step in the diagnostic system, signal analysis step, analyze these data and whether surpass setting value, surpass setting value and begin diagnosis automatically;
When beginning to diagnose, signal analysis step is at first analyzed the various motion state data of the rotating machinery in the device databases, extract the characteristic parameter of rotating machinery vibrating fault data, the sign obtaining step is according to the confidence level numerical value of these calculation of characteristic parameters signs;
System is according to the data in the diagnostic knowledge database, and inference step calculates the confidence level numerical value of all fault signature parameters after diagnosing, and the threshold value restriction according to certain forms candidate's fault collection;
System is data in the knowledge base rule of thumb again, and candidate's fault is carried out backward reasoning, mate the rule of various faults one by one, the confidence level numerical value of reaching a conclusion;
Judge the satisfaction to the result by data processing step, then diagnosis finishes; If dissatisfied, then can diagnose in more detail again;
System provides the several data interactive mode, system adopts selects different data to diagnose with different diagnosis positions, the foundation that system sets up according to fault makes an explanation to diagnostic result, system proposes the fault handling suggestion according to the data of storage, system will preserve diagnostic result, print diagnosis report.
Advantage of the present invention and technique effect are:
1, be applicable to that the rotating machinery vibrating failure diagnosis system is made up of three storehouses and seven functional modules, separate between the module, the reliability height.Man-machine interface close friend, easy to use.
2, design of Knowledge Base has demonstrated fully the requirement of fault diagnosis, and the modularization of knowledge base and opening make that the working service of knowledge base is very convenient.
3, set up the fault diagnosis knowledge base that adapts to Turbo-generator Set, hydraulic generator unit and the compressor train of China's actual conditions, amount of diagnostic information is big, and is practical.
4, adopted forward and reverse mixed inference strategy, the automatic acquisition capability of particularly powerful sign, overcome other diagnostic system and used the next difficulty of artificial input tape and uncertain usually, improved the real-time of fault diagnosis, the personnel that lack the diagnosis experience also can obtain the diagnostic result of domain expert's level.
Description of drawings
Fig. 1 is the structural representation of Rotary Fault Diagnosis System;
Fig. 2 is the single card microcomputer structural representation;
Fig. 3 is interface on the single card microcomputer and sensor, memory module, interface module connection diagram;
Fig. 4 is a knowledge acquisition process synoptic diagram;
Fig. 5 is the synoptic diagram that concerns of fault and sign;
Fig. 6 is the Module Division synoptic diagram of knowledge base;
Fig. 7 is the knowledge base maintenance block diagram;
Fig. 8 is a sign acquisition process synoptic diagram;
Fig. 9 is the diagnostic reasoning process synoptic diagram.
Embodiment
Following examples are used to illustrate the present invention, but are not used for limiting the scope of the invention.
As shown in Figure 1, the general structure of Rotary Fault Diagnosis System of the present invention is by rotating machinery, the signal acquisition module on the single card microcomputer, data management module, and three databases and seven functional modules of inside computer system are formed.
Signal acquisition module is the data processor that is provided with in single card microcomputer, and described signal acquisition module is used for the signal of the various operation characteristics of rotating machinery is gathered, and the described signal that will collect is exported after treatment.
The data processor that data management module is provided with in single card microcomputer, described data management module are used to receive the signal that described signal acquisition module is exported, and the described signal that receives is carried out data pre-service and temporary, with pretreated data output.
Memory module is the internal storage location of computer system, and described memory module is used for storage facilities database, sign variable storehouse, diagnostic knowledge database.
Interface module, described interface module comprises input end and output terminal, the storage unit of input termination data management module, output termination computer system
Three databases are
(1) device databases
Adopt calculation procedure storage equipment structured data, as bearings mode, critical rotary speed and rated speed etc., and the various information that arrive of sensor acquisition, involving vibrations data, temperature, pressure, flow and power etc.By its character, the data in the device databases can be divided into four big classes, they are current data, historical data, start and stop data and alert data.Because the memory space of vibration data is very big, adopts independently private database.
(2) sign factbase
Adopting calculation procedure to deposit all indications data that need in the diagnostic reasoning process and produce, is the main foundation of fault diagnosis.Sign variable is to collect in the signal analyse block slave unit database to handle by analysis after the data to be sent to the sign factbase.
(3) diagnostic knowledge base
The employing calculation procedure is deposited and is diagnosed relevant various knowledge datas, comprises background knowledge data, experimental knowledge data, procedural knowledge data, DECISION KNOWLEDGE data and control knowledge data etc., and they are cores of fault diagnostic system.
Seven functional modules are
(1) signal analyse block
Adopt calculation procedure that the master data in the database is carried out time domain, frequency domain and trend analysis etc., draw the magnitude numerical value of amplitude and various frequency contents and variation tendency data etc.At present, vibration signal being carried out spectrum analysis is to realize the intelligentized main path of fault diagnosis.
(2) sign acquisition module
Adopt the data in the calculation procedure elder generation fetch equipment database, and extract sign in the analysis result of basis signal analysis module, calculate the confidence level of sign, or be deposited in the device databases by the confidence level that the domain expert rule of thumb obtains some sign.
(3) diagnostic reasoning module
Adopt the data in the calculation procedure elder generation fetch equipment database, and carry out the reasoning diagnosis according to the data in the knowledge data in the knowledge base, the sign factual data.The reasoning diagnostic procedure divides two-stage, at first utilizes the meta-knoeledge data to carry out metalevel reasoning, determines candidate's fault collection, utilizes the Failure Diagnostic Code data to carry out the failure level reasoning again, and diagnostic method is rule-based mixed inference.
(4) diagnostic interpretation module
Adopt calculation procedure according to the data of the data in the diagnostic knowledge database, knowledge acquisition module output to user interpretation diagnostic reasoning process and diagnosis, it is to obtain by the relevant regular data of calling in the record reasoning process.
(5) knowledge acquisition module
Adopt calculation procedure input diagnostic knowledge, diagnostic knowledge is to grow out of nothing, the process that quality improves constantly.Knowledge acquisition module provides the means that knowledge data base is managed and safeguards, also comprises dictionary management module, knowledge management module and knowledge maintenance module in knowledge acquisition module.The dictionary management module is mainly finished dictionary for translation, comprises the editor and the output of fault dictionary, sign dictionary, figure dictionary etc.Knowledge management module is mainly finished all kinds of knowledge, comprise the editor and the output of meta-knoeledge, diagnostic rule and countermeasure knowledge, described output can be to show or print, the foundation that knowledge management module also comprises knowledge base with cancel, the input of knowledge, deletion, insertion, modification, retrieve and browse etc.The knowledge maintenance module is finished the grammar mistake inspection of knowledge, consistance, redundancy inspection etc., the type and the position of pointing out the knowledge mistake.
(6) fault processing module
The employing calculation procedure reads the data in the diagnostic knowledge database, and exports the last diagnostic result according to the data of diagnostic reasoning module, knowledge acquisition module, utilizes the countermeasure knowledge data, provides the handling suggestion for specific fault.
(7) data processing module
Be the central processing unit of computing system, it links together each module and database, can control the operation of diagnostic system, and with the computer-internal representation or intend the form organization knowledge of natural language, the input and the output of control data.
As accompanying drawing 2 are structures of a kind of typical single card microcomputer data processor, and single card microcomputer of the present invention and computer system adopt plug connector or local area network to be connected, are the collections that are exclusively used in the rotating machinery vibrating data, to data pre-service, the temporary data of storing up.It is a modular construction, has 11 module slots, except microprocessor, output interface module and memory module, also has 8 input slots fitting key phase module, vibration acquisition module, analogue collection module and switch acquisition module as required.Described single card microcomputer detects the scene process simulation quantity sensor such as the key phase sensor of rotating speed, the sensor that detects displacement, speed and the acceleration of vibration, detected temperatures, pressure, flow, flow velocity and transducer signal is imported corresponding acquisition module, change analog electrical signal into digital signal by the A/D conversion, its signal and data flow are as shown in Figure 3.The veneer function is according to the state of automatic identification equipments such as rotating speed and load, carries out data acquisition according to the different conditions of equipment.Under steady operational status, gather with timing mode, and state is next gathers according to change in rotational speed in lifting speed.The data of gathering are carried out software digital filter, waveform and spectrum signature value are calculated and data compression, store into then in time (year, month, day, time) database, lifting speed database, historical data base and the Mishap Database, so that subsequent analysis.
Obtaining of diagnostic knowledge
As shown in Figure 4, diagnostic system is based on the system of knowledge, and the quality and quantity of knowledge has determined its problem-solving ability.The method that diagnostic knowledge obtains can be divided into directly obtains and obtains indirectly two big classes.Directly obtaining of knowledge needs to solve the machine learning problem.Machine learning is a quite complicated process, needs a large amount of domain knowledges as the environment of supporting machine learning.Up to the present, directly the obtaining the practicability stage that do not reach of knowledge can't obtain the people with computing machine and all be difficult to the diagnostic knowledge that obtains.At present, obtaining of knowledge mainly is to use manual method, relies on knowledge engineering to be an apprentice of in domain expert or the corresponding books data and extracts, and is input to the diagnostic knowledge database then.
The design of diagnostic system needs domain expert, knowledge engineer and has the knowledge base of a large amount of heuristic knowledges in foundation.The domain expert is the people who has expertise in certain field.When dealing with problems, they can make conjecture surely, can recognize effective method for solving quickly.The knowledge engineer is the main deviser of system, and knowledge acquisition, input are mainly finished by the knowledge engineer.Knowledge engineer's task is on the basis of the key concept of understanding the field and aims of systems, be ready to the problem outline, discuss with the domain expert, how perquisition fault diagnosis conclusion draws, confidence level how, got rid of the possibility of other fault why, and what inference form is, whether omitted middle inference step, require which sign of input, what the inner link between the sign is, how data gather, how are the reliability of data and real-time, how the phenomenon of contradiction explains how fault is handled, and the effect after the processing how, whether there are other leftover problems or error in judgement occurs, or the like.The knowledge engineer puts in order the knowledge of collecting on the basis that fully understands and classifies, and passes through relevant expert's affirmation at last, be input to become in the system system can with the knowledge of refining be deposited into knowledge data base.
As shown in Figure 5,, need propose a series of requirements, mainly comprise:, which sign then will occur and not occur if there is certain fault to the relation between fault and sign, sign and the sign for the diagnostic knowledge that obtains from different channels is put in order; If which fault is certain sign then may exist and not exist; If certain sign do not occur, then can get rid of which fault; When a certain fault of diagnosis, which sign occurring is necessary condition, and which sign is an adequate condition, and which sign is a necessary and sufficient condition etc.
This shows that obtaining of diagnostic knowledge is a job that needs cost plenty of time and energy.If do not have broad knowledge source and strong knowledge acquisition, there is not a large amount of high-quality domain knowledges, it is impossible wanting to develop a real expert diagnostic system.
The rotary machinery fault diagnosis knowledge that the present invention uses is the analysis by a large amount of field failure cases, approach such as domain expert's informal discussion and model test and Computer Simulation obtain, contained Turbo-generator Set, rotating machineries such as hydraulic generator unit and compressor train comprise mass unbalance, the macro-axis initial bending, rotor thermal bending, element falling, misalign, sound is bumped and is rubbed, oil whirl, oil whip, steam flow excitation, the electromagnetic force imbalance, stator or blade openings are inhomogeneous, cavitation erosion causes vibration, rotating stall, surge, bearing is loosening, stator core is loosening, frame is loosening, turbine water induction, more than 500 sign of the common vibration fault of kind more than 20 such as the vibration of foundation and mesomerism.
The knowledge-base design of Rotary Fault Diagnosis System
The classification of 1 diagnostic knowledge
For ease of the tissue and the description of knowledge base, need carry out suitable classification to diagnostic knowledge.The sorting technique of diagnostic knowledge has multiple, and is relevant with the method for solving of field question.The present invention is divided into sign knowledge, experimental knowledge, meta-knoeledge and DECISION KNOWLEDGE with diagnostic knowledge.Sign knowledge is the qualitative or quantitative description to the performance of the various features of fault, be according to sensor to data and the data that obtain by analysis, be the main foundation of diagnostic reasoning; Experimental knowledge is the summary of domain expert's long-term practice experience, is the judgement that the cause-effect relationship between fault and the sign is done; Meta-knoeledge is used to delineate the structure and the content of domain knowledge, instructs the selection of experimental knowledge, and optimization system structure etc. are the knowledge of highest level; DECISION KNOWLEDGE is whether should or to take what kind of treatment measures when breaking down.
The function of 2 knowledge bases
Expert diagnostic system is based on the system of knowledge, thus knowledge base in system in occupation of important status, the whether success of foundation of knowledge base is depended in the success or failure of system works.The foundation of knowledge base should be able to be satisfied following several functional requirements:
(1) Knowledge Representation Method of taking can fully be expressed the each side information of domain knowledge completely, can make amendment according to actual needs and expand.
(2) institutional framework of knowledge base is reasonable, has both helped knowledge representation, helps knowledge-base management and maintenance again, increases work efficiency.
(3) logically should guarantee completeness, consistance and nonredundancy between the each several part of knowledge base, guarantee the correct and high-level efficiency of system's reasoning.
The tissue of 3 knowledge bases
As shown in Figure 6,, consider the adequacy of knowledge representation and the convenience of completeness, knowledge base management and maintenance etc., knowledge base has been carried out modular division according to the functional requirement of the type and the knowledge base of diagnostic knowledge.
(1) dictionary editor
Convenient for reasoning, the knowledge that is stored in the computing machine is to be stored in the computing machine by the form of certain coding convention with the knowledge code, and system will provide the explain information of natural language form to the user.Therefore in the structure of knowledge base, add the dictionary editor module, wherein stored the natural language implication of knowledge code.The dictionary editor comprises fault dictionary and figure dictionary etc.
In fault dictionary, failure code F * * expression, as code " F01 " expression " imbalance " fault, code " F02 " expression " misaligns " fault etc.
In the figure dictionary, figure code represents with the English of the executable program of figure, as code " Wave " expression " time domain waveform ", and code " Spect " expression " spectrogram " etc.
Dictionary editor's function has not only been created condition for the explanation function that strengthens MAINTENANCE OF KNOWLEDGE BASE function and system, simultaneously, can adopt Chinese form fully in the diagnostic reasoning process median surface, has strengthened the transparency of system works and the acceptability of system.
(2) sign storehouse
Be used to deposit the sign that the fault through taxonomic revision shows.Sign is made up of attribute, sign value and the sign obtain manner of sign.Attribute representation's class sign of sign, usefulness S * * expression, the occurrence or the physical meaning of sign value representation sign, usefulness V * * expression, each symptom attribute has one or several sign values.As using code " S01 " expression " in the relative rumble spectrum of bearing ", with code " V01 " expression " a frequency multiplication composition is bigger ", code " V02 " expression " two frequency multiplication compositions are bigger ", then code " (S01; V01) " expression " a frequency multiplication composition is bigger in the relative rumble spectrum of bearing ", code " (S01, V02) " expression " two frequency multiplication compositions are bigger in the relative rumble spectrum of bearing ".And for example code " (S14, V01) " expression " phase invariant when rotating speed is constant " etc.The sign obtain manner is the code of the prior regulation of system, with " DIAL " or " AUTO " expression, represents that respectively sign is dialogue obtain manner or automatic obtain manner.Sign is divided into the sign that the sign obtained automatically and dialogue are obtained, and the sign of obtaining is automatically calculated the confidence level of sign automatically by computing machine, for promptness and the accuracy rate that improves fault diagnosis provides reliable assurance.
(3) meta-knoeledge storehouse and experimental knowledge storehouse
The meta-knoeledge storehouse is identical on method for expressing with the experimental knowledge storehouse, promptly all use the method for expressing of rule, just in terms of content, the topmost requisite sign of fault has been caught in the meta-knoeledge storehouse, determine candidate's fault according to the meta-knoeledge storehouse, created condition for improving system's Reasoning Efficiency.
Rule is made up of number of regulation, regular prerequisite, abundant confidence level and necessary confidence level, and each fault has some rules.Number of regulation R * * expression, it represents a diagnostic rule.The rule prerequisite is the operator (﹠amps of one or several signs with regulation; Expression " with ", | expression " or ") combine.Fully confidence level is the numerical metric of regular prerequisite to the degree of support of conclusion, and necessary confidence level is the numerical metric of regular prerequisite to the negative degree of conclusion, and they are the numbers of boundary between 0-1.The general type of rule expression is as follows:
Failure code Fxx
Number of regulation Rxx
Rule prerequisite ((Sxx, Vxx) ﹠amp; (Sxx, Vxx))
Abundant confidence level CF1
Necessary confidence level CF2
For example, a rule of diagnosis imbalance fault is:
Failure code F01
Number of regulation R06
Rule prerequisite ((S01, V01) ﹠amp; (S13, V01) ﹠amp; (S14, V01))
Abundant confidence level 0.90
Necessary confidence level 1.0
The regular prerequisite of representing with Chinese is:
If a frequency multiplication composition is bigger in the relative rumble spectrum of bearing
And amplitude was constant when rotating speed was constant
And phase invariant when rotating speed is constant
For another example, a rule of diagnosis oil whip fault is:
Failure code F04
Number of regulation R11
Rule prerequisite ((S01, V07) ﹠amp; (S19, V01) ﹠amp; (S20, V01))
Abundant confidence level 0.95
Necessary confidence level 1.0
The regular prerequisite of representing with Chinese is:
If the low frequency component of (0.35-0.48) frequency multiplication is bigger in the rumble spectrum
And rotating speed rises to a certain value, and vibration increases suddenly
And speed drop is to a certain value, and vibration reduces suddenly
The existence that some fault is got rid of by the system that is set to of the necessary confidence level of rule provides approach, for example, if phase change when rotating speed is constant then can be got rid of imbalance fault.
(4) countermeasure knowledge base
The editor of countermeasure knowledge base is simpler, is made up of failure code and countermeasure knowledge.As the countermeasure of rotor rubbing fault may be:
1. according to the expansion rule of cylinder and rotor, the reasonable disposition dynamic and static gaps.
2. improve shafting dynamic balance quality and hot lower rotor part to neutrality, guarantee the unit amplitude in allowed limits.
3. should strict control degree of rocking in the start and stop process, degree of eccentricity, up and down temperature difference of the cylinder, main steam and reheat steam temperature, the main steam degree of superheat, that unit expands is poor, stage head and axial translation etc. within the limits prescribed.
4. when main steam temperature descends suddenly, returning-oil temperature is answered shutdown inspection when rising surpasses setting suddenly.
Must beat gate stop-start when 5. judder taking place in the start-up course, forbid to rush firmly critical rotary speed; Do not allow in any case near critical rotary speed, to be detained, must not blindly carry out low speed warming yet.
6. when unit generation frictional vibration, the size and the rate of change of reply vibration are controlled as strict as possible, in time beat gate stop-start, in case permanent bending of rotor takes place.
7. can monitor separately frictional vibration during conditions permit.
Modular structure can be used for handling the different piece of knowledge base respectively.When system need increase some function, for example increase a fault, only need in fault dictionary, to increase failure code, in the sign storehouse, increase the sign relevant with this fault, in rule base, increase corresponding diagnostic rule, in the countermeasure knowledge base, increase the handling suggestion relevant, obtain the calculating (for the sign of obtaining automatically) that program increases the sign confidence level, utilize the diagnostic reasoning of system can be the diagnosing malfunction of increase in sign with this fault.
4 MAINTENANCE OF KNOWLEDGE BASE
As shown in Figure 7 because the huge day by day and institutional framework of knowledge base scale, hierarchical relationship is complicated day by day, after knowledge base is built up, test and use in it safeguarded just seem especially important.Because a variety of causes, always there is some deficiency in knowledge base, should constantly expand new knowledge according to actual operating position, deletes useless knowledge, revises vicious knowledge, progressively improves the quality of knowledge base and the level of system.Therefore, system also provides perfect knowledge base maintenance function except editting functions such as increase, modification, storage, deletion are provided.Its energy self-verifying misspelling, convert lowercase to capitalization, in the rule prerequisite left and right sides bracket number whether equate and the position whether correct, whether the position of legal character is correct, whether have unallowable instruction digit, whether the confidence level setting crosses the border, and whether the sign in the rule exists, whether rule repeats, conflict or inconsistent etc., provides reliable assurance for reducing the human error.
The rotary machinery fault diagnosis knowledge base that the present invention uses is on the basis that diagnostic knowledge obtains, the Failure Diagnostic Code of Turbo-generator Set, hydraulic generator unit and compressor train is left in separately the knowledge base, each knowledge base comprise the common vibration fault of diagnosis the type equipment 1000 surplus a diagnostic rule.
The sign of vibration fault is obtained
Obtaining automatically of sign is the prerequisite that the expert diagnosis ability plays a role, if there is not the automatic acquisition capability of strong sign, even system has the domain experts' experience knowledge of a large amount of preciousnesses, also can not carry out automatic diagnosis to fault.Therefore, the sign acquisition capability is an important indicator of estimating the fault diagnosis expert system performance.From the angle of fault diagnosis the sign of vibration fault is classified below, discuss principle and sign confidence level Calculation Method that sign is obtained.
The type of 1 vibration fault sign
In general, sign is the abnormal occurrence that unit occurs, as vibrate increase, axial displacement and surpass setting value etc., angle from fault diagnosis, sign is the various phenomenons that help failure judgement, comprise some normal phenomenon, as vibrate stable, axial displacement is normal etc., because utilize normal phenomenon can get rid of some fault.According to different in kind, the vibration fault sign can be divided into following a few class.
(1) instantaneous value type sign
Instantaneous value type sign is meant that sign is to determine that by the data in a certain moment more than the twice of rotating speed greater than first critical speed, a frequency multiplication amplitude is bigger in the rumble spectrum, unit load carrying etc.
(2) rate of change type sign
Rate of change type sign is meant that sign is to determine that by the data in the difference moment increase suddenly as amplitude, a frequency multiplication phase place gradually changed when rotating speed was constant, along with load increases vibration increase etc.
(3) figure sign
The figure sign is meant the feature that figure had that obtains through signal analysis, is sinusoidal wave as waveform, and frequency spectrum is a fir shape, and orbit of shaft center is a banana-shaped etc., but does not comprise the trend analysis figure, and it shows as rate of change type sign.
(4) integrated-type sign
The integrated-type sign is meant the sign that obtains according to ejusdem generis a plurality of sensors, and is basic identical as the equidirectional vibration phase in rotor both sides, and the vibration of shaft coupling bearings at both ends is bigger etc.
The principle that 2 signs are obtained
(1) needs of fault diagnosis
Sign is obtained the means as fault diagnosis, for the fault diagnosis service, can not become isolated behavior.For the vibration fault of large rotating machinery, generally do not show obvious characteristics.If as diagnosis basis, then in most cases can fail to pinpoint a disease in diagnosis at the scene, and when diagnostic result was correct, fault may be quite serious, do not reach the effect of trouble-saving and control with the sign of laboratory typical fault.
(2) difference of diagnosis object
Fault diagnosis is at the privileged site of particular rack, as diagnosis object is steam turbine, the hydraulic turbine or compressor, steam turbine is high, medium and low voltage rotor or generator amature, the diagnosis position is rotor, bearing or bearing seat etc., do not specify clear and definite diagnosis object, fault diagnosis is nonsensical.In common rotating machinery, the rotating speed of compressor train is the highest, and the rotating speed of Turbo-generator Set takes second place, and the rotating speed of hydraulic generator unit is minimum.For dissimilar rotating machineries, vibration standard has sizable difference.Even for specific unit, before and after different bearing portions even maintenance, the vibration of permission also is different, need set different values when sign is obtained.
(3) character of fault
Equally, sign is at specific fault.For specific fault, its sign performance has the branch of power in the specific stage, judges that sign is normally or unusual standard should be different.For example, unbalance vibration shows particularly outstandingly near critical rotor speed.For different faults, even the language performance mode of sign is identical, its essence also is distinguishing.For example,, all have sign " a frequency multiplication amplitude is bigger in the rumble spectrum ", but it is different to the degree of support of two kinds of faults for imbalance fault and rotor rubbing fault.Can judge more greatly according to a frequency multiplication amplitude to have imbalance fault, logically frequently just the rotor rubbing fault can take place when amplitude is greater than dynamic and static gaps but have only.So for the identical sign of different faults, its confidence level will be calculated respectively.
(4) combined effect of sign
From the sign tracing trouble is to the affirmation and negation degree of fault rather than according to the degree of correlation of sign and fault according to sign.Sometimes single sign can not play the effect of affirmation and negation.For example, oil whip shows as the low frequency component less than 1/2 frequency multiplication generally speaking, and the air gap exciting shows as the low frequency component greater than 1/2 frequency multiplication, and rotating stall shows simultaneously less than 1/2 frequency multiplication with greater than the low frequency component of 1/2 frequency multiplication.If only just be judged as the rotating stall fault, then easily rotating stall fault and oil whip and air gap excitation fault are obscured according to certain low frequency component.Therefore, when constituting the necessary condition of fault, can not determine the confidence level of fault according to single sign by a plurality of signs.
The method that 3 signs are obtained
As shown in Figure 8, to obtain be the process of finishing the sign fact of master data in the sign factbase in the slave unit database to sign.It is that the master data that earlier data collection and status monitoring is obtained is carried out essential analysis, as vibration data is carried out time domain, frequency domain and trend analysis etc., convert characteristic by analysis to, amplitude size as frequently logical and various frequency contents, the variable quantities of amplitude and phase place etc. obtain program through sign again, calculate the confidence level of sign, become the sign fact, use when offering the system diagnostics reasoning with confidence level size.
It is a lot of to be used for the method that sign obtains, and as fuzzy mathematics, neural network, fractal geometry and wavelet transformation etc., wherein, according to the characteristic frequency of vibration fault, utilizes the spectrum analysis result to determine the size of different frequency composition, is method commonly used at present.
The calculating of 4 sign confidence levels
(1) calculating of instantaneous value type sign confidence level
Confidence level both can also can be represented with the continuous function form with discrete numeric representation.When sign adopted the discretize value, its confidence level non-0 was 1, and the confidence level of instantaneous value type sign mainly is this form.For example sign " generating unit speed is greater than 2000r/min ", " unit load carrying ", " the diagnosis position is 1 watt ", " No. 6 bear vibration (17-21) Hz amplitude is greater than a frequency multiplication amplitude " etc. judge they only whether to set up needs and characteristic directly compare.
When sign adopted the serialization subordinate function to represent, its confidence level then was the value between [0,1].Subordinate function is that the subjectivity of the ambiguity of things outwardness quantizes.In instantaneous value type sign, the confidence level of calculating each frequency content size mainly is this form.
For example, when the confidence level of the sign " a frequency multiplication amplitude is bigger in the rumble spectrum " of calculating imbalance fault, reach reaching under the condition of logical frequency amplitude more than 60% with a frequency multiplication amplitude more than 60% of alarming value at satisfied logical amplitude frequently, adopted a frequency multiplication amplitude and logical amplitude ratio method frequently, be shown below.
CF(1X)=A
(1X)/(a
1A
(TX)+a
2A
(LX)+a
3A
(HX)) (1)
And as CF (1X)〉1 the time, CF (1X)=1.
Wherein CF (1X) is the confidence level of imbalance fault sign " a frequency multiplication amplitude is bigger in the rumble spectrum ", and A (1X), A (TX), A (LX) and A (HX) are respectively the amplitudes of a frequency multiplication, logical frequency, low frequency and high frequency, a
1, a
2, a
3For less than 1 scale-up factor.By (1) formula as can be known, when logical frequency amplitude is constant, one frequency multiplication amplitude is big more, the confidence level of sign is also big more, but the increase of logical frequency, low frequency and high frequency amplitude will make the confidence level of sign reduce when a frequency multiplication amplitude is constant, and coefficient a1, a2, a3 are provided with because of the different differences to some extent of equipment and diagnosis position.
For another example, when the confidence level of the sign " a frequency multiplication amplitude is bigger in the rumble spectrum " of calculating the rotor rubbing fault, reach more than the alarming value and a frequency multiplication amplitude reaches under the logical condition of amplitude more than 60% frequently satisfying logical amplitude frequently, adopted a frequency multiplication amplitude and frequency multiplication alarming value method relatively, be shown below.
CF(1X)=A
(1X)/(a
1A
(TX)+a
2A
(BJ1)) (2)
And as CF (1X)〉1 the time, CF (1X)=1.
Wherein CF (1X) is the confidence level of rotor rubbing failure symptom " a frequency multiplication amplitude is bigger in the rumble spectrum ", A
(BJ1)Be the alarming value of a frequency multiplication amplitude, a
1For less than 1 coefficient, a
2For greater than 1 coefficient.
Usually, when the confidence level of the sign " X frequency multiplication amplitude is bigger in the rumble spectrum " of calculating certain fault, logical amplitude frequently reaches certain condition and X frequency multiplication amplitude reaches under the situation of certain condition satisfying, adopted X frequency multiplication amplitude and other frequency multiplication amplitude and alarming value method relatively, be shown below.
CF
(X)=A
(x)/(∑
aiA
(ix)+∑biA
(iBJ)) (3)
And as CF (X)〉1 the time, CF (X)=1.
Wherein CF (X) is the confidence level of certain failure symptom " X frequency multiplication amplitude is bigger in the rumble spectrum ", A
(ix)Be the amplitude of i bar spectral line, A
(iBJ)Be the alarming value of i bar spectral line, ai, bi are coefficient, i=1, and 2 ..., N, N are the number of frequency spectrum.
(2) calculating of rate of change type sign confidence level
The calculating of rate of change type sign confidence level need be handled difference data constantly, therefore needs to select some groups of data.Select which data and data storage method and wait to diagnose the character of fault relevant, generally require selected data should comprise the sign that contingent time of fault and fault may occur.The subordinate function form is adopted in the calculating of sign confidence level usually.For example, when the confidence level of the sign " amplitude increased suddenly when rotating speed was constant " of calculating unit release failure, as follows with the program of C language establishment:
CF(A
1)=0;
for(i=1;i<j;i++)
if(fabs(speed[i+1]-speed[i])<n)
CF(A
i+1)=max(CF(A
i),(A
i+1-A
i)/A
b);
if(CF(A
j)>1) CF(A
j)=1;
CF (A wherein
i) be the confidence level of sign " amplitude increased suddenly when rotating speed was constant ", j is the group number of selected data, A
iBe the logical frequency amplitude of i group data, n is the threshold value to two adjacent groups data moment rotation speed change amount, A
bBe the threshold value that amplitude increases, n and A
bSetting relevant with device type and oscillatory property, for Turbo-generator Set, can get 10% of 20r/min and alarming value respectively.Program description for the j group data of selecting, if the rotation speed change amount of two adjacent groups data, is then calculated the confidence level that the two adjacent groups data amplitudes increases less than threshold value, and is got wherein maximal value as the confidence level of sign.
(3) calculating of figure sign confidence level
At present, the confidence level of figure sign is calculated also relatively difficulty, and reason is test pattern and the effective pattern analysis method that lacks the same category of device field failure.Obtained certain progress though obtain the confidence level of figure sign according to fractal geometry and small wave converting method, precision is not high enough, can not use in practice.A kind of method of accommodation is that Figure recognition is converted to parameter recognition, utilizes above-mentioned sign confidence level computing method.For example, when the confidence level of the sign of calculating imbalance fault " waveform is sinusoidal wave ", remain the confidence level of the sign " a frequency multiplication amplitude is bigger in the rumble spectrum " of calculating imbalance fault in fact.Even different is that a frequency multiplication amplitude is very little, if but account for logical large percentage frequently, waveform still shows as sine wave, even a frequency multiplication amplitude is very big conversely, if but to account for logical ratio frequently less, and distorting will appear in waveform.When diagnosing imbalance fault at the scene,, judge whether waveform is that sine wave is nonsensical, and the sine wave on the theory significance also is impossible occur if logical frequency amplitude is less.Therefore,, can require a frequency multiplication amplitude the time, utilize similar (1) formula to calculate the confidence level of sign " waveform is for sinusoidal wave " greater than certain threshold value according to the needs of fault diagnosis.
(4) calculating of integrated-type sign confidence level
The calculating of integrated-type sign confidence level relates to the data of a plurality of same property sensors, and normally different diagnosis positions, and therefore, the factor of its required consideration is generally more complicated.For example, when the confidence level of the sign " the equidirectional vibration phase in rotor both sides is basic identical " of calculating rotor single order imbalance fault, must consider the influence that other rotor vibration shape produces it by shaft coupling in the axle system, and the influence of the vibration shapes such as rotor self second order and three rank, therefore need set up the expression formula of a more complicated according to the diagnostic knowledge convergence strategy.So the confidence level of this type sign is calculated and is used less, only some structures are calculated than the manifest signs confidence level than simple and fault signature.For example, when the confidence level of the sign " bearing and the vibration of foundation differ less " of calculating vibration of foundation fault, reach more than the alarming value satisfying basal amplitude, adopted the method for bearing amplitude and basal amplitude comparison, be shown below.
CF(J)=1-(A
(zX)-A
(JX)/A
(BJZ) (4)
And as CF (J)〉1 the time, CF (J)=1, when CF (J)<0, CF (J)=0.
Wherein CF (J) is the confidence level of vibration of foundation failure symptom " bearing and the vibration of foundation differ less ", A
(zX), A
(JX), A
(BJz)It is respectively the alarming value of bearing, basal amplitude and the vibration of foundation.
Diagnostic reasoning
As shown in Figure 9, inference strategy mainly contains forward reasoning, backward reasoning and mixed inference.According to the characteristics of rotating machinery vibrating failure diagnosis problem, the present invention selects the mixed inference strategy based on backward reasoning, its workflow.
Start diagnostic system dual mode is arranged: automatically with manual.Diagnostic system is the dynamic data of analytical equipment constantly, analyzes these data and whether surpasses setting value, surpasses setting value and begins diagnosis automatically, also can be as required by manually starting at any time.
When beginning to diagnose, earlier the data that are stored in the device databases are analyzed, obtained the characteristic parameter of data, the sign acquisition module is then according to the confidence level of these calculation of characteristic parameters signs.
According to the meta-knoeledge storehouse, by forward reasoning, calculate the confidence level of all faults, the threshold value restriction according to certain forms candidate's fault collection.As according to " frequency multiplication is bigger in the rumble spectrum ", that the equipment that can obtain exists is uneven, misalign, bump and rub and candidate's fault such as resonance, and arranges from big to small according to confidence level.
Knowledge base is rule of thumb carried out backward reasoning to candidate's fault again, mates the rule of these faults one by one, the confidence level of reaching a conclusion.The computing method of fault credibility are as follows:
1) regular precondition is single sign
If E1 then F01 CFr
CF=CF
r×CF(E1)
CF wherein
rBe the confidence level of rule itself, CF (E1) is the confidence level of sign E1, and CF is the confidence level of conclusion.
2) regular precondition is the combination of sign
A. be the AND AND connection between the sign:
If E1 AND E2 then F01 CFr
CF=CFr×MIN{CF(E1),CF(E2)}
B. between the sign be OR " or " connect:
If E1 OR E2 then F01 CFr
CF=CFr×MAX{CF(E1),CF(E2)}
C. be that % " weighting " connects between the sign:
If E1%E2 then F01 CFr
CF=CFr×[CF(E1)×W(E1)+CF(E2)×W(E2)]
Wherein W (E1) and W (E2) are respectively the weights of sign E1 and E2, and W (E1)+W (E2)=1.0 is arranged.
3) many rules are supported same conclusion
If certain fault has only a diagnostic rule, then the confidence level of conclusion is exactly the confidence level of this fault.Now each fault all has some diagnostic rules, if the confidence level of every regular conclusion is CF1, and CF2 ..., CFn, then the confidence level of fault is got maximal value, i.e. fault credibility CF=MAX{CF1, CF2 ..., CFn}.If certain rule conclusion is negated the existence of fault, then the confidence level of fault is zero, and fault does not exist.
If satisfied to the result, then diagnosis finishes; If dissatisfied, then can select to talk with diagnostic mode, obtain in the new sign adding sign factbase by man-machine conversation and diagnose in more detail.
Many human-computer interaction functions also are provided in addition, diagnose with different diagnosis positions as selecting different data, can diagnostic result be made an explanation according to the foundation that fault is set up, the fault handling suggestion can rule of thumb be proposed, diagnostic result can be preserved, diagnosis report etc. can be printed.
Adopt the method examination of systems technology automatic diagnosis vibration fault
In order to examine the correctness of diagnostic result, after diagnostic system is set up, hundreds of on-the-spot fault case and the rotor test platforms that take place that utilization is collected have carried out simulation test, successfully diagnosed out uneven, misalign, the common vibration faults of kind more than 20 such as rotor rubbing, element falling and rotating stall, more than the rate of accuracy reached to 90% of diagnostic result, the diagnostic result method for expressing is as shown in table 1.Facts have proved that vibrating failure diagnosis method of the present invention has stronger intelligent behavior, can play expert advisor's effect to the field staff.It can the potential fault of early detection equipment, reduces the time of failure judgement, avoids or the generation of minimizing accident, can promote the maintenance system from emergency maintenance, periodic maintenance to the transformation of repair based on condition of component etc., thereby create huge economic benefit and social benefit.
Table 1 rotor rubbing and hot imbalance fault automatic diagnosis result
Machine set type: homemade 200MW unit
Diagnosis position: 2 watts of horizontal directions
Generating unit speed: 1533-1132rpm
Data Date: 1998 02 month 00: 45: 28-1998 02 month on the 21st 21
00: 50: 10
One. the automatic diagnosis result:
Sequence number fault title confidence level
1 rotor rubbing 1.0
2 hot uneven 0.65
Two. to the explanation of diagnostic result
1. the rotor rubbing fault draws according to following sign:
(1) amplitude severe overweight confidence level 1.0
2. hot imbalance fault draws according to following sign:
(1) the big confidence level 0.75 of a frequency multiplication amplitude in the rumble spectrum
Amplitude and phase change confidence level 1.0 when (2) rotating speed is constant
Three. the fault handling suggestion
1. to the handling suggestion of rotor rubbing fault:
(1) checks the whether good of rotor to the neutral equilibrium state.
(2) the machine number of times is opened in proper extension jiggering time or increase.
2. to the handling suggestion of hot imbalance fault:
(1) proper extension warm-up period.
(2) carry out transient equilibrium in case of necessity.
More than be preferred forms of the present invention, according to content disclosed by the invention, some identical, replacement schemes that those of ordinary skill in the art can expect apparently all should fall into the scope of protection of the invention.
Claims (18)
1. a rotating machinery vibrating failure diagnosis device is characterized in that, comprising:
Signal acquisition module, described signal acquisition module are used for the signal of the various operation characteristics of rotating machinery is gathered, and with the signal output that collects;
Data management module, described data management module are used to receive the signal that described signal acquisition module is exported, and the described signal that receives is carried out data pre-service and temporary, with pretreated data output;
Memory module, described memory module are used for storage facilities database, sign variable storehouse, diagnostic knowledge database;
Interface module, described interface module comprises input end and output terminal, input termination data management module, output termination memory module;
Signal analyse block is used for the slave unit database and reads the various operation characteristic data of rotating machinery, and described data are carried out exporting after the Treatment Analysis;
The sign acquisition module is used for the sign variable that the fetch equipment database is exported, to described data computation confidence value, with the confidence value output after calculating;
The diagnostic reasoning module is used for the data of fetch equipment database, and according to the data in the data in the diagnostic knowledge database, the sign factual database judge, reasoning handles, result is exported;
The diagnostic interpretation module is used for the data of fetch equipment database and according to the data in the diagnostic knowledge database, the fault diagnosis conclusion is outputed in the sign factbase and with data according to data be sent to output device after treatment;
Knowledge acquisition module is used for reading the data of diagnostic knowledge base, reads the back data are managed, safeguard, export;
Fault processing module is used for the diagnostic result data according to the output of diagnostic reasoning module, and according to the countermeasure knowledge data in the knowledge acquisition module, draws after treatment for specific fault handling suggestion data and export;
Data processing module is used to read, controls, exports with upper module and data of database, and described module can be carried out exchanges data with peripherals.
2. rotating machinery vibrating failure diagnosis device as claimed in claim 1; it is characterized in that; in described device databases, store various operation characteristics of rotating machinery and structured data; described data are divided into current data, historical data, start and stop data and alert data; described data from data management module, read by signal analyse block, sign acquisition module, diagnostic interpretation module, the input and output of described data are controlled by data processing module.
3. rotating machinery vibrating failure diagnosis device as claimed in claim 1, it is characterized in that, in described sign factual database, store data, sign numerical values recited data, the sign obtain manner data of rotating machinery fault symptom attribute, described data from the diagnostic interpretation module, read by fault processing module, the input and output of described data are controlled by data processing module.
4. rotating machinery vibrating failure diagnosis device as claimed in claim 1, it is characterized in that, in described diagnostic knowledge base, store the knowledge data relevant with rotating machinery vibrating failure diagnosis, described knowledge data comprises background knowledge data, experimental knowledge data, procedural knowledge data, DECISION KNOWLEDGE and control knowledge data, described data from knowledge acquisition module, read by fault processing module, the input and output of described data are controlled by data processing module.
5. as the described rotating machinery vibrating failure diagnosis device of one of arbitrary claim of claim 2 to 4, it is characterized in that, the Treatment Analysis that described signal analyse block is carried out data is the Treatment Analysis to master data in the device databases, described master data comprises time domain, frequency domain and the trend analysis to data, analyze back output amplitude and the sizes values of various frequency contents and the data of variation tendency, the input and output of described data are controlled by data processing module.
6. as the described rotating machinery vibrating failure diagnosis device of one of arbitrary claim of claim 2 to 4, it is characterized in that, described sign acquisition module computational data confidence value, being described module is converted to sign factual data in the sign factual database with the master data in the device databases, and the input and output of described data are controlled by data processing module.
7. as the described rotating machinery vibrating failure diagnosis device of one of arbitrary claim of claim 2 to 4, it is characterized in that, the reasoning diagnosis of described diagnostic reasoning module, being used for that the diagnostic knowledge database data is carried out metalevel reasoning handles, determine candidate's fault collection, utilize the Failure Diagnostic Code knowledge data to carry out the failure level reasoning again, the input and output of described data are controlled by data processing module.
8. as the described rotating machinery vibrating failure diagnosis device of one of arbitrary claim of claim 2 to 4, it is characterized in that,
In described knowledge acquisition module, include dictionary management module, knowledge management module and knowledge maintenance module again;
Described dictionary management module is used for the knowledge of knowledge diagnosis database being deposited into database with the agreement code and dictionary being translated, edited and exports, and described dictionary comprises fault dictionary, sign dictionary, figure dictionary;
Described knowledge management module is used for meta-knoeledge, diagnostic rule and countermeasure knowledge are edited, exported, described editor comprise to the foundation of knowledge base with cancel, input, deletion, insertion, the modification of knowledge, retrieve and browse;
Described knowledge maintenance module is used for the grammar mistake inspection to knowledge, and with check result output, described inspection comprises consistance, redundancy inspection, points out the type and the position of knowledge mistake;
The input and output of dictionary management module, knowledge management module and knowledge maintenance module data are controlled by data processing module in the described knowledge acquisition module.
9. as the described rotating machinery vibrating failure diagnosis device of one of arbitrary claim of claim 2 to 4, it is characterized in that, described data processing module is that central processing unit is used to read and handles each module, each data of database, and described central processing unit also carries out exchanges data with peripheral system.
10. a rotating machinery vibrating failure diagnosis method is characterized in that, comprising:
The signals collecting step, described signals collecting step is used for the signal of the various operation characteristics of rotating machinery is gathered, and the described signal output that will collect;
Data management step, described data management step are used to receive the signal that described signals collecting step is exported, and the described signal that receives is carried out data pre-service and temporary, with pretreated data output;
Storing step, described storing step are used for data storing to device databases, sign variable storehouse, diagnostic knowledge database;
Input and output step, described input and output step comprise input step and output step, and input step connects the data management process, the output step connects storing step;
Signal analysis step is used for the slave unit database and reads the various operation characteristic data of rotating machinery, and described data are carried out exporting after the Treatment Analysis;
The sign obtaining step is used for reading the sign variable that is equipped with database data and/or signal analysis step output, to described data computation confidence value, with the confidence value output after calculating;
The diagnostic reasoning step is used for reading diagnostic knowledge database knowledge data, and according to the data of sign factual database output judge, reasoning handles, result is exported;
The diagnostic interpretation step is used for reading the data of diagnostic reasoning step data, device databases, the fault diagnosis conclusion is outputed in the sign factbase and with data according to data is sent to output device after treatment;
The knowledge acquisition step is used for reading the data of diagnostic knowledge base, read the back to the data management, safeguard, output;
The fault handling step is used to read the diagnostic result data of diagnostic reasoning step output, and reads the countermeasure knowledge data in the knowledge acquisition step, draws after treatment for specific fault handling suggestion data and exports;
Data processing step is used to read, controls, exports above step and data of database, and described step can be carried out exchanges data with peripherals.
11. rotating machinery vibrating failure diagnosis method as claimed in claim 10; it is characterized in that; in described device databases, store various operation characteristics of rotating machinery and structured data; described data are divided into current data, historical data, start and stop data and alert data; described data from the data management step, by signal analysis step; sign obtaining step, diagnostic interpretation step read, and the input and output of described data are controlled by data processing step.
12. rotating machinery vibrating failure diagnosis method as claimed in claim 10, it is characterized in that, in described sign factual database, store data, sign numerical values recited data, the sign obtain manner data of rotating machinery fault symptom attribute, described data from the diagnostic interpretation step, read by the fault handling step, the input and output of described data are controlled by data processing step.
13. rotating machinery vibrating failure diagnosis method as claimed in claim 10, it is characterized in that, in described diagnostic knowledge base, store the knowledge data relevant with rotating machinery vibrating failure diagnosis, described knowledge data comprises background knowledge data, experimental knowledge data, procedural knowledge data, DECISION KNOWLEDGE and control knowledge data, described data from the knowledge acquisition step, read by the fault handling step, the input and output of described data are controlled by data processing step.
14. as the described rotating machinery vibrating failure diagnosis method of one of arbitrary claim of claim 11 to 13, it is characterized in that, the Treatment Analysis that described signal analysis step is carried out data is the Treatment Analysis to master data in the device databases, described master data comprises time domain, frequency domain and the trend analysis to data, analyze back output amplitude and the sizes values of various frequency contents and the data of variation tendency, the input and output of described data are controlled by data processing step.
15. as the described rotating machinery vibrating failure diagnosis method of one of arbitrary claim of claim 11 to 13, it is characterized in that, described sign obtaining step computational data confidence value, being described step is converted to sign factual data in the sign factual database with the master data in the device databases, and the input and output of described data are controlled by data processing step.
16. as the described rotating machinery vibrating failure diagnosis method of one of arbitrary claim of claim 11 to 13, it is characterized in that, the reasoning diagnosis of described diagnostic reasoning step, be used for carrying out the metalevel reasoning processing to reading the diagnostic knowledge database data, determine candidate's fault collection, utilize the Failure Diagnostic Code knowledge data to carry out the failure level reasoning again, the input and output of described data are controlled by data processing step.
17. as the described rotating machinery vibrating failure diagnosis method of one of arbitrary claim of claim 11 to 13, it is characterized in that,
In described knowledge acquisition step, include dictionary management step, information management step and knowledge maintenance step again;
Described dictionary management step is used for the knowledge of knowledge diagnosis database being deposited into database with the agreement code and dictionary being translated, edited and exports, and described dictionary comprises fault dictionary, sign dictionary, figure dictionary;
Described information management step is used for meta-knoeledge, diagnostic rule and countermeasure knowledge are edited, exported, described editor comprise to the foundation of knowledge base with cancel, input, deletion, insertion, the modification of knowledge, retrieve and browse;
Described knowledge maintenance step is used for the grammar mistake inspection to knowledge, and with check result output, described inspection comprises consistance, redundancy inspection, points out the type and the position of knowledge mistake;
The input and output of dictionary management step, information management step and knowledge maintenance step data are controlled by data processing step in the described knowledge acquisition step.
18. rotating machinery vibrating failure diagnosis method as claimed in claim 10 is characterized in that, to the workflow of described rotating machinery vibrating failure diagnosis be,
Described workflow starts diagnostic system as required at any time, the various motion state data of rotating machinery are constantly gathered, analyzed to signals collecting step in the diagnostic system, signal analysis step, analyze these data and whether surpass setting value, surpass setting value and begin diagnosis automatically;
When beginning to diagnose, signal analysis step is at first analyzed the various motion state data of the rotating machinery in the device databases, extract the characteristic parameter of rotating machinery vibrating fault data, the sign obtaining step is according to the confidence level numerical value of these calculation of characteristic parameters signs;
System is according to the data in the diagnostic knowledge database, and inference step calculates the confidence level numerical value of all fault signature parameters after diagnosing, and the threshold value restriction according to certain forms candidate's fault collection;
System is data in the knowledge base rule of thumb again, and candidate's fault is carried out backward reasoning, mate the rule of various faults one by one, the confidence level numerical value of reaching a conclusion;
Judge the satisfaction to the result by data processing step, then diagnosis finishes; If dissatisfied, then can diagnose in more detail again;
System provides the several data interactive mode, system adopts selects different data to diagnose with different diagnosis positions, the foundation that system sets up according to fault makes an explanation to diagnostic result, system proposes the fault handling suggestion according to the data of storage, system will preserve diagnostic result, print diagnosis report.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2007101760524A CN101135601A (en) | 2007-10-18 | 2007-10-18 | Rotating machinery vibrating failure diagnosis device and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2007101760524A CN101135601A (en) | 2007-10-18 | 2007-10-18 | Rotating machinery vibrating failure diagnosis device and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101135601A true CN101135601A (en) | 2008-03-05 |
Family
ID=39159808
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNA2007101760524A Pending CN101135601A (en) | 2007-10-18 | 2007-10-18 | Rotating machinery vibrating failure diagnosis device and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101135601A (en) |
Cited By (84)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102087138A (en) * | 2009-10-26 | 2011-06-08 | 福禄克公司 | System and method for vibration analysis and phase analysis of vibration waveforms using dynamic statistical averaging of tachometer data to accurately calculate rotational speed |
CN102095560A (en) * | 2010-11-09 | 2011-06-15 | 中国人民解放军重庆通信学院 | Mechanical fault judgment system and method based on noise test |
CN101799366B (en) * | 2010-01-27 | 2011-08-24 | 北京信息科技大学 | Mechanical failure prediction feature extraction method |
CN102192825A (en) * | 2010-01-15 | 2011-09-21 | 福禄克公司 | User interface system and method for diagnosing a rotating machine condition not based upon prior measurement history |
CN102207426A (en) * | 2011-03-17 | 2011-10-05 | 北京必可测科技有限公司 | Shafting state monitoring method for rotary machine |
CN102288283A (en) * | 2011-05-13 | 2011-12-21 | 北京必可测科技有限公司 | Method and device for monitoring vibration faults of turbo generator set |
CN102358542A (en) * | 2011-08-18 | 2012-02-22 | 上海交通大学 | Mine hoist fault diagnosis method and system based on expert system |
CN102400902A (en) * | 2010-09-15 | 2012-04-04 | 中国石油天然气股份有限公司 | Method for evaluating reliability of performance state of reciprocating compressor |
CN102426055A (en) * | 2011-09-01 | 2012-04-25 | 兰州理工大学 | Vibration state information acquisition and characteristic data resource protection system for double-span rotor system |
CN102466566A (en) * | 2010-11-03 | 2012-05-23 | 财团法人工业技术研究院 | Power equipment abnormality detection device and detection method thereof |
CN102522705A (en) * | 2011-11-22 | 2012-06-27 | 广东电网公司电力科学研究院 | Transformer maintenance method and device |
CN102736027A (en) * | 2012-07-18 | 2012-10-17 | 南京因泰莱配电自动化设备有限公司 | Circuit breaker failure diagnosis method based on circuit breaker dynamic property test instrument |
CN102854006A (en) * | 2011-06-22 | 2013-01-02 | 霍尼韦尔国际公司 | Severity analysis apparatus and method for shafts of rotating machinery |
CN102901627A (en) * | 2011-07-26 | 2013-01-30 | 通用电气公司 | Fuzzy logic based system monitoring system and method |
CN103064340A (en) * | 2011-10-21 | 2013-04-24 | 沈阳高精数控技术有限公司 | Failure prediction method facing to numerically-controlled machine tool |
CN103076168A (en) * | 2013-01-09 | 2013-05-01 | 西安交通大学 | Diagnosis method for mechanical faults of circuit breaker |
CN103398846A (en) * | 2013-08-16 | 2013-11-20 | 大连美恒时代科技有限公司 | Method and platform system for analyzing health of reducer |
CN103471841A (en) * | 2013-09-30 | 2013-12-25 | 国家电网公司 | Method for diagnosing vibration faults of rotary machine |
CN103498706A (en) * | 2013-06-25 | 2014-01-08 | 武汉大学 | Turboset performance monitoring and diagnosing method based on general logic table |
CN103545922A (en) * | 2013-09-24 | 2014-01-29 | 许继集团有限公司 | Multi-scenario analysis based intelligent alarm inference method |
CN103808405A (en) * | 2012-11-08 | 2014-05-21 | 极晨智道信息技术(北京)有限公司 | Automatic diagnostic method of gas power generator group vibration fault of device thereof |
CN104062967A (en) * | 2013-03-20 | 2014-09-24 | 广州汽车集团股份有限公司 | Fault diagnosis method and device of start stop system |
CN104154989A (en) * | 2014-07-25 | 2014-11-19 | 新疆金风科技股份有限公司 | Vibration monitoring method and vibration monitoring system for unstable state rotating equipment |
CN104236613A (en) * | 2014-07-14 | 2014-12-24 | 北京理工大学 | Portable monitoring, diagnosing and on-site verifying system for sensing devices on highway network |
CN104677619A (en) * | 2015-02-11 | 2015-06-03 | 中煤科工集团重庆研究院有限公司 | Rotating machinery fault feature extraction method based on complex signal bilateral spectrum |
CN104880247A (en) * | 2015-05-04 | 2015-09-02 | 华中科技大学 | Combined alarming method for on-line monitoring system for rotary machinery |
CN104895627A (en) * | 2015-04-28 | 2015-09-09 | 广东电网有限责任公司电力科学研究院 | Steam flow excited vibration suppression method and system of steam turbine |
CN104991547A (en) * | 2015-05-19 | 2015-10-21 | 重庆大学 | Multi-fault diagnosis method driven by practical fault symptom data |
CN105136282A (en) * | 2015-05-29 | 2015-12-09 | 江阴市华恒仪表有限公司 | Vibration monitoring protection instrument |
CN105521997A (en) * | 2014-09-30 | 2016-04-27 | 宝山钢铁股份有限公司 | Method for diagnosing faults of rolling mill roller system on basis of vibration signals |
CN105841966A (en) * | 2016-04-06 | 2016-08-10 | 西安西热振动研究所有限公司 | Turbo generator set vibration fault diagnosis method based on forward reasoning |
CN106289115A (en) * | 2015-05-14 | 2017-01-04 | 北京三叶瑞风能源科技有限公司 | A kind of fan coupler based on computer technology misaligns trouble-shooter and method |
CN106339743A (en) * | 2015-07-08 | 2017-01-18 | 罗伯特·博世有限公司 | Electronic Operating Data Memory for a Rotationally Operating Machine |
CN106762343A (en) * | 2016-12-29 | 2017-05-31 | 北京中元瑞讯科技有限公司 | The diagnostic method of the hydraulic generator set thrust bearing failure based on online data |
CN107014628A (en) * | 2015-10-02 | 2017-08-04 | 斯凯孚加拿大有限公司 | Inexpensive online condition monitoring |
CN107063613A (en) * | 2016-11-23 | 2017-08-18 | 北京中元瑞讯科技有限公司 | The analysis and diagnosis method of turbine-generator units Rubbing faults based on online data |
CN107153876A (en) * | 2017-05-25 | 2017-09-12 | 南通大学 | Machine vision shutter Self-tuning System intelligent control method based on Expert Rules |
CN107607321A (en) * | 2017-09-06 | 2018-01-19 | 成都大汇物联科技有限公司 | A kind of equipment fault accurate positioning method |
CN107655690A (en) * | 2017-10-30 | 2018-02-02 | 王才旺 | Motor bearings method for diagnosing faults based on artificial neural network |
CN107891994A (en) * | 2017-11-09 | 2018-04-10 | 北京九天翱翔科技有限公司 | A kind of full Intelligent flight device flight test error analytical system |
CN108387309A (en) * | 2018-04-25 | 2018-08-10 | 哈尔滨电气股份有限公司 | A kind of turbine shafting vibrating data collection, pretreatment and remotely send system |
CN108708773A (en) * | 2018-05-11 | 2018-10-26 | 湖北华电襄阳发电有限公司 | A kind of Steam Turbine Fault Diagnosis Methods, system and device |
CN108803569A (en) * | 2018-06-11 | 2018-11-13 | 哈尔滨锅炉厂有限责任公司 | Station boiler diagnostic expert system and its method for diagnosing faults |
CN108918126A (en) * | 2018-07-25 | 2018-11-30 | 北京振测智控科技有限公司 | A kind of rotating machinery vibrating intelligent fault diagnosis method based on fining fault model |
CN108982096A (en) * | 2018-06-01 | 2018-12-11 | 杭州电子科技大学 | Industrial robot crank axle wear detecting method based on heuristic rule system |
CN109361394A (en) * | 2018-10-09 | 2019-02-19 | 中国人民解放军91388部队 | Dynamic data recording system in a kind of test of Underwater Battery |
CN109855873A (en) * | 2018-12-12 | 2019-06-07 | 华润电力技术研究院有限公司 | The method for diagnosing faults and device of steam turbine main shaft |
CN110118582A (en) * | 2019-06-12 | 2019-08-13 | 北京博识创智科技发展有限公司 | A kind of rotating machinery fault diagnosis method and system |
CN110131193A (en) * | 2018-02-02 | 2019-08-16 | 中国航发商用航空发动机有限责任公司 | Aero-engine surge fault monitoring method and system |
CN110160813A (en) * | 2019-05-22 | 2019-08-23 | 湃方科技(北京)有限责任公司 | Monitoring state of rotating equipment method and device |
CN110163374A (en) * | 2018-12-07 | 2019-08-23 | 贵州航天风华精密设备有限公司 | A kind of fault diagnosis reasoning system based on Word generic configuration |
CN110233776A (en) * | 2019-05-31 | 2019-09-13 | 湃方科技(北京)有限责任公司 | A kind of rotary-type mechanical equipment state monitoring method and equipment |
CN110322018A (en) * | 2019-06-19 | 2019-10-11 | 上海电力学院 | A kind of power plant fans fault early warning system based on fuzzy reasoning |
CN110347115A (en) * | 2018-04-08 | 2019-10-18 | 华中科技大学 | The method and system of main shaft resonance speed on-line checking and optimization |
CN110377001A (en) * | 2019-06-04 | 2019-10-25 | 上海华电奉贤热电有限公司 | Industrial equipment intelligent Fault Diagnose Systems and method based on data fusion |
CN110513160A (en) * | 2019-09-25 | 2019-11-29 | 哈尔滨汽轮机厂有限责任公司 | A kind of turbine water induction, into cold security alarm and method for early warning |
CN110579368A (en) * | 2019-09-26 | 2019-12-17 | 上海电气电站设备有限公司 | Rotating machinery vibration fault intelligent diagnosis system and method based on simulation calculation |
CN110617981A (en) * | 2019-09-16 | 2019-12-27 | 江苏方天电力技术有限公司 | Fault diagnosis method for phase modulator |
CN110631850A (en) * | 2019-08-23 | 2019-12-31 | 西安陕鼓动力股份有限公司 | Large-scale rotating machine operation state fault diagnosis system and method |
CN110678821A (en) * | 2017-05-25 | 2020-01-10 | 日本电气株式会社 | Processing device, processing method, and program |
CN110794815A (en) * | 2019-11-29 | 2020-02-14 | 哈尔滨汽轮机厂有限责任公司 | Remote intelligent operation and maintenance service system for steam turbine |
CN111141382A (en) * | 2020-01-15 | 2020-05-12 | 北京英华达软件工程有限公司 | Vibration-based multi-dimensional fan blade self-diagnosis device and method |
CN111207916A (en) * | 2020-01-09 | 2020-05-29 | 东南大学 | Blade inclination angle adjustable rubs device |
CN111255674A (en) * | 2020-01-21 | 2020-06-09 | 武汉瑞莱保能源技术有限公司 | System and method for detecting state of rotating mechanical equipment |
CN111582128A (en) * | 2020-04-30 | 2020-08-25 | 电子科技大学 | Mechanical fault sparse representation method based on wolf pack parameterized joint dictionary |
CN111736033A (en) * | 2020-05-09 | 2020-10-02 | 国网浙江省电力有限公司湖州供电公司 | Power grid fault rapid diagnosis positioning system |
CN111950200A (en) * | 2020-08-11 | 2020-11-17 | 哈电发电设备国家工程研究中心有限公司 | Power generation equipment fault diagnosis method based on axle center track fusion |
CN112115556A (en) * | 2020-09-28 | 2020-12-22 | 重庆长安汽车股份有限公司 | In-vehicle vibration simulation analysis method based on finished vehicle start-stop working condition and storage medium |
CN112334924A (en) * | 2018-07-10 | 2021-02-05 | 住友重机械工业株式会社 | Display method for construction machine and support device for construction machine |
CN112559602A (en) * | 2021-02-21 | 2021-03-26 | 北京工业大数据创新中心有限公司 | Method and system for determining target sample of industrial equipment symptom |
CN112901289A (en) * | 2021-03-22 | 2021-06-04 | 哈尔滨汽轮机厂有限责任公司 | Blade vibration monitoring device at top of low-pressure last-stage moving blade of steam turbine |
CN112945535A (en) * | 2021-02-20 | 2021-06-11 | 广东石油化工学院 | Rotating machinery fault detection method and device based on numerical simulation |
CN113295412A (en) * | 2021-05-26 | 2021-08-24 | 华能澜沧江水电股份有限公司 | Method for detecting reason of unbalanced stress of guide bearing of vertical water turbine generator set |
CN113632026A (en) * | 2019-08-29 | 2021-11-09 | 亿可能源科技(上海)有限公司 | Fault diagnosis method and system for rotary mechanical equipment and storage medium |
CN113670604A (en) * | 2021-08-24 | 2021-11-19 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Method and device for diagnosing misalignment fault of coupler of steam turbine generator unit |
CN113983033A (en) * | 2021-10-25 | 2022-01-28 | 燕山大学 | Control method and control device for identifying working condition of hydraulic cylinder of bucket rod of excavator |
CN114020942A (en) * | 2021-10-27 | 2022-02-08 | 上海华虹宏力半导体制造有限公司 | OPC verification expert system and diagnosis method |
CN114034487A (en) * | 2022-01-11 | 2022-02-11 | 成都中科翼能科技有限公司 | Engine rotor blade dynamic signal output method and device based on digital board card |
TWI758824B (en) * | 2020-08-18 | 2022-03-21 | 神通資訊科技股份有限公司 | Abnormality detection and breakage detection system for mechanical operation and the method thereof |
CN114235367A (en) * | 2021-12-14 | 2022-03-25 | 中电华创电力技术研究有限公司 | Rotary machine vibration integrated management system |
CN114252250A (en) * | 2021-12-09 | 2022-03-29 | 郑州恩普特科技股份有限公司 | Mechanical fault diagnosis method based on component decomposition |
CN114441124A (en) * | 2021-12-17 | 2022-05-06 | 中国航发湖南动力机械研究所 | Helicopter transmission system test bed vibration test system and method |
CN115270896A (en) * | 2022-09-28 | 2022-11-01 | 西华大学 | Intelligent diagnosis method for identifying loosening fault of main bearing of aircraft engine |
CN116878878A (en) * | 2023-09-05 | 2023-10-13 | 万向钱潮股份公司 | Bearing test reinforcing and fastening device |
-
2007
- 2007-10-18 CN CNA2007101760524A patent/CN101135601A/en active Pending
Cited By (118)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102087138A (en) * | 2009-10-26 | 2011-06-08 | 福禄克公司 | System and method for vibration analysis and phase analysis of vibration waveforms using dynamic statistical averaging of tachometer data to accurately calculate rotational speed |
US9008997B2 (en) | 2009-10-26 | 2015-04-14 | Fluke Corporation | System and method for vibration analysis and phase analysis of vibration waveforms using dynamic statistical averaging of tachometer data to accurately calculate rotational speed |
CN102192825B (en) * | 2010-01-15 | 2015-05-20 | 福禄克公司 | User interface system and method for diagnosing a rotating machine condition not based upon prior measurement history |
CN102192825A (en) * | 2010-01-15 | 2011-09-21 | 福禄克公司 | User interface system and method for diagnosing a rotating machine condition not based upon prior measurement history |
US8924163B2 (en) | 2010-01-15 | 2014-12-30 | Fluke Corporation | User interface system and method for diagnosing a rotating machine condition not based upon prior measurement history |
CN101799366B (en) * | 2010-01-27 | 2011-08-24 | 北京信息科技大学 | Mechanical failure prediction feature extraction method |
CN102400902B (en) * | 2010-09-15 | 2014-12-24 | 中国石油天然气股份有限公司 | Method for evaluating reliability of performance state of reciprocating compressor |
CN102400902A (en) * | 2010-09-15 | 2012-04-04 | 中国石油天然气股份有限公司 | Method for evaluating reliability of performance state of reciprocating compressor |
CN102466566A (en) * | 2010-11-03 | 2012-05-23 | 财团法人工业技术研究院 | Power equipment abnormality detection device and detection method thereof |
CN102466566B (en) * | 2010-11-03 | 2014-08-13 | 财团法人工业技术研究院 | Power equipment abnormality detection device and detection method thereof |
CN102095560A (en) * | 2010-11-09 | 2011-06-15 | 中国人民解放军重庆通信学院 | Mechanical fault judgment system and method based on noise test |
CN102095560B (en) * | 2010-11-09 | 2013-04-17 | 中国人民解放军重庆通信学院 | Mechanical fault judgment method based on noise test |
CN102207426A (en) * | 2011-03-17 | 2011-10-05 | 北京必可测科技有限公司 | Shafting state monitoring method for rotary machine |
CN102288283A (en) * | 2011-05-13 | 2011-12-21 | 北京必可测科技有限公司 | Method and device for monitoring vibration faults of turbo generator set |
CN102288283B (en) * | 2011-05-13 | 2014-02-12 | 北京必可测科技股份有限公司 | Method and device for monitoring vibration faults of turbo generator set |
CN102854006A (en) * | 2011-06-22 | 2013-01-02 | 霍尼韦尔国际公司 | Severity analysis apparatus and method for shafts of rotating machinery |
CN102901627B (en) * | 2011-07-26 | 2016-12-21 | 通用电气公司 | system monitoring system and method based on fuzzy logic |
CN102901627A (en) * | 2011-07-26 | 2013-01-30 | 通用电气公司 | Fuzzy logic based system monitoring system and method |
CN102358542A (en) * | 2011-08-18 | 2012-02-22 | 上海交通大学 | Mine hoist fault diagnosis method and system based on expert system |
CN102426055A (en) * | 2011-09-01 | 2012-04-25 | 兰州理工大学 | Vibration state information acquisition and characteristic data resource protection system for double-span rotor system |
CN103064340A (en) * | 2011-10-21 | 2013-04-24 | 沈阳高精数控技术有限公司 | Failure prediction method facing to numerically-controlled machine tool |
CN103064340B (en) * | 2011-10-21 | 2014-12-03 | 沈阳高精数控技术有限公司 | Failure prediction method facing to numerically-controlled machine tool |
CN102522705B (en) * | 2011-11-22 | 2015-04-22 | 广东电网公司电力科学研究院 | Transformer maintenance method and device |
CN102522705A (en) * | 2011-11-22 | 2012-06-27 | 广东电网公司电力科学研究院 | Transformer maintenance method and device |
CN102736027A (en) * | 2012-07-18 | 2012-10-17 | 南京因泰莱配电自动化设备有限公司 | Circuit breaker failure diagnosis method based on circuit breaker dynamic property test instrument |
CN103808405A (en) * | 2012-11-08 | 2014-05-21 | 极晨智道信息技术(北京)有限公司 | Automatic diagnostic method of gas power generator group vibration fault of device thereof |
CN103076168A (en) * | 2013-01-09 | 2013-05-01 | 西安交通大学 | Diagnosis method for mechanical faults of circuit breaker |
CN103076168B (en) * | 2013-01-09 | 2015-01-21 | 西安交通大学 | Diagnosis method for mechanical faults of circuit breaker |
CN104062967B (en) * | 2013-03-20 | 2016-12-28 | 广州汽车集团股份有限公司 | The method for diagnosing faults of start stop system and device |
CN104062967A (en) * | 2013-03-20 | 2014-09-24 | 广州汽车集团股份有限公司 | Fault diagnosis method and device of start stop system |
CN103498706A (en) * | 2013-06-25 | 2014-01-08 | 武汉大学 | Turboset performance monitoring and diagnosing method based on general logic table |
CN103398846A (en) * | 2013-08-16 | 2013-11-20 | 大连美恒时代科技有限公司 | Method and platform system for analyzing health of reducer |
CN103398846B (en) * | 2013-08-16 | 2016-06-22 | 大连美恒时代科技有限公司 | A kind of decelerator health analysis method and analysis platform system thereof |
CN103545922A (en) * | 2013-09-24 | 2014-01-29 | 许继集团有限公司 | Multi-scenario analysis based intelligent alarm inference method |
CN103545922B (en) * | 2013-09-24 | 2015-10-28 | 许继集团有限公司 | Based on the intelligent alarm inference method of many scene analysis |
CN103471841B (en) * | 2013-09-30 | 2015-08-12 | 国家电网公司 | A kind of rotating machinery vibrating failure diagnosis method |
CN103471841A (en) * | 2013-09-30 | 2013-12-25 | 国家电网公司 | Method for diagnosing vibration faults of rotary machine |
CN104236613A (en) * | 2014-07-14 | 2014-12-24 | 北京理工大学 | Portable monitoring, diagnosing and on-site verifying system for sensing devices on highway network |
CN104154989B (en) * | 2014-07-25 | 2015-09-09 | 新疆金风科技股份有限公司 | The vibration monitoring method of unstable state slewing and vibration monitor system |
CN104154989A (en) * | 2014-07-25 | 2014-11-19 | 新疆金风科技股份有限公司 | Vibration monitoring method and vibration monitoring system for unstable state rotating equipment |
CN105521997A (en) * | 2014-09-30 | 2016-04-27 | 宝山钢铁股份有限公司 | Method for diagnosing faults of rolling mill roller system on basis of vibration signals |
CN104677619A (en) * | 2015-02-11 | 2015-06-03 | 中煤科工集团重庆研究院有限公司 | Rotating machinery fault feature extraction method based on complex signal bilateral spectrum |
CN104895627A (en) * | 2015-04-28 | 2015-09-09 | 广东电网有限责任公司电力科学研究院 | Steam flow excited vibration suppression method and system of steam turbine |
CN104880247A (en) * | 2015-05-04 | 2015-09-02 | 华中科技大学 | Combined alarming method for on-line monitoring system for rotary machinery |
CN106289115A (en) * | 2015-05-14 | 2017-01-04 | 北京三叶瑞风能源科技有限公司 | A kind of fan coupler based on computer technology misaligns trouble-shooter and method |
CN104991547B (en) * | 2015-05-19 | 2018-02-27 | 重庆大学 | A kind of Multiple Fault Diagnosis Method of physical fault sign variable driving |
CN104991547A (en) * | 2015-05-19 | 2015-10-21 | 重庆大学 | Multi-fault diagnosis method driven by practical fault symptom data |
CN105136282A (en) * | 2015-05-29 | 2015-12-09 | 江阴市华恒仪表有限公司 | Vibration monitoring protection instrument |
CN106339743A (en) * | 2015-07-08 | 2017-01-18 | 罗伯特·博世有限公司 | Electronic Operating Data Memory for a Rotationally Operating Machine |
CN107014628A (en) * | 2015-10-02 | 2017-08-04 | 斯凯孚加拿大有限公司 | Inexpensive online condition monitoring |
CN105841966A (en) * | 2016-04-06 | 2016-08-10 | 西安西热振动研究所有限公司 | Turbo generator set vibration fault diagnosis method based on forward reasoning |
CN107063613A (en) * | 2016-11-23 | 2017-08-18 | 北京中元瑞讯科技有限公司 | The analysis and diagnosis method of turbine-generator units Rubbing faults based on online data |
CN106762343A (en) * | 2016-12-29 | 2017-05-31 | 北京中元瑞讯科技有限公司 | The diagnostic method of the hydraulic generator set thrust bearing failure based on online data |
CN106762343B (en) * | 2016-12-29 | 2019-01-15 | 北京中元瑞讯科技有限公司 | The diagnostic method of hydraulic generator set thrust bearing failure based on online data |
CN110678821B (en) * | 2017-05-25 | 2022-09-27 | 日本电气株式会社 | Processing device, processing method, and program |
CN110678821A (en) * | 2017-05-25 | 2020-01-10 | 日本电气株式会社 | Processing device, processing method, and program |
CN107153876A (en) * | 2017-05-25 | 2017-09-12 | 南通大学 | Machine vision shutter Self-tuning System intelligent control method based on Expert Rules |
CN107607321A (en) * | 2017-09-06 | 2018-01-19 | 成都大汇物联科技有限公司 | A kind of equipment fault accurate positioning method |
CN107607321B (en) * | 2017-09-06 | 2019-11-05 | 成都大汇物联科技有限公司 | A kind of equipment fault accurate positioning method |
CN107655690A (en) * | 2017-10-30 | 2018-02-02 | 王才旺 | Motor bearings method for diagnosing faults based on artificial neural network |
CN107891994A (en) * | 2017-11-09 | 2018-04-10 | 北京九天翱翔科技有限公司 | A kind of full Intelligent flight device flight test error analytical system |
CN110131193A (en) * | 2018-02-02 | 2019-08-16 | 中国航发商用航空发动机有限责任公司 | Aero-engine surge fault monitoring method and system |
CN110347115A (en) * | 2018-04-08 | 2019-10-18 | 华中科技大学 | The method and system of main shaft resonance speed on-line checking and optimization |
CN108387309A (en) * | 2018-04-25 | 2018-08-10 | 哈尔滨电气股份有限公司 | A kind of turbine shafting vibrating data collection, pretreatment and remotely send system |
CN108708773A (en) * | 2018-05-11 | 2018-10-26 | 湖北华电襄阳发电有限公司 | A kind of Steam Turbine Fault Diagnosis Methods, system and device |
CN108982096A (en) * | 2018-06-01 | 2018-12-11 | 杭州电子科技大学 | Industrial robot crank axle wear detecting method based on heuristic rule system |
CN108982096B (en) * | 2018-06-01 | 2020-04-24 | 杭州电子科技大学 | Industrial robot crankshaft abrasion detection method based on heuristic rule system |
CN108803569A (en) * | 2018-06-11 | 2018-11-13 | 哈尔滨锅炉厂有限责任公司 | Station boiler diagnostic expert system and its method for diagnosing faults |
CN112334924A (en) * | 2018-07-10 | 2021-02-05 | 住友重机械工业株式会社 | Display method for construction machine and support device for construction machine |
CN108918126A (en) * | 2018-07-25 | 2018-11-30 | 北京振测智控科技有限公司 | A kind of rotating machinery vibrating intelligent fault diagnosis method based on fining fault model |
CN109361394A (en) * | 2018-10-09 | 2019-02-19 | 中国人民解放军91388部队 | Dynamic data recording system in a kind of test of Underwater Battery |
CN110163374A (en) * | 2018-12-07 | 2019-08-23 | 贵州航天风华精密设备有限公司 | A kind of fault diagnosis reasoning system based on Word generic configuration |
CN110163374B (en) * | 2018-12-07 | 2022-02-11 | 贵州航天风华精密设备有限公司 | Fault diagnosis reasoning system based on Word general configuration |
CN109855873A (en) * | 2018-12-12 | 2019-06-07 | 华润电力技术研究院有限公司 | The method for diagnosing faults and device of steam turbine main shaft |
CN110160813A (en) * | 2019-05-22 | 2019-08-23 | 湃方科技(北京)有限责任公司 | Monitoring state of rotating equipment method and device |
CN110233776A (en) * | 2019-05-31 | 2019-09-13 | 湃方科技(北京)有限责任公司 | A kind of rotary-type mechanical equipment state monitoring method and equipment |
CN110377001A (en) * | 2019-06-04 | 2019-10-25 | 上海华电奉贤热电有限公司 | Industrial equipment intelligent Fault Diagnose Systems and method based on data fusion |
CN110118582A (en) * | 2019-06-12 | 2019-08-13 | 北京博识创智科技发展有限公司 | A kind of rotating machinery fault diagnosis method and system |
CN110322018A (en) * | 2019-06-19 | 2019-10-11 | 上海电力学院 | A kind of power plant fans fault early warning system based on fuzzy reasoning |
CN110631850A (en) * | 2019-08-23 | 2019-12-31 | 西安陕鼓动力股份有限公司 | Large-scale rotating machine operation state fault diagnosis system and method |
CN110631850B (en) * | 2019-08-23 | 2021-05-11 | 西安陕鼓动力股份有限公司 | Large-scale rotating machine operation state fault diagnosis system and method |
CN113632026A (en) * | 2019-08-29 | 2021-11-09 | 亿可能源科技(上海)有限公司 | Fault diagnosis method and system for rotary mechanical equipment and storage medium |
CN110617981A (en) * | 2019-09-16 | 2019-12-27 | 江苏方天电力技术有限公司 | Fault diagnosis method for phase modulator |
CN110617981B (en) * | 2019-09-16 | 2021-06-15 | 江苏方天电力技术有限公司 | Fault diagnosis method for phase modulator |
CN110513160A (en) * | 2019-09-25 | 2019-11-29 | 哈尔滨汽轮机厂有限责任公司 | A kind of turbine water induction, into cold security alarm and method for early warning |
CN110579368A (en) * | 2019-09-26 | 2019-12-17 | 上海电气电站设备有限公司 | Rotating machinery vibration fault intelligent diagnosis system and method based on simulation calculation |
CN110794815A (en) * | 2019-11-29 | 2020-02-14 | 哈尔滨汽轮机厂有限责任公司 | Remote intelligent operation and maintenance service system for steam turbine |
CN111207916A (en) * | 2020-01-09 | 2020-05-29 | 东南大学 | Blade inclination angle adjustable rubs device |
CN111207916B (en) * | 2020-01-09 | 2021-01-12 | 东南大学 | Blade inclination angle adjustable rubs device |
CN111141382A (en) * | 2020-01-15 | 2020-05-12 | 北京英华达软件工程有限公司 | Vibration-based multi-dimensional fan blade self-diagnosis device and method |
CN111255674B (en) * | 2020-01-21 | 2022-08-09 | 武汉瑞莱保科技有限公司 | System and method for detecting state of rotating mechanical equipment |
CN111255674A (en) * | 2020-01-21 | 2020-06-09 | 武汉瑞莱保能源技术有限公司 | System and method for detecting state of rotating mechanical equipment |
CN111582128A (en) * | 2020-04-30 | 2020-08-25 | 电子科技大学 | Mechanical fault sparse representation method based on wolf pack parameterized joint dictionary |
CN111582128B (en) * | 2020-04-30 | 2022-05-03 | 电子科技大学 | Mechanical fault sparse representation method based on wolf pack parameterized joint dictionary |
CN111736033A (en) * | 2020-05-09 | 2020-10-02 | 国网浙江省电力有限公司湖州供电公司 | Power grid fault rapid diagnosis positioning system |
CN111950200A (en) * | 2020-08-11 | 2020-11-17 | 哈电发电设备国家工程研究中心有限公司 | Power generation equipment fault diagnosis method based on axle center track fusion |
TWI758824B (en) * | 2020-08-18 | 2022-03-21 | 神通資訊科技股份有限公司 | Abnormality detection and breakage detection system for mechanical operation and the method thereof |
CN112115556A (en) * | 2020-09-28 | 2020-12-22 | 重庆长安汽车股份有限公司 | In-vehicle vibration simulation analysis method based on finished vehicle start-stop working condition and storage medium |
CN112945535A (en) * | 2021-02-20 | 2021-06-11 | 广东石油化工学院 | Rotating machinery fault detection method and device based on numerical simulation |
CN112559602A (en) * | 2021-02-21 | 2021-03-26 | 北京工业大数据创新中心有限公司 | Method and system for determining target sample of industrial equipment symptom |
CN112559602B (en) * | 2021-02-21 | 2021-07-13 | 北京工业大数据创新中心有限公司 | Method and system for determining target sample of industrial equipment symptom |
CN112901289A (en) * | 2021-03-22 | 2021-06-04 | 哈尔滨汽轮机厂有限责任公司 | Blade vibration monitoring device at top of low-pressure last-stage moving blade of steam turbine |
CN113295412B (en) * | 2021-05-26 | 2022-10-11 | 华能澜沧江水电股份有限公司 | Method for detecting cause of unbalanced stress of guide bearing of vertical water turbine generator set |
CN113295412A (en) * | 2021-05-26 | 2021-08-24 | 华能澜沧江水电股份有限公司 | Method for detecting reason of unbalanced stress of guide bearing of vertical water turbine generator set |
CN113670604B (en) * | 2021-08-24 | 2024-05-03 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Method and device for diagnosing misalignment fault of coupling of steam turbine generator unit |
CN113670604A (en) * | 2021-08-24 | 2021-11-19 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Method and device for diagnosing misalignment fault of coupler of steam turbine generator unit |
CN113983033A (en) * | 2021-10-25 | 2022-01-28 | 燕山大学 | Control method and control device for identifying working condition of hydraulic cylinder of bucket rod of excavator |
CN113983033B (en) * | 2021-10-25 | 2022-07-01 | 燕山大学 | Control method and control device for identifying working condition of hydraulic cylinder of bucket rod of excavator |
CN114020942A (en) * | 2021-10-27 | 2022-02-08 | 上海华虹宏力半导体制造有限公司 | OPC verification expert system and diagnosis method |
CN114252250A (en) * | 2021-12-09 | 2022-03-29 | 郑州恩普特科技股份有限公司 | Mechanical fault diagnosis method based on component decomposition |
CN114252250B (en) * | 2021-12-09 | 2023-08-01 | 郑州恩普特科技股份有限公司 | Mechanical fault diagnosis method based on component decomposition |
CN114235367A (en) * | 2021-12-14 | 2022-03-25 | 中电华创电力技术研究有限公司 | Rotary machine vibration integrated management system |
CN114235367B (en) * | 2021-12-14 | 2024-01-19 | 中电华创电力技术研究有限公司 | Comprehensive management system for vibration of rotary machine |
CN114441124A (en) * | 2021-12-17 | 2022-05-06 | 中国航发湖南动力机械研究所 | Helicopter transmission system test bed vibration test system and method |
CN114034487A (en) * | 2022-01-11 | 2022-02-11 | 成都中科翼能科技有限公司 | Engine rotor blade dynamic signal output method and device based on digital board card |
CN115270896A (en) * | 2022-09-28 | 2022-11-01 | 西华大学 | Intelligent diagnosis method for identifying loosening fault of main bearing of aircraft engine |
CN116878878A (en) * | 2023-09-05 | 2023-10-13 | 万向钱潮股份公司 | Bearing test reinforcing and fastening device |
CN116878878B (en) * | 2023-09-05 | 2023-11-14 | 万向钱潮股份公司 | Bearing test reinforcing and fastening device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101135601A (en) | Rotating machinery vibrating failure diagnosis device and method | |
Yang et al. | VIBEX: an expert system for vibration fault diagnosis of rotating machinery using decision tree and decision table | |
CN1026832C (en) | Apparatus for controlling sensor processing algorithms response to expert sensor diagnoses | |
Tay et al. | Fault diagnosis based on rough set theory | |
JPH0692914B2 (en) | Equipment / facility condition diagnosis system | |
CN110617981B (en) | Fault diagnosis method for phase modulator | |
CN105806614A (en) | Embedded dual server based failure diagnosis method and system for rotation machines in heat-engine plant | |
CN108918126A (en) | A kind of rotating machinery vibrating intelligent fault diagnosis method based on fining fault model | |
Devaney et al. | Case-Based Reasoning for Gas Turbine Diagnostics. | |
Xue et al. | A parallel distributed knowledge-based system for turbine generator fault diagnosis | |
Takizawa et al. | An intelligent man-machine system for future nuclear power plants | |
Yang et al. | Reinforcing fuzzy rule-based diagnosis of turbomachines with case-based reasoning | |
Gemmell et al. | A consultative expert system for fault diagnosis of turbine-generator plant | |
Yang et al. | Fuzzy diagnosis of turbomachines | |
Hudon et al. | Innovative web system for condition-based maintenance of generators | |
Sheppard et al. | Incorporating Model-Based Reasoning in Interactive Maintenance Aids | |
CN108615047A (en) | The construction method of fault diagnosis knowledge model towards Wind turbines equipment | |
Muller | The task and function of an expert system in steam-turbo-generator diagnostics | |
Hewitt et al. | Vibration diagnostics by expert systems that link to machinery databases | |
Goel et al. | Availability and profit analysis of gas turbine system using fuzzy trapezoidal numbers with different left height and right height | |
Jorgensen et al. | Centralized Power Room Monitoring Systems (COPM) Design and Implementation | |
Wang et al. | A flexible automatic test system for rotating-turbine machinery | |
Sleeman et al. | Towards painless knowledge acquisition | |
Bosmans | Expert Systems Provide Support For A Proactive Machinery Management Methodology. | |
Kontargyri et al. | An expert system for fault diagnosis, repairing and maintenance of electrical machines |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20080305 |