CN105159286A - Spacecraft on-orbit anomaly alarming and fault diagnosing system - Google Patents
Spacecraft on-orbit anomaly alarming and fault diagnosing system Download PDFInfo
- Publication number
- CN105159286A CN105159286A CN201510608592.XA CN201510608592A CN105159286A CN 105159286 A CN105159286 A CN 105159286A CN 201510608592 A CN201510608592 A CN 201510608592A CN 105159286 A CN105159286 A CN 105159286A
- Authority
- CN
- China
- Prior art keywords
- reasoning
- confidence level
- telemetry
- diagnosis
- knowledge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
- G05B23/0227—Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions
- G05B23/0229—Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions knowledge based, e.g. expert systems; genetic algorithms
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a spacecraft on-orbit anomaly alarming and fault diagnosing system. A knowledge editor inputs well-compiled alarming diagnosis knowledge; a data buffer area buffers inputted original telemetering data; a data area extracts telemetering data or a telemetering instruction from the data buffer area when a reasoning controller carries out logic matching operation and stores the data or the instruction; a rule area loads the well-compiled alarming diagnosis knowledge from the knowledge editor, and in the rule area, each piece of the alarming diagnosis knowledge is called a rule; the reasoning controller carries out logic matching operation on the original telemetering data in the data area and the alarming diagnosis knowledge in the rule area to acquire diagnosis results; a diagnosis result which needs to be outputted is selected to be outputted to a blackboard; the blackboard stores the diagnosis result acquired through the logic matching operation by the reasoning controller; and a result buffer area buffers the diagnosis result which is selected to be outputted by the reasoning controller and the result is sent to a client, and after a user checks the diagnosis result via the client, a confirmation message is answered.
Description
Technical field
The invention belongs to space flight fault diagnosis technology field, particularly relate to a kind of spacecraft abnormal alarm and fault diagnosis system in-orbit.
Background technology
The core of inference machine subsystem carries out reasoning from logic computing according to the measuring and control data of expertise and input, and the final abnormality releasing spacecraft, its essence is and realize the virtual machine that has logical reasoning ability.Early stage expert system mainly adopts determinacy reasoning algorithm, and the evidence of this method representation is deterministic.Such as ground shadow state, not to be area of illumination be exactly shadow zone, does not have ambiguity.Its reasoning process is based on mathematical logic, and reasoning process is tight, and conclusion is also accurate, or sets up, or is false.But the evidence adopted in the diagnostic procedure of reality is not completely accurate, and some information is perfect not, and some has uncertainty.Such as, in shadow state, the description for penumbra region is just more difficult, penumbra when from shadow at last, adopt Accurate Reasoning to be difficult to describe to this.
Summary of the invention
For solving the problem, the invention provides a kind of spacecraft abnormal alarm and fault diagnosis system in-orbit.
Spacecraft of the present invention is abnormal alarm and fault diagnosis system in-orbit, and it comprises: knowledge editor, data buffer, reasoning and decision device, data field, blackboard, formula area and result buffer;
Knowledge editor, for inputting compiled alarm diagnosis knowledge;
Data buffer, for cushioning the original telemetry of input, original telemetry comprises telemetry and telemetry command;
Data field, for extracting telemetry when reasoning and decision device carries out logic matching operation or telemetry command and storing it from data buffer;
Formula area, for loading compiled alarm diagnosis knowledge from knowledge editor, in formula area, each alarm diagnosis knowledge is referred to as rule;
Reasoning and decision device, carries out logic matching operation by the original telemetry in data field and the alarm diagnosis knowledge in formula area, obtains diagnostic result; And select to need the diagnostic result exported to export blackboard to;
Blackboard, for storing the diagnostic result that reasoning and decision device is obtained by logic matching operation;
Result buffer, selects the diagnostic result of output for cushioning reasoning and decision device and is sent to client, after user checks diagnostic result by this client, replying confirmation.
Further, reasoning and decision device comprises:
Reliability assessment module, the assessment of the parameter confidence level that takes remote measurement to the original telemetry of input, obtains the telemetry of band confidence level; Wherein, telecommand, inference machine safeguard initial value table information together with this original telemetry as the fact of spacecraft fault diagnosis reasoning;
Evidence derivation module, carries out logical operation according to the telemetry of the telecommand on ground, initial value table information that inference machine is safeguarded and described band confidence level and obtains evidence, and so-called evidence is exactly according to the true status information that draws with factual knowledge and warning message;
Fault diagnosis module, carries out fault diagnosis according to described evidence in conjunction with alarm diagnosis knowledge, releases diagnostic result;
Result output module, exports according to alarm diagnosis knowledge-chosen diagnostic result.
Wherein, described reliability assessment module comprises:
Rule statistic unit, obtains remote measurement statistical law by carrying out statistics to the Changing Pattern of telemetry parameter;
Confidence level obtains unit, is mated by the remote measurement statistical law of new telemetry parameter with the remote measurement statistical law of history, and obtains the confidence level of remote measurement in conjunction with confidence factor.
Wherein, described evidence derivation module comprises:
Based on the derivation judging and carry out based on confidence level pass-algorithm two kinds of modes of fuzzy mathematics of transfiniting of degree of membership, wherein, the confidence level pass-algorithm based on fuzzy mathematics comprises: the confidence level pass-algorithm of the single fact and combination true add right reliabiliL pass-algorithm.
Wherein, described fault diagnosis module comprises: forward reasoning, backward reasoning, framework rule-based reasoning based on possibility.
Wherein, the output principle in result output module is: the higher output speed of confidence level is faster; If the result of low confidence level maintains the long time also need to export; The time nearer impact of data on Output rusults is larger; When confidence level is 0.9, output time is 1 minute; When confidence level is 0.6, output time is 1 hour; Confidence level is greater than the output of 0.5 support result, confidence level is less than not exporting of 0.5 support result.
Further, in formula area, each rule is provided with active control list, first judges whether the active control list of the rule in this formula area all sets up when carrying out reasoning, sets up and then enables this rule, otherwise this rule can not be selected to carry out reasoning computing.
Wherein, described fault diagnosis module comprises: real-time diagnosis unit, early warning diagnosis unit, playback diagnosis unit, checking diagnosis unit and spread function unit.
Beneficial effect:
The present invention can infer whether spacecraft exception occurs, when an exception occurs can automatic search, mate corresponding expertise, and provide alarm failure location and fault auxiliary process decision information.And the present invention can realize reexamining history telemetry, ex-post analysis Spacecraft anomaly is reported to the police, diagnosis is located and the decision-making of fault auxiliary process.
This system is adapted to remote measurement analog quantity and quantity of state two class parameter, can according to history telemetry data conversion rule, and calculate reliability coefficient and the confidence level of telemetry, the accuracy of Analysis on confidence should reach more than 95%.
Accompanying drawing explanation
Fig. 1 is spacecraft of the present invention abnormal alarm and fault diagnosis system schematic diagram in-orbit;
Fig. 2 is real-time diagnosis cell schematics of the present invention;
Fig. 3 is playback diagnosis unit schematic diagram of the present invention;
Fig. 4 is early warning diagnosis unit schematic diagram of the present invention;
Fig. 5 is checking diagnosis unit schematic diagram of the present invention;
Fig. 6 of the present inventionly judges embodiment one schematic diagram based on transfiniting of degree of membership.
Embodiment
A large amount of fuzzy concepts is there is when spacecraft fault diagnosis knowledge description, it is exactly such as a fuzzyyer concept for transfiniting, numerical value is how many for transfiniting, how many for seriously to transfinite, accurately can not define, therefore also adopt the subordination method in fuzzy reasoning to carry out complex reasoning to these fuzzy concepts in the present system.Also need the confidence level of adjoint fuzzy mathematics evaluation except carrying out numerical operation when mathematical operation.Therefore also need on reasoning algorithm in conjunction with some contents in fuzzy reasoning.Finally when diagnostic result is exported, when export, need to set up empirical model according to user behavior analysis, final formation spacecraft fault diagnosis mathematical model.
Specific implementation is as follows:
As shown in Figure 1, spacecraft of the present invention is abnormal alarm and fault diagnosis system in-orbit, and it comprises: knowledge editor, data buffer, reasoning and decision device, data field, blackboard, formula area and result buffer;
Knowledge editor, for inputting compiled alarm diagnosis knowledge;
Data buffer, for cushioning the original telemetry of input, original telemetry comprises telemetry and telemetry command;
Data field, for extracting telemetry when reasoning and decision device carries out logic matching operation or telemetry command and storing it from data buffer;
Formula area, for loading compiled alarm diagnosis knowledge from knowledge editor, in formula area, each alarm diagnosis knowledge is referred to as rule;
Reasoning and decision device, carries out logic matching operation by the original telemetry in data field and the alarm diagnosis knowledge in formula area, obtains diagnostic result; And select to need the diagnostic result exported to export blackboard to;
Blackboard, for storing the diagnostic result that reasoning and decision device is obtained by logic matching operation;
Result buffer, selects the diagnostic result of output for cushioning reasoning and decision device and is sent to client, after user checks diagnostic result by this client, replying confirmation.
Further, reasoning and decision device comprises:
Reliability assessment module, the assessment of the parameter confidence level that takes remote measurement to the original telemetry of input, obtains the telemetry of band confidence level; Wherein, telecommand, inference machine safeguard initial value table information together with this original telemetry as the fact of spacecraft fault diagnosis reasoning; The fundamental purpose of telemetry parameter reliability assessment is that true credibility is observed in assessment, by certain error code can be there is after telemetry ground receiver, Analysis on confidence be exactly the credibility judging these data, each each data stamp confidence level label, represent the degree of support to evidence, send into inference machine and carry out reasoning computing.The theoretical foundation of reliability assessment is theory of probability.By adding up the Changing Pattern of telemetry parameter, if after receiving new telemetry, judge that new telemetry Changing Pattern mates with the Compound Degree of the remote measurement statistical law of statistics, if meet higher, be high confidence level telemetry, otherwise be low confidence level.Telemetry affects the result of reasoning to a great extent due to the reason of error code, especially in the near-earth satellite time out of the station, the bit error rate of data is very high, normal data may be flooded, this time, inference conclusion cannot be differentiated substantially, and therefore Water demand telemetry draws the believable coefficient of data.This coefficient participates in reasoning as the confidence factor of factural information, finally can release the confidence level of conclusion according to this confidence level.
Evidence derivation module, carries out logical operation according to the telemetry of the telecommand on ground, initial value table information that inference machine is safeguarded and described band confidence level and obtains evidence, and so-called evidence is exactly according to the true status information that draws with factual knowledge and warning message; Generating evidence is exactly according to the true process forming evidence with factual knowledge, is exactly the process that the warning knowledge of foundation telemetry and telemetry parameter forms warning message in the present system.The reasoning computing generating evidence adopts fuzzy reasoning method, is exactly mainly adopt subordination method, and the transmission method of confidence level.Introduce respectively below:
Fault diagnosis module, carries out fault diagnosis according to described evidence in conjunction with alarm diagnosis knowledge, releases diagnostic result;
Result output module, exports according to alarm diagnosis knowledge-chosen diagnostic result.For the output how determining the reasoning results, the behavior of spacecraft being monitored by assayer, we suppose there is following hypothesis:
The confidence level computational mathematics model of Output rusults not only for the output of confidence level result, also for shooting conditions inspection that process monitoring and fault handling monitor.Exciting of process monitoring has certain similarity with output condition, is all to meet certain hour condition to carry out exporting or carrying out next step action.
Further, described reliability assessment module comprises:
Rule statistic unit, obtains remote measurement statistical law by carrying out statistics to the Changing Pattern of telemetry parameter;
Confidence level obtains unit, is mated by the remote measurement statistical law of new telemetry parameter with the remote measurement statistical law of history, and obtains the confidence level of remote measurement in conjunction with confidence factor.
Wherein, described evidence derivation module comprises:
Based on the derivation judging and carry out based on confidence level pass-algorithm two kinds of modes of fuzzy mathematics of transfiniting of degree of membership, wherein, the confidence level pass-algorithm based on fuzzy mathematics comprises: the confidence level pass-algorithm of the single fact and combination true add right reliabiliL pass-algorithm.
Embodiment one is judged based on transfiniting of degree of membership
Example 1: area of illumination busbar voltage reduces (under-voltage)
42V ± 0.5V is should be at area of illumination busbar voltage normal value.The reason causing voltage to reduce has:
(1) parallel regulator fault causes point flow valuve excessive, and solar battery array output power is shunted, and busbar voltage controls to lose efficacy, and can not be load supplying.Check that bus error signal exports: northern VN4 (southern VN12) >=6V.-12V powers whether open a way (remote measurement code name).
(2) moon shade is entered.(normal phenomenon calculates according to CALCULATING PREDICTION)
(3) load current overcurrent on bus.Cannot recover normal before unshorting factor
(4) solar array reverse, stall.Recover windsurfing normal condition.
According to discussion research and actual conditions with user, exception for spacecraft is divided into two parts to process, first be report to the police, namely detect for telemetry parameter transfiniting under numerous conditions, spacecraft state transition, export as alarming result; Then be exactly the diagnosis of fault, fault is located in detail, the reason that analysis of failure occurs, final to out of order solution.
Below just according to the fault alarm diagnosis that area of illumination busbar voltage reduces, analyze, arrange out warning knowledge (factual knowledge) and fault diagnosis knowledge, and then carry out the description of reasoning process.
Fact knowledge
Ra1: if in area of illumination busbar voltage lower than 41.5V, then area of illumination busbar voltage reduces.
Ra2: reduce in area of illumination busbar voltage, if be in a moon shadow state, then normally.
Ra3: reduce in area of illumination busbar voltage, if solar array reverses or stall, then normally.The alarm rule of solar array can be quoted windsurfing and reverse or stall.
Diagnostic knowledge
Rd1: if area of illumination busbar voltage reduces, judge whether shunt is shunted excessive, if excessive, for shunt fault causes busbar voltage to reduce; Otherwise for unknown cause causes busbar voltage to reduce.
Rd2: if area of illumination busbar voltage reduces, judge that whether bus load current is excessive, if excessive, for short circuit causes voltage to reduce; Otherwise for unknown cause causes busbar voltage to reduce.
Area of illumination busbar voltage in alarm rule Ra1 is then regarded as lower than 41.5V and transfinites, transfinite lower than 41.5 for this regular common judgement, being greater than 41.5 does not transfinite, and realizes also fairly simple, but there is a problem, if busbar voltage is 41.50001 whether also to transfinite.This problem is transfinited, alternatively transfinite (sampling error).Cause the reason of this problem to be a Ra1 inherently fuzzy concept, if adopt accurate describing method, when parameter in critical zone time will be difficult to describe, the selection of critical value has larger impact to result.In fuzzy mathematics, there is reasonable solution for this situation, adopt membership function to describe judgement of transfiniting exactly.Being exactly busbar voltage as shown in Figure 6 to transfinite the degree of membership curve judged lower than 41.5.Curve in figure 6 represents and judges that busbar voltage surpasses the degree of membership curve of lower limit, and horizontal ordinate is bus voltage value, and ordinate is the degree of transfiniting.
Can find out that the degree of transfiniting is 80% when busbar voltage is 41.5 time from the graph, if when parameter is 41.4, the degree of transfiniting is 95%, if represent time parameter is 41.6 that the degree of transfiniting is 4%.If parameter is 41.50001, the degree that transfinites is close to 80%, if the duration is longer, (system carries out integration to the degree of transfiniting, acquire a certain degree and excite subsequent action), can exciting equally reports to the police exports, or excites follow-up reasoning process.
If be exactly reach 80% when the degree of transfiniting and maintain the regular hour from physical significance, it is super lower limit; If maintain the long time lower than 80%, it is also super lower limit; If transfinited, degree also maintains the shorter time higher than 80% is also super lower limit.This physical significance also meets expert and observes the mode of thinking transfinited, and namely transfinites higher, then can regard as immediately transfinites; Not serious if transfinited, but continue, then always also can think super lower limit.
For the analysis of above situation, we can find out, adopt the judgement of transfiniting based on degree of membership, can well solve the critical value fuzzy problem of simple overload alarm
Based on the confidence level pass-algorithm embodiment of fuzzy mathematics
1) the confidence level pass-algorithm of the single fact:
If support that the fact of conclusion only has one, and the confidence level CF (E) of known true E and factual knowledge
IFETHENH
Confidence level CF (H, E), then the confidence level of conclusion H is exactly:
CF(H)＝CF(E)*CF(H，E)
2) what combination was true adds right reliabiliL pass-algorithm
If the known fact has multiple formation one to combine true E
E＝E1∧E2∧E3∧……∧En，
And the confidence level CF (Ei) of known each fact, and the weight coefficient P (Ei) of each fact in this combination fact, and factual knowledge
IFETHENH
Confidence level CF (H, E), then the confidence level of conclusion H is exactly:
Further, described fault diagnosis module comprises: forward reasoning, backward reasoning, framework rule-based reasoning based on possibility.
Forward reasoning: mainly adopt forward reasoning mode to carry out in the present system, namely from the fact, through reasoning from logic, finally draw inference conclusion.The foundation main for spacecraft fault diagnosis is measuring and control data, in time receiving new measuring and control data, starts reasoning.
Backward reasoning be conclusion solve process, first suppose a conclusion when reasoning, then search this conclusion and whether set up, and if set up; could think this conclusion be set up.In spacecraft fault diagnosis, the reasoning for state transition adopts reverse manner to carry out.The shooting conditions of reasoning is state generation saltus step, and whether this time, system was assumed to the normal variation (automatic control or remote control) of state, then search the condition meeting normal variation and meet, if met, is exactly normal variation, otherwise is ANOMALOUS VARIATIONS.For backward reasoning, require that conclusion is easy to hypothesis, such reasoning is pointed, and thrust Performance Ratio is better.
Framework rule-based reasoning based on possibility: in spacecraft fault diagnosis language, having a class diagnostic knowledge to adopt frame mode to describe, is exactly first write setting fault, is describing the form of expression of fault.Such as excessively shunt fault for shunt, its phenomenon is reduce in area of illumination busbar voltage, and partial current is higher.For kind knowledge, if phenomenon does not all occur, then rule can not activate; Once there be phenomenon to occur, then suppose that fault occurs, calculate the confidence level of fault conclusion immediately, if Reliability ratio is higher, then think release conclusion.Frame inference strategy is determined by the input mode of knowledge.
Wherein, the output principle in result output module is: the higher output speed of confidence level is faster; If the result of low confidence level maintains the long time also need to export; The time nearer impact of data on Output rusults is larger; When confidence level is 0.9, output time is 1 minute; When confidence level is 0.6, output time is 1 hour; Confidence level is greater than the output of 0.5 support result, confidence level is less than not exporting of 0.5 support result.Diagnostic result exports the experimental formula that confidence level calculates:
Wherein
O
frepresent the confidence level that diagnostic result exports;
C
f(t, h) represents the confidence level of result diagnostic result h in t;
μ
trepresent that t is to the disturbance degree exported, thinking a time weight value, is a membership function.
μ
t＝e
t。
Further, in formula area, each rule is provided with active control list, first judges whether the active control list of the rule in this formula area all sets up when carrying out reasoning, sets up and then enables this rule, otherwise this rule can not be selected to carry out reasoning computing.
Further, described fault diagnosis module comprises: real-time diagnosis unit, early warning diagnosis unit, playback diagnosis unit, checking diagnosis unit and spread function unit.
Real-time diagnosis unit: real time execution pattern is system primary operating mode, realizes reporting to the police to the real-time diagnosis of spacecraft, describes the operational process of real time execution pattern in fig. 2.(1) starting: monitoring and scheduling module starts inference machine, is that real-time mode runs by optimum configurations, the obtain manner of inference machine according to mode parameter determination data, the preserving type of the reasoning results.(2) diagnostic knowledge is loaded: load diagnostic knowledge from database time inference machine starts, build various reasoning object, complete the initialization procedure to inference machine.(3) loading initial value table: the current state recording spacecraft when real-time mode in system, loading these status informations, for the abnormal saltus step of comparison spacecraft state when starting simultaneously.(4) measuring and control data is sent: when inference machine runs, the measuring and control data that real-time reception measuring and control data sending module sends, here mainly telecommand data.(5) measuring and control data is sent: measuring and control data sending module sends telemetry and sends to telemetry Analysis on confidence module simultaneously, for analyzing the confidence level of telemetry, sends to inference machine again after having analyzed by network.(6) measuring and control data is sent: the telemetry parameter stamping confidence level label is sent to inference machine by telemetry Analysis on confidence module.Inference machine adopts and carries out reasoning with the data of confidence level label.(7) history measuring and control data is read: in reasoning process, sometimes need history measuring and control data to carry out, directly read by satellite integrated data base, and buffer memory in systems in which, when reading history telemetry in order to the needs of performance, need to pre-read data, ensure the speed of reasoning.(8) preserve diagnostic result: after a frame reasoning is carried out, analyze the result released, using these the reasoning results as in diagnostic result write into Databasce.(9) diagnostic result is sent: after the diagnostic result that inference machine reasoning makes new advances, send to alarm diagnosis client by network, user checks diagnostic result by browser.(10) diagnostic result is confirmed: after user checks diagnostic result, according to the correctness of explain information judged result, and diagnostic result is confirmed, represent that user has known this result, confirmation result is sent to inference machine by network by client, inference machine according to the confidence level of the confirmation results modification the reasoning results of user, for next step reasoning
Playback diagnosis unit, in data readback pattern inference machine to historical data base in measuring and control data carry out diagnostic analysis, monitoring spacecraft the exception once occurred.Inference machine is started with playback mode by monitoring and scheduling module, and user by the time end of playback diagnostic clients end input write playback, and starts reasoning process.In playback diagnostic mode, inference machine directly reads measuring and control data and carries out diagnostic analysis from satellite integrated data base, and result is sent to alarm diagnosis client.After playback mode runs, inference machine process is automatically out of service.The operational process of data of description playback mode in figure 3.Start, send control command, display reasoning operation progress msg, loading diagnostic knowledge, read playback measuring and control data, diagnostic reasoning, storage playback result, display playback result.
Early warning diagnosis unit: when modes of warning runs, needs two inference machines and runs, and one is run at real-time mode, and another runs at modes of warning.After receiving telemetry, telemetry prediction module is extrapolated to remote measurement numerical value, and the spacecraft status information needed when extrapolation needs the inference machine run from real-time mode to obtain.The inference machine that remote measurement predicted data sends to modes of warning to run, inference machine carries out diagnostic analysis according to these predicted data, receive the diagnostic result that real-time mode sends simultaneously, finally the result that real-time mode does not exit is sent to alarm indication client, shows with the form of early warning result.The inference machine that modes of warning inference machine and real-time mode run all in the form of services continuous service on backstage, by the ruuning situation of dispatching and monitoring module monitors process.The operational process of modes of warning is described in the diagram.Start, load diagnostic knowledge, transmission measuring and control data, real-time diagnosis, transmission real-time status result, computational prediction data, early warning diagnosis, store early warning diagnostic result, display early warning result.
Checking diagnosis unit: in Verify in System pattern, system verification client reads measuring and control data from system, more regular according to the analog parameter of user's input, generates verification msg, again according to the transmission rate of real-time telemetry data, send to inference machine with the form of telemetry frame.Inference machine runs with Validation Mode, and Receipt Validation data carry out diagnostic reasoning, finally diagnostic result is sent to the display of alarm diagnosis client.
Verify in System modular system checking client safeguards the clock of telemetry, requires that inference machine also carries out reasoning according to this clock.After checking completes, inference machine process exits automatically.The operational process of data of description system verification pattern in Figure 5.Start, start checking inference machine, selection verification msg, transmission verification msg, checking diagnosis, store the result, show the result.
Further, the inference step in reasoning and decision device comprises:
Step 0, load diagnostic rule f1-fm, regular fi is made up of n evidence and a conclusion;
Step 1, utilizes " patent " to assess the original telemetry x1---xn in n evidence for regular fi, obtains telemetry confidence level y1---yn;
Step 2, for i-th evidence, the evidence prestoring original telemetry xi judges fuzzy interval ci, utilizes degree of membership algorithm to calculate the reliability coefficient di of original telemetry xi in evidence judgement fuzzy interval based on original telemetry xi;
Reliability coefficient di is multiplied with telemetry confidence level yi and obtains Certainty Factor ei;
Step 3, repeats step 2, completes the calculating of all Certainty Factor e1-en in regular fi;
Step 4, utilizes the calculating of confidence level pass-algorithm for the decision confidence of regular fi;
Step 5, the decision confidence computation rule fi utilizing assessment algorithm integrating step 4 to obtain whether output alarm information.
Step 6, repeats step 1 to 5, completes the reasoning process of strictly all rules.
Certainly; the present invention also can have other various embodiments; when not deviating from the present invention's spirit and essence thereof; those of ordinary skill in the art are when making various corresponding change and distortion according to the present invention, but these change accordingly and are out of shape the protection domain that all should belong to the claim appended by the present invention.
Claims (8)
1. spacecraft abnormal alarm and a fault diagnosis system in-orbit, is characterized in that, comprising: knowledge editor, data buffer, reasoning and decision device, data field, blackboard, formula area and result buffer;
Knowledge editor, for inputting compiled alarm diagnosis knowledge;
Data buffer, for cushioning the original telemetry of input, original telemetry comprises telemetry and telemetry command;
Data field, for extracting telemetry when reasoning and decision device carries out logic matching operation or telemetry command and storing it from data buffer;
Formula area, for loading compiled alarm diagnosis knowledge from knowledge editor, in formula area, each alarm diagnosis knowledge is referred to as rule;
Reasoning and decision device, carries out logic matching operation by the original telemetry in data field and the alarm diagnosis knowledge in formula area, obtains diagnostic result; And select to need the diagnostic result exported to export blackboard to;
Blackboard, for storing the diagnostic result that reasoning and decision device is obtained by logic matching operation;
Result buffer, selects the diagnostic result of output for cushioning reasoning and decision device and is sent to client, after user checks diagnostic result by this client, replying confirmation.
2. spacecraft abnormal alarm and fault reasoning system in-orbit as claimed in claim 1, it is characterized in that, reasoning and decision device comprises:
Reliability assessment module, the assessment of the parameter confidence level that takes remote measurement to the original telemetry of input, obtains the telemetry of band confidence level; Wherein, telecommand, inference machine safeguard initial value table information together with this original telemetry as the fact of spacecraft fault diagnosis reasoning;
Evidence derivation module, carries out logical operation according to the telemetry of the telecommand on ground, initial value table information that inference machine is safeguarded and described band confidence level and obtains evidence, and so-called evidence is exactly according to the true status information that draws with factual knowledge and warning message;
Fault diagnosis module, carries out fault diagnosis according to described evidence in conjunction with alarm diagnosis knowledge, releases diagnostic result;
Result output module, exports according to alarm diagnosis knowledge-chosen diagnostic result.
3. spacecraft abnormal alarm and fault diagnosis system in-orbit as claimed in claim 2, it is characterized in that, described reliability assessment module comprises:
Rule statistic unit, obtains remote measurement statistical law by carrying out statistics to the Changing Pattern of telemetry parameter;
Confidence level obtains unit, is mated by the remote measurement statistical law of new telemetry parameter with the remote measurement statistical law of history, and obtains the confidence level of remote measurement in conjunction with confidence factor.
4. spacecraft abnormal alarm and fault diagnosis system in-orbit as claimed in claim 2, it is characterized in that, described evidence derivation module comprises:
Based on the derivation judging and carry out based on confidence level pass-algorithm two kinds of modes of fuzzy mathematics of transfiniting of degree of membership, wherein, the confidence level pass-algorithm based on fuzzy mathematics comprises: the confidence level pass-algorithm of the single fact and combination true add right reliabiliL pass-algorithm.
5. spacecraft abnormal alarm and fault diagnosis system in-orbit as claimed in claim 2, it is characterized in that, described fault diagnosis module comprises: forward reasoning, backward reasoning, framework rule-based reasoning based on possibility.
6. spacecraft abnormal alarm and fault diagnosis system in-orbit as claimed in claim 2, it is characterized in that, the output principle in result output module is: the higher output speed of confidence level is faster; If the result of low confidence level maintains the long time also need to export; The time nearer impact of data on Output rusults is larger; When confidence level is 0.9, output time is 1 minute; When confidence level is 0.6, output time is 1 hour; Confidence level is greater than the output of 0.5 support result, confidence level is less than not exporting of 0.5 support result.
7. spacecraft abnormal alarm and fault diagnosis system in-orbit as claimed in claim 1, it is characterized in that, in formula area, each rule is provided with active control list, first judge when carrying out reasoning whether the active control list of the rule in this formula area all sets up, set up and then enable this rule, otherwise this rule can not be selected to carry out reasoning computing.
8. spacecraft abnormal alarm and fault diagnosis system in-orbit as claimed in claim 5, it is characterized in that, described fault diagnosis module comprises: real-time diagnosis unit, early warning diagnosis unit, playback diagnosis unit, checking diagnosis unit and spread function unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510608592.XA CN105159286B (en) | 2015-09-22 | 2015-09-22 | A kind of in-orbit abnormal alarm of spacecraft and fault diagnosis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510608592.XA CN105159286B (en) | 2015-09-22 | 2015-09-22 | A kind of in-orbit abnormal alarm of spacecraft and fault diagnosis system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105159286A true CN105159286A (en) | 2015-12-16 |
| CN105159286B CN105159286B (en) | 2017-12-08 |
Family
ID=54800171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510608592.XA Active CN105159286B (en) | 2015-09-22 | 2015-09-22 | A kind of in-orbit abnormal alarm of spacecraft and fault diagnosis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105159286B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106371030A (en) * | 2016-08-29 | 2017-02-01 | 丹阳亿豪电子科技有限公司 | New energy automobile battery fault diagnosis method based on uncertainty reasoning |
| CN106647695A (en) * | 2016-12-05 | 2017-05-10 | 航天恒星科技有限公司 | Method and system for monitoring running state of on-orbit spacecraft |
| CN110333710A (en) * | 2019-06-28 | 2019-10-15 | 中国空间技术研究院 | A kind of detection of spacecraft on-orbit fault and fault processing system and method |
| CN111193474A (en) * | 2020-01-14 | 2020-05-22 | 北京空间飞行器总体设计部 | High-precision autonomous diagnosis method for satellite solar wing output current |
| CN111240966A (en) * | 2020-01-03 | 2020-06-05 | 中国建设银行股份有限公司 | Alarm information processing method and system |
| CN111274543A (en) * | 2020-01-17 | 2020-06-12 | 北京空间飞行器总体设计部 | Spacecraft system anomaly detection method based on high-dimensional space mapping |
| CN112085869A (en) * | 2020-09-18 | 2020-12-15 | 陕西千山航空电子有限责任公司 | Civil aircraft flight safety analysis method based on flight parameter data |
| CN112965849A (en) * | 2021-03-05 | 2021-06-15 | 中国科学院微小卫星创新研究院 | Satellite fault diagnosis inference machine system and method |
| CN113570059A (en) * | 2021-07-21 | 2021-10-29 | 北京航天测控技术有限公司 | Spacecraft decision reasoning method, device and system |
| CN117742304A (en) * | 2024-02-09 | 2024-03-22 | 珠海市南特金属科技股份有限公司 | Fault diagnosis method and system for crankshaft double-top vehicle control system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101083019A (en) * | 2006-12-31 | 2007-12-05 | 中国人民解放军63791部队 | Rapid evaluating system based on roomage state sensing |
| CN101590918A (en) * | 2009-06-19 | 2009-12-02 | 上海微小卫星工程中心 | Method for automatic fault diagnosis of satellite and diagnostic system thereof |
| CN102495875A (en) * | 2011-12-02 | 2012-06-13 | 上海海洋大学 | Marine disaster early warning expert system based on data mining |
-
2015
- 2015-09-22 CN CN201510608592.XA patent/CN105159286B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101083019A (en) * | 2006-12-31 | 2007-12-05 | 中国人民解放军63791部队 | Rapid evaluating system based on roomage state sensing |
| CN101590918A (en) * | 2009-06-19 | 2009-12-02 | 上海微小卫星工程中心 | Method for automatic fault diagnosis of satellite and diagnostic system thereof |
| CN102495875A (en) * | 2011-12-02 | 2012-06-13 | 上海海洋大学 | Marine disaster early warning expert system based on data mining |
Non-Patent Citations (2)
| Title |
|---|
| 王家伍: "航天发射一体化建设与决策支持技术研究", 《装备指挥技术学院学报》 * |
| 王环等: "构建多航天器在轨管理支持平台", 《航天器工程》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106371030A (en) * | 2016-08-29 | 2017-02-01 | 丹阳亿豪电子科技有限公司 | New energy automobile battery fault diagnosis method based on uncertainty reasoning |
| CN106647695A (en) * | 2016-12-05 | 2017-05-10 | 航天恒星科技有限公司 | Method and system for monitoring running state of on-orbit spacecraft |
| CN110333710A (en) * | 2019-06-28 | 2019-10-15 | 中国空间技术研究院 | A kind of detection of spacecraft on-orbit fault and fault processing system and method |
| CN111240966A (en) * | 2020-01-03 | 2020-06-05 | 中国建设银行股份有限公司 | Alarm information processing method and system |
| CN111240966B (en) * | 2020-01-03 | 2023-10-24 | 中国建设银行股份有限公司 | Alarm information processing method and system |
| CN111193474A (en) * | 2020-01-14 | 2020-05-22 | 北京空间飞行器总体设计部 | High-precision autonomous diagnosis method for satellite solar wing output current |
| CN111274543A (en) * | 2020-01-17 | 2020-06-12 | 北京空间飞行器总体设计部 | Spacecraft system anomaly detection method based on high-dimensional space mapping |
| CN112085869A (en) * | 2020-09-18 | 2020-12-15 | 陕西千山航空电子有限责任公司 | Civil aircraft flight safety analysis method based on flight parameter data |
| CN112965849A (en) * | 2021-03-05 | 2021-06-15 | 中国科学院微小卫星创新研究院 | Satellite fault diagnosis inference machine system and method |
| CN113570059A (en) * | 2021-07-21 | 2021-10-29 | 北京航天测控技术有限公司 | Spacecraft decision reasoning method, device and system |
| CN117742304A (en) * | 2024-02-09 | 2024-03-22 | 珠海市南特金属科技股份有限公司 | Fault diagnosis method and system for crankshaft double-top vehicle control system |
| CN117742304B (en) * | 2024-02-09 | 2024-05-07 | 珠海市南特金属科技股份有限公司 | Fault diagnosis method and system for crankshaft double-top vehicle control system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105159286B (en) | 2017-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105159286A (en) | Spacecraft on-orbit anomaly alarming and fault diagnosing system | |
| Marseguerra et al. | Optimal reliability/availability of uncertain systems via multi-objective genetic algorithms | |
| CN112104005B (en) | Power grid dispatching method and system considering new energy prediction uncertainty | |
| Yang et al. | A Petri net approach to early failure detection and isolation for preventive maintenance | |
| Pan et al. | Real-time digital twin machine learning-based cost minimization model for renewable-based microgrids considering uncertainty | |
| Wang et al. | Comprehensive reliability evaluation of multistate complex electromechanical systems based on similarity of cloud models | |
| Liu et al. | Resilience assessment and importance measure for interdependent critical infrastructures | |
| Jin et al. | A methodology for equipment condition simulation and maintenance threshold optimization oriented to the influence of multiple events | |
| JPH0877211A (en) | Maintenance support device for plant | |
| Khalil Ur et al. | Sensitivity study on availability of I&C components using bayesian network | |
| Xu et al. | Research on time-dependent failure modeling method of integrating discrete dynamic event tree with fault tree | |
| CN111046633A (en) | LSTM-based power grid primary frequency modulation data prediction method and device | |
| CN106371030A (en) | New energy automobile battery fault diagnosis method based on uncertainty reasoning | |
| CN114186872A (en) | Emergency state assessment method and device for nuclear power plant and computer equipment | |
| CN114743703A (en) | Reliability analysis method, device, equipment and storage medium for nuclear power station unit | |
| Lin et al. | Enhancing the operational resilience of advanced reactors with digital twins by recurrent neural networks | |
| Xiang et al. | A preliminary study of power system reliability considering cloud service reliability | |
| Purba et al. | The implementation of fault tree analysis approaches in nuclear power plant probabilistic safety assessment | |
| CN103854133A (en) | Nuclear power plant mitigation system performance index evaluation method and system | |
| Chen et al. | Prediction of Automatic Scram during Abnormal Conditions of Nuclear Power Plants Based on Long Short-Term Memory (LSTM) and Dropout | |
| Xiong et al. | Research on Health Condition Assessment Method for Spacecraft Power Control System Based on SVM and Cloud Model | |
| Levenets et al. | Studies of the features of the sorption of an europium by natural and synthetic zeolites for using it in the nuclear energy | |
| CN110427689A (en) | Combustion engine unit group of planes monitoring, diagnosing method based on new information technology | |
| CN110889541A (en) | Power system risk scheduling decision method and device | |
| Yu et al. | An online fault diagnosis method for nuclear power plant based on combined artificial neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |