CN113570059A - Spacecraft decision reasoning method, device and system - Google Patents
Spacecraft decision reasoning method, device and system Download PDFInfo
- Publication number
- CN113570059A CN113570059A CN202110828361.5A CN202110828361A CN113570059A CN 113570059 A CN113570059 A CN 113570059A CN 202110828361 A CN202110828361 A CN 202110828361A CN 113570059 A CN113570059 A CN 113570059A
- Authority
- CN
- China
- Prior art keywords
- conclusion
- current
- spacecraft
- rule
- interpretation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000012545 processing Methods 0.000 claims description 14
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 5
- 206010063385 Intellectualisation Diseases 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 17
- 238000004590 computer program Methods 0.000 description 9
- 230000004044 response Effects 0.000 description 8
- 238000012423 maintenance Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/045—Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to a spacecraft decision reasoning method, a spacecraft decision reasoning device and a spacecraft decision reasoning system, wherein the method comprises the following steps: acquiring current telemetering data; extracting parameters and instructions from the current telemetry data; updating the corresponding target facts in the fact base according to the parameters and the instructions to obtain known facts; searching a rule matched with the known fact in a rule base to obtain a rule set; and interpreting the rules in the rule set according to the known facts to obtain a current interpretation conclusion. By the aid of the spacecraft decision support system based on the expert inference engine, knowledge of experts can be simulated through the inference engine layer according to the fact base, the rule base and the like of the knowledge base, auxiliary decisions are provided for users, and automation and intellectualization of spacecraft fault handling decision support are achieved.
Description
Technical Field
The application relates to the technical field of knowledge bases, in particular to a spacecraft decision reasoning method, device and system.
Background
Due to the complexity of a spacecraft system, the working environment and the task variability, system faults have randomness, and therefore, the corresponding measurement and control decision and treatment activities have obvious uncertainty. Therefore, in the face of the problems existing in the practical use of the spacecraft system, the reasonable and dynamic determination of the measurement and control and treatment activities is the key for improving the management efficiency and the benefit of the spacecraft.
In the prior art, judgment and treatment decisions of spacecraft faults mostly depend on the experience of engineering personnel, and are not automatic and intelligent.
Disclosure of Invention
In order to solve the technical problem that the spacecraft fault judgment and handling decision is not automated and intelligent enough, the embodiment of the application provides a spacecraft decision reasoning method, device and system.
In a first aspect, an embodiment of the present application provides a spacecraft decision inference method, where the method includes:
acquiring current telemetering data;
extracting parameters and instructions from the current telemetry data;
updating the corresponding target facts in the fact base according to the parameters and the instructions to obtain known facts;
searching rules matched with known facts in a rule base to obtain a rule set;
and interpreting the rules in the rule set according to the known facts to obtain a current interpretation conclusion.
Optionally, prior to acquiring the telemetry data, the method further comprises:
and constructing a fact base and a rule base based on empirical knowledge of an expert of the spacecraft, factual knowledge of the spacecraft and a logical relation between the running state of the spacecraft and the telemetering data.
Optionally, interpreting the rules in the rule set according to the known facts to obtain a current interpretation conclusion, including:
reading and analyzing rules in the rule set;
associating variables in the rules with corresponding known facts in a fact base;
creating a data interpretation queue;
acquiring a pointer list corresponding to the data interpretation queue;
sequentially acquiring current parameter pointers from the pointer list;
matching and executing a corresponding rule based on a corresponding known fact according to the current parameter pointer to obtain a current interpretation conclusion;
wherein the data interpretation queue characterizes an order of the interpretation rules.
Optionally, interpreting the rules in the rule set according to the known facts to obtain a current interpretation conclusion, including:
determining a first rule to be interpreted as a current rule to be interpreted according to known facts;
judging the current rule to be judged according to the intermediate judgment conclusion in the intermediate conclusion area and the known fact to obtain a corresponding intermediate judgment conclusion;
storing the intermediate interpretation conclusion to an intermediate conclusion area, and updating the known fact according to the intermediate interpretation conclusion;
monitoring the intermediate conclusion area, and determining a next rule to be interpreted by combining the intermediate conclusion area and the updated known facts;
taking the next rule to be interpreted as the current rule to be interpreted, executing the interpretation of the current rule to be interpreted according to the intermediate interpretation conclusion in the intermediate conclusion area and the known fact to obtain the corresponding intermediate interpretation conclusion until the interpretation of all the rules in the rule set is completed to obtain the current interpretation conclusion.
Optionally, the method further comprises:
if the current interpretation conclusion is an unexpected conclusion, searching a remote control instruction for controlling the spacecraft according to the current interpretation conclusion;
acquiring updated telemetering data after the spacecraft responds to the remote control instruction;
and taking the updated telemetering data as the current telemetering data, and executing the extraction of parameters and instructions from the current telemetering data until the current interpretation conclusion is the expected conclusion.
Optionally, prior to acquiring the current telemetry data, the method further comprises:
configuring an inference environment;
initializing inference engine parameters and states;
and creating a memory.
Optionally, the method further comprises:
storing the current interpretation conclusion in a database;
and issuing the current interpretation conclusion to a network where the spacecraft is located in a broadcasting mode.
Optionally, the parameters or the instructions corresponding to the known facts whose interpretation conclusion is abnormal are reported repeatedly within the preset time length.
In a second aspect, an embodiment of the present application provides a spacecraft decision reasoning apparatus, where the apparatus includes:
the data acquisition module is used for acquiring current telemetering data;
the data processing module is used for extracting parameters and instructions from the current telemetering data;
the first matching module is used for updating the corresponding target facts in the fact base according to the parameters and the instructions to obtain known facts;
the second matching module is used for searching the rules matched with the known facts in the rule base to obtain a rule set;
and the interpretation module is used for interpreting the rules in the rule set according to the known facts to obtain the current interpretation conclusion.
In a third aspect, embodiments of the present application provide a computer-readable storage medium having stored thereon a computer program, which, when executed by an inference engine, causes the inference engine to perform the steps of a method according to any one of the preceding claims.
In a fourth aspect, embodiments of the present application provide a server comprising a memory, an inference engine, and a computer program stored on the memory and operable on a processor, the inference engine executing the program to perform the steps of the method according to any preceding method.
In a fifth aspect, an embodiment of the present application provides a spacecraft decision reasoning system, where the system includes: a knowledge base, a database and an inference engine; the knowledge base comprises a rule base and a fact base; the inference engine realizes spacecraft decision reasoning by executing the steps of the spacecraft decision reasoning method of any one of the preceding claims.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:
the embodiment of the application acquires current telemetering data; extracting parameters and instructions from the current telemetry data; updating the corresponding target facts in the fact base according to the parameters and the instructions to obtain known facts; searching rules matched with known facts in a rule base to obtain a rule set; and interpreting the rules in the rule set according to the known facts to obtain a current interpretation conclusion. The spacecraft decision support system based on the expert inference engine can simulate the knowledge of experts through an inference engine layer according to a fact base, a rule base and the like of a knowledge base, provides an auxiliary decision for a user, and realizes the automation and the intellectualization of spacecraft fault handling decision support. The mutual independence of reasoning and rules is realized, and the knowledge updating and self-enrichment are facilitated. According to the method and the system, the intelligent fault diagnosis and decision technology is applied to fault diagnosis of the spacecraft system, so that engineering personnel are assisted to timely eliminate faults of the spacecraft system, the maintenance efficiency of the spacecraft is improved, and the working safety of the spacecraft is guaranteed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flow chart of a spacecraft decision inference method according to an embodiment;
fig. 2 is a block diagram of a spacecraft decision inference apparatus according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The application provides a spacecraft decision reasoning system, which comprises: the system comprises a knowledge base, an inference engine and a database, wherein the knowledge base comprises a fact base and a rule base of problems to be solved in the field of spacecraft.
The rule base comprises a plurality of rules, and each rule is provided with a rule condition and a corresponding rule conclusion. The rule is spacecraft system fault knowledge which is made by a spacecraft field expert according to experience and general knowledge in the spacecraft field, is a judgment rule for judging whether the spacecraft has faults or not, is expressed into a series of production rules through a rule description language, and is generally designed into manual rules containing vocabulary, syntax and semantic features. A rule is typically the structure of If (condition) Then (action). IF P THEN Q, P is a condition and Q is a conclusion, meaning: if a condition occurs, then a conclusion occurs. Rules can be added, changed, and deleted.
The fact library comprises a fact set used for storing all facts in the current system, and the facts comprise description objects and description relations. The fact base is used for storing facts and is the basis for the operation of the reasoning method.
The inference engine is connected with the knowledge base, invokes facts and rules in the knowledge base according to the acquired telemetering data through the inference engine, partially matches the facts in the fact base with conditions of the rules, judges the operation state of the spacecraft by adopting an inference algorithm, judges whether the spacecraft is in fault, and judges the decision to be taken after the fault occurs. The inference algorithm employs inference and conflict resolution strategies, and may employ a forward inference algorithm and/or a reverse inference algorithm. The inference engine may control the execution of the system. The inference engine is a set of programs used for controlling and coordinating the whole system.
Forward reasoning, also known as fact-driven reasoning, is a method of inferring conclusions from raw data by applying knowledge in a knowledge base according to a certain strategy. This approach goes from data to conclusion and is also called data-driven or bottom-up strategy. The inference engine based on forward reasoning can at least realize that: according to the data in the database, the knowledge in the selected knowledge base is known; storing the conclusion obtained by using the knowledge into a database, and recording the used knowledge (for explanation); and judging when the reasoning should be finished, and asking questions to the user if necessary.
The database is connected with the knowledge base and the inference engine and is used for storing expression information in the process of reasoning decision or fault diagnosis, wherein the expression information comprises an initial state, an intermediate conclusion and a final conclusion.
The spacecraft decision reasoning system may further comprise an interpreter coupled to the reasoning engine and the database, the interpreter being configured to interpret the reasoning process and the inferences using a pre-fabricated textual approach. The user can understand the method conveniently; the interpretation information base is stored in the database. The interpreter tracks and records the inference steps and rules adopted in the inference process, uses the factual knowledge in the knowledge base through a text interpretation method to explain definition and description of facts used in the inference process to a user, tracks the inference process of the inference machine through the tracking interpretation method to explain the inference process of a current conclusion to the user, makes detailed explanation on the inference decision process of the spacecraft, and improves the traceability of the decision and the user interaction friendliness.
Fig. 1 is a schematic flow chart of a spacecraft decision inference method according to an embodiment. Referring to fig. 1, the method includes the steps of:
s1000: current telemetry data is acquired.
S2000: parameters and instructions are extracted from the current telemetry data.
S3000: and updating the corresponding target facts in the fact base according to the parameters and the instructions to obtain the known facts.
S4000: searching the rule base for rules matching the known facts to obtain a rule set.
S5000: and interpreting the rules in the rule set according to the known facts to obtain a current interpretation conclusion.
The current telemetry data includes equipment data characterizing the current operating state of the spacecraft, instructions to control the spacecraft (remote control instructions). The device data includes operating parameters of various components in the spacecraft.
The inference engine acquires current telemetering data from the database through the communication interface, and the current telemetering data represents the current spacecraft state.
The inference mechanism is an important link in a spacecraft decision inference system, and determines the value and the efficiency of the spacecraft decision inference system. As far as reasoning is concerned, it contains two basic aspects: knowledge and logic. The present application is knowledge and rule based deductive reasoning.
The inference engine acquires current telemetry data in real time, the telemetry data being received in the form of data packets. The data packet comprises an engineering value and an original code, the engineering value is used for rule judgment, and the original code is used for client display.
Step S2000 specifically includes: unpacking and preprocessing the current telemetering data according to the data configuration information so as to extract parameters and instructions. Because the spacecraft is a very large device, various parts are arranged inside the spacecraft, and each part may have problems when the spacecraft runs, the configuration information is provided by engineering personnel, the configuration information includes events which need to be monitored currently by the engineering personnel (for example, which part or parts need to be monitored whether to have a fault or not), the parts monitored corresponding to each event to be monitored may be different, and therefore, according to the data configuration information, corresponding parameters and instructions need to be extracted from current telemetering data, and irrelevant parameters and instructions which cannot be used temporarily can be filtered. The parameters and the instructions are operation state parameters of certain parts of the spacecraft corresponding to the current event to be monitored and instructions for causing the state parameters to change the spacecraft to execute.
Step S3000 specifically includes: the fact base comprises a large number of facts, the facts in the fact base are in an initialized state before inference and interpretation, the extracted parameters and the extracted instructions have corresponding target facts in the fact base, and the target facts are assigned or the values corresponding to the target facts are refreshed according to the parameters and the instructions, so that the target facts become known facts. The number of known facts is at least one.
Step S4000 specifically includes: the facts in the fact base include variables and their values, and may also include relationships between variables, one variable representing a parameter or instruction, and the values of the variables or the relationships between the variables may vary depending on the current operating state of the spacecraft or the current telemetry data received.
And the rules in the rule base are used for interpreting the known facts according to rule conditions to obtain rule conclusions. Therefore, the rules also include variables, and the same variable can obtain different rule conclusions under the known fact conditions of different values or different variable relationships. By associating the variables of the known facts with the variables in the rules, the rules corresponding to the known facts can be found and matched. That is, matching the fact with the corresponding rule is performed, and the rule corresponding to the fact is screened out.
Step S5000 specifically includes: and interpreting the corresponding rule according to the known fact to obtain a corresponding current interpretation conclusion.
The method is a spacecraft decision support method based on an expert inference engine, receives telemetering data, and completes decision support of spacecraft faults step by step through an inference engine by utilizing a rule base and a fact base in a created knowledge base. Receiving telemetering data, analyzing, monitoring and judging parameters and instructions of the data, and giving decision information by combining knowledge and rules in a knowledge base to provide decision support for fault handling of the spacecraft.
The current interpretation conclusion may be a final decision conclusion or may only be an intermediate or temporary conclusion based on current known facts. The current interpretation conclusions include at least one.
In a specific embodiment, before step S1000, the spacecraft decision reasoning method further includes the following steps:
and constructing a fact base and a rule base based on empirical knowledge of the spacecraft, factual knowledge of the spacecraft and logical relations between the operation state of the spacecraft and the telemetering data.
Specifically, the empirical knowledge of the spacecraft is empirical knowledge (expert theoretical data) provided by a spacecraft expert according to industry experience, the factual knowledge of the spacecraft is conventional industry knowledge in the field of the spacecraft, and the logical relationship between the spacecraft operation state and the telemetering data is knowledge extraction and knowledge representation after knowledge acquisition, knowledge review and knowledge consistency check according to historical empirical data of the spacecraft and real-time monitoring data of the spacecraft operation. And storing the historical telemetering data and the domain knowledge of the fault information in the form of facts and rules so as to construct a spacecraft fault information knowledge base. So as to store the knowledge, and the content of the knowledge and the relation between the knowledge can be clearly and completely embodied in the library.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 1 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In a specific embodiment, step S5000 specifically includes: reading and analyzing rules in the rule set; associating variables in the rules with corresponding known facts in a fact base; creating a data interpretation queue; acquiring a pointer list corresponding to the data interpretation queue; sequentially acquiring current parameter pointers from the pointer list; matching and executing a corresponding rule based on a corresponding known fact according to the current parameter pointer to obtain a current interpretation conclusion; wherein the data interpretation queue characterizes an order of the interpretation rules.
Specifically, the inference engine reads and analyzes the rules in the rule set, and analyzes the preconditions and conclusions of the rules into different expression structures, and all rules of the same parameter or instruction are associated with the parameter or instruction in a linked list form, so as to obtain a rule linked list corresponding to each parameter or instruction.
The inference engine is an operation module of the inference method. The inference engine of the application creates a blackboard area and puts the obtained known facts into the blackboard area. The inference machine completes the creation of the memory related to the parameters or the instructions and the dynamic creation of the data interpretation queue through creating and managing the blackboard area. The data interpretation queue comprises a parameter interpretation queue and an instruction interpretation queue. The parameter interpretation queue is provided with a corresponding parameter pointer list, and the instruction interpretation queue is provided with a corresponding instruction pointer list.
Matching and executing a corresponding rule according to the current parameter pointer to obtain a current interpretation conclusion, which specifically comprises the following steps:
and the inference machine selects a current parameter pointer from the parameter pointer list, executes the rule corresponding to the current parameter pointer to obtain a corresponding intermediate interpretation conclusion, selects the next parameter pointer as the current parameter pointer, executes the rule corresponding to the current parameter pointer, and completes the interpretation of the rules corresponding to all the parameters in a circulating manner.
The inference machine is further used for selecting a current instruction pointer from the instruction pointer list, executing the rule corresponding to the current instruction pointer to obtain a corresponding intermediate interpretation conclusion, selecting a next instruction pointer as the current instruction pointer, executing the rule corresponding to the current instruction pointer, and thus circularly completing interpretation of the rules corresponding to all instructions.
In the embodiment, the inference engine extracts known facts from the fact base according to the pointer list, and then performs preliminary inference according to corresponding rules to obtain some intermediate interpretation conclusions, which are put into the intermediate conclusion area. When all the preliminary reasoning processes of the inference engine are finished, the inference engine creates a data interpretation queue again according to all the intermediate interpretation conclusions so as to achieve the purpose of taking out the intermediate interpretation conclusions from the intermediate conclusion region, deep reasoning is carried out by combining with known facts, some new intermediate interpretation conclusions can be generated in the deep reasoning process, and the inference engine puts the obtained new intermediate interpretation conclusions into the intermediate conclusion region until one round of deep reasoning is finished (namely, the rules meeting the conditions are matched completely). And then, establishing a data interpretation queue, taking out the obtained new intermediate interpretation conclusion from the intermediate conclusion area, putting the intermediate interpretation conclusion into an inference machine for reasoning, and performing the next round of deep reasoning. According to the flow, circulation is carried out successively until a new intermediate interpretation conclusion cannot be obtained by carrying out deep reasoning in the reasoning machine, and then the current interpretation conclusion is obtained.
In a specific embodiment, step S5000 specifically includes: determining a first rule to be interpreted as a current rule to be interpreted according to known facts; judging the current rule to be judged according to the intermediate judgment conclusion in the intermediate conclusion area and the known fact to obtain a corresponding intermediate judgment conclusion; storing the intermediate interpretation conclusion to an intermediate conclusion area, and updating the known fact according to the intermediate interpretation conclusion; monitoring the intermediate conclusion area, and determining a next rule to be interpreted by combining the intermediate conclusion area and the updated known facts; taking the next rule to be interpreted as the current rule to be interpreted, executing the interpretation of the current rule to be interpreted according to the intermediate interpretation conclusion in the intermediate conclusion area and the known fact to obtain the corresponding intermediate interpretation conclusion until the interpretation of all the rules in the rule set is completed to obtain the current interpretation conclusion.
The rule engine of the rule base is used for determining rules applicable to known facts, matching the rules with the facts and matching out the condition parts of the facts meeting the rules.
In this particular embodiment, the inference engine loads the known facts into the blackboard area. According to the current known fact of the fact area, a rule which can be matched is selected and executed from the rule area to obtain an intermediate interpretation conclusion, the intermediate conclusion is stored in the blackboard area, and the known fact of the blackboard area is updated according to the intermediate interpretation conclusion; determining the next rule to be interpreted by monitoring the intermediate conclusion of the blackboard area and the updated known fact, taking the next rule to be interpreted as the current rule to be interpreted, circularly performing the interpretation of the current rule to be interpreted according to the intermediate interpretation conclusion in the intermediate conclusion area and the known fact to obtain the corresponding intermediate interpretation conclusion until the interpretation of all the rules in the rule set is completed to obtain the current interpretation conclusion.
There may be more than one current interpretation conclusion, which is a temporary conclusion or a final conclusion that can be obtained at present and from which no new conclusion can be generated.
The blackboard area is used for storing all facts required by interpretation and interpretation conclusions. As well as the area where intermediate or provisional conclusions are stored.
In one embodiment, the spacecraft decision reasoning method further comprises the steps of: if the current interpretation conclusion is an unexpected conclusion, searching a remote control instruction for controlling the spacecraft according to the current interpretation conclusion; acquiring updated telemetering data after the spacecraft responds to the remote control instruction; and taking the updated telemetering data as the current telemetering data, and executing the extraction of parameters and instructions from the current telemetering data until the current interpretation conclusion is the expected conclusion.
In particular, if the current interpretation conclusion is not the desired conclusion, or is not the final conclusion, but is an intermediate result, it may be because the desired conclusion or the final conclusion cannot be reached yet according to the existing facts, and therefore, more known facts need to be obtained to further infer until the desired conclusion or the final conclusion is reached.
Acquiring more of the known facts requires controlling the spacecraft to change certain operating states of the spacecraft in order to obtain updated telemetry data that characterizes the spacecraft in the new operating state. And the sent remote control instruction is searched based on the current interpretation conclusion and is used for changing the state of a certain part or parts of the spacecraft so as to cooperatively acquire updated telemetric data, and the updated telemetric data is used for carrying out the next interpretation and promoting the reasoning of a final conclusion or an expected conclusion.
The remote control command is a rule conclusion of a rule condition in the rule base. That is, the rule conclusion may be a specific fault conclusion, may be a conclusion that the spacecraft is working normally, or may be a further remote control command when no conclusion is temporarily presumed. Certainly, the inference engine may also be a further control scheme when the inference result is not concluded temporarily, and the inference engine matches the corresponding remote control instruction according to the control scheme.
The embodiment is a cyclic process, if the current interpretation conclusion is not the expected conclusion or not the final conclusion, the spacecraft is controlled by the remote control instruction obtained according to the current interpretation conclusion, the updated telemetering data is obtained according to the remote control instruction, and data interpretation is carried out again according to the updated telemetering data until the current interpretation conclusion is the expected result.
In one embodiment, the spacecraft decision reasoning method further comprises: and if the current interpretation conclusion of the expected result is a fault conclusion, searching a fault solution strategy corresponding to the fault conclusion, processing the fault according to the solution strategy, or providing the fault solution strategy for the engineering personnel of the terminal, and overhauling the spacecraft by the engineering personnel according to the fault solution strategy.
The knowledge base of the present application also includes a decision base coupled to the inference engine for storing faults and corresponding fault solutions.
Whether the spacecraft breaks down or not is analyzed in an inference mode through the established knowledge base according to the telemetering data, the spacecraft is rapidly searched and positioned to the final fault or the most possible fault, the dynamically established knowledge base system is inquired, the maintenance decision is automatically analyzed and given, and the maintenance decision is provided for maintenance personnel, so that the maintenance personnel can shorten the fault inquiry time, and the spacecraft can be rapidly repaired.
The inference mode of the inference engine can also adopt a mixed inference mode combining forward inference and reverse inference, firstly, forward inference searches out a production formula rule needing further inference confirmation, and then, the whole inference process is completed by combining a known interpretation conclusion according to a conflict resolution strategy in a reverse inference mode.
And reasoning the telemetry data according to the created knowledge base to obtain a processing decision of the spacecraft fault. And determining a rule corresponding to the telemetering data, reasoning the telemetering data by adopting a reasoning machine according to the rule, and determining a fault reason and a decision scheme, wherein the telemetering data comprises parameters and instructions. Parameters and instructions in the telemetered data are analyzed, monitored and judged according to facts and rules in a knowledge base to obtain processing decisions.
The spacecraft is a complex device, and any fault can cause the whole device to stop running, so that economic loss and potential safety hazard are caused to enterprises. If the faults can not be timely, effectively and properly treated after the faults occur, the service life of the press machine can be seriously shortened, and the production efficiency is influenced. Therefore, the spacecraft decision reasoning method, the spacecraft decision reasoning device and the spacecraft decision reasoning system have very important significance for researching spacecraft fault diagnosis.
In one embodiment, before step S1000, the method further comprises: configuring an inference environment; initializing inference engine parameters and states; and creating a memory.
Specifically, the inference engine is started, namely, the setting of various parameters and states of the inference engine is completed before the inference starts to be interpreted. The inference engine obtains configuration information, including: interpretation content, instruction delay time, result retention information, etc. The inference engine acquires the current on-board state from the database and initializes the on-board state. Initializing the attribute parameters of the inference engine. And initializing interpretation contents. And initializing an interpretation condition. A blackplate region is created. And resolving the telemetry data.
The data sent by the data processing system is in the form of data packets, and the data contains original codes and engineering values, wherein the engineering values are used for judging the data, and the original codes are used for displaying by a client, so that the data needs to be processed by a data analysis module, and the data becomes a fact for an inference engine to use. Unpacking the telemetry data into facts is placed into the blackboard area created by the inference engine. Updating the target facts in the fact repository with the obtained facts results in known facts. An inference engine is run. The reasoning engine provides a service of telemetering parameter interpretation, and monitors and records the state of the spacecraft in real time in the reasoning process, so that a user can accurately master the state of the spacecraft. Acquiring interpretation data, and scheduling a knowledge base according to interpretation conditions to perform data interpretation. When the state of the spacecraft is changed, the system must record and store in real time so as to ensure that the system can accurately master the state of the spacecraft at the time after being restarted. And the operation interpreter provides an interpretation for the interpretation conclusion and explains the reason for the conclusion. The interpretation includes at least which rules are executed, the status of the relevant parameters and instructions at the time, the expected values of the parameters at the time, and the engineering values at the time. The interpretation cannot be repeated for the same interpretation conclusion. When the state of the spacecraft mastered by the system comes in and goes out with the actual situation, the system needs to receive manual intervention to correct certain facts so as to help the system to accurately master the situation. The communication interface is a window for the server to make an interaction with the outside, where the reception and transmission of information are performed. And sending the interpretation result to the master control server software. And reading the data interpretation server configuration information and writing the configuration information.
The method takes the fault of radiator leakage of an outer loop of a certain spacecraft as an implementation case, and relates to parameters such as pf pressure, pg pressure, a pump a memory state, a pump a rotating speed and radiator leakage wet surface processing identification, and the whole reasoning process and decision conclusion of a reasoning machine are as follows.
Step 1) monitoring the on-off states of self-locking valves g and h or i and j and a temperature control valve on duty, and judging whether a thermal control unit automatically isolates a leakage loop;
step 2) if the software is not automatically isolated, the ground sends B634 instruction to close the self-locking valves g and h, and sends B644 instruction to close the self-locking valves i and j, and after about 20 s: judging whether Pf is larger than 400 kPa;
step 3) if Pf is larger than 400kPa, and the latching valves i and j are closed, sending an instruction B643 to open the latching valves i and j;
step 4) if the Pg is larger than 400kPa and the self-locking valves g and h are closed, sending an instruction B633 to open the self-locking valves g and h;
step 5) if Pf and Pg are not more than 400kPa, if Pf is more than or equal to 30kPa, judging that the circuit where Pf is located is normal and the circuit where Pg is located is leaked, sending B643 to open latching valves i and j, and keeping the latching valves g and h in a closed state;
step 6) if the Pg is larger than or equal to 30kPa, judging that the circuit where the Pg is located is normal, and if the circuit where the Pf is located is leaked, sending B633 to open self-locking valves g and h, and keeping the self-locking valves i and j in a closed state;
step 7) if Pf and Pg both continuously decrease and the difference is less than 30kPa, judging that the loops where Pf and Pg both leak, and sending B634 to close latching valves g and h and sending B644 to close latching valves i and j;
step 8) after the above treatment, if the Pf loop is normal and the Pg loop is leaked, injecting the radiator leakage treatment identifier 5A, sending B629 to open the self-locking valves B and c, closing the self-locking valves d and e, and enabling the temperature control valve a to work;
step 9) or sending B630 to open the self-locking valves d and e, closing the self-locking valves B and c, enabling the temperature control valve B to work, observing whether the self-locking valves i and j are closed or not if Pf is lower than the alarm pressure when the radiator leakage processing identifier is 5A, and sending B644 to close the self-locking valves i and j if the radiator leakage processing identifier is in an open state;
step 10) if the Pg loop is normal and the Pf loop is leaked, injecting a radiator leakage processing identifier A5, sending B629 to open the self-locking valves B and c, closing the self-locking valves d and e, and enabling the temperature control valve a to work;
step 11) or sending B630 to open the self-locking valves d and e, closing the self-locking valves B and c, enabling the temperature control valve B to work, observing whether the self-locking valves g and h are closed or not if Pg is lower than the alarm pressure when the radiator leakage processing identifier is A5, and sending B634 to close the self-locking valves g and h if the radiator leakage processing identifier is in an open state.
In one embodiment, the method further comprises:
storing the current interpretation conclusion in a database;
and issuing the current interpretation conclusion to a network where the spacecraft is located in a broadcasting mode.
Specifically, the method further comprises: and interpreting the reasoning process and the obtained current interpretation conclusion.
In one embodiment, the method further comprises:
and carrying out non-repeated error reporting on the parameters or instructions corresponding to the known facts of which the current interpretation conclusion is abnormal within the preset time length.
Specifically, the report cannot be repeated for the same problem. When a certain parameter or instruction is abnormal, the abnormal state may be in a certain period of time, the abnormality cannot be reported every time, the user is prompted once, the abnormal time period and other related information are recorded, and the user continues to interpret the abnormal time period and other related information.
In one embodiment, the method further comprises:
and if the current interpretation conclusion is abnormal and is an unexpected conclusion, not reporting errors to the parameters or the instructions corresponding to the known fact that the current interpretation conclusion is abnormal within the preset instruction response time after the corresponding remote control instruction is sent to the spacecraft.
Specifically, the remote control command response time is set, and a certain time is required for parameter change from the sending of the remote control command to the acquisition of the acquired telemetering data from the water chemistry system response to the ground, and the time is called the command response time. The response time lengths of different remote control instructions are different, usually within several seconds, and meanwhile, the response time lengths of related parameters influenced by the same remote control instruction are different, so that the related parameters are in an unstable state in the response time length of the remote control instruction, and at the moment, if the related parameters are interpreted abnormally, the phenomenon is normal, and no error is reported. The response time of the remote control command can be set uniformly, and each remote control command can be set independently.
Fig. 2 is a block diagram of a spacecraft decision inference apparatus according to an embodiment.
Referring to fig. 2, the apparatus includes:
a data acquisition module 1000 for acquiring current telemetry data;
a data processing module 2000 for extracting parameters and instructions from the current telemetry data;
the first matching module 3000 is configured to update a corresponding target fact in the fact base according to the parameter and the instruction to obtain a known fact;
the second matching module 4000 is used for searching the rules matched with the known facts in the rule base to obtain a rule set;
and the interpretation module 5000 is used for interpreting the rules in the rule set according to the known facts to obtain a current interpretation conclusion.
In one embodiment, the apparatus further comprises:
and the construction module is used for constructing the fact base and the rule base based on empirical knowledge of the spacecraft, factual knowledge of the spacecraft and the logical relationship between the spacecraft running state and the telemetering data.
In one particular embodiment, the interpretation module 5000 includes:
the analysis module is used for reading and analyzing the rules in the rule set;
the association module is used for associating the variables in the rules with the corresponding known facts in the fact base;
the queue creating module is used for creating a data interpretation queue;
the pointer list acquisition module is used for acquiring a pointer list corresponding to the data interpretation queue;
the pointer acquisition module is used for sequentially acquiring the current parameter pointers from the pointer list;
and the execution module is used for matching and executing the corresponding rule according to the current parameter pointer based on the corresponding known fact to obtain the current interpretation conclusion.
In one particular embodiment, the interpretation module 5000 includes:
the selection module is used for determining a first rule to be interpreted as a current rule to be interpreted according to known facts;
the sub-interpretation module is used for interpreting the current rule to be interpreted according to the intermediate interpretation conclusion in the intermediate conclusion area and the known fact to obtain a corresponding intermediate interpretation conclusion;
the storage and update module is used for storing the intermediate interpretation conclusion to the intermediate conclusion area and updating the known fact according to the intermediate interpretation conclusion;
the selection module is also used for monitoring the intermediate junction talking area and determining the next rule to be interpreted by combining the intermediate junction talking area and the updated known facts;
and the sub-cycle module is used for taking the next rule to be interpreted as the current rule to be interpreted, interpreting the current rule to be interpreted according to the intermediate interpretation conclusion in the intermediate conclusion area and the known fact to obtain a corresponding intermediate interpretation conclusion until the interpretation of all the rules in the rule set is completed to obtain the current interpretation conclusion.
In one embodiment, the apparatus further comprises:
the instruction searching module is used for searching a remote control instruction for controlling the spacecraft according to the current interpretation conclusion if the current interpretation conclusion is an unexpected conclusion;
the data acquisition module 1000 is further configured to acquire updated telemetry data after the spacecraft responds to the remote control instruction;
and the circulating module is used for taking the updated telemetering data as the current telemetering data, and executing the extraction of parameters and instructions from the current telemetering data until the current interpretation conclusion is the expected conclusion.
In one embodiment, the apparatus further comprises:
a configuration module for configuring an inference environment;
the initialization module is used for initializing parameters and states of the inference engine;
and the memory creating module is used for creating the memory.
In one embodiment, the apparatus further comprises:
the storage module is used for storing the current interpretation conclusion to the database;
and the issuing module is used for issuing the current interpretation conclusion to a network where the spacecraft is located in a broadcast mode.
In one embodiment, the apparatus further comprises:
and the error reporting module is used for carrying out non-repeated error reporting on the parameters or the instructions corresponding to the known facts of which the current interpretation conclusion is abnormal within the preset time length.
In one embodiment, the spacecraft decision reasoning apparatus provided herein may be implemented in the form of a computer program that is executable on a computer device. The memory of the computer device may store various program modules constituting the spacecraft decision reasoning apparatus, such as a data acquisition module 1000, a data processing module 2000, a first matching module 3000, a second matching module 4000 and an interpretation module 5000 shown in fig. 2. The computer program constituted by the respective program modules causes the processor to execute the steps of the spacecraft decision reasoning method of the various embodiments of the present application described in the present specification.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring current telemetering data; extracting parameters and instructions from the current telemetry data; updating the corresponding target facts in the fact base according to the parameters and the instructions to obtain known facts; searching rules matched with known facts in a rule base to obtain a rule set; and interpreting the rules in the rule set according to the known facts to obtain a current interpretation conclusion.
The processor implements the steps of any of the above spacecraft decision reasoning methods when executing the computer program.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring current telemetering data; extracting parameters and instructions from the current telemetry data; updating the corresponding target facts in the fact base according to the parameters and the instructions to obtain known facts; searching rules matched with known facts in a rule base to obtain a rule set; and interpreting the rules in the rule set according to the known facts to obtain a current interpretation conclusion.
The computer program when executed by a processor implements the steps of any of the above described spacecraft decision reasoning methods.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A spacecraft decision reasoning method, the method comprising:
acquiring current telemetering data;
extracting parameters and instructions from the current telemetry data;
updating the corresponding target facts in the fact base according to the parameters and the instructions to obtain known facts;
searching a rule matched with the known fact in a rule base to obtain a rule set;
and interpreting the rules in the rule set according to the known facts to obtain a current interpretation conclusion.
2. The method of claim 1, wherein prior to said acquiring telemetry data, the method further comprises:
and constructing the fact base and the rule base based on empirical knowledge of the spacecraft, factual knowledge of the spacecraft and logic relations between the operation state of the spacecraft and the telemetering data.
3. The method according to claim 1, wherein the interpreting the rules in the rule set according to the known facts to obtain a current interpretation conclusion comprises:
reading and analyzing rules in the rule set;
associating variables in the rules with corresponding known facts in a fact base;
creating a data interpretation queue;
acquiring a pointer list corresponding to the data interpretation queue;
sequentially acquiring current parameter pointers from the pointer list;
and matching and executing a corresponding rule according to the current parameter pointer based on the corresponding known fact to obtain a current interpretation conclusion.
4. The method according to claim 1, wherein the interpreting the rules in the rule set according to the known facts to obtain a current interpretation conclusion comprises:
determining a first rule to be interpreted as a current rule to be interpreted according to the known fact;
judging the current rule to be judged according to the intermediate judgment conclusion in the intermediate conclusion area and the known fact to obtain a corresponding intermediate judgment conclusion;
storing the intermediate interpretation conclusion to an intermediate conclusion area, and updating the known fact according to the intermediate interpretation conclusion;
monitoring the intermediate conclusion area, and determining a next to-be-interpreted rule by combining the intermediate conclusion area and the updated known facts;
taking the next rule to be interpreted as the current rule to be interpreted, executing the interpretation of the current rule to be interpreted according to the intermediate interpretation conclusion in the intermediate conclusion area and the known fact to obtain a corresponding intermediate interpretation conclusion until the interpretation of all the rules in the rule set is completed to obtain the current interpretation conclusion.
5. The method of claim 1, further comprising:
if the current interpretation conclusion is an unexpected conclusion, searching a remote control instruction for controlling the spacecraft according to the current interpretation conclusion;
acquiring updated telemetering data after the spacecraft responds to the remote control instruction;
taking the updated telemetry data as current telemetry data, and executing the parameter and instruction extraction from the current telemetry data until the current interpretation conclusion is the expected conclusion.
6. The method of claim 1, wherein prior to acquiring current telemetry data, the method further comprises:
configuring an inference environment;
initializing inference engine parameters and states;
and creating a memory.
7. The method of claim 1, further comprising:
storing the current interpretation conclusion in a database;
and issuing the current interpretation conclusion to a network where the spacecraft is located in a broadcasting mode.
8. The method of claim 1, further comprising:
and carrying out non-repeated error reporting on the parameters or instructions corresponding to the known facts of which the current interpretation conclusion is abnormal within the preset time length.
9. A spacecraft decision reasoning apparatus, the apparatus comprising:
the data acquisition module is used for acquiring current telemetering data;
the data processing module is used for extracting parameters and instructions from the current telemetering data;
the first matching module is used for updating the corresponding target fact in the fact base according to the parameters and the instructions to obtain a known fact;
the second matching module is used for searching the rule matched with the known fact in the rule base to obtain a rule set;
and the interpretation module is used for interpreting the rules in the rule set according to the known facts to obtain a current interpretation conclusion.
10. A spacecraft decision reasoning system, the system comprising: a knowledge base, a database and an inference engine; the knowledge base comprises a rule base and a fact base;
the inference engine implements spacecraft decision reasoning by performing the steps of the spacecraft decision reasoning method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110828361.5A CN113570059A (en) | 2021-07-21 | 2021-07-21 | Spacecraft decision reasoning method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110828361.5A CN113570059A (en) | 2021-07-21 | 2021-07-21 | Spacecraft decision reasoning method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113570059A true CN113570059A (en) | 2021-10-29 |
Family
ID=78166097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110828361.5A Pending CN113570059A (en) | 2021-07-21 | 2021-07-21 | Spacecraft decision reasoning method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113570059A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114118426A (en) * | 2022-01-27 | 2022-03-01 | 广东粤港澳大湾区硬科技创新研究院 | Frame fault diagnosis method, device and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR19990016257A (en) * | 1997-08-13 | 1999-03-05 | 김징완 | Reasoning Method and Device of Expert System with Hierarchical Knowledge Base |
| CN101710393A (en) * | 2009-11-25 | 2010-05-19 | 北京航空航天大学 | Method for knowledge expressing and reasoning mechanism of expert system |
| US20100262955A1 (en) * | 1999-10-13 | 2010-10-14 | Robert Bedichek | Method for integration of interpretation and translation in a microprocessor |
| CN103218451A (en) * | 2013-04-27 | 2013-07-24 | 北京空间飞行器总体设计部 | Automatic spacecraft test data interpreting method |
| CN105159286A (en) * | 2015-09-22 | 2015-12-16 | 北京空间飞行器总体设计部 | Spacecraft on-orbit anomaly alarming and fault diagnosing system |
| CN105184372A (en) * | 2015-10-09 | 2015-12-23 | 电子科技大学 | Knowledge network construction method and apparatus |
| CN106844775A (en) * | 2017-03-02 | 2017-06-13 | 上海交通大学 | Spacecraft malfunction rapid detection system |
| CN107577806A (en) * | 2017-09-26 | 2018-01-12 | 北京空间技术研制试验中心 | Spacecraft data automated interpretation system and interpretation method |
| CN108959489A (en) * | 2018-06-23 | 2018-12-07 | 上海泽阳智能科技有限公司 | A kind of efficient data exchange and data source partition method |
| CN109062954A (en) * | 2018-06-23 | 2018-12-21 | 上海泽阳智能科技有限公司 | A kind of efficient data exchange and data source shielding system |
-
2021
- 2021-07-21 CN CN202110828361.5A patent/CN113570059A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR19990016257A (en) * | 1997-08-13 | 1999-03-05 | 김징완 | Reasoning Method and Device of Expert System with Hierarchical Knowledge Base |
| US20100262955A1 (en) * | 1999-10-13 | 2010-10-14 | Robert Bedichek | Method for integration of interpretation and translation in a microprocessor |
| CN101710393A (en) * | 2009-11-25 | 2010-05-19 | 北京航空航天大学 | Method for knowledge expressing and reasoning mechanism of expert system |
| CN103218451A (en) * | 2013-04-27 | 2013-07-24 | 北京空间飞行器总体设计部 | Automatic spacecraft test data interpreting method |
| CN105159286A (en) * | 2015-09-22 | 2015-12-16 | 北京空间飞行器总体设计部 | Spacecraft on-orbit anomaly alarming and fault diagnosing system |
| CN105184372A (en) * | 2015-10-09 | 2015-12-23 | 电子科技大学 | Knowledge network construction method and apparatus |
| CN106844775A (en) * | 2017-03-02 | 2017-06-13 | 上海交通大学 | Spacecraft malfunction rapid detection system |
| CN107577806A (en) * | 2017-09-26 | 2018-01-12 | 北京空间技术研制试验中心 | Spacecraft data automated interpretation system and interpretation method |
| CN108959489A (en) * | 2018-06-23 | 2018-12-07 | 上海泽阳智能科技有限公司 | A kind of efficient data exchange and data source partition method |
| CN109062954A (en) * | 2018-06-23 | 2018-12-21 | 上海泽阳智能科技有限公司 | A kind of efficient data exchange and data source shielding system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114118426A (en) * | 2022-01-27 | 2022-03-01 | 广东粤港澳大湾区硬科技创新研究院 | Frame fault diagnosis method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Darimont et al. | Formal refinement patterns for goal-driven requirements elaboration | |
| CN101657766B (en) | Online fault detection and avoidance framework for distributed factory control systems | |
| DE602005004997T2 (en) | Diagnostic procedure and system | |
| CN111177485B (en) | Parameter rule matching based equipment fault prediction method, equipment and medium | |
| CN111008154B (en) | Android application automatic test method and system based on reinforcement learning | |
| CN113570059A (en) | Spacecraft decision reasoning method, device and system | |
| Borroek et al. | Analysis on Knowledge Layer Application for Knowledge Based System | |
| CN103198232A (en) | Method and device for determining human reliability of staff members of digital main control room | |
| CN110489093A (en) | A kind of lasting building method, device, terminal and storage medium towards AI application | |
| Bremond et al. | Case studies in learning models and testing without reset | |
| Armengol et al. | A knowledge level model of knowledge-based reasoning | |
| Dolk et al. | An active modeling system for econometric analysis | |
| TWI774326B (en) | Method for generating a process model | |
| Lydiard | Overview of current practice and research initiatives for the verification and validation of KBS | |
| Foehr et al. | Implementation of a methodology for consideration of product quality within discrete manufacturing | |
| Antonelli et al. | An Iterative and Collaborative Approach to Specify Scenarios using Natural Language. | |
| Sandeep et al. | CLIPS based decision support system for water distribution networks | |
| Kartam et al. | Towards a foundation for evaluating AI planners | |
| Gamzayev et al. | Handling of expert knowledge in software product lines development with usage of repertory grids method | |
| Sheppard et al. | Combining model-based and case-based expert systems | |
| CN117171364B (en) | Operation and maintenance knowledge graph updating method and device | |
| da Silva et al. | A framework for expert systems development integrated to a SCADA/EMS environment | |
| Gallant et al. | USING AUTOMATED TECHNIQUESTO | |
| WO2013060389A1 (en) | Control of a machine | |
| Nowinski et al. | A knowledge acquisition and processing strategy based on formal concept analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |