CN117273478A - Alarm handling decision method, system and storage medium for fusing rules and cases - Google Patents
Alarm handling decision method, system and storage medium for fusing rules and cases Download PDFInfo
- Publication number
- CN117273478A CN117273478A CN202311055593.7A CN202311055593A CN117273478A CN 117273478 A CN117273478 A CN 117273478A CN 202311055593 A CN202311055593 A CN 202311055593A CN 117273478 A CN117273478 A CN 117273478A
- Authority
- CN
- China
- Prior art keywords
- case
- event
- data
- alarm
- decision
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000011282 treatment Methods 0.000 claims abstract description 42
- 230000004927 fusion Effects 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 14
- 239000013589 supplement Substances 0.000 claims description 6
- 238000012986 modification Methods 0.000 claims description 5
- 230000004048 modification Effects 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 3
- 238000007500 overflow downdraw method Methods 0.000 claims description 3
- 238000011369 optimal treatment Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000010006 flight Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- WBWWGRHZICKQGZ-HZAMXZRMSA-M taurocholate Chemical compound C([C@H]1C[C@H]2O)[C@H](O)CC[C@]1(C)[C@@H]1[C@@H]2[C@@H]2CC[C@H]([C@@H](CCC(=O)NCCS([O-])(=O)=O)C)[C@@]2(C)[C@@H](O)C1 WBWWGRHZICKQGZ-HZAMXZRMSA-M 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
- G06F16/2455—Query execution
- G06F16/24564—Applying rules; Deductive queries
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Computer Security & Cryptography (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Operations Research (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses an alarm handling decision method, a system and a storage medium for fusing rules and cases, which comprise the following steps: s1, collecting and operating a treatment rule file by a rule applicable reasoning model for associated storage; s2, acquiring civil aviation unsafe event data by using a case-applicable reasoning model, and storing the civil aviation unsafe event data in an associated mode according to event types, event characteristic parameters and case disposal flow data; s3, acquiring real-time alarm information and aircraft state data, obtaining rule decision suggestions based on an operation rule database, performing similarity calculation processing based on event case data sets, selecting case disposition flow data with highest similarity as case decision suggestions, and performing data fusion to obtain comprehensive decision suggestions and outputting the comprehensive decision suggestions. The invention not only utilizes the operation instructions of regulations and manuals, but also can match the optimal treatment rules when solving the alarm, can rapidly give out comprehensive decision suggestions, and can also give out treatment decision suggestions corresponding to the type of combined alarm, thereby helping the commander to conduct treatment command.
Description
Technical Field
The invention relates to the technical field of civil aviation alarm processing application, in particular to an alarm processing decision method, an alarm processing decision system and a storage medium for fusing rules and cases.
Background
The flight operation safety is not only the life line of an airline company, but also the basis of all air transportation services, in recent years, whether an aeronautical accident is caused by airplane model design (such as Boeing 737MAX-8 airplane), or an accident caused by operation command of the airline company, the aviation safety is rapidly and widely focused in society, and always draws the mood of people, so that the safety is ensured, the service work is improved, and normal flight striving is always the operation aim of civil aviation flights. While the aircraft is flying, devices on the aircraft (such as an onboard warning system) can send warning information to ground operation commanders (including airline personnel, controllers and the like), the warning information is generally divided into two categories, wherein the first category is a conventional risk warning (such as a transponder code warning, a yaw warning, a low oil quantity warning, a near-earth warning, a take-off form warning, an overspeed warning, a stall warning and the like), and the other category is a core risk warning, such as a near-earth warning, a TCAS anti-collision warning, a mechanical fault warning (such as a failure), a dangerous airway weather warning and the like. The disposal flow or the solution method of the alarm information is recorded in files such as a regulation specification, an airline security manual and the like; at present, when an aircraft flight gives an alarm, operation commanders all deal with and solve according to rules of regulations and manuals, and because of time shortage, the problem that the rules are inappropriately applied or all aviation condition scenes cannot be covered is inevitably solved, if the approval process is changed for a long time, the operation difficulty of pilots is increased, and the operation commander has mishandling potential safety hazard. Moreover, the handling rules recorded by regulations and manuals are relatively few compared with the actual flight situation, and often the handling rules recorded by regulations and manuals are handling rules of a single specific alarm, so that in many cases, depending on the abundant experience of commanders, especially in the face of multiple alarm situations, it is difficult to obtain reasonable handling rules and measures in a short time, which seriously affects the command work of the aircraft flight under the alarm event.
Disclosure of Invention
The invention aims at solving the technical problems pointed out by the background technology, and provides an alarm treatment decision method, an alarm treatment decision system and a storage medium for fusing rules and cases, wherein the comprehensive decision suggestion not only utilizes operation instructions of regulations and manuals, but also can match optimal specific treatment rules and measures from the same or similar cases before when solving alarms, and the comprehensive decision suggestion can give out comprehensive treatment suggestions more quickly and scientifically to help commanders to carry out alarm comprehensive treatment command operation.
The aim of the invention is achieved by the following technical scheme:
an alarm handling decision method integrating rules and cases, comprising an alarm handling decision system, the method comprising:
s1, a rule applicable reasoning model is built in an alarm disposal decision system, an operation rule database is arranged in the rule applicable reasoning model, operation disposal rule files including regulations and manuals are collected and input into the operation rule database for associated storage, and operation rule data in the operation rule database are associated storage according to the navigation condition type, navigation condition characteristic parameters and disposal flow data, wherein the navigation condition type comprises an alarm type;
s2, constructing a case applicable reasoning model in the alarm disposal decision system, wherein an event case data set is arranged in the case applicable reasoning model, acquiring civil aviation unsafe event data and inputting the event case data set, and the event case data in the event case data set is stored in an associated mode according to event types, event characteristic parameters and case disposal flow data; the event type comprises an alarm event type, the characteristic items of the event characteristic parameters comprise model information, alarm type, event reason, operation stage, engine state information and aeronautical situation environment, each characteristic item comprises characteristic information distributed according to a hierarchical architecture, the aeronautical situation environment comprises a natural environment and a sailing environment, the alarm types are divided according to single alarms and combined alarms, and the characteristic items and the characteristic information of the event characteristic parameters are distributed with weights according to the hierarchical levels;
s3, acquiring real-time alarm information and aircraft state data to form a combined data input alarm treatment decision system, extracting corresponding alarm feature information and aeronautical situation feature information by a rule applicable reasoning model, obtaining rule decision suggestions based on an operation rule database, wherein the alarm feature information corresponds to the alarm type in the aeronautical situation type, the aeronautical situation feature information corresponds to aeronautical situation feature parameters in the operation rule database, and the rule decision suggestions correspond to treatment flow data in the operation rule database;
the case-applicable reasoning model extracts feature data from the combined data according to the event feature parameters, wherein the feature data corresponds to feature items and feature information of the event feature parameters and is distributed according to a hierarchy; the case-applicable reasoning model is internally provided with a trained similarity calculation model, the similarity calculation model carries out similarity calculation processing on the feature data and the combination weight value in the event case data set, the event case data is output according to the arrangement of the similarity, and case treatment flow data in the event case data with the highest similarity is extracted to be used as case decision suggestion;
and carrying out data fusion on the rule decision suggestions and the case decision suggestions to obtain comprehensive decision suggestions.
In order to better realize the alarm handling decision method of the invention, the aeronautical situation type in the step S1 also comprises a non-alarm type, the event type in the step S2 also comprises a non-alarm event type, and the rule decision suggestion and the case decision suggestion are respectively obtained according to the steps S1 to S3, and the data fusion is carried out to obtain the comprehensive decision suggestion under the non-alarm condition.
Under the thought of the alarm handling decision method of the invention, another preferable expansion technical scheme is as follows: in step S1, an independent alarm handling rule database is divided inside the operation rule database, and operation rule data with an aeronautical situation type being an alarm type is stored in the alarm handling rule database; in step S2, the event case data set is internally divided into an independent alarm case rule database, and alarm case rule data with an event type of an alarm type is stored in the alarm handling rule database.
Preferably, in step S3, the similarity calculation model includes a similarity euclidean distance calculation formula:
wherein D (s, t) represents Euclidean distance between a source case and a target case after processing, the source case is extracted feature data, the target case is event feature parameters screened in an event case data set, k represents a retrieval attribute number, n represents total number of retrieval attributes, and w k An attribute weight representing the search attribute number k; d (D) k (s, t) represents the distance between the source case and the target case in the attribute dimension of the search attribute number k.
Preferably, the rule decision suggestion and the case decision suggestion are data fusion method rules based on rule decision suggestion as main and case decision suggestion as supplement.
Preferably, constructing the event case data set in the case-applicable reasoning model further comprises the following modification and expansion methods: and (3) extracting case treatment flow data with highest similarity based on the combined data in the step (S3), modifying event case data corresponding to the case treatment flow data, and storing the event case data in an event case data set as event case data.
The alarm treatment decision system integrating rules and cases comprises an alarm information input module, a rule applicable reasoning model, a case applicable reasoning model and a comprehensive decision suggestion integration module, wherein the alarm information input module is used for acquiring real-time alarm information and aircraft state data; an operation rule database is arranged in the rule applicable reasoning model, operation treatment rule files including regulations and manuals are collected by the rule applicable reasoning model and input into the operation rule database for associated storage, and operation rule data in the operation rule database are associated and stored according to the navigation condition type, navigation condition characteristic parameters and treatment flow data, wherein the navigation condition type comprises an alarm type; the case applicable reasoning model is internally provided with an event case data set, the case applicable reasoning model collects civil aviation unsafe event data and inputs the event case data set, event case data in the event case data set is stored in an associated mode according to event types, event characteristic parameters and case disposal flow data, and the event characteristic parameters are stored in a hierarchical mode according to characteristic items and characteristic information and are distributed with weights in a hierarchical mode; the rule applicable reasoning model obtains rule decision suggestions based on the operation rule database, the case applicable reasoning model carries out similarity calculation processing based on the event case data set and outputs the event case data according to the similarity degree, and case disposition flow data in event case data with highest similarity degree is selected as case decision suggestions; and the comprehensive decision suggestion fusion module fuses the rule decision suggestions and the case decision suggestions to obtain comprehensive decision suggestions and outputs the comprehensive decision suggestions.
A storage medium comprising a memory storing an executable program and a processor implementing the steps of the alert handling decision method of the present invention when the executable program is executed.
Compared with the prior art, the invention has the following advantages:
(1) The invention obtains the characteristic data based on the combination data such as real-time alarm information, obtains the corresponding rule decision suggestion through the rule applicable reasoning model, obtains the case decision suggestion through the case applicable reasoning model, and then obtains the comprehensive decision suggestion through data fusion.
(2) The invention can cover more alarm situations by the data of event case data set in case applicable reasoning model, can realize the comprehensive decision suggestion of single alarm, can give out the practical and scientific treatment decision suggestion facing to the combined alarm type, and can quickly give the treatment decision suggestion to the commander by means of personal experience or a small part of experience compared with the traditional method, thereby helping the commander to quickly and correctly conduct decision command.
Drawings
FIG. 1 is a flow chart of a method according to a first embodiment;
FIG. 2 is a schematic block diagram of an alarm handling decision system in an embodiment;
fig. 3 is a schematic diagram of data modification and expansion in event case data set in an embodiment.
Detailed Description
The invention is further illustrated by the following examples:
example 1
As shown in fig. 1, a method for integrating rules and cases into an alarm handling decision, including an alarm handling decision system, includes:
s1, a rule applicable reasoning model is built in the alarm disposal decision system, an operation rule database is arranged in the rule applicable reasoning model, operation disposal rule files including regulations and manuals are collected and input into the operation rule database for associated storage, and operation rule data in the operation rule database are associated and stored according to the navigation condition type, the navigation condition characteristic parameters and the disposal flow data. The aeronautical situation type comprises an alarm type (the alarm type is type data corresponding to alarm information, and the invention can be applied to non-alarm types in an expanding way, such as regulations and handbooks, and other non-alarm treatment rules are stored in the handbook; preferably, an independent alarm handling rule database is divided in the operation rule database, and operation rule data with the aeronautical situation type as the alarm type is stored in the alarm handling rule database; the rule applicable reasoning model of the embodiment independently builds the alarm treatment rule database, is mainly applied to the treatment decision of the alarm information (or is only applied to the treatment decision of the alarm information), and can quickly and accurately obtain rule decision suggestions.
S2, constructing a case applicable reasoning model in the alarm disposal decision system, wherein an event case data set is arranged in the case applicable reasoning model, acquiring civil aviation unsafe event data and inputting the event case data set, and the event case data in the event case data set is stored in an associated mode according to event types, event characteristic parameters and case disposal flow data; preferably, the event type in this embodiment includes an alarm type (for civil aviation unsafe event data that does not include an alarm type, the event data is not stored in the event case data set, and the invention can be extended to a non-alarm type); the event case data set is internally divided into an independent alarm case rule database, and alarm case rule data with the event type being the alarm type is stored in the alarm handling rule database (the alarm case rule data is source civil aviation unsafe event data, and the scientificity, rationality and safety of the case handling rule flow are checked by civil aviation specialists). Preferably, if there are multiple case handling flow data under the same event type and event feature parameters, the multiple case handling flow data sets the recommended priority. The event type includes an alarm event type, the feature items of the event feature parameters include model information (model corresponding to aircraft manufacturer), an alarm type, event cause (cause feature corresponding to event), an operation stage (feature information of the operation stage includes taxi and take-off stage, climb stage, cruise stage, descent stage, approach and landing stage), engine state information (feature information thereof includes information of start state, idle state, acceleration state, cruise state, taxi state, and whether engine state under the above feature information is stable, overload, oil pressure, oil temperature, etc.), a aviation environment (including natural environment, navigation environment), each feature item includes feature information distributed in hierarchical architecture, the aviation environment includes natural environment and navigation environment, wherein the alarm type is classified according to single alarm and combined alarm (i.e., the alarm type in the event feature parameters is classified according to single alarm and combined alarm, the alarm type is more than the alarm type in the operation rule database, and the type in the single alarm classification of the event feature parameters is also more than the alarm type in the rule database, because the alarm type in the rule database is a manual and the feature parameters may be classified according to single alarm and combined alarm types, and the single alarm types may be defined by regulations and types besides the manual. The feature items and feature information of the event feature parameters are distributed with weights in layers (the feature items comprise feature information distributed according to a hierarchical architecture, the weight of one feature item is the sum of the first hierarchical weights of the feature information under the hierarchy, and the like); the table of feature item codes and weight assignments of the event feature parameters is exemplified as follows:
s3, acquiring real-time alarm information (the real-time alarm information is the alarm information generated by the aircraft) and aircraft state data (the real-time aircraft state data is based on data including real-time flight parameter data and equipment on the aircraft, the data range of the real-time aircraft state data is the addition and supplement of the alarm information, such as data including corresponding records of a transponder and the like), forming a combined data input alarm treatment decision system, extracting corresponding alarm feature information and aviation condition feature information by using a rule applicable reasoning model, and obtaining rule decision suggestion based on an operation rule database, wherein the alarm feature information corresponds to an alarm type in an aviation condition type, the aviation condition feature information corresponds to aviation condition feature parameters in the operation rule database, and the rule decision suggestion corresponds to treatment flow data in the operation rule database.
The case applicable reasoning model extracts feature data from the combined data according to the event feature parameters, wherein the feature data corresponds to feature items and feature information of the event feature parameters and is distributed according to a hierarchy (the data in the feature data comprises corresponding data of the feature items and the feature information, the data in the feature data corresponds to the hierarchy, and the data in the feature data also corresponds to and is matched with the weight of the event feature parameters). The case-applicable reasoning model is internally provided with a trained similarity calculation model, the similarity calculation model performs similarity calculation processing on the feature data in the event case data set in combination with the weight (the similarity calculation only focuses on the similarity of the feature data and the data in the event feature parameters), the event case data is output according to the similarity degree arrangement, and case treatment flow data in the event case data with the highest similarity degree is extracted and used as case decision advice (in some embodiments, the case decision advice can be output according to the similarity degree arrangement).
And carrying out data fusion on the rule decision advice and the case decision advice to obtain comprehensive decision advice, outputting the comprehensive decision advice, the rule decision advice and the case decision advice in sequence, and outputting the treatment flow data corresponding to the case event case data with high similarity.
For example: the method comprises the steps that when an airline ground operation control center receives 'oil quantity low' alarm information of a flight XX8181 at a certain time (the alarm information comprises a flight stage of 'airway flight', and the like), a rule application reasoning model of an alarm disposal decision system (which can be installed in the ground operation control center system) gives a rule decision suggestion for starting a backup program disposal, and disposal flow data is given at the same time; the case treatment flow data of all event case data given by the case applicable reasoning model is also case treatment flow data which is obtained by starting the backup and descent program treatment and arranging according to the specific characteristic parameters and the similarity, and the case decision proposal with the highest extracted similarity gives the case treatment flow data which is optimal according to the specific characteristic parameters. And then carrying out data synthesis operation fusion processing on the rule decision advice and the case decision advice (the optimal case treatment flow data) to obtain the comprehensive decision advice.
In the invention, real-time alarm information has definite alarm types corresponding to the alarm types in the operation rule database (from regulations and manuals) and has high corresponding degree (the characteristic data is in one-to-one correspondence), and rule decision suggestions can be obtained through characteristic recognition of the characteristic data very quickly. As an extension application, the information combining the real-time alarm information and the aircraft state data also contains some other types of alarm information, if the one-to-one corresponding operation rule data cannot be found in the operation rule database, then the case decision suggestion can not be output, at this time, the case decision suggestion is output only according to the case applicable reasoning model, and the comprehensive decision suggestion is not fused with the rule decision suggestion.
In some embodiments, the similarity calculation model of the case-applicable reasoning model may use euclidean distance to perform similarity calculation processing, where the similarity calculation model includes a similarity euclidean distance calculation formula:
wherein D (s, t) represents Euclidean distance between a source case and a target case after processing, the source case is extracted feature data, the target case is event feature parameters screened in an event case data set, k represents retrieval attribute numbers (numbers corresponding to feature items or feature information), n represents total number of retrieval attributes (total number of feature items or feature information), and w k The attribute weight value indicating the search attribute number k. D (D) k (s, t) represents the distance between the source case (extracted feature data) and the target case (event feature parameters screened out in the event case data set) in the attribute dimension of the search attribute number k (the number corresponding to the feature item or the feature information).
In some embodiments, the rule decision suggestion and case decision suggestion data fusion method rule is to perform data fusion based on rule decision suggestion as a main and case decision suggestion as a supplement (the purpose of data fusion is to make two decision suggestions mainly for a collective operation process). Under the condition of single alarm types of rule decision suggestions and case decision suggestions, if the case decision suggestions are more specific than the rule decision suggestions, adopting a specific rule flow of which the rule decision suggestions are dominant lines and the case decision suggestions as supplement to perform data fusion. Under the fusion alarm type, data fusion is carried out by taking case decision advice as a main part and rule decision advice as a supplement.
In some embodiments, as shown in fig. 3, constructing the event case data set in the case-applicable reasoning model further includes the following modification and expansion methods: based on the combined data extraction in the step S3, obtaining case treatment flow data with highest similarity, modifying event case data corresponding to the case treatment flow data, and storing the event case data as event case data in an event case data set; if the event case data in the event case data set is not more, firstly, the case disposition flow data with highest similarity (disposition decision of new alarm information can be faced, and rapid decision is assisted by commander) is called, and decision and post-scientific demonstration are carried out in specific flight alarm to form an event case data for storage.
As shown in fig. 2, an alarm handling decision system for fusing rules and cases includes an alarm information input module, a rule applicable reasoning model, a case applicable reasoning model, and a comprehensive decision suggestion fusion module, where the alarm information input module is used to collect real-time alarm information and aircraft state data. The rule applicable reasoning model is internally provided with an operation rule database, operation treatment rule files including regulations and manuals are collected by the rule applicable reasoning model and input into the operation rule database for associated storage, and operation rule data in the operation rule database are associated and stored according to the navigation condition type, navigation condition characteristic parameters and treatment flow data, wherein the navigation condition type comprises an alarm type. The case-applicable reasoning model is internally provided with an event case data set, the case-applicable reasoning model collects civil aviation unsafe event data and inputs the event case data set, event case data in the event case data set is stored in an associated mode according to event types, event characteristic parameters and case disposal flow data, and the event characteristic parameters are stored in a hierarchical mode according to characteristic items and characteristic information and are distributed with weights in a hierarchical mode. The rule applicable reasoning model obtains rule decision suggestions based on the operation rule database, the case applicable reasoning model carries out similarity calculation processing based on the event case data set and outputs the event case data according to the similarity, and case disposition flow data in event case data with highest similarity is selected as case decision suggestions. And the comprehensive decision suggestion fusion module fuses the rule decision suggestions and the case decision suggestions to obtain comprehensive decision suggestions and outputs the comprehensive decision suggestions.
Example two
The embodiment can be generalized to non-alarm applications, and compared with the first embodiment, the embodiment has the following technical changes: the navigation condition type in step S1 further includes a non-alarm type (the inference model applicable to the embodiment rule may also separately construct a non-alarm disposition rule database, the non-alarm disposition rule database stores operation rule data with the navigation condition type being the non-alarm type), the event type in step S2 further includes a non-alarm event type (the inference model applicable to the embodiment case may also separately construct a non-alarm case rule database, the non-alarm case rule database stores non-alarm case rule data with the event type being the non-alarm type), and decision suggestions and case decision suggestions under the condition of rule non-alarm are obtained according to steps S1 to S3 of the first embodiment respectively, and data fusion is performed to obtain comprehensive decision suggestions under the condition of non-alarm.
A storage medium comprising a memory storing an executable program and a processor implementing the steps of the alert handling decision method of the present invention when the processor executes the executable program.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (8)
1. A method for integrating rules and cases in alarm treatment decision-making is characterized in that: including an alert handling decision system, the method comprising:
s1, a rule applicable reasoning model is built in an alarm disposal decision system, an operation rule database is arranged in the rule applicable reasoning model, operation disposal rule files including regulations and manuals are collected and input into the operation rule database for associated storage, and operation rule data in the operation rule database are associated storage according to the navigation condition type, navigation condition characteristic parameters and disposal flow data, wherein the navigation condition type comprises an alarm type;
s2, constructing a case applicable reasoning model in the alarm disposal decision system, wherein an event case data set is arranged in the case applicable reasoning model, acquiring civil aviation unsafe event data and inputting the event case data set, and the event case data in the event case data set is stored in an associated mode according to event types, event characteristic parameters and case disposal flow data; the event type comprises an alarm event type, the characteristic items of the event characteristic parameters comprise model information, alarm type, event reason, operation stage, engine state information and aeronautical situation environment, each characteristic item comprises characteristic information distributed according to a hierarchical architecture, the aeronautical situation environment comprises a natural environment and a sailing environment, the alarm types are divided according to single alarms and combined alarms, and the characteristic items and the characteristic information of the event characteristic parameters are distributed with weights according to the hierarchical levels;
s3, acquiring real-time alarm information and aircraft state data to form a combined data input alarm treatment decision system, extracting corresponding alarm feature information and aeronautical situation feature information by a rule applicable reasoning model, obtaining rule decision suggestions based on an operation rule database, wherein the alarm feature information corresponds to the alarm type in the aeronautical situation type, the aeronautical situation feature information corresponds to aeronautical situation feature parameters in the operation rule database, and the rule decision suggestions correspond to treatment flow data in the operation rule database;
the case-applicable reasoning model extracts feature data from the combined data according to the event feature parameters, wherein the feature data corresponds to feature items and feature information of the event feature parameters and is distributed according to a hierarchy; the case-applicable reasoning model is internally provided with a trained similarity calculation model, the similarity calculation model carries out similarity calculation processing on the feature data and the combination weight value in the event case data set, the event case data is output according to the arrangement of the similarity, and case treatment flow data in the event case data with the highest similarity is extracted to be used as case decision suggestion;
and carrying out data fusion on the rule decision suggestions and the case decision suggestions to obtain comprehensive decision suggestions.
2. The alert handling decision method for fusing rules and cases as recited in claim 1, wherein: the navigation condition type in the step S1 also comprises a non-alarm type, the event type in the step S2 also comprises a non-alarm event type, rule decision suggestions and case decision suggestions are respectively obtained according to the steps S1 to S3, and data fusion is carried out to obtain comprehensive decision suggestions under the non-alarm condition.
3. An alarm handling decision method of fusing rules and cases according to claim 1 or 2, characterized in that: in step S1, an independent alarm handling rule database is divided inside the operation rule database, and operation rule data with an aeronautical situation type being an alarm type is stored in the alarm handling rule database; in step S2, the event case data set is internally divided into an independent alarm case rule database, and alarm case rule data with an event type of an alarm type is stored in the alarm handling rule database.
4. The alert handling decision method for fusing rules and cases as recited in claim 1, wherein: in step S3, the similarity calculation model includes a similarity euclidean distance calculation formula:
wherein D (s, t) represents Euclidean distance between a source case and a target case after processing, the source case is extracted feature data, the target case is event feature parameters screened in an event case data set, k represents a retrieval attribute number, n represents total number of retrieval attributes, and w k An attribute weight representing the search attribute number k; d (D) k (s, t) represents the distance between the source case and the target case in the attribute dimension of the search attribute number k.
5. The alert handling decision method for fusing rules and cases as recited in claim 1, wherein: the data fusion method rule of the rule decision suggestion and the case decision suggestion is to fuse data according to the rule decision suggestion as a main and the case decision suggestion as a supplement.
6. The alert handling decision method for fusing rules and cases as recited in claim 1, wherein: the event case data set in the case-applicable reasoning model is constructed by the following modification and expansion methods: and (3) extracting case treatment flow data with highest similarity based on the combined data in the step (S3), modifying event case data corresponding to the case treatment flow data, and storing the event case data in an event case data set as event case data.
7. An alarm handling decision system integrating rules and cases, characterized in that: the system comprises an alarm information input module, a rule applicable reasoning model, a case applicable reasoning model and a comprehensive decision suggestion fusion module, wherein the alarm information input module is used for acquiring real-time alarm information and aircraft state data; an operation rule database is arranged in the rule applicable reasoning model, operation treatment rule files including regulations and manuals are collected by the rule applicable reasoning model and input into the operation rule database for associated storage, and operation rule data in the operation rule database are associated and stored according to the navigation condition type, navigation condition characteristic parameters and treatment flow data, wherein the navigation condition type comprises an alarm type; the case applicable reasoning model is internally provided with an event case data set, the case applicable reasoning model collects civil aviation unsafe event data and inputs the event case data set, event case data in the event case data set is stored in an associated mode according to event types, event characteristic parameters and case disposal flow data, and the event characteristic parameters are stored in a hierarchical mode according to characteristic items and characteristic information and are distributed with weights in a hierarchical mode; the rule applicable reasoning model obtains rule decision suggestions based on the operation rule database, the case applicable reasoning model carries out similarity calculation processing based on the event case data set and outputs the event case data according to the similarity degree, and case disposition flow data in event case data with highest similarity degree is selected as case decision suggestions; and the comprehensive decision suggestion fusion module fuses the rule decision suggestions and the case decision suggestions to obtain comprehensive decision suggestions and outputs the comprehensive decision suggestions.
8. A storage medium comprising a memory and a processor, the memory storing an executable program, characterized in that the processor implements the steps of the alarm handling decision method of one of claims 1 to 6 when executing the executable program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311055593.7A CN117273478B (en) | 2023-08-21 | 2023-08-21 | Alarm handling decision method and system integrating rules and cases |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311055593.7A CN117273478B (en) | 2023-08-21 | 2023-08-21 | Alarm handling decision method and system integrating rules and cases |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117273478A true CN117273478A (en) | 2023-12-22 |
| CN117273478B CN117273478B (en) | 2024-04-12 |
Family
ID=89220427
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311055593.7A Active CN117273478B (en) | 2023-08-21 | 2023-08-21 | Alarm handling decision method and system integrating rules and cases |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117273478B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040008253A1 (en) * | 2002-07-10 | 2004-01-15 | Monroe David A. | Comprehensive multi-media surveillance and response system for aircraft, operations centers, airports and other commercial transports, centers and terminals |
| CN106097233A (en) * | 2016-05-31 | 2016-11-09 | 中国民航大学 | A kind of Route reform conflict Resolution method of case-based reasioning |
| CN112749207A (en) * | 2020-12-29 | 2021-05-04 | 大连海事大学 | Deep sea emergency disposal auxiliary decision making system based on case reasoning |
| CN113626616A (en) * | 2021-08-25 | 2021-11-09 | 中国电子科技集团公司第三十六研究所 | Aircraft safety early warning method, device and system |
| KR102343993B1 (en) * | 2020-09-01 | 2021-12-28 | 주식회사 피에스글로벌 | Providing method of disaster response manual |
| CN114819207A (en) * | 2022-03-22 | 2022-07-29 | 中国民航科学技术研究院 | Data evidence-based aircraft continuous airworthiness auxiliary management system and method |
| CN115087938A (en) * | 2019-12-23 | 2022-09-20 | 埃姆普里萨有限公司 | System and method for agnostic system functional state determination and fault automation management |
| CN115358586A (en) * | 2022-08-22 | 2022-11-18 | 中铁十五局集团有限公司 | Auxiliary decision-making method and system for monitoring key risk points of shield engineering |
| CN116429445A (en) * | 2023-04-18 | 2023-07-14 | 江西洪都航空工业集团有限责任公司 | Intelligent aero-engine diagnosis system |
-
2023
- 2023-08-21 CN CN202311055593.7A patent/CN117273478B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040008253A1 (en) * | 2002-07-10 | 2004-01-15 | Monroe David A. | Comprehensive multi-media surveillance and response system for aircraft, operations centers, airports and other commercial transports, centers and terminals |
| CN106097233A (en) * | 2016-05-31 | 2016-11-09 | 中国民航大学 | A kind of Route reform conflict Resolution method of case-based reasioning |
| CN115087938A (en) * | 2019-12-23 | 2022-09-20 | 埃姆普里萨有限公司 | System and method for agnostic system functional state determination and fault automation management |
| KR102343993B1 (en) * | 2020-09-01 | 2021-12-28 | 주식회사 피에스글로벌 | Providing method of disaster response manual |
| CN112749207A (en) * | 2020-12-29 | 2021-05-04 | 大连海事大学 | Deep sea emergency disposal auxiliary decision making system based on case reasoning |
| CN113626616A (en) * | 2021-08-25 | 2021-11-09 | 中国电子科技集团公司第三十六研究所 | Aircraft safety early warning method, device and system |
| CN114819207A (en) * | 2022-03-22 | 2022-07-29 | 中国民航科学技术研究院 | Data evidence-based aircraft continuous airworthiness auxiliary management system and method |
| CN115358586A (en) * | 2022-08-22 | 2022-11-18 | 中铁十五局集团有限公司 | Auxiliary decision-making method and system for monitoring key risk points of shield engineering |
| CN116429445A (en) * | 2023-04-18 | 2023-07-14 | 江西洪都航空工业集团有限责任公司 | Intelligent aero-engine diagnosis system |
Non-Patent Citations (6)
| Title |
|---|
| 吴兴旺 等: "飞机技术派遣智能决策支持系统框架研究――基于大数据视角", 计算机技术与发展, vol. 27, no. 11, 30 November 2017 (2017-11-30), pages 159 - 165 * |
| 宋敦波;: "基于GIS的火箭飞行应急决策仿真系统研究", 计算机测量与控制, vol. 18, no. 03, 25 March 2010 (2010-03-25), pages 623 - 625 * |
| 张攀科: "水上跑道侵入风险演化机理及预警模型研究", 中国博士学位论文全文数据库 工程科技Ⅱ辑, no. 07, 15 July 2020 (2020-07-15), pages 1 - 167 * |
| 李晓明 等: "基于案例推理的某型航空发动机防喘控制系统故障诊断", 科学技术与工程, vol. 18, no. 21, 28 July 2018 (2018-07-28), pages 320 - 326 * |
| 潘亚东 等: "基于案例推理的飞机排故训练系统", 中国民航大学学报, vol. 30, no. 03, 15 June 2012 (2012-06-15), pages 42 - 46 * |
| 石荣 等: "基于CBR的飞行事故及事故征候辅助调查方法", 空军工程大学学报(自然科学版), vol. 11, no. 05, 25 October 2010 (2010-10-25), pages 21 - 25 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117273478B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2421220C (en) | Information system and method using analyses based on object-centric longitudinal data | |
| US7440906B1 (en) | Identification, categorization, and integration of unplanned maintenance, repair and overhaul work on mechanical equipment | |
| EP3336636B1 (en) | Machine fault modelling | |
| Cacciabue | A methodology of human factors analysis for systems engineering: theory and applications | |
| US9196165B2 (en) | Assessing feasibility of an aircraft trajectory | |
| CN106910376B (en) | Air traffic operation control instruction monitoring method and system | |
| CN109284896B (en) | Human error mode influence analysis method | |
| CN104932519A (en) | Unmanned aerial vehicle flight command auxiliary decision-making system based on expert knowledge and design method thereof | |
| Odisho et al. | Applying machine learning to enhance runway safety through runway excursion risk mitigation | |
| Liu et al. | Bayesian network method for fault diagnosis of civil aircraft environment control system | |
| Washington et al. | Adoption of a Bayesian belief network for the system safety assessment of remotely piloted aircraft systems | |
| CN110481804B (en) | Flight auxiliary system and aircraft | |
| Rao et al. | A state-based approach to modeling general aviation accidents | |
| Puranik | A methodology for quantitative data-driven safety assessment for general aviation | |
| US20230032571A1 (en) | Systems and methods for an agnostic system functional status determination and automatic management of failures | |
| CN117273478B (en) | Alarm handling decision method and system integrating rules and cases | |
| Onken et al. | Assistant systems for aircraft guidance: cognitive man-machine cooperation | |
| Mehta et al. | Airplane crash severity prediction using machine learning | |
| Janakiraman et al. | Using ADOPT algorithm and operational data to discover precursors to aviation adverse events | |
| Yang | Aircraft landing gear extension and retraction control system diagnostics, prognostics and health management | |
| Li et al. | Virtual Co-Pilot: Multimodal Large Language Model-enabled Quick-access Procedures for Single Pilot Operations | |
| Shuo et al. | Integrated Vehicle Health Management technology and its applications in commerical aviation | |
| Loe et al. | Visualization of Business Intelligence Insights into Aviation Accidents | |
| Li et al. | An Overview of Civil Aviation Accidents and Risk Analysis | |
| Ören et al. | Landing sequencing modelling with fuzzy logic: Opportunistic approach for unmanned aerial systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |