Intelligent decision-making method and device for abnormity of command and control system

Abstract

The invention provides an intelligent decision-making method and device for the abnormity of a command and control system, and the method comprises the steps: building a real-time abnormity processing and equipment measurement data abnormity knowledge base for the thinking logic of the abnormity judgment of the command and control system accumulated by professionals in a target flight process for many years, and forming an abnormity analysis model based on a rule base; the method comprises the following steps: establishing an exception decision-making tree, expressing the exception decision-making tree into knowledge which can be identified by a computer by using a production rule, forming a judgment rule knowledge base, traversing the rule base according to an exception phenomenon in a target flight process, and reasoning a reason of data exception, thereby realizing rapid intelligent analysis on command and control system processing exception and equipment measurement data transmission exception. The subjectivity and finiteness of manual analysis are overcome, and the intelligence and reliability of abnormal problem judgment of the command and control system are improved.

Description

Technical Field

[0001] The present invention relates to the field of command and control technology, and in particular to an abnormal intelligent decision-making method and device for a command and control system. Background Art

[0002] During the flight of the target, problems such as unstable data transmission and abnormal processing results may occur. We hope to locate and solve them quickly, but the causes of the problems are usually complex. The premise of accurate analysis is to have an overall grasp of the system. There are many factors involved. To analyze the causes, the current manual inspection method is not only inefficient, but more importantly, the test personnel need more professional technical knowledge. If they lack experience, they may not be able to draw conclusions about the problem at all. Therefore, it is necessary to determine the analysis process, formulate judgment rules and methods, and quickly locate abnormal processing results based on the analysis of the working conditions of each system. Command decisions are made on this basis. At present, this part of the work is mainly implemented manually, and there are the following disadvantages:

[0003] 1) Since the command and control system is a complex and large system, the location of abnormal problems is often a reflection of a series of abnormalities. The amount of data that needs to be observed is relatively large and the update speed is fast. Manual interpretation is difficult to meet the real-time analysis requirements.

[0004] 2) The system's abnormal judgment requires the experience and knowledge of experts. Due to differences in individual technical levels, manual abnormal positioning may lead to misjudgment or omission of some abnormal situations, thus affecting the accuracy and stability of command decisions. Summary of the invention

[0005] The present invention aims to provide an abnormal intelligent decision-making method and device for a command and control system that overcomes the above-mentioned problems or at least partially solves the above-mentioned problems.

[0006] To achieve the above object, the technical solution of the present invention is specifically implemented as follows:

[0007] One aspect of the present invention provides an abnormal intelligent decision-making method for a command and control system, comprising:

[0008] Receiving original measurement data, and performing anomaly analysis on the original measurement data according to a preset information format to obtain a measurement data anomaly knowledge base;

[0009] Acquire real-time data, perform anomaly analysis on the real-time data, and obtain a real-time anomaly processing knowledge base;

[0010] An abnormal event in the measurement data abnormality knowledge base and the real-time abnormality processing knowledge base is used as a root node, and all causes of the abnormal event are used as branches of the tree to form an inverted tree structure, thereby generating an abnormality decision tree;

[0011] Convert each decision tree path in the abnormal decision tree into an expression of a production rule;

[0012] A judgment rule knowledge base is established, an abnormal event to be analyzed is obtained, the judgment rule knowledge base is traversed, and the abnormal cause of the abnormal event to be analyzed is obtained.

[0013] Optionally, the receiving raw measurement data and performing abnormality analysis on the raw measurement data according to a preset information format includes:

[0014] The correctness of filling in each field in the data format of the original measurement data is analyzed and checked to determine whether the original measurement data has the following errors: frame length error, source address error, destination address error, category code error, target number error, and conversion dimension error.

[0015] Optionally, the acquiring of real-time data and performing abnormal analysis on the real-time data includes:

[0016] If the real-time data is effectively tracked but the trajectory or track is not processed, analyze whether it is due to optical equipment abnormality, radar equipment abnormality or satellite navigation equipment abnormality;

[0017] If there is a result for the trajectory or track, but it is obviously inconsistent with the actual flight, analyze whether it is a position anomaly or a speed anomaly.

[0018] Optionally, the step of establishing a judgment rule knowledge base, obtaining an abnormal event to be analyzed, traversing the judgment rule knowledge base, and analyzing the abnormal causes of the abnormal event to be analyzed includes:

[0019] In the case where the abnormal event to be analyzed is measurement data, a rule table, a rule parameter table and an abnormal phenomenon table are set, and when performing abnormal analysis, abnormality positioning is performed according to the rule table, the rule parameter table and the abnormal phenomenon table;

[0020] In the case where the abnormal event to be analyzed is real-time data, an abnormal rule dictionary is set. When performing abnormal analysis, the information of the abnormal rule dictionary is read, and the judgment rule knowledge base is queried according to the abnormal phenomenon that occurs to locate the abnormality.

[0021] Optionally, the expression of the production rule includes:

[0022] IF X THEN Y;

[0023] The production rules use AND and / or OR statements to combine two or more rules to form multiple conditions or conclusions.

[0024] Another aspect of the present invention provides an abnormal intelligent decision-making device for a command and control system, comprising:

[0025] A first analysis module is used to receive raw measurement data, perform anomaly analysis on the raw measurement data according to a preset information format, and obtain a measurement data anomaly knowledge base;

[0026] The second analysis module is used to obtain real-time data, perform anomaly analysis on the real-time data, and obtain a real-time anomaly processing knowledge base;

[0027] A generating module, configured to generate an abnormal decision tree by taking the abnormal events in the measurement data abnormality knowledge base and the real-time abnormality processing knowledge base as root nodes and all the causes of the abnormal events as branches of the tree to form an inverted tree structure;

[0028] A conversion module, used for converting each decision tree path in the abnormal decision tree into an expression of a production rule;

[0029] The abnormal analysis module is used to establish a judgment rule knowledge base, obtain abnormal events to be analyzed, traverse the judgment rule knowledge base, and obtain the abnormal causes of the abnormal events to be analyzed.

[0030] Optionally, the first analysis module receives the original measurement data in the following manner, and performs abnormality analysis on the original measurement data according to a preset information format:

[0031] The correctness of filling in each field in the data format of the original measurement data is analyzed and checked to determine whether the original measurement data has the following errors: frame length error, source address error, destination address error, category code error, target number error, and conversion dimension error.

[0032] Optionally, the second analysis module obtains real-time data and performs abnormality analysis on the real-time data in the following manner:

[0033] If the real-time data is effectively tracked but the trajectory or track is not processed, analyze whether it is due to optical equipment abnormality, radar equipment abnormality or satellite navigation equipment abnormality;

[0034] If there is a result for the trajectory or track, but it is obviously inconsistent with the actual flight, analyze whether it is a position anomaly or a speed anomaly.

[0035] Optionally, the abnormal analysis module establishes a judgment rule knowledge base in the following manner, obtains the abnormal event to be analyzed, traverses the judgment rule knowledge base, and finds the abnormal cause of the abnormal event to be analyzed:

[0036] In the case where the abnormal event to be analyzed is measurement data, a rule table, a rule parameter table and an abnormal phenomenon table are set, and when performing abnormal analysis, abnormality positioning is performed according to the rule table, the rule parameter table and the abnormal phenomenon table;

[0037] In the case where the abnormal event to be analyzed is real-time data, an abnormal rule dictionary is set. When performing abnormal analysis, the information of the abnormal rule dictionary is read, and the judgment rule knowledge base is queried according to the abnormal phenomenon that occurs to locate the abnormality.

[0038] Optionally, the expression of the production rule includes:

[0039] IF X THEN Y;

[0040] The production rules use AND and / or OR statements to combine two or more rules to form multiple conditions or conclusions.

[0041] It can be seen that, through the abnormal intelligent decision-making method and device for the command and control system provided by the present invention, the problems of slow analysis and positioning and poor accuracy of abnormal situations in the command and control system due to the different complex and diverse states and types of flight targets are solved. The thinking logic of abnormal judgment of the command and control system during the target flight accumulated by professionals over the years is used to establish a real-time processing of abnormalities and equipment measurement data abnormality knowledge base, form an abnormal analysis model based on the rule base, establish an abnormal decision tree, and use production rules to express it as knowledge that can be recognized by the computer to form a judgment rule knowledge base. During the target flight, the rule base is traversed according to the abnormal phenomena to infer the causes of the data abnormalities, thereby realizing rapid intelligent analysis of the command and control system processing abnormalities and equipment measurement data transmission abnormalities, overcoming the subjectivity and limitations of manual analysis, and improving the intelligence and reliability of abnormal problem judgment of the command and control system. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0043] Figure 1 A flowchart of an abnormal intelligent decision-making method for a command and control system provided by an embodiment of the present invention;

[0044] Figure 2 A schematic diagram of a measurement data anomaly location decision tree provided in an embodiment of the present invention;

[0045] Figure 3 A schematic diagram of a decision tree for abnormal location of real-time processing results provided by an embodiment of the present invention;

[0046] Figure 4 The rules provided for the embodiments of the present invention are intended to represent;

[0047] Figure 5 A schematic diagram showing rule parameters provided in an embodiment of the present invention;

[0048] Figure 6 The abnormal phenomenon provided by the embodiment of the present invention is schematically shown;

[0049] Figure 7 A specific example flow chart of an abnormal intelligent decision-making method for a command and control system provided by an embodiment of the present invention;

[0050] Figure 8 A schematic diagram of the structure of an abnormal intelligent decision-making device for a command and control system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0052] Figure 1 A flowchart showing an abnormal intelligent decision-making method for a command and control system provided by an embodiment of the present invention is shown. Figure 1 The abnormal intelligent decision-making method of the command and control system provided by the embodiment of the present invention includes:

[0053] S1, receiving original measurement data, performing anomaly analysis on the original measurement data according to a preset information format, and obtaining a measurement data anomaly knowledge base.

[0054] As an optional implementation manner of the embodiment of the present invention, the receiving of raw measurement data and performing abnormality analysis on the raw measurement data according to a preset information format includes:

[0055] The correctness of filling in each field in the data format of the original measurement data is analyzed and checked to determine whether the original measurement data has the following errors: frame length error, source address error, destination address error, category code error, target number error, and conversion dimension error.

[0056] Specifically, although the data content of each type of measurement equipment is different, there are some common fields, such as source, destination, coding, information category, data length and data content. In addition to the common fields, different types of measurement and control data also have their own agreed formats. Through the unified information format agreement, the correctness of each field in the data format is automatically analyzed and checked against the information transmission specification.

[0057] The details are as follows:

[0058] 1. Frame length error

[0059] The data communication data receiving module determines that the data packet is not received due to the frame length error.

[0060] 2. The source address and destination address are incorrect.

[0061] Field data sends the original measurement and control data to the command and control system through multicast. If the destination address is wrong, the command and control system will not receive the measurement data. The wrong source address will cause the measurement data to not match the equipment and cannot be displayed normally.

[0062] 3. Category code error

[0063] After the measurement data packet enters the command and control system, it needs to be parsed according to different data categories and matching different data formats. If the category is wrong, the parsing function does not correspond to the agreed protocol, which will cause data parsing errors.

[0064] 4. Target number error

[0065] If the target number in the measurement data packet is incorrectly filled in, the parsed data will correspond to other targets, which will seriously affect subsequent processing and command decisions.

[0066] 5. Error in converting dimensions

[0067] The original measurement data received by the command and control system needs to be converted according to the agreed dimension before data processing and display. If the dimension is wrong, the parsed data will be wrong.

[0068] S2, acquiring real-time data, performing anomaly analysis on the real-time data, and obtaining a real-time anomaly processing knowledge base.

[0069] As an optional implementation of the embodiment of the present invention, the acquiring of real-time data and performing abnormal analysis on the real-time data includes:

[0070] If the real-time data is effectively tracked but the trajectory or track is not processed, analyze whether it is due to optical equipment abnormality, radar equipment abnormality or satellite navigation equipment abnormality;

[0071] If there is a result for the trajectory or track, but it is obviously inconsistent with the actual flight, analyze whether it is a position anomaly or a speed anomaly.

[0072] Specifically, when the data transmission between the field equipment and the command center is strictly in accordance with the transmission specifications, but the real-time trajectory / track processing results are abnormal, there are usually two situations: one is that the equipment tracking is displayed but there is no processing result; the other is that the trajectory / track is processed in real time, but the result is obviously inconsistent with the actual situation. The following are explained separately:

[0073] 1. The measurement data is effectively tracked, but the trajectory or track is not processed

[0074] (1) If it is an optical device, the reason for no processing results may be:

[0075] ●The angle of intersection of two stations does not meet the intersection condition (greater than 15 and less than 165)

[0076] ●The distance between different surfaces is too large and does not meet the intersection condition

[0077] ●Too many outliers in the measured data, and the data did not pass the data screening

[0078] ●The data time of the two devices is not synchronized and cannot be intersected

[0079] ●The threshold of the detection is unreasonable and exceeds the area

[0080] ●Handle abnormal software exit

[0081] (2) If it is a radar device, the reason for no processing results may be:

[0082] ●Too many outliers in the measured data, and the data did not pass the data screening

[0083] ●The measurement data time period is unstable and the time is fixed

[0084] (3) If it is a satellite navigation device, the reason for no processing results may be:

[0085] ●Too many outliers in the measured data, and the data did not pass the data screening

[0086] ●The time and frequency of the measured data are unstable

[0087] 2. The trajectory / track has some results but is obviously inconsistent with the actual flight

[0088] (1) Abnormal position

[0089] ● Mistracking of measuring equipment

[0090] ●Continuous large areas of wild values ​​appear in the measured data, and the processing results diverge

[0091] ●The measurement equipment is not tracked, the status is set to valid

[0092] (2) Abnormal speed

[0093] ●The measured data itself does not contain velocity information, so it is wrong to extrapolate the position

[0094] ●Measurement data speed value error

[0095] S3, using the abnormal events in the measurement data abnormality knowledge base and the real-time abnormality processing knowledge base as root nodes and all causes of the abnormal events as tree branches to form an inverted tree structure, thereby generating an abnormality decision tree.

[0096] Specifically, a tree structure is used to describe all the cause events, intermediate transmission events and their mutual relationships that may cause system abnormalities. The present invention takes the abnormal event as the root node and all the causes of the event as the branches of the tree to form an inverted tree structure, which are connected into a huge tree diagram to form a decision tree. According to the analysis of the charge abnormality in the previous chapter, decision trees are established for the measurement data abnormality and the real-time processing abnormality. Among them, the measurement data abnormality decision tree is as follows: Figure 2 As shown; real-time processing of abnormal decision trees as shown Figure 3 shown.

[0097] S4, converting each decision tree path in the abnormal decision tree into an expression of a production rule.

[0098] Specifically, the abnormal problem location technology designed by the present invention is designed based on the knowledge expression of production rules and decision trees. The command and control system is built into a tree structure from data reception to real-time processing of the abnormal causes, and the system structure is graded. The top level is the abnormal phenomenon conclusion, the next level is the cause of the abnormality, and the next level is the various branches of the cause of the abnormality, and so on, and the classification is carried out layer by layer until it cannot be divided.

[0099] As an optional implementation of the embodiment of the present invention, the expression of the production rule includes:

[0100] IF X THEN Y;

[0101] The production rules use AND and / or OR statements to combine two or more rules to form multiple conditions or conclusions.

[0102] Among them, production rules are used to describe knowledge with strong causal relationships. The anomaly analysis rules with causal relationships accumulated by domain experts are expressed using production rules. Each rule of the production rule has a causal relationship, and its corresponding rule expression form is:

[0103] IF X THEN Y

[0104] Production rules use AND and OR statements to combine two or more rules to form multiple conditions or conclusions. The production rule method is also called the rule-based method. It can express the judgment rules of exception analysis more intuitively and conveniently, and occupies less storage space. X is the condition and Y is the conclusion.

[0105] According to the experience of the accusation system experts, the abnormal judgment rules are connected into a decision tree to make the reasoning process fast and organized. To this end, the present invention needs to convert each decision tree path into the expression form of production rules. The judgment rule is expressed by the production method as follows:

[0106] R1: IF L! = L true THEN Information frame length is abnormal

[0107] R2: IF S! = S true THEN Information source is abnormal

[0108] R3: IF D! = D true THEN The destination is abnormal

[0109] R4: IF M! = M true THEN target number is abnormal

[0110] R5: IF B! = Btrue THEN Category code is abnormal

[0111] The present invention charges the system for real-time data processing anomalies. According to the established decision tree model, the judgment rule is expressed by a production method, which is divided into two situations: there are processing results but the results are abnormal and there are no processing results. They are expressed by production statements as follows:

[0112] 1. No results found

[0113] R1: IF the equipment is not tracked THEN there is no processing result

[0114] R2: If the equipment is an optical equipment and (the intersection angle does not meet the requirements or the distance between the two optical equipment is too large or the measured data does not pass the data check) then no processing results

[0115] R3: If the equipment is radar equipment and the measured data does not pass the data check then there is no processing result

[0116] R4: If the satellite navigation equipment and (the measurement data frequency is unstable or the measurement data does not pass the data check) then there is no processing result

[0117] R5: If real-time processing software exception then no processing result

[0118] 2. There are processing results but abnormal situations

[0119] R1: If the processing time is abnormal or the processing location is abnormal, then the processing result is abnormal

[0120] R2: If the time system is abnormal, then the processing result time is abnormal

[0121] R3: If the equipment time is abnormal then the processing result time is abnormal

[0122] R4: If the measuring equipment is mistracked then the processing result is abnormal

[0123] R5: If the processing software is abnormal, then the processing result position is abnormal

[0124] R6: If the equipment is not tracking, the status error is set to valid, then the processing result position is abnormal

[0125] R7: If the equipment has no speed value and the position extrapolation speed method is wrong, then handle the speed abnormality

[0126] R8: If the equipment speed value is wrong then handle the speed exception

[0127] During the actual joint debugging or flight process, the known abnormal or normal conclusions are used to infer the cause of the abnormality, which is the reverse reasoning process of the above rules.

[0128] The present invention adopts a fast analysis method of a decision tree to establish an abnormality judgment model for receiving and real-time processing abnormalities of the command system data, and the abnormality judgment rule base facilitates retrieval and improves reasoning efficiency.

[0129] S5, establishing a judgment rule knowledge base, obtaining an abnormal event to be analyzed, traversing the judgment rule knowledge base, and obtaining an abnormal cause of the abnormal event to be analyzed.

[0130] As an optional implementation of the embodiment of the present invention, the establishment of a judgment rule knowledge base, obtaining an abnormal event to be analyzed, traversing the judgment rule knowledge base, and the abnormal cause of the abnormal event to be analyzed includes:

[0131] In the case where the abnormal event to be analyzed is measurement data, a rule table, a rule parameter table and an abnormal phenomenon table are set, and when performing abnormal analysis, abnormality positioning is performed according to the rule table, the rule parameter table and the abnormal phenomenon table;

[0132] In the case where the abnormal event to be analyzed is real-time data, an abnormal rule dictionary is set. When performing abnormal analysis, the information of the abnormal rule dictionary is read, and the judgment rule knowledge base is queried according to the abnormal phenomenon that occurs to locate the abnormality.

[0133] Specifically, for an abnormality in the original measurement data received by the command and control system or an abnormal phenomenon in real-time data processing, reverse reasoning is first used to search for possible causes of the abnormality, and then the correctness of the inference is verified by forward reasoning of the abnormal cause. For the command and control system, which belongs to the field of emergency decision-making, the conclusions obtained by forward reasoning are not very purposeful, and it is difficult for commanders to obtain a complete and effective set of emergency decision-making plans in a short period of time; reverse reasoning is to find the premise through the conclusion, which can improve the credibility of the reasoning results. Therefore, the use of mixed reasoning can give play to the advantages of the two reasoning methods and solve problems such as weak purpose and blind target selection. Forward and reverse reasoning make the reasoning more credible.

[0134] Therefore, the design of real-time processing exception location is as follows: add the function of processing log storage to the real-time processing program, write the exception rule dictionary in each preprocessing and processing branch judgment condition analysis process, then read the dictionary information in the exception analysis module, query the rule library according to the abnormal phenomenon, and realize the location of the exception.

[0135] The principle of abnormal analysis of original measurement data is the same as above. Design rule table, rule parameter table, abnormal phenomenon table Figure 4 , Figure 5 , Figure 6 shown.

[0136] The present invention Figure 7 Taking the example, the abnormal intelligent decision-making method of the command and control system provided by the embodiment of the present invention is further explained. The present invention can also capture abnormal information, thereby issuing abnormal information warning and generating abnormal information logs; classifying and counting abnormal information; analyzing and comparing abnormal results, and locating abnormalities; and generating abnormal analysis reports based on the classified and counted abnormal information and the abnormal locating results, thereby providing an analysis report for commanders.

[0137] It can be seen that through the abnormal intelligent decision-making method for the command and control system provided by the present invention, the thinking logic of abnormal judgment of the command and control system during the target flight accumulated by professionals over the years is used to establish a real-time processing of abnormalities and equipment measurement data abnormality knowledge base, form an abnormal analysis model based on the rule base, establish an abnormal decision tree, and use production rules to express it as knowledge that can be recognized by the computer to form a judgment rule knowledge base. During the target flight, the rule base is traversed according to the abnormal phenomena, and the cause of the data abnormality is inferred, thereby realizing rapid intelligent analysis of the command and control system processing abnormalities and equipment measurement data transmission abnormalities, overcoming the subjectivity and limitations of manual analysis, and improving the intelligence and reliability of abnormal problem judgment of the command and control system.

[0138] Figure 8The structure diagram of the abnormal intelligent decision-making device of the command and control system provided by the embodiment of the present invention is shown. The abnormal intelligent decision-making device of the command and control system applies the above method. The following is only a brief description of the structure of the abnormal intelligent decision-making device of the command and control system. For other matters not covered, please refer to the relevant description in the abnormal intelligent decision-making method of the command and control system. Figure 8 The abnormal intelligent decision-making device of the command and control system provided by the embodiment of the present invention includes:

[0139] A first analysis module is used to receive raw measurement data, perform anomaly analysis on the raw measurement data according to a preset information format, and obtain a measurement data anomaly knowledge base;

[0140] The second analysis module is used to obtain real-time data, perform anomaly analysis on the real-time data, and obtain a real-time anomaly processing knowledge base;

[0141] A generating module, configured to generate an abnormal decision tree by taking the abnormal events in the measurement data abnormality knowledge base and the real-time abnormality processing knowledge base as root nodes and all the causes of the abnormal events as branches of the tree to form an inverted tree structure;

[0142] A conversion module, used for converting each decision tree path in the abnormal decision tree into an expression of a production rule;

[0143] The abnormal analysis module is used to establish a judgment rule knowledge base, obtain abnormal events to be analyzed, traverse the judgment rule knowledge base, and obtain the abnormal causes of the abnormal events to be analyzed.

[0144] As an optional implementation manner of the embodiment of the present invention, the first analysis module receives the original measurement data in the following manner, and performs abnormality analysis on the original measurement data according to a preset information format:

[0145] The correctness of filling in each field in the data format of the original measurement data is analyzed and checked to determine whether the original measurement data has the following errors: frame length error, source address error, destination address error, category code error, target number error, and conversion dimension error.

[0146] As an optional implementation of the embodiment of the present invention, the second analysis module obtains real-time data and performs abnormal analysis on the real-time data in the following manner:

[0147] If the real-time data is effectively tracked but the trajectory or track is not processed, analyze whether it is due to optical equipment abnormality, radar equipment abnormality or satellite navigation equipment abnormality;

[0148] If there is a result for the trajectory or track, but it is obviously inconsistent with the actual flight, analyze whether it is a position anomaly or a speed anomaly.

[0149] As an optional implementation of the embodiment of the present invention, the abnormal analysis module establishes a judgment rule knowledge base in the following manner, obtains the abnormal event to be analyzed, traverses the judgment rule knowledge base, and finds the abnormal cause of the abnormal event to be analyzed:

[0150] In the case where the abnormal event to be analyzed is measurement data, a rule table, a rule parameter table and an abnormal phenomenon table are set, and when performing abnormal analysis, abnormality positioning is performed according to the rule table, the rule parameter table and the abnormal phenomenon table;

[0151] In the case where the abnormal event to be analyzed is real-time data, an abnormal rule dictionary is set. When performing abnormal analysis, the information of the abnormal rule dictionary is read, and the judgment rule knowledge base is queried according to the abnormal phenomenon that occurs to locate the abnormality.

[0152] As an optional implementation of the embodiment of the present invention, the expression of the production rule includes:

[0153] IF X THEN Y;

[0154] The production rules use AND and / or OR statements to combine two or more rules to form multiple conditions or conclusions.

[0155] It can be seen that through the abnormal intelligent decision-making device for the command and control system provided by the present invention, the thinking logic of abnormal judgment of the command and control system during the target flight accumulated by professionals over the years is used to establish a real-time processing of abnormalities and equipment measurement data abnormality knowledge base, form an abnormal analysis model based on the rule base, establish an abnormal decision tree, and use production rules to express it as knowledge that can be recognized by the computer to form a judgment rule knowledge base. During the target flight, the rule base is traversed according to the abnormal phenomena, and the cause of the data abnormality is inferred, thereby realizing rapid intelligent analysis of the command and control system processing abnormalities and equipment measurement data transmission abnormalities, overcoming the subjectivity and limitations of manual analysis, and improving the intelligence and reliability of abnormal problem judgment of the command and control system.

[0156] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. An abnormal intelligent decision-making method for a command and control system, characterized in that: include: Receiving original measurement data, and performing anomaly analysis on the original measurement data according to a preset information format to obtain a measurement data anomaly knowledge base; Acquire real-time data, perform anomaly analysis on the real-time data, and obtain a real-time anomaly processing knowledge base; An abnormal event in the measurement data abnormality knowledge base and the real-time abnormality processing knowledge base is used as a root node, and all causes of the abnormal event are used as branches of the tree to form an inverted tree structure, thereby generating an abnormality decision tree; Convert each decision tree path in the abnormal decision tree into an expression of a production rule; A judgment rule knowledge base is established, an abnormal event to be analyzed is obtained, the judgment rule knowledge base is traversed, and the abnormal cause of the abnormal event to be analyzed is obtained.

2. The method according to claim 1, characterized in that The receiving of raw measurement data and performing abnormality analysis on the raw measurement data according to a preset information format comprises: The correctness of filling in each field in the data format of the original measurement data is analyzed and checked to determine whether the original measurement data has the following errors: frame length error, source address error, destination address error, category code error, target number error, and conversion dimension error.

3. The method according to claim 2, characterized in that The acquiring of real-time data and performing abnormal analysis on the real-time data comprises: If the real-time data is effectively tracked but the trajectory or track is not processed, analyze whether it is due to optical equipment abnormality, radar equipment abnormality or satellite navigation equipment abnormality; If there is a result for the trajectory or track, but it is obviously inconsistent with the actual flight, analyze whether it is a position anomaly or a speed anomaly.

4. The method according to claim 3, characterized in that The determination rule knowledge base is established, the abnormal event to be analyzed is obtained, the determination rule knowledge base is traversed, and the abnormal cause of the abnormal event to be analyzed includes: In the case where the abnormal event to be analyzed is measurement data, a rule table, a rule parameter table and an abnormal phenomenon table are set, and when performing abnormal analysis, abnormality positioning is performed according to the rule table, the rule parameter table and the abnormal phenomenon table; In the case where the abnormal event to be analyzed is real-time data, an abnormal rule dictionary is set. When performing abnormal analysis, the information of the abnormal rule dictionary is read, and the judgment rule knowledge base is queried according to the abnormal phenomenon that occurs to locate the abnormality.

5. The method according to claim 4, characterized in that The expression of the production rule includes: IF X THEN Y; The production rules use AND and / or OR statements to combine two or more rules to form multiple conditions or conclusions.

6. An abnormal intelligent decision-making device for a command and control system, characterized in that: include: A first analysis module is used to receive raw measurement data, perform anomaly analysis on the raw measurement data according to a preset information format, and obtain a measurement data anomaly knowledge base; The second analysis module is used to obtain real-time data, perform anomaly analysis on the real-time data, and obtain a real-time anomaly processing knowledge base; A generating module, configured to generate an abnormal decision tree by taking the abnormal events in the measurement data abnormality knowledge base and the real-time abnormality processing knowledge base as root nodes and all the causes of the abnormal events as branches of the tree to form an inverted tree structure; A conversion module, used for converting each decision tree path in the abnormal decision tree into an expression of a production rule; The abnormal analysis module is used to establish a judgment rule knowledge base, obtain abnormal events to be analyzed, traverse the judgment rule knowledge base, and obtain the abnormal causes of the abnormal events to be analyzed.

7. The device according to claim 6, characterized in that The first analysis module receives the original measurement data in the following manner and performs abnormal analysis on the original measurement data according to a preset information format: The correctness of filling in each field in the data format of the original measurement data is analyzed and checked to determine whether the original measurement data has the following errors: frame length error, source address error, destination address error, category code error, target number error, and conversion dimension error.

8. The device according to claim 7, characterized in that The second analysis module obtains real-time data and performs abnormal analysis on the real-time data in the following manner: If the real-time data is effectively tracked but the trajectory or track is not processed, analyze whether it is due to optical equipment abnormality, radar equipment abnormality or satellite navigation equipment abnormality; If there is a result for the trajectory or track, but it is obviously inconsistent with the actual flight, analyze whether it is a position anomaly or a speed anomaly.

9. The device according to claim 8, characterized in that The abnormal analysis module establishes a judgment rule knowledge base in the following manner, obtains the abnormal event to be analyzed, traverses the judgment rule knowledge base, and finds the abnormal cause of the abnormal event to be analyzed: In the case where the abnormal event to be analyzed is measurement data, a rule table, a rule parameter table and an abnormal phenomenon table are set, and when performing abnormal analysis, abnormality positioning is performed according to the rule table, the rule parameter table and the abnormal phenomenon table; In the case where the abnormal event to be analyzed is real-time data, an abnormal rule dictionary is set. When performing abnormal analysis, the information of the abnormal rule dictionary is read, and the judgment rule knowledge base is queried according to the abnormal phenomenon that occurs to locate the abnormality.

10. The device according to claim 9, characterized in that The expression of the production rule includes: IF X THEN Y; The production rules use AND and / or OR statements to combine two or more rules to form multiple conditions or conclusions.

Images