Fuzzy reasoning-based rule base construction method for aircraft and unmanned aerial vehicle control
By fuzzy partitioning of input and output variables in aircraft and drone control, building the rule front and back matrix, the problem of name conflicts in the rule base variables and confusing inference results in the existing technology is solved, and the rule base is realized Completeness and correctness of reasoning results.
Patent Information
- Application Number
- CN202411175726.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-11-26
AI Technical Summary
In the control of aircraft and drone, the existing fuzzy inference system has caused conflicts in variable names and confusing inference results, and even contradictory problems.
By fuzzy partitioning of input and output variables, a rule prepart and rule backpart matrix is constructed, and a complete rule library is obtained to avoid variable name conflicts and confusion in inference results.
It realizes the completeness of the rule base and the comprehensiveness of information, ensures the correctness of the inference results, and avoids conflicts and contradictions between rules.
Smart Images

Figure CN119024701A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of intelligent control of aircraft and unmanned aerial vehicles, and specifically relates to a method for constructing a rule base based on fuzzy reasoning for aircraft and unmanned aerial vehicle control. Background Art
[0002] As artificial intelligence technology becomes increasingly mature, it has gradually been applied to aircraft and UAV control. Among them, the fuzzy reasoning algorithm, which is highly similar to the human reasoning process, is currently the most widely used autonomous decision-making algorithm. It uses aircraft situation information as input and outputs control strategies to control aircraft and UAVs.
[0003] With the development of modern avionics technology, more and more variables need to be considered in model input, the decision-making process is becoming more and more complicated, the complexity of fuzzy reasoning systems is increasing, the number of rules and their sources are increasing, and existing fuzzy reasoning systems often fill in the rule base directly based on human experience. The rule base often mixes a large number of rules filled in by different experts from different eras, and there are often conflicts in variable names between different fuzzy reasoning rules, and confusing or even contradictory reasoning results.
[0004] This application is proposed in view of the above-mentioned technical defects. Summary of the invention
[0005] The purpose of this application is to provide a method for constructing a rule base based on fuzzy reasoning for aircraft and unmanned aerial vehicle control, so as to overcome or alleviate at least one of the known technical defects.
[0006] The technical solution of this application is:
[0007] A method for constructing a rule base for aircraft and unmanned aerial vehicle control based on fuzzy reasoning, comprising:
[0008] Rule precondition construction steps:
[0009] Perform fuzzy partitioning on each input variable;
[0010] Combine the fuzzy partitions of each input variable to construct a rule antecedent matrix. Each row of the rule antecedent matrix is a fuzzy partition combination of an input variable, representing a rule antecedent.
[0011] Steps to build rule post-processing:
[0012] Perform fuzzy partitioning on each output variable;
[0013] For each output variable, a rule consequent matrix is constructed based on its fuzzy partition. Each element in the rule consequent matrix represents a rule consequent.
[0014] Steps to build a rule base:
[0015] For each output variable, fill in the corresponding elements in the rule consequent matrix into the rule antecedent matrix to obtain the rule base of the fuzzy partition output of each output variable.
[0016] According to at least one embodiment of the present application, in the above-mentioned method for constructing a rule base for aircraft and drone control based on fuzzy reasoning, the input variable is situation information.
[0017] According to at least one embodiment of the present application, in the above-mentioned method for constructing a rule base for aircraft and drone control based on fuzzy reasoning, the input variables specifically include altitude, speed, and angle.
[0018] According to at least one embodiment of the present application, in the above-mentioned aircraft and drone control rule base construction method based on fuzzy reasoning, the output variables specifically include threat level, left turn, and right turn.
[0019] According to at least one embodiment of the present application, in the above-mentioned method for constructing a rule base based on fuzzy reasoning for aircraft and drone control, the rule consequent matrix is a column vector corresponding to each row of the rule antecedent matrix;
[0020] After adding the row elements in the rule consequent matrix of each output variable to each row of the rule antecedent matrix, the rule base of the fuzzy partition output of its output variable is obtained.
[0021] This application has at least the following beneficial technical effects:
[0022] A method for constructing a rule base based on fuzzy reasoning for aircraft and unmanned aerial vehicle control is provided. The input variables and their output variables are sorted out, fuzzy partitioning is performed, and a complete rule antecedent matrix and a rule consequent matrix are constructed and merged. The rule base of the fuzzy partition output of each input variable and output variable can be obtained in turn. The complete rule base can be quickly constructed, including a complete rule set that does not contradict all reasoning results. The complete rule set is stored and arranged for easy inspection. The completeness of the fuzzy reasoning system rules, the comprehensiveness of information and the correctness of reasoning can be guaranteed to a great extent, and the conflict of variable names between fuzzy reasoning rules, and the confusion or even contradiction of reasoning results can be avoided. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 It is a schematic diagram of a method for constructing a rule base based on fuzzy reasoning for aircraft and UAV control provided in an embodiment of the present application.
[0024] In order to better illustrate the present embodiment, some contents of the drawings may be omitted, which is only used for illustrative purposes and should not be construed as limiting the present application. DETAILED DESCRIPTION
[0025] In order to make the technical solution and advantages of the present application clearer, the technical solution of the present application will be described in further detail in detail and in detail with reference to the accompanying drawings. It can be understood that the specific embodiments described here are only partial embodiments of the present application, which are only used to explain the present application, not to limit the present application. It should be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, and other related parts can refer to the general design.
[0026] In addition, unless otherwise defined, the technical terms or scientific terms used in the description of this application shall have the usual meanings understood by those of ordinary skill in the art to which this application belongs. The words used in the description of this application to indicate orientation are only used to indicate relative directions or positional relationships. When the absolute position of the described object changes, its relative positional relationship may also change accordingly. The word "include" used in the description of this application indicates that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, but does not exclude other elements or objects.
[0027] A rule base construction method for aircraft and UAV control based on fuzzy reasoning, such as Figure 1 shown.
[0028] Rule precondition construction steps:
[0029] Fuzzy partition is performed on each input variable, and the input variables may specifically include situation information such as height, speed, and angle.
[0030] When there are n input variables, each input variable can be divided into m fuzzy partitions, with A ij represents the j-th fuzzy partition of the ith input variable.
[0031] Combine the fuzzy partitions of each input variable to construct a rule antecedent matrix. Each row of the rule antecedent matrix is a fuzzy partition combination of an input variable, representing a rule antecedent. The number of rule antecedents is m. n The data structure is simple and can be more easily received by the computer without losing the rule information.
[0032] In a specific example, the design-related implementation code is as follows:
[0033] The fuzzy partition of each input variable is represented as a two-dimensional list var_pool, where each row is a sublist of the list var_pool:
[0034] var_pool = [[A 11 ,A 12 ,…,A 1m ],[A 21 ,A 22 ,…,A2m ],…,[A n1 ,A n2 ,…,A nm ]];
[0035] Initialize an expandable list array:
[0036] array = [[]];
[0037] Execute the following loop to combine the fuzzy partitions of each input variable in the list array: for var in var_pool do: for i in array:
[0038] for j in var:
[0039] array=[i+[j]]
[0040]
[0041] Steps to build rule post-processing:
[0042] Each output variable is fuzzily partitioned, and the output variable may specifically include threat level, left turn, right turn and other control-related information.
[0043] For each output variable, a rule consequent matrix is constructed based on its fuzzy partition. Each element in the rule consequent matrix represents a rule consequent.
[0044] When there are l output variables, the kth output variable is y k , and fuzzy partition it into B k1 ,B k2 ,….
[0045] The regular consequent matrix is a column vector corresponding to each row of the regular antecedent matrix, with m n When a row condition in the rule antecedent matrix is met, the row element in the rule consequent matrix is taken. The corresponding relationship is determined by the domain experts.
[0046] Steps to build a rule base:
[0047] For each output variable, the corresponding elements in the rule consequent matrix are filled into the rule antecedent matrix to obtain the rule base of the fuzzy partition output of each output variable.
[0048] After adding the row elements in the rule consequent matrix of each output variable to each row of the rule antecedent matrix, the rule base of the fuzzy partition output of the output variable is obtained. For the k-th output variable, the following implementation code is designed: for i∈{0,1,2,…,m n},do:
[0049] complete_decision_matrix[i]=[array[i],B k_ ];
[0050] The rule base for the fuzzy partition output of the kth output variable is as follows:
[0051]
[0052] In a specific example, the input variables are height x1, speed x2, angle x3, and the output variable is the threat level. Based on the above-disclosed rule base construction method for aircraft and drone control based on fuzzy reasoning, the rule base is constructed as follows:
[0053] For x1, x2, and x3, we divide x1 into three fuzzy partitions on the domain, from small to large: low a1, medium a2, and high a3; x2 is divided into three fuzzy partitions on the domain, from small to large: slow b1, medium b2, and fast b3; x3 is divided into three fuzzy partitions on the domain, from small to large: small c1, medium c2, and large c3. We have var_pool = [[a1,a2,a3], [b1,b2,b3], [c1,c2,c3]], and the rule antecedent matrix is constructed as follows:
[0054]
[0055] The output variables are fuzzy partitioned into weak threat, moderate threat, and high threat, and a rule consequence matrix is constructed. Then, after filling in the corresponding rows of the rule antecedent matrix, a rule base for fuzzy partition output of threat degree is obtained.
[0056] In the rule base construction method for aircraft and unmanned aerial vehicle control based on fuzzy reasoning disclosed in the above-mentioned embodiment, the input variables and their output variables are sorted out, fuzzy partitioning is performed, and a complete rule antecedent matrix and a rule consequent matrix are constructed and merged, so that the rule base of the fuzzy partition output of each input variable and output variable can be obtained in turn, and a complete rule base can be quickly constructed, which contains a complete rule set that does not contradict all reasoning results, and is stored and arranged for easy inspection. It can ensure the completeness of the fuzzy reasoning system rules, the comprehensiveness of information and the correctness of reasoning to a great extent, and avoid the occurrence of variable name conflicts between fuzzy reasoning rules, and confusing or even contradictory reasoning results.
[0057] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. Those skilled in the art should understand that the scope of protection of the present application is obviously not limited to these specific embodiments. Without departing from the principles of the present application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the scope of protection of the present application.
Claims
1. A method for constructing a rule base based on fuzzy reasoning for aircraft and unmanned aerial vehicle control, characterized in that: include: Rule precondition construction steps: Perform fuzzy partitioning on each input variable; Combine the fuzzy partitions of each input variable to construct a rule antecedent matrix. Each row of the rule antecedent matrix is a fuzzy partition combination of an input variable, representing a rule antecedent. Steps to build rule post-processing: Perform fuzzy partitioning on each output variable; For each output variable, a rule consequent matrix is constructed based on its fuzzy partition. Each element in the rule consequent matrix represents a rule consequent. Steps to build a rule base: For each output variable, fill in the corresponding elements in the rule consequent matrix into the rule antecedent matrix to obtain the rule base of the fuzzy partition output of each output variable.
2. The method for constructing a rule base based on fuzzy reasoning for aircraft and unmanned aerial vehicle control according to claim 1 is characterized in that: The input variable is situation information.
3. The method for constructing a rule base based on fuzzy reasoning for aircraft and unmanned aerial vehicle control according to claim 2 is characterized in that: The input variables specifically include height, speed, and angle.
4. The method for constructing a rule base based on fuzzy reasoning for aircraft and unmanned aerial vehicle control according to claim 3 is characterized in that: The output variables specifically include threat level, left turn, and right turn.
5. The method for constructing a rule base based on fuzzy reasoning for aircraft and unmanned aerial vehicle control according to claim 1 is characterized in that: The regular consequent matrix is a column vector corresponding to each row of the regular antecedent matrix; After adding the row elements in the rule consequent matrix of each output variable to each row of the rule antecedent matrix, the rule base of the fuzzy partition output of its output variable is obtained.
