Evaluation method and device for survivability of unmanned maritime systems based on complex networks

Abstract

The present invention provides a method and device for evaluating the survivability of unmanned marine systems based on complex networks. The method comprises: A, judging whether all typical survival models A in the survival situation diagram of the current j-layer system are δ Indicates that they all exist in the situation diagram. If they exist, go to B. If they do not exist, record the first stage identification stop layer information as γ layer and go to C. B, according to A δ Perform model recognition and extraction on the survival situation diagram of the j-layer system, extract the recognition results to the j+1 layer, and return A; C, determine whether there is one or several A in the survival situation diagram of the current γ+k layer system δ If it exists, go to D. If it does not exist, record the number of layers increased by the second-stage recognition stop layer γ+k relative to the first-stage stop layer γ as the second-stage recognition layer number information β and go to E. D, according to A δ Perform model recognition and extraction on the survival situation diagram of the γ+k layer system, extract the recognition result to the γ+(k+1) layer, and return it to C; E to obtain the system survivability assessment result W.

Description

Technical Field

[0001] The present invention relates to technical fields such as big data, system science, and system warfare, and in particular to the assessment of the survivability of unmanned attack weapon systems at sea. Background Art

[0002] With the gradual improvement of main battle equipment capabilities and the development and gradual improvement of communication link technology, system-based warfare is becoming a major trend in future warfare. In past wars, the combat capabilities of individual equipment were primarily assessed. In future wars, however, platform-based, information-based, and system-based warfare will increasingly dominate the battlefield. Therefore, how to effectively assess system survivability will become a key issue for breakthroughs in future warfare. Summary of the Invention

[0003] In order to solve the problems existing in the existing survivability assessment methods, the present invention proposes a complex network-based survivability assessment method for unmanned maritime systems, which is implemented using electronic equipment with computing capabilities. The method includes:

[0004] Step A: Determine whether all the typical survival models A defined before evaluation exist in the survival situation diagram of the current j-th layer system. δ If it exists, go to step B; if it does not exist, record the first stage identification stop layer information as γ layers and go to step C, where j and γ are both integers and greater than or equal to 1;

[0005] Step B, according to the typical survival model A δ Perform model recognition and extraction on the survival situation diagram of the j-layer system, and extract the recognition results to the j+1 layer; take the j+1 layer as the current j layer and return to step A;

[0006] Step C: Determine whether there is one or several typical survival models A in the survival situation diagram of the current γ+k-th layer system. δ If it exists, proceed to step D; if it does not exist, record the number of layers γ+k of the second-stage identification stop layer increased relative to the first-stage stop layer γ as the second-stage identification layer number information β and proceed to step E, where k and β are both integers and greater than or equal to 1;

[0007] Step D, according to the canonical survival model A δ Perform model recognition and extraction on the survival situation diagram of the γ+k layer system, and extract the recognition results to the γ+(k+1) layer; use the γ+(k+1) layer as the current γ+k layer and return to step C;

[0008] Step E, based on the first stage identification layer number information γ, the second stage identification layer number information β, and the typical survival model A δ , the capability base of typical models The basic assessment coefficient R1 of the first-level survivability (hereinafter referred to as the basic assessment coefficient, R1>1), the basic capability adjustment coefficient Δw and other information are used to finally obtain the system survivability assessment result W;

[0009] Among them, step A and step B complete the first stage of situation map recognition, and step C and step D complete the situation map for the second stage of recognition.

[0010] Step A may further include:

[0011] Step A1: Determine the current identification layer j information, according to the typical survival model A set before identification δ The identification rule confirms whether all typical survival models A δ All exist in the current layer;

[0012] Step A2: If all typical survival models A are confirmed in step A1 δ All exist in the current layer and go to step B; if all typical survival models A are confirmed in step A1 δ If none of them exist in the current layer, go to step C.

[0013] Step B may further include:

[0014] Step B1: According to different typical survival models A δ And the corresponding identification rules are used to identify the current j-layer situation map. Each point can be identified by the typical survival model A δ Repeated identification and use of the typical survival model A identified in this layer δ The physical centers of all the included monomers are extracted as identification points into the j+1 layer until all the typical survival models in the layer are identified and extracted;

[0015] Step B2: All the typical survival models A in step B1 δ The physical center identification point is displayed in j+1, and the other points are not displayed in the j+1 layer, forming the j+1 layer situation map;

[0016] Step B3: Let j = j + 1, take the j + 1 layer as the current j layer, and return to step A.

[0017] Step C may further include: Step C1: Determine the current identification layer γ+k information, according to the typical survival model A δ Identification rules confirm whether there is a typical survival model A δ In the current layer;

[0018] Step C2: If the typical survival model A is confirmed in step C1 δ In the current layer, go to step D; if it is confirmed in step C1 that there is no typical survival model Aδ If it exists in the current layer, go to step E.

[0019] Step D may further include:

[0020] Step D1: According to different typical survival models A δ The corresponding identification rules are used to identify the current γ+k layer situation map. Each point can be identified by the typical survival model A δ Repeated identification and use of the typical survival model A identified in this layer δ The physical centers of all the monomers contained are extracted as identification points into the γ+(k+1) layer until all the typical survival models in this layer are identified and extracted;

[0021] Step D2: All the typical survival models A in step D1 δ The physical center identification point is displayed in γ+(k+1), and the other points are not displayed in the γ+(k+1) layer, forming the γ+(k+1) layer situation map;

[0022] Step D3: Let k=k+1, take the γ+(k+1) layer as the current γ+k layer, and return to step C.

[0023] Step E may further include:

[0024] Step E1: According to the first stage, the number of layers γ and the lth typical survival model A δl Capacity base Basic evaluation coefficient R1, comprehensive evaluation of the survivability W of the i-th layer from the first layer to the γ-th layer i ;

[0025] First, the first typical survival model A δl The survivability at layer i is calculated as:

[0026]

[0027] in, represents the lth typical survival model A in the i-th transition layer δl The viability of (α Al ) i Represents the lth typical survival model A δl Capacity base to the power of i, Represents the lth typical survival model A in the i-th transition layer δl the number of

[0028] Then according to Evaluate the survivability W of the i-th transition layer i :

[0029]

[0030] Among them, R i is the comprehensive evaluation coefficient of the i-th transition layer, and the coefficient is calculated as R i =(R1) i , δ1 is the typical survival model A of the i-th transition layer δ The sum of the types;

[0031] Step E2: Based on the number of layers β identified in the second stage and combined with the relevant information in step E1, the survival capacity W of the second stage stop layer, i.e. the γ+β layer, is calculated. γ+β Conduct assessments;

[0032] First, the sth typical survival model A δs The survivability in the γ+β layer is calculated:

[0033]

[0034] in, represents the sth typical survival model A in the γ+β transition layer δs The ability to survive, Represents the sth typical survival model A δs Capacity base to the power of γ+m, represents the sth typical survival model A in the γ+β transition layer δS the number of

[0035] Then according to The survivability W of the γ+β transition layer is evaluated using a formula similar to formula (2). γ+β :

[0036]

[0037] Among them, R γ+β is the comprehensive evaluation coefficient of the γ+β transition layer, and the coefficient calculation method is R γ+β =(R1) γ+β , δ2 is the typical survival model A of the γ+β transition layer δ The sum of the types;

[0038] Step E3: Finally, based on the survivability of the first layer to the γth layer and the γth + βth layer obtained in steps E1 and E2, a comprehensive evaluation calculation can be performed to obtain the final system survivability evaluation result W:

[0039]

[0040] The present invention also provides a complex network-based unmanned marine system survivability assessment device, which is implemented using an electronic device with computing capabilities. The device includes:

[0041] The first judgment module determines whether all the typical survival models A defined before the evaluation are in the survival situation diagram of the current j-layer system. δ All exist in the situation diagram, where j is an integer greater than or equal to 1;

[0042] The first recognition module, when the judgment result of the first judgment module is existence, according to the typical survival model A δ Perform model recognition and extraction on the survival situation diagram of the j-layer system, and extract the recognition results to the j+1 layer; take the j+1 layer as the current j layer and return to the first judgment module;

[0043] The first recording module: when the judgment result of the first judgment module is negative, the first stage identification stopping layer information is recorded as γ layers, and the second judgment module is entered, where γ is an integer greater than or equal to 1;

[0044] The second judgment module determines whether there is one or several typical survival models A in the survival situation diagram of the current γ+k layer system. δ ;

[0045] The second recognition module, when the judgment result of the second judgment module is yes, according to the typical survival model A δ Perform model recognition and extraction on the survival situation diagram of the γ+k layer system, and extract the recognition results to the γ+(k+1) layer; use the γ+(k+1) layer as the current γ+k layer and return to the second judgment module, where k is an integer greater than or equal to 1;

[0046] A second recording module, when the result of the second judgment module is negative, records the number of layers increased by the second-stage identification stop layer number γ+k relative to the first-stage stopping layer number γ as the second-stage identification layer number information β and enters the information into the system survivability assessment module, where β is an integer greater than or equal to 1;

[0047] The system survivability assessment module is based on the first-stage identification layer number information γ, the second-stage identification layer number information β, and the typical survival model A δ , the capacity base of each typical model The basic assessment coefficient R1 of the first-level survivability, the basic capability adjustment coefficient Δw and other information are used to finally obtain the system survivability assessment result W;

[0048] The first judgment module and the first recognition module complete the first stage of situation map recognition, and the second judgment module and the second recognition module complete the second stage of situation map recognition.

[0049] Furthermore, the system survivability assessment module may further include the following submodules:

[0050] The first survivability evaluation submodule is based on the first stage identification layer number γ, the lth typical survival model A δl Capacity base Basic evaluation coefficient R1, comprehensive evaluation of the survivability W of the i-th layer from the first layer to the γ-th layer i ;

[0051] First, the first typical survival model A δl The survivability at layer i is calculated as:

[0052]

[0053] in, Represents the lth typical survival model A in the i-th transition layer δl The viability of (α Al ) i Represents the lth typical survival model A δl Capacity base to the power of i, Represents the lth typical survival model A in the i-th transition layer δl the number of

[0054] Then according to Evaluate the survivability W of the i-th transition layer i :

[0055]

[0056] Among them, R i is the comprehensive evaluation coefficient of the i-th transition layer, and the coefficient is calculated as R i =(R1) i , δ1 is the typical survival model A of the i-th transition layer δ The sum of the types;

[0057] The second survivability evaluation submodule, based on the second stage identification layer number β and combined with the relevant information in step E1, evaluates the survivability W of the second stage stop layer, i.e., the γ+β layer. γ+β Conduct assessments;

[0058] First, the sth typical survival model A δs The survivability in the γ+β layer is calculated:

[0059]

[0060] in, represents the sth typical survival model A in the γ+β transition layer δs The ability to survive, Represents the sth typical survival model A δs Capacity base to the power of γ+m, represents the sth typical survival model A in the γ+β transition layer δS the number of

[0061] Then according to The survivability W of the γ+β transition layer is evaluated using a formula similar to formula (2). γ+β :

[0062]

[0063] Among them, R γ+β is the comprehensive evaluation coefficient of the γ+β transition layer, and the coefficient calculation method is R γ+β =(R1) γ+β , δ2 is the typical survival model A of the γ+β transition layer δ The sum of the types;

[0064] The system survivability comprehensive evaluation submodule, based on the survivability of the first to γth layers and the γth + βth layers obtained in the first survivability evaluation submodule and the second survivability evaluation submodule, comprehensively evaluates and calculates the final system survivability evaluation result W:

[0065]

[0066] The present invention also provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps in the above-mentioned evaluation method are implemented.

[0067] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps in the above-mentioned evaluation method are implemented.

[0068] According to the above solution of the present invention, the present invention can achieve the following technical effects:

[0069] 1. Good data foundation: This invention proposes a typical survival model and applies the graph recognition method to effectively achieve the purpose of abstracting the actual survival situation, laying a good foundation for subsequent evaluation and analysis.

[0070] 2. Strong operability: The present invention effectively simplifies complex problems by analyzing them layer by layer and finally synthesizing them, which significantly reduces the complexity of the overall analysis process and makes it highly operable.

[0071] 3. High objectivity: The present invention analyzes the survival situation diagram during the analysis process, and rarely uses methods such as expert judgment, so that the final result is more objective.

[0072] 4. High credibility: Since the analysis of the present invention is based on a good data foundation and has good objectivity during the analysis process, its analysis results have higher credibility.

[0073] In summary, this complex network-based system survivability assessment method can be used to evaluate system survivability and make up for the shortcomings of existing assessment methods.

[0074] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 Flow chart of the evaluation method according to the present invention

[0076] Figure 2 The situation distribution map according to the present invention

[0077] Figure 3 The A1 capability model according to the present invention

[0078] Figure 4 The A2 capability model according to the present invention

[0079] Figure 5 For the layer 2 network according to the present invention

[0080] Figure 6 For the layer 3 network according to the present invention

[0081] Figure 7 For the Layer 4 network according to the present invention

[0082] Figure 8 Schematic diagram of the evaluation device according to the present invention

[0083] Figure 9 Basic structure diagram of electronic equipment for implementing the present invention DETAILED DESCRIPTION

[0084] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention, in conjunction with the accompanying drawings. It should be understood that the embodiments described are only some of the embodiments of the present invention, and not all of them. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the present invention, its application, or use.

[0085] Complex networks are a common method for analyzing the state of complex cyber-physical systems. By abstracting, modeling, and identifying complex systems, they can effectively analyze complex physical systems. The application of complex networks offers a more comprehensive perspective than other methods. Existing common analysis methods primarily focus on localized analysis or analyze the system after decomposition. These methods are unable to adequately describe and analyze the overall state of the global network. Complex network-based methods are designed to address these shortcomings.

[0086] The analysis method based on complex networks pays more attention to the coupling, connection and interaction relationships between various systems and modules. This method is a holistic evaluation through global analysis and solution. It is an evaluation method from the whole to the part and then back to the whole. Therefore, this method has natural superiority and accuracy for the analysis of systematic and complex systems.

[0087] Combining complex systems methods with the problem of system survivability assessment is a promising approach to addressing current challenges. By first abstracting the system model to determine its current survivability, then gradually assessing the system's survivability through layer-by-layer abstract analysis, and finally comprehensively evaluating the survivability assessment results at different layers to reach a final conclusion, this process effectively moves from the overall to the local and then back to the overall, ensuring the accuracy and objectivity of the analysis results.

[0088] The thinking and analysis methods of complex networks provide scientific and rigorous thinking and analysis methods, and provide a good prescription for the assessment of system survivability. By combining methods and technologies such as graph recognition and big data, the goal of objective analysis and accurate results is achieved, truly starting from the actual situation and achieving the goal of objectivity and rigor.

[0089] Based on this, the present invention proposes a method for evaluating the survivability of unmanned attack weapon systems at sea based on complex networks.

[0090] The complex network-based system survivability evaluation method of the present invention is implemented by an electronic device with computing capabilities, completes the situation map recognition in two stages, and comprehensively evaluates the recognition results obtained in the two stages to finally obtain the system survivability evaluation result. Figure 1 The following is a flow chart of the evaluation method of the survivability of unmanned attack weapon systems at sea based on complex networks. Figure 1 As shown, the method includes the following steps:

[0091] Step A: Determine whether all the typical survival models (or capabilities, A) defined before the evaluation exist in the survival situation diagram of the current j-th layer system. δIf it exists, go to step B; if it does not exist, record the first stage identification stop layer information as γ layers and go to step C, where j and γ are both integers and greater than or equal to 1;

[0092] Step B, according to the typical survival model A δ Perform model recognition and extraction on the survival situation diagram of the j-layer system, and extract the recognition results to the j+1 layer; take the j+1 layer as the current j layer and return to step A;

[0093] Step C: Determine whether there is one or several typical survival models A in the survival situation diagram of the current γ+k-th layer system. δ If it exists, proceed to step D; if it does not exist, record the number of layers γ+k of the second-stage identification stop layer increased relative to the first-stage stop layer γ as the second-stage identification layer number information β and proceed to step E, where k and β are both integers and greater than or equal to 1;

[0094] Step D, according to the canonical survival model A δ Perform model recognition and extraction on the survival situation diagram of the γ+k layer system, and extract the recognition results to the γ+(k+1) layer; use the γ+(k+1) layer as the current γ+k layer and return to step C;

[0095] Step E, based on the first stage identification layer number information γ, the second stage identification layer number information β, and the typical survival model A δ , the capability base of typical models The basic assessment coefficient R1 of the first-level survivability (hereinafter referred to as the basic assessment coefficient, R1>1), the basic capability adjustment coefficient Δw and other information are finally obtained to obtain the system survivability assessment result W.

[0096] In the above steps, steps A and B complete the first phase of situation map identification, steps C and D complete the situation map for the second phase of identification, and step E conducts a comprehensive evaluation of the identification results of the four steps in the two phases, ultimately obtaining the system survivability assessment results. Through these steps, a complex network-based system survivability assessment can be achieved, achieving intelligent and data-based assessment results. This addresses the practical problems of existing assessment methods, such as inauthentic analysis sources, poor operability, strong reliance on subjective experience, and low credibility.

[0097] Among them, the step A states "determine whether all the typical survival models (or capabilities, A) defined before the evaluation exist in the survival situation diagram of the current j-th layer system δIf it exists, go to step B; if it does not exist, record the number of layers identified in the first stage as γ layers and go to step C. The method is as follows: the survival state in the actual combat scenario is converted into a situation distribution map, and then according to the typical survival model A defined in advance, δ , confirm whether all typical survival models A δ All of them exist in the situation diagram, and it is determined whether the current identification stage is completed. Step A specifically includes the following steps:

[0098] Step A1: Determine the current identification layer j information, according to the typical survival model A set before identification δ The identification rule confirms whether all typical survival models A δ All exist in the current layer;

[0099] Step A2: If all typical survival models A are confirmed in step A1 δ All exist in the current layer and go to step B; if all typical survival models A are confirmed in step A1 δ If none of them exist in the current layer, go to step C.

[0100] Among them, the "according to the typical survival model A" in step B δ Perform model recognition and extraction on the survival situation diagram of the j-layer system, and extract the recognition results to the j+1 layer; take the j+1 layer as the current j layer and return to step A. The method is as follows: According to the typical survival model A δ The recognition rule recognizes the j-layer situation map, then abstracts and extracts the recognition result of the layer to form the j+1-layer situation map and returns to step A. Step B specifically includes the following steps:

[0101] Step B1: According to different typical survival models A δ And the corresponding identification rules are used to identify the current j-layer situation map. Each point can be identified by the typical survival model A δ Repeated identification and use of the typical survival model A identified in this layer δ The physical centers of all the included monomers are extracted as identification points into the j+1 layer until all the typical survival models in the layer are identified and extracted;

[0102] Step B2: All the typical survival models A in step B1 δ The physical center identification point is displayed in j+1, and the other points are not displayed in the j+1 layer, forming the j+1 layer situation map;

[0103] Step B3: Let j = j + 1, take the j + 1 layer as the current j layer, and return to step A.

[0104] Among them, the "determine whether there is one or several typical survival models A in the survival situation diagram of the current γ+k layer system" in step C δ If it exists, then go to step D; if it does not exist, then record the number of layers increased by the second-stage identification stop layer γ+k relative to the first-stage stopping layer γ as the second-stage identification layer number information β and go to step E". The method is as follows: According to the typical survival model A δ , confirm whether there is a typical survival model A through graph search δ In the situation diagram, it is determined whether the current identification stage is completed. Step C specifically includes the following steps:

[0105] Step C1: Determine the current recognition layer γ+k information, according to the typical survival model A δ Identification rules confirm whether there is a typical survival model A δ In the current layer;

[0106] Step C2: If the typical survival model A is confirmed in step C1 δ In the current layer, go to step D; if it is confirmed in step C1 that there is no typical survival model A δ If it exists in the current layer, go to step E.

[0107] Among them, the "according to the typical survival model A" in step D δ Perform model recognition and extraction on the survival situation diagram of the γ+k layer system, and extract the recognition results to the γ+(k+1) layer; take the γ+(k+1) layer as the current γ+k layer and return to step C. The method is as follows: According to the typical survival model A δ The recognition rule recognizes the γ+k layer situation map, and then abstracts and extracts the recognition result of this layer to form the γ+(k+1) layer situation map and returns to step C. Step D specifically includes the following steps:

[0108] Step D1: According to different typical survival models A δ The corresponding identification rules are used to identify the current γ+k layer situation map. Each point can be identified by the typical survival model A δ Repeated identification and use of the typical survival model A identified in this layer δ The physical centers of all the monomers contained are extracted as identification points into the γ+(k+1) layer until all the typical survival models in this layer are identified and extracted;

[0109] Step D2: All the typical survival models A in step D1 δ The physical center identification point is displayed in γ+(k+1), and the other points are not displayed in the γ+(k+1) layer, forming the γ+(k+1) layer situation map;

[0110] Step D3: Let k=k+1, take the γ+(k+1) layer as the current γ+k layer, and return to step C.

[0111] Among them, the step E described in "according to the first stage identification layer number information γ, the second stage identification layer number information β, the typical survival model A δ , the capability base of typical models After the basic assessment coefficient R1 of the first layer of survivability (hereinafter referred to as the basic assessment coefficient, R1>1), the basic capability adjustment coefficient Δw and other information, the system survivability assessment result W is finally obtained. The method is as follows: according to the recognition results obtained in the previous step, the results of different recognition layers are sorted out respectively, and finally the survivability assessment result W is obtained. This step E specifically includes the following steps:

[0112] Step E1: According to the first stage, the number of layers γ and the lth typical survival model A δl Capacity base Basic evaluation coefficient R1, comprehensive evaluation of the survivability W of the i-th layer from the first layer to the γ-th layer i ;

[0113] First, the first typical survival model A δl The survivability at layer i is calculated using the following algorithm:

[0114]

[0115] in, Represents the lth typical survival model A in the i-th transition layer δl The viability of (α Al ) i Represents the lth typical survival model A δl Capacity base to the power of i, Represents the lth typical survival model A in the i-th transition layer δl the number of

[0116] Then according to Evaluate the survivability W of the i-th transition layer i , the specific algorithm used is:

[0117]

[0118] Among them, R i is the comprehensive evaluation coefficient of the i-th transition layer, and the coefficient is calculated as R i =(R1) i , δ1 is the typical survival model A of the i-th transition layer δ The sum of the types;

[0119] Step E2: Based on the number of layers β identified in the second stage and combined with the relevant information in step E1, the survival capacity W of the second stage stop layer, i.e. the γ+β layer, is calculated. γ+β Conduct assessments;

[0120] First, the sth typical survival model A δs The survivability of the γ+β layer is calculated using the following algorithm:

[0121]

[0122] in, represents the sth typical survival model A in the γ+β transition layer δs The ability to survive, Represents the sth typical survival model A δs Capacity base to the power of γ+m, represents the sth typical survival model A in the γ+β transition layer δS the number of

[0123] Then according to The survivability W of the γ+β transition layer is evaluated using a formula similar to formula (2). γ+β , the specific algorithm used is:

[0124]

[0125] Among them, R γ+β is the comprehensive evaluation coefficient of the γ+β transition layer, and the coefficient calculation method is R γ+β =(R1) γ+β , δ2 is the typical survival model A of the γ+β transition layer δ The sum of the types;

[0126] Step E3: Finally, based on the survivability of the first layer to the γth layer and the γth + βth layer obtained in steps E1 and E2, a comprehensive evaluation calculation can be performed to obtain the final system survivability evaluation result W. The specific algorithm used is:

[0127]

[0128] This algorithm can be used to evaluate the survivability of systems based on complex networks.

[0129] The method of the present invention is further described below by taking the evaluation of the survivability of a certain unmanned attack weapon system at sea as an example.

[0130] Assume that the current situation distribution of a certain maritime unmanned attack weapon system is as follows: Figure 2 The basic assessment coefficient is 1.5 and the adjustment coefficient is 50.

[0131] There are two types of ability models: A1 is facing the attack direction, where the distance between point 2 and point 1 is no more than 1.5 distances, and the angle between the line from 1 to 2 and the attack direction is 130° to 140° counterclockwise, where the distance between point 4 and point 1 is no more than 1.5 distances, and the angle between the line from 1 to 4 and the attack direction is 130° to 140° clockwise, where the distance between point 3 and point 1 is no more than 3 distances, and the angle between the line from 1 to 3 and the attack direction is 130° to 140° counterclockwise, where the distance between point 5 and point 1 is no more than 3 distances, and the angle between the line from 1 to 5 and the attack direction is 130° to 140° counterclockwise, five points form a group, the ability base is 5, and the specific shape is as follows: Figure 3 shown.

[0132] A2 is facing the attack direction, where the distance between point 2 and point 1 is no more than 1.5 distances, and the angle between the line from 1 to 2 and the attack direction is 40° to 50° counterclockwise, where the distance between point 4 and point 1 is no more than 1.5 distances, and the angle between the line from 1 to 4 and the attack direction is 40° to 50° clockwise, where the distance between point 3 and point 1 is no more than 3 distances, and the angle between the line from 1 to 3 and the attack direction is 40° to 50° counterclockwise, where the distance between point 5 and point 1 is no more than 3 distances, and the angle between the line from 1 to 5 and the attack direction is 40° to 50° counterclockwise, five points form a group, and the ability base is 10. The specific shape is as follows: Figure 4 shown.

[0133] According to the method requirements, the system survivability assessment is carried out. First, step A is entered for judgment. Both models exist in the situation diagram. Then, step B is entered. After extraction, the generated second-layer network is as follows Figure 5 shown.

[0134] Then return to step A for discrimination. The two models still exist in the second layer. Enter step B and generate the third layer network after extraction, such as Figure 6 shown.

[0135] Return to step A and find that only one model exists. Go to step C. After judgment, there is a model in the network. Go to step D. After extraction, the model is as follows Figure 7 As shown:

[0136] Return to step C. After judgment, it is found that there is no capability model in the 4th layer, and enter step E.

[0137] Based on the above steps, we can get: γ = 2, β = 1, so we have the following results:

[0138] W 1 =1.5×5×15×10×12

[0139] W 2 =1.5 2 ×5 2 ×4×11 2 ×1

[0140] W 3 =1.5 3 ×5 3 ×1

[0141] W=W 1 +W 2 +W 3 +Δw

[0142] W=13500+27225+421.875+50=41196.875

[0143] Under this situation, the system's survivability is 41196.875.

[0144] The present invention also provides a complex network-based assessment device for the survivability of unmanned maritime systems, which is implemented by an electronic device with computing capabilities, such as Figure 8 As shown, the device includes the following modules:

[0145] The first judgment module determines whether all the typical survival models A defined before the evaluation are in the survival situation diagram of the current j-layer system. δ All exist in the situation diagram, where j is an integer greater than or equal to 1;

[0146] The first recognition module, when the judgment result of the first judgment module is existence, according to the typical survival model A δ Perform model recognition and extraction on the survival situation diagram of the j-layer system, and extract the recognition results to the j+1 layer; take the j+1 layer as the current j layer and return to the first judgment module;

[0147] The first recording module: when the judgment result of the first judgment module is negative, the first stage identification stopping layer information is recorded as γ layers, and the second judgment module is entered, where γ is an integer greater than or equal to 1;

[0148] The second judgment module determines whether there is one or several typical survival models A in the survival situation diagram of the current γ+k layer system. δ ;

[0149] The second recognition module, when the judgment result of the second judgment module is yes, according to the typical survival model A δ Perform model recognition and extraction on the survival situation diagram of the γ+k layer system, and extract the recognition results to the γ+(k+1) layer; use the γ+(k+1) layer as the current γ+k layer and return to the second judgment module, where k is an integer greater than or equal to 1;

[0150] A second recording module, when the result of the second judgment module is negative, records the number of layers increased by the second-stage identification stop layer number γ+k relative to the first-stage stopping layer number γ as the second-stage identification layer number information β and enters the information into the system survivability assessment module, where β is an integer greater than or equal to 1;

[0151] The system survivability assessment module is based on the first-stage identification layer number information γ, the second-stage identification layer number information β, and the typical survival model A δ , the capacity base of each typical model The basic assessment coefficient R1 of the first-level survivability, the basic capability adjustment coefficient Δw and other information are finally obtained to obtain the system survivability assessment result W.

[0152] In the aforementioned modules, the first judgment module and the first identification module complete the first phase of situation map recognition, while the second judgment module and the second identification module complete the situation map for the second phase of recognition. The system survivability assessment module comprehensively evaluates the recognition results of the four modules in these two phases, ultimately obtaining the system survivability assessment results. Through these modules, the survivability assessment of unmanned attack weapon systems at sea can be achieved through intelligent, data-based assessment, resolving practical issues in existing assessment methods, such as inauthentic analysis sources, poor operability, strong reliance on subjective experience, and low credibility.

[0153] Among them, the system survivability assessment module states that “according to the first stage identification layer number information γ, the second stage identification layer number information β, the typical survival model A δ , the capacity base of each typical model The basic assessment coefficient R1 of the first layer of survivability, the basic capability adjustment coefficient Δw and other information are used to finally obtain the system survivability assessment result W". The method is as follows: According to the recognition results obtained in the previous module, the results of different recognition layers are sorted out respectively, and finally the survivability assessment result W is obtained. The system survivability assessment module specifically includes the following submodules:

[0154] The first survivability evaluation submodule is based on the first stage identification layer number γ, the lth typical survival model A δl Capacity base Basic evaluation coefficient R1, comprehensive evaluation of the survivability W of the i-th layer from the first layer to the γ-th layer i ;

[0155] First, the first typical survival model A δl The survivability at layer i is calculated as:

[0156]

[0157] in, Represents the lth typical survival model A in the i-th transition layer δl The viability of (α Al ) i Represents the lth typical survival model A δl Capacity base to the power of i, Represents the lth typical survival model A in the i-th transition layer δl the number of

[0158] Then according to Evaluate the survivability W of the i-th transition layer i :

[0159]

[0160] Among them, R i is the comprehensive evaluation coefficient of the i-th transition layer, and the coefficient is calculated as R i =(R1) i , δ1 is the typical survival model A of the i-th transition layer δ The sum of the types;

[0161] The second survivability evaluation submodule, based on the second stage identification layer number β and combined with the relevant information in step E1, evaluates the survivability W of the second stage stop layer, i.e., the γ+β layer. γ+β Conduct assessments;

[0162] First, the sth typical survival model A δs The survivability in the γ+β layer is calculated:

[0163]

[0164] in, represents the sth typical survival model A in the γ+β transition layer δs The ability to survive, Represents the sth typical survival model A δs Capacity base to the power of γ+m, represents the sth typical survival model A in the γ+β transition layer δS the number of

[0165] Then according to The survivability W of the γ+β transition layer is evaluated using a formula similar to formula (2). γ+β :

[0166]

[0167] Among them, Rγ+β is the comprehensive evaluation coefficient of the γ+β transition layer, and the coefficient calculation method is R γ+β =(R1) γ+β , δ2 is the typical survival model A of the γ+β transition layer δ The sum of the types;

[0168] The system survivability comprehensive evaluation submodule, based on the survivability of the first to γth layers and the γth + βth layers obtained in the first survivability evaluation submodule and the second survivability evaluation submodule, comprehensively evaluates and calculates the final system survivability evaluation result W:

[0169]

[0170] This algorithm can be used to evaluate the survivability of systems based on complex networks.

[0171] The electronic device with computing capability for implementing the above method of the present invention may be a server, a personal computer, a mobile phone, etc. Figure 9 The basic structure of the electronic equipment is shown in FIG. Figure 9 As shown, an electronic device with computing capabilities includes: a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, near field communication (NFC) or other technologies. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the electronic device housing, or an external keyboard, touchpad or mouse, etc.

[0172] Those skilled in the art will understand that Figure 9 The structure shown in the figure is merely a structural diagram of the portion related to the technical solution of the present disclosure and does not limit the electronic device to which the technical solution of the present disclosure is applied. Specific electronic devices may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement. The memory of the electronic device with computing capabilities stores a computer program. When the processor of the electronic device with computing capabilities executes the computer program, the steps of the above-mentioned method of the present disclosure can be implemented.

[0173] The present invention also discloses a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above method of the present invention.

[0174] The above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the specific implementation methods of the present invention can still be modified or some technical features can be replaced by equivalents without departing from the spirit of the technical solutions of the present invention, and all of them should be included in the scope of the technical solutions for which protection is sought.

Claims

1. A complex network-based method for evaluating the survivability of an unmanned attack weapon system at sea, implemented using an electronic device with computing capabilities, characterized in that: The steps include: Step A: Determine whether all the typical survival models A defined before evaluation exist in the survival situation diagram of the current j-th layer system. δ If it exists, go to step B; if it does not exist, record the first stage identification stop layer information as γ layers and go to step C, where j and γ are both integers and greater than or equal to 1; Step B, according to the typical survival model A δ Perform model recognition and extraction on the survival situation diagram of the j-layer system, and extract the recognition results to the j+1 layer; take the j+1 layer as the current j layer and return to step A; Step C: Determine whether there is one or several typical survival models A in the survival situation diagram of the current γ+k-th layer system. δ If it exists, proceed to step D; if it does not exist, record the number of layers γ+k of the second-stage identification stop layer increased relative to the first-stage stop layer γ as the second-stage identification layer number information β and proceed to step E, where k and β are both integers and greater than or equal to 1; Step D, according to the canonical survival model A δ Perform model recognition and extraction on the survival situation diagram of the γ+k layer system, and extract the recognition results to the γ+(k+1) layer; use the γ+(k+1) layer as the current γ+k layer and return to step C; Step E, based on the first stage identification stop layer information γ, the second stage identification layer information β, and the typical survival model A δ , the capability base of the typical model α Aδ , the basic assessment coefficient R1 of the first layer survivability, the basic capability adjustment coefficient Δw information, and finally obtain the system survivability assessment result W; Among them, step A and step B complete the first stage of situation map recognition, and step C and step D complete the situation map for the second stage of recognition.

2. The evaluation method according to claim 1, further comprising: In step A, further comprising: Step A1: Determine the current identification layer j information, according to the typical survival model A set before identification δ The identification rule confirms whether all typical survival models A δ All exist in the current layer; Step A2: If all typical survival models A are confirmed in step A1 δ All exist in the current layer and go to step B; if all typical survival models A are confirmed in step A1 δ If none of them exist in the current layer, go to step C.

3. The evaluation method according to claim 1, further comprising: In step B, further comprising: Step B1: According to different typical survival models A δ And the corresponding identification rules are used to identify the current j-layer situation map. Each point can be identified by the typical survival model A δ Repeated identification and use of the typical survival model A identified in this layer δ The physical centers of all the included monomers are extracted as identification points into the j+1 layer until all the typical survival models in the layer are identified and extracted; Step B2: All the typical survival models A in step B1 δ The physical center identification point is displayed in j+1, and the other points are not displayed in the j+1 layer, forming the j+1 layer situation map; Step B3: Let j = j + 1, take the j + 1 layer as the current j layer, and return to step A.

4. The evaluation method according to claim 1, further comprising: In step C, further comprising: Step C1: Determine the current recognition layer γ+k information, according to the typical survival model A δ Identification rules confirm whether there is a typical survival model A δ In the current layer; Step C2: If the typical survival model A is confirmed in step C1 δ In the current layer, go to step D; if it is confirmed in step C1 that there is no typical survival model A δ If it exists in the current layer, go to step E.

5. The evaluation method according to claim 1, further comprising: In step D, further comprising: Step D1: According to different typical survival models A δ The corresponding identification rules are used to identify the current γ+k layer situation map. Each point can be identified by the typical survival model A δ Repeated identification and use of the typical survival model A identified in this layer δ The physical centers of all the monomers contained are extracted as identification points into the γ+(k+1) layer until all the typical survival models in this layer are identified and extracted; Step D2: All the typical survival models A in step D1 δ The physical center identification point is displayed in γ+(k+1), and the other points are not displayed in the γ+(k+1) layer, forming the γ+(k+1) layer situation map; Step D3: Let k=k+1, take the γ+(k+1) layer as the current γ+k layer, and return to step C.

6. The evaluation method according to any one of claims 1 to 5, further comprising: In step E, further comprising: Step E1: According to the first stage, the number of layers γ and the lth typical survival model A δl Capacity base Basic evaluation coefficient R1, comprehensive evaluation of the survivability W of the i-th transition layer from the first layer to the γth layer i ; First, the first typical survival model A δl The survivability at the i-th transition layer is calculated as: in, Represents the lth typical survival model A in the i-th transition layer δl The ability to survive, Represents the lth typical survival model A δl Capacity base to the power of i, Represents the lth typical survival model A in the i-th transition layer δl the number of Then according to Evaluate the survivability W of the i-th transition layer i : Among them, R i is the comprehensive evaluation coefficient of the i-th transition layer, and the coefficient is calculated as R i =(R1) i , δ1 is the typical survival model A of the i-th transition layer δ The sum of the types; Step E2: Based on the number of layers β identified in the second stage and combined with the relevant information in step E1, the survivability W of the second stage stop layer, i.e., the γ+β transition layer, is calculated. γ+β Conduct assessments; First, the sth typical survival model A δs The survivability in the γ+β transition layer is calculated as: in, represents the sth typical survival model A in the γ+β transition layer δs The ability to survive, Represents the sth typical survival model A δs Capacity base to the power of γ+m, represents the sth typical survival model A in the γ+β transition layer δS the number of Then according to The survivability W of the γ+β transition layer is evaluated using a formula similar to formula (2). γ+β : Among them, R γ+β is the comprehensive evaluation coefficient of the γ+β transition layer, and the coefficient calculation method is R γ+β =(R1) γ+β , δ2 is the typical survival model A of the γ+β transition layer δ The sum of the types; Step E3: Finally, based on the survivability of the first layer to the γth layer and the γ+βth transition layer obtained in steps E1 and E2, a comprehensive evaluation calculation can be performed to obtain the final system survivability evaluation result W:

7. A complex network-based survivability assessment device for unmanned maritime attack weapon systems, implemented using electronic equipment with computing capabilities, characterized in that: The device includes: The first judgment module determines whether all the typical survival models A defined before the evaluation are in the survival situation diagram of the current j-layer system. δ All exist in the situation diagram, where j is an integer greater than or equal to 1; The first recognition module, when the judgment result of the first judgment module is existence, according to the typical survival model A δ Perform model recognition and extraction on the survival situation diagram of the j-layer system, and extract the recognition results to the j+1 layer; take the j+1 layer as the current j layer and return to the first judgment module; The first recording module: when the judgment result of the first judgment module is negative, the first stage identification stopping layer information is recorded as γ layers, and the second judgment module is entered, where γ is an integer greater than or equal to 1; The second judgment module determines whether there is one or several typical survival models A in the survival situation diagram of the current γ+k layer system. δ ; The second recognition module, when the judgment result of the second judgment module is yes, according to the typical survival model A δ Perform model recognition and extraction on the survival situation diagram of the γ+k layer system, and extract the recognition results to the γ+(k+1) layer; use the γ+(k+1) layer as the current γ+k layer and return to the second judgment module, where k is an integer greater than or equal to 1; A second recording module, when the result of the second judgment module is negative, records the number of layers increased by the second-stage identification stop layer number γ+k relative to the first-stage stopping layer number γ as the second-stage identification layer number information β and enters the information into the system survivability assessment module, where β is an integer greater than or equal to 1; The system survivability assessment module is based on the first stage identification of the stopping layer number information γ, the second stage identification of the layer number information β, and the typical survival model A δ , the capacity base of each typical model The basic assessment coefficient R1 of the first layer of survivability and the basic capability adjustment coefficient Δw information are used to finally obtain the system survivability assessment result W; The first judgment module and the first recognition module complete the first stage of situation map recognition, and the second judgment module and the second recognition module complete the second stage of situation map recognition.

8. The evaluation device according to claim 7, characterized in that The system survivability assessment module further includes the following submodules: The first survivability evaluation submodule is based on the first stage identification layer number γ, the lth typical survival model A δl Capacity base Basic evaluation coefficient R1, comprehensive evaluation of the survivability W of the i-th transition layer from the first layer to the γth layer i ; First, the first typical survival model A δl The survivability at the i-th transition layer is calculated as: in, Represents the lth typical survival model A in the i-th transition layer δl The ability to survive, Represents the lth typical survival model A δl Capacity base to the power of i, Represents the lth typical survival model A in the i-th transition layer δl the number of Then according to Evaluate the survivability W of the i-th transition layer i : Among them, R i is the comprehensive evaluation coefficient of the i-th transition layer, and the coefficient is calculated as R i =(R1) i , δ1 is the typical survival model A of the i-th transition layer δ The sum of the types; The second survivability evaluation submodule, based on the second stage identification layer number β and combined with the relevant information in step E1, evaluates the survivability W of the second stage stop layer, i.e., the γ+β transition layer. γ+β Conduct assessments; First, the sth typical survival model A δs The survivability in the γ+β transition layer is calculated as: in, represents the sth typical survival model A in the γ+β transition layer δs The ability to survive, Represents the sth typical survival model A δs Capacity base to the power of γ+m, represents the sth typical survival model A in the γ+β transition layer δS the number of Then according to The survivability W of the γ+β transition layer is evaluated using a formula similar to formula (2). γ+β : Among them, R γ+β is the comprehensive evaluation coefficient of the γ+β transition layer, and the coefficient calculation method is R γ+β =(R1) γ+β , δ2 is the typical survival model A of the γ+β transition layer δ The sum of the types; The system survivability comprehensive evaluation submodule, based on the survivability of the first layer to the γth layer and the γth + βth transition layer obtained in the first survivability evaluation submodule and the second survivability evaluation submodule, can obtain the final system survivability evaluation result W through comprehensive evaluation calculation:

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of the evaluation method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the evaluation method according to any one of claims 1 to 6 are implemented.

Images