A method for evaluating the system contribution rate of high power microwave weapons in coordinated air defense

Abstract

The present application provides a method for evaluating the system contribution rate of high-power microwave weapons in coordinated air defense, the method comprising: constructing a fuzzy wavelet neural network; selecting a fuzzy wavelet neural network input index and preprocessing the collected index data; training the fuzzy wavelet neural network using the preprocessed data; evaluating the incoming target using the trained fuzzy wavelet neural network to obtain the combat effectiveness of the first target and the combat effectiveness of the second target respectively; according to the combat effectiveness of the first target and the combat effectiveness of the second target, using a system contribution rate solution method based on combat effectiveness increment to determine the system contribution rate of high-power microwave weapons in coordinated air defense operations. The method provided by the present application intuitively obtains the overall gain of high-power microwave weapons for coordinated air defense operations.

Description

Technical Field

[0001] The present application relates to the technical field of system contribution rate assessment methods for coordinated combat, and in particular to a system contribution rate assessment method for coordinated air defense with high-power microwave weapons. Background Art

[0002] With the progress of modern science and technology and the change of war forms, various weapon systems are increasingly dependent on microelectronics and computer control. Under this condition, "intelligent" weapons have gradually become a powerful weapon in the hands of various military powers. To deal with this new type of weapon that uses complex electronic equipment and flexible combat methods, traditional air defense weapons can no longer ensure the combat efficiency of air defense interception and guarantee the security of our country's territory. Therefore, it is imperative to develop a new generation of air defense weapons.

[0003] As a new type of weapon, high-power microwave weapons are different from other weapon systems in that they not only "soft kill" the target, but also extend the "soft kill" to the "hard kill" level by virtue of their killing mechanism. They use electromagnetic energy to interfere with or burn out sensitive components such as electronic equipment or computers in enemy weapon systems. They can damage various sensors and achieve information blindness; they can also destroy communications and data link equipment; they can also disrupt computer networks and weapon control units. Therefore, they have great military application potential in space confrontation, information confrontation and anti-precision strike. In addition, the lobe of the microwave beam is large, so the range of attack is large, so the accuracy requirements for tracking and aiming can be reduced, which not only reduces the cost of using high-power microwave weapons, but also facilitates the attack on fast-moving targets at close range. Thus, it complements the existing short-range air defense weapons, strengthens the protection against incoming weapons, and ensures our safety.

[0004] At present, the research on high-power microwave weapons is mainly focused on revealing the damage mechanism and damage mode of high-power microwave weapons, but the coordinated combat effect of high-power microwave weapons and traditional weapons in actual combat and the system contribution rate of high-power microwave weapons in coordinated combat have not been studied. The solution of the system contribution rate of high-power microwave weapons in coordinated air defense operations can help combatants better understand the actual effect of high-power microwave weapons in a combat and how to use them in conjunction with traditional air defense weapons, so as to give full play to the role of different weapons in different scenarios. Summary of the invention

[0005] The present application provides a method for evaluating the system contribution rate of high-power microwave weapons in coordinated air defense, which can be used to solve the technical problem of the lack of a method for determining the system contribution rate of high-power microwave weapons in coordinated air defense operations.

[0006] The present application provides a method for evaluating the system contribution rate of high-power microwave weapons coordinated air defense, the method comprising:

[0007] Construct fuzzy wavelet neural network;

[0008] Select the fuzzy wavelet neural network input index and pre-process the collected index data;

[0009] Use the preprocessed data to train the fuzzy wavelet neural network;

[0010] The trained fuzzy wavelet neural network is used to evaluate the incoming target, and the combat effectiveness of the first target and the combat effectiveness of the second target are obtained respectively; the combat effectiveness of the first target is the combat effectiveness of the combat using only medium- and short-range air defense weapons; the combat effectiveness of the second target is the combat effectiveness of the coordinated combat using high-power microwave weapons and medium- and short-range air defense weapons;

[0011] According to the combat effectiveness of the first target and the combat effectiveness of the second target, the system contribution rate of high-power microwave weapons in coordinated air defense operations is determined by using a system contribution rate solution method based on combat effectiveness increment.

[0012] Optionally, the fuzzy wavelet neural network model includes five layers;

[0013] Among them, the first layer is the input layer, which corresponds to 5 input indicators;

[0014] Assume that there is N r The fuzzy rules are as follows:

[0015]

[0016] Among them, x i is the i-th input variable of the system, i=1:5, A ij Fuzzy membership function is a fuzzy language set characterized by j is the weight between the fuzzy layer and the output layer, μ j The output of the fuzzy layer, y j is the output of the entire network;

[0017] The second layer is the membership function layer. The second layer selects the Gaussian function as the membership function:

[0018]

[0019] Among them, c ij represents the central parameter under the jth rule; σ ij represents the scaling parameter under the jth rule;

[0020] The third layer is the fuzzy rule layer. Each node represents a fuzzy rule R. The output of each node is:

[0021]

[0022] Among them, Π represents the logical "AND" operation;

[0023] The fourth layer is the wavelet function layer, which selects the first-order partial derivative of the Gaussian function As the mother wavelet function; according to the selected mother wavelet function, it is put into the neurons of the second layer as the activation function after scaling and translation transformation:

[0024]

[0025] r=1:N ω ,i=1:5

[0026] Among them, t ri represents the translation parameter of the wavelet, d ri Represents the scaling parameter of the wavelet, subscript r i Indicates that the i-th input corresponds to the r-th wavelet neuron, N ω Represents the number of wavelet neurons, the output result of the fourth layer of the network:

[0027]

[0028] Among them, w r is the weight connecting the hidden layer and the output layer;

[0029] The fifth layer is the output layer, which multiplies the fourth layer output by the third layer node output:

[0030]

[0031] in, v j Represents the output value of the jth wavelet function;

[0032] The output result of the fifth layer is expressed as:

[0033]

[0034] Optionally, the fuzzy wavelet neural network input indicators are divided into two types: interception effect indicators and combat cost indicators; wherein the interception effect indicators include the number of intercepted targets, the time to complete the interception targets, and the degree of target damage; the combat cost indicators include the amount of interception ammunition consumed and the integrity of one's own side.

[0035] Optionally, a fuzzy wavelet neural network input index is selected and the collected index data is preprocessed, including:

[0036] Select the fuzzy wavelet neural network input indicators and quantify and normalize the collected indicator data.

[0037] Optionally, the indicator data is quantified, including:

[0038] Number of intercepted targets: Set the number of incoming targets obtained by the ship detection system as N1. After air defense interception, the number of targets is set as N2. The ratio of the number of successfully intercepted targets to the total number of incoming targets is:

[0039] n=N2 / N1

[0040] According to n=0~1, the number of interception targets is quantized to 1~10;

[0041] Time required to complete the interception of the target: According to the target speed and target position obtained by the ship detection system, determine the total time t1 required for the target to reach the ship, and the time t2 from the target being detected to the target being intercepted and destroyed, then:

[0042] t=t2 / t1

[0043] The time taken to intercept the target is represented by the ratio t, and the time taken to intercept the target is divided into 10~1 intervals according to t=0~1;

[0044] Target damage degree: Due to the characteristics of anti-ship missiles that they will be damaged when hit, this indicator specifically refers to UAVs; it is quantified as 2, 4, 6, 8, and 10 in order of no damage, slight damage, moderate damage, severe damage, and destruction;

[0045] Interception ammunition consumption: According to the number of resources carried by the ship, the ammunition consumption is quantified in intervals of 0 to 100% to 10 to 10%;

[0046] Own integrity: Quantify the integrity of the ship into 2, 4, 6, 8, and 10 according to no damage, slight damage, moderate damage, severe damage, and sinking.

[0047] Optionally, normalize the indicator data, including:

[0048] To achieve normalization:

[0049] [y,ps]=mapminmax(x,y min ,y max )

[0050] Among them, y is the quantized index, ps is the structure that records the normalized mapping, and the mapping function used in the mapminmax function is:

[0051]

[0052] Among them, xmin and x max is the minimum and maximum value of the original data x, y min and max is the range parameter of the mapping, which is adjustable and defaults to -1 and 1. In this case, the mapping is normalized to [-1, 1]. min Set to 0, y max Set to 1.

[0053] Optionally, a system contribution rate solution method based on combat effectiveness increment is used to determine the system contribution rate of high-power microwave weapons in coordinated air defense operations, including:

[0054] According to the combat effectiveness of the first target and the combat effectiveness of the second target, the system contribution rate of high-power microwave weapons in coordinated air defense operations is determined.

[0055] Optionally, the system contribution rate is determined by the following method:

[0056] η=μ(k)1-μ(k)2

[0057] Wherein, μ(k)1 is the air defense combat effectiveness evaluation value after adding high-power microwave weapons obtained by fuzzy wavelet neural network, and μ(k)2 is the air defense effectiveness evaluation value before adding high-power microwave weapons obtained by fuzzy wavelet neural network.

[0058] In the method for solving the combat effectiveness of the present application, the fuzzy wavelet neural network is based on the fuzzy wavelet neural network, which is a combination of the fuzzy neural network and the wavelet neural network. The fuzzy neural network solves the uncertainty problem of battlefield environment information, and the wavelet neural network enhances the self-learning ability of the network. Combining the two can participate in the training of the neural network according to the existing empirical rules on the one hand, and on the other hand, it has good stability and convergence speed, improves the generalization ability in complex environments, and ensures the accuracy and rapidity of the combat effectiveness evaluation; when selecting the fuzzy wavelet neural network input index, not only the interception effect of air defense operations is considered, but also the interception consumption and the integrity of the own side are selected. The combat cost of our side during the combat process is fully considered, so that the evaluated combat effectiveness can be more comprehensive and credible. In the step of solving the system contribution rate, a solution method based on the combat effectiveness increment is adopted to solve the indirect contribution rate of high-power microwave weapons in coordinated air defense operations, which reflects the contribution and military benefits of high-power microwave weapons in air defense operations from the side, and can more intuitively obtain the comprehensive gain of high-power microwave weapons for coordinated air defense operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1A schematic flow chart of a method for evaluating the system contribution rate of high-power microwave weapons coordinated air defense provided in an embodiment of the present application;

[0060] Figure 2 A schematic diagram of a fuzzy wavelet neural network provided in an embodiment of the present application;

[0061] Figure 3 A schematic diagram of the classification of fuzzy wavelet neural network input indicators provided in the embodiment of the present application;

[0062] Figure 4 A schematic diagram of solving the system contribution rate provided in the embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0064] Let's first combine Figure 1 The possible system architecture applicable to the embodiments of the present application is introduced.

[0065] like Figure 1 As shown, the method provided by the present application comprises the following steps:

[0066] Step S101, constructing a fuzzy wavelet neural network.

[0067] In the embodiment of the present application, the fuzzy wavelet neural network model is divided into five layers, such as Figure 2 shown.

[0068] The first layer is the input layer, which corresponds to 5 input indicators;

[0069] Assume that there is N r The fuzzy rules are as follows:

[0070]

[0071] Among them, x i is the i-th input variable of the system (i=1:5), A ij Fuzzy membership function is a fuzzy language set characterized by j is the weight between the fuzzy layer and the output layer, μ j The output of the fuzzy layer, y j is the output of the entire network.

[0072] The second membership function layer, since the Gaussian membership function can maintain the original distribution of the data, the Gaussian function is selected as the membership function in the second layer:

[0073]

[0074] Among them, c ij , σ ij They represent the central parameter and scaling parameter under the j-th rule respectively.

[0075] The third layer is the fuzzy rule layer. Each node represents a fuzzy rule R. The output of each node is:

[0076]

[0077] Among them, Π represents the logical "AND" operation, that is, taking the smaller operation.

[0078] The fourth layer is the wavelet function layer, which selects the first-order partial derivative of the Gaussian function As the mother wavelet function, this function has good fitting performance. According to the selected mother wavelet function, after scaling and translation transformation, it is put into the neurons of the second layer as the activation function:

[0079]

[0080] Among them, t ri and d ri Respectively represent the translation parameter and scaling parameter of the wavelet, subscript r i Indicates that the i-th input corresponds to the r-th wavelet neuron, N ω Represents the number of wavelet neurons, the output result of the fourth layer of the network:

[0081]

[0082] Among them, w r is the weight connecting the hidden layer and the output layer.

[0083] The fifth layer is the output layer, which multiplies the output of the fourth layer (wavelet layer) by the node output of the third layer (fuzzy rule layer):

[0084]

[0085] in, v j Represents the output value of the jth wavelet function.

[0086] The output result of the fifth layer is expressed as:

[0087]

[0088] Step S102, selecting a fuzzy wavelet neural network input index and preprocessing the collected index data.

[0089] Specifically, in the embodiment of the present application, a fuzzy wavelet neural network input index is selected and the collected index data is quantized and normalized.

[0090] The input indicators of the fuzzy wavelet neural network are divided into two types: interception effect indicators and combat cost indicators, with a total of five items; among them, the interception effect indicators include the number of intercepted targets, the time required to complete the interception target, and the degree of target damage; the combat cost indicators include the interception missile consumption and the integrity of the own side, such as Figure 3 As shown. The more intercepted targets there are, the less time it takes to complete the interception, the higher the degree of target damage, the better the interception effect, and the higher the combat effectiveness. In a war, the less interception ammunition consumed and the higher the integrity of the own side, the better the air defense combat effect and the higher the efficiency. In general, the better the interception effect and the lower the combat cost, the more successful the ship air defense interception and the better the efficiency evaluation value. The efficiency evaluation value is proportional to the attack intention and inversely proportional to the combat cost.

[0091] In the embodiment of the present application, the indicator data is quantified, including:

[0092] Number of intercepted targets: Set the number of incoming targets obtained by the ship detection system (the number of assumed incoming targets) as N1. After air defense interception, the number of targets is set to N2. The ratio of the number of successfully intercepted targets to the total number of incoming targets is:

[0093] n=N2 / N1

[0094] The number of interception targets is quantized to 1 to 10 in equal intervals (0.1) from n = 0 to 1;

[0095] Time consumption for intercepting the target: According to the target speed and target position obtained by the ship detection system, calculate the total time t1 required for the target to reach the ship, and the time t2 from the target being detected to the target being intercepted and destroyed, then:

[0096] t=t2 / t1

[0097] The time consumption of intercepting the target can be expressed by the ratio t, and the time consumption of intercepting the target is successively 10 to 1 at intervals (0.1) from t = 0 to 1;

[0098] Target damage degree: Due to the characteristics of anti-ship missiles that are damaged when hit, this indicator refers specifically to drones. It is quantified as 2, 4, 6, 8, and 10 in order of no damage, slight damage (no impact on flight), moderate damage (affects flight but can continue to perform missions), severe damage (must return), and destroyed;

[0099] Interception ammunition consumption: According to the number of resources carried by the ship, the ammunition consumption is quantified in intervals of 0 to 100% to 10 to 10%;

[0100] The integrity of the ship is quantified into 2, 4, 6, 8, and 10 according to no damage, slight damage (does not affect combat), moderate damage (affects navigation but not combat), severe damage (must return), and sinking.

[0101] In the embodiment of the present application, the indicator data is normalized, including:

[0102] The above normalization can be achieved by using the mapminmax function in Matlab:

[0103] [y,ps]=mapminmax(x,y min ,y max )

[0104] Among them, y is the quantized index, ps is the structure that records the normalized mapping, and the mapping function used in the mapminmax function is:

[0105]

[0106] Among them, x min and x max is the minimum and maximum value of the original data x, y min and max is the range parameter of the mapping, which is adjustable and defaults to -1 and 1. The mapping is normalized to [-1, 1]. min Set to 0, y max Set to 1.

[0107] In the embodiment of the present application, the pre-processed data is used to train a fuzzy wavelet neural network until the evaluation error of the combat effectiveness is less than 5%.

[0108] Step S103: training a fuzzy wavelet neural network using the preprocessed data.

[0109] Substitute the preprocessed data into the fuzzy wavelet neural network and perform iterative training on the fuzzy wavelet neural network. The learning rate is set to 0.001. When the combat effectiveness evaluation error is less than 5%, the fuzzy wavelet neural network training is completed.

[0110] Step S104, using the trained fuzzy wavelet neural network to evaluate the incoming target, and respectively obtain the combat effectiveness of the first target and the combat effectiveness of the second target.

[0111] The first target combat effectiveness is the combat effectiveness of using only medium- and short-range air defense weapons. The second target combat effectiveness is the combat effectiveness of using high-power microwave weapons in coordinated operations with medium- and short-range air defense weapons.

[0112] It should be noted that in order to accurately calculate the system contribution rate of high-power microwave weapons, the target type, flight altitude, flight speed and enemy distance of the first combat target and the second combat target are the same.

[0113] Step S105, according to the first target combat effectiveness and the second target combat effectiveness, a system contribution rate solution method based on combat effectiveness increment is used to determine the system contribution rate of high-power microwave weapons in the coordinated air defense operations.

[0114] Based on the combat effectiveness of the first target and the combat effectiveness of the second target, the system contribution rate of high-power microwave weapons in coordinated air defense operations is determined.

[0115] Specifically, in the embodiment of the present application, the system contribution rate is determined by the following method:

[0116] η=μ(k)1-μ(k)2

[0117] Wherein, μ(k)1 is the air defense combat effectiveness evaluation value after adding high-power microwave weapons obtained by fuzzy wavelet neural network, and μ(k)2 is the air defense effectiveness evaluation value before adding high-power microwave weapons obtained by fuzzy wavelet neural network.

[0118] In the method for solving the combat effectiveness of the present application, the fuzzy wavelet neural network is based on the fuzzy wavelet neural network, which is a combination of the fuzzy neural network and the wavelet neural network. The fuzzy neural network solves the uncertainty problem of battlefield environment information, and the wavelet neural network enhances the self-learning ability of the network. Combining the two can participate in the training of the neural network according to the existing empirical rules on the one hand, and on the other hand, it has good stability and convergence speed, improves the generalization ability in complex environments, and ensures the accuracy and rapidity of the combat effectiveness evaluation; when selecting the fuzzy wavelet neural network input index, not only the interception effect of air defense operations is considered, but also the interception consumption and the integrity of the own side are selected. The combat cost of our side during the combat process is fully considered, so that the evaluated combat effectiveness can be more comprehensive and credible. In the step of solving the system contribution rate, a solution method based on the combat effectiveness increment is adopted to solve the indirect contribution rate of high-power microwave weapons in coordinated air defense operations, which reflects the contribution and military benefits of high-power microwave weapons in air defense operations from the side, and can more intuitively obtain the comprehensive gain of high-power microwave weapons for coordinated air defense operations.

[0119] Those skilled in the art can clearly understand that the technology in the embodiments of the present application can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a disk, an optical disk, etc., including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application or some parts of the embodiments.

[0120] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the service construction device and service loading device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

[0121] The above-described embodiments of the present application do not constitute a limitation on the protection scope of the present application.

Claims

1. A method for evaluating the system contribution rate of high-power microwave weapons coordinated air defense, characterized in that: The method comprises: Construct fuzzy wavelet neural network; Select the fuzzy wavelet neural network input index and pre-process the collected index data; Use the preprocessed data to train the fuzzy wavelet neural network; The trained fuzzy wavelet neural network is used to evaluate the incoming target, and the combat effectiveness of the first target and the combat effectiveness of the second target are obtained respectively; the combat effectiveness of the first target is the combat effectiveness of the combat using only medium- and short-range air defense weapons; the combat effectiveness of the second target is the combat effectiveness of the coordinated combat using high-power microwave weapons and medium- and short-range air defense weapons; According to the first target combat effectiveness and the second target combat effectiveness, a system contribution rate solution method based on combat effectiveness increment is used to determine the system contribution rate of high-power microwave weapons in the coordinated air defense operations; The fuzzy wavelet neural network model includes five layers; Among them, the first layer is the input layer, which corresponds to 5 input indicators; Assume that there is N r The fuzzy rules are as follows: R j :IF x1is A 1j ANDx2is A2jAND…x i is A ij THEN Among them, x i is the i-th input variable of the system, i=1:5, A ij Fuzzy membership function is a fuzzy language set characterized by j is the weight between the fuzzy layer and the output layer, μ j The output of the fuzzy layer, y j is the output of the entire network; The second layer is the membership function layer. The second layer selects the Gaussian function as the membership function: Among them, c ij represents the central parameter under the jth rule; σ ij represents the scaling parameter under the jth rule; The third layer is the fuzzy rule layer. Each node represents a fuzzy rule R. The output of each node is: Among them, Π represents the logical "AND" operation; The fourth layer is the wavelet function layer, which selects the first-order partial derivative of the Gaussian function As the mother wavelet function; according to the selected mother wavelet function, it is put into the neurons of the second layer as the activation function after scaling and translation transformation: r=1:N ω ,i=1:5 Among them, t ri represents the translation parameter of the wavelet, d ri represents the scaling parameter of the wavelet, the subscript ri indicates that the ith input corresponds to the rth wavelet neuron, N ω Represents the number of wavelet neurons, the output result of the fourth layer of the network: Among them, w r is the weight connecting the hidden layer and the output layer; The fifth layer is the output layer, which multiplies the fourth layer output by the third layer node output: in, v j Represents the output value of the jth wavelet function; The output result of the fifth layer is expressed as: Select the fuzzy wavelet neural network input index and pre-process the collected index data, including: Select the fuzzy wavelet neural network input index and quantify and normalize the collected index data; Quantitative processing of indicator data, including: Number of intercepted targets: Set the number of incoming targets obtained by the ship detection system as N1. After air defense interception, the number of targets is set as N2. The ratio of the number of successfully intercepted targets to the total number of incoming targets is: n=N2 / N1 According to n=0~1, the number of interception targets is quantized to 1~10; Time required to complete the interception of the target: According to the target speed and target position obtained by the ship detection system, determine the total time t1 required for the target to reach the ship, and the time t2 from the target being detected to the target being intercepted and destroyed, then: t=t2 / t1 The time taken to intercept the target is represented by the ratio t, and the time taken to intercept the target is divided into 10~1 intervals according to t=0~1; Target damage degree: Due to the characteristics of anti-ship missiles that they will be damaged when hit, this indicator specifically refers to UAVs; it is quantified as 2, 4, 6, 8, and 10 in order of no damage, slight damage, moderate damage, severe damage, and destruction; Interception ammunition consumption: According to the number of resources carried by the ship, the ammunition consumption is quantified in intervals of 0 to 100% to 10 to 10%; Own integrity: Quantify the integrity of the ship into 2, 4, 6, 8, and 10 according to no damage, slight damage, moderate damage, severe damage, and sinking.

2. The method for evaluating the system contribution rate of high-power microwave weapons coordinated air defense as claimed in claim 1, characterized in that: The fuzzy wavelet neural network input indicators are divided into two types: interception effect indicators and combat cost indicators; among them, the interception effect indicators include the number of intercepted targets, the time consumed to complete the interception target, and the degree of target damage; the combat cost indicators include the interception missile consumption and the integrity of the own side.

3. The system contribution rate evaluation method of high-power microwave weapons coordinated air defense as claimed in claim 1, characterized in that: Normalize the indicator data, including: To achieve normalization: [y,ps] = mapminmax(x,y min ,and max ) Among them, y is the quantized index, ps is the structure that records the normalized mapping, and the mapping function used in the mapminmax function is: Among them, x min and x max is the minimum and maximum value of the original data x, y min and max is the range parameter of the mapping, which is adjustable and defaults to -1 and 1. In this case, the mapping is normalized to [-1, 1]. min Set to 0, y max Set to 1.

4. The method for evaluating the system contribution rate of high-power microwave weapons coordinated air defense according to claim 1, characterized in that: The system contribution rate of high-power microwave weapons in coordinated air defense operations is determined by using a system contribution rate solution method based on combat effectiveness increment, including: According to the combat effectiveness of the first target and the combat effectiveness of the second target, the system contribution rate of high-power microwave weapons in coordinated air defense operations is determined.

5. The method for evaluating the system contribution rate of high-power microwave weapons coordinated air defense as claimed in claim 1, characterized in that: The system contribution rate is determined by the following method: η=μ(k)1-μ(k)2 Wherein, μ(k)1 is the air defense combat effectiveness evaluation value after adding high-power microwave weapons obtained by fuzzy wavelet neural network, and μ(k)2 is the air defense effectiveness evaluation value before adding high-power microwave weapons obtained by fuzzy wavelet neural network.

Images