Unmanned ship intelligent cabin system task execution capability assessment method based on three-flow cooperation theory

Abstract

The invention discloses an unmanned ship intelligent cabin system task execution capability evaluation method based on a three-flow cooperation theory, and the method comprises the steps: determining all parameters for supporting the operation of an unmanned ship intelligent cabin system, and forming an unmanned ship intelligent cabin system parameter set through all parameters; obtaining a first weight of each parameter in the parameter set of the intelligent cabin system of the unmanned ship and a fourth weight of each parameter in the parameter set of the flow represented by each parameter based on a neural network; determining a second weight of each parameter and a fifth weight of each parameter in a parameter set of the flow represented by the parameter based on historical data; correcting the second weight based on the first weight of the parameter to obtain a third weight; correcting the fifth weight based on the fourth weight of the parameter to obtain a sixth weight; and extracting a parameter value corresponding to each parameter from the current state data of the unmanned ship intelligent cabin system, and determining the task execution capability of the unmanned ship intelligent cabin system by combining the third weight and the sixth weight of each parameter.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned ships, and in particular to a method for evaluating the task execution capability of an intelligent engine room system of an unmanned ship based on three-stream collaboration theory. Background Art

[0002] In recent years, with the application of intelligent ship technology and the upgrading of marine equipment technology, the development of unmanned ships has become a new direction for the development of marine engineering. By setting up special scientific and technological research and development projects, issuing industrial support policies in the civil and military fields, and formulating industry standards, we actively cultivate unmanned and intelligent industries and strive to enhance national defense capabilities.

[0003] In the process of performing missions, unmanned ships are severely limited in external communication and external support due to the characteristics of long-distance and long-range missions. They must rely on themselves to achieve self-operation and maintenance throughout the mission cycle, which puts an urgent need for intelligent cabin technology. By adopting various autonomous monitoring and autonomous operation and maintenance control methods to optimize the mission execution decision of unmanned ships, it is of great significance to reduce the possibility of functional failure caused by system and equipment failures, system performance degradation leading to reduced combat capability and even failure return, maintain the integrity of the power system function, and improve the completion of the mission.

[0004] As a key link in the realization of intelligent engine rooms, the accuracy of the task execution capability assessment results will directly affect the optimization effect of unmanned ships on task planning decisions and operation and maintenance control decisions. Therefore, since the concept of unmanned ships was proposed, the task execution capability assessment method has always been a key issue in the research of unmanned ship intelligent engine room technology. In recent years, with the development and application of technologies such as big data and artificial intelligence, the task execution capability assessment method has developed rapidly, and related analysis and research have continued to deepen, gradually developing and forming a variety of assessment methods based on physical models, knowledge models, data-driven models, and hybrid models. However, most of the existing execution capability assessment methods are concentrated on the equipment level, lacking consideration of the interaction and dependency between various devices and components in the system, and have not established a comprehensive and scientific task execution capability assessment indicator system for the entire system. The weight setting of the indicator cannot be dynamically adjusted to adapt to changes in the system operation mode, and cannot be adaptively adjusted with changes in the system life cycle, making it difficult to support accurate assessment of the overall task completion capability of the system. Summary of the invention

[0005] In view of this, the present invention provides a method for evaluating the task execution capability of an unmanned ship's intelligent engine room system based on the three-stream collaboration theory, which can solve the problem of measuring the overall healthy operation level of the unmanned ship's intelligent engine room system and its support for the unmanned ship's task matching.

[0006] In order to solve the above technical problems, the present invention is implemented as follows.

[0007] A method for evaluating the mission execution capability of an unmanned ship intelligent engine room system based on the three-stream synergy theory includes:

[0008] Step S1: Determine various parameters representing material flow, energy flow, and information flow that support the operation of the unmanned ship intelligent cabin system, and form an unmanned ship intelligent cabin system parameter set with all the parameters;

[0009] Step S2: inputting the historical data of the operation of the unmanned ship intelligent cabin system and the various parameters in the parameter set of the unmanned ship intelligent cabin system into the trained neural network model, and obtaining the first weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fourth weight of each parameter in the parameter set of the flow represented by each parameter;

[0010] Step S3: Based on the historical data of the operation of the unmanned ship intelligent cabin system, determine the second weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fifth weight of each parameter in the parameter set of the flow represented by each parameter; based on the first weight of the parameter, modify the second weight to obtain the third weight; based on the fourth weight of the parameter, modify the fifth weight to obtain the sixth weight;

[0011] Step S4: extracting parameter values ​​corresponding to various parameters from the current state data of the unmanned ship intelligent cabin system, and determining the task execution capability of the unmanned ship intelligent cabin system in combination with the third weight and the sixth weight of each parameter.

[0012] Preferably, the step S2 includes: forming a material flow parameter set with parameters representing material flow, forming an energy flow parameter set with parameters representing energy flow, and forming an information flow parameter set with parameters representing information flow; all parameters in the material flow parameter set, the information flow parameter set and the energy flow parameter set together constitute the unmanned ship intelligent cabin system parameter set; inputting the historical data of the operation of the unmanned ship intelligent cabin system and each parameter in the unmanned ship intelligent cabin system parameter set into the trained neural network model to obtain the first weight of each parameter in the unmanned ship intelligent cabin system parameter set and the fourth weight in the parameter set of the flow represented by each parameter.

[0013] Preferably, the step S3: based on the historical data of the operation of the unmanned ship intelligent cabin system, determining the second weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fifth weight of each parameter in the parameter set of the flow represented by each parameter; based on the first weight of the parameter, correcting the second weight to obtain the third weight; based on the fourth weight of the parameter, correcting the fifth weight to obtain the sixth weight, includes:

[0014] Step S31: constructing a historical efficacy matrix of the unmanned ship intelligent cabin system based on the historical data of the operation of the unmanned ship intelligent cabin system, and constructing a historical evaluation matrix based on the historical efficacy matrix;

[0015] Step S32: Determine the second weight of each parameter in the parameter set of the unmanned ship intelligent engine room system and the fifth weight of each parameter in the parameter set of the flow it represents based on the historical evaluation matrix; correct the second weight based on the first weight of the parameter in the parameter set of the unmanned ship intelligent engine room system to obtain the third weight of the parameter in the parameter set of the unmanned ship intelligent engine room system; correct the fifth weight based on the fourth weight of the parameter in the parameter set of the flow to obtain the sixth weight of the parameter in the parameter set of the flow.

[0016] Preferably, the step S31 includes:

[0017] Step S311: Obtain S historical observation samples from the historical data, and construct a historical efficacy value matrix X based on the S historical observation samples. S :

[0018]

[0019] Wherein, S represents the number of historical observation samples, N represents the number of parameters in the parameter set of the unmanned ship intelligent cabin system; x ij It represents the power value of the observed value of the i-th parameter in the parameter set in the j-th observation sample, and its calculation formula is

[0020]

[0021] Among them, v i max Take the maximum value of the i-th parameter in S historical observation samples, v i min Take the minimum value of the i-th parameter in S historical observation samples; v i,j The calculation method is

[0022]

[0023] Among them, c i,j represents the observed value of the i-th parameter in the parameter set of the unmanned ship intelligent cabin system in the j-th observation sample; K i,j represents the theoretical target value corresponding to the i-th parameter in the parameter set of the unmanned ship intelligent cabin system in the j-th observation sample;

[0024] Step S312: Calculate the historical efficacy value matrix X S Perform normalization:

[0025]

[0026] Then we get the historical evaluation matrix X′ S :

[0027]

[0028] Among them, x i ' ,j represents the historical evaluation value of the i-th parameter in the j-th historical observation sample of the unmanned ship intelligent cabin system parameter set;

[0029] The step S32 comprises:

[0030] Step S321: Based on the historical evaluation matrix X′ S , calculate the information entropy of each parameter:

[0031]

[0032] Where J = 1 / ln(S); only when x′ ij = 0, take H i Represents the information entropy of the i-th parameter in the parameter set of the unmanned ship intelligent cabin system;

[0033] Step S322: For each parameter in the unmanned ship intelligent cabin system parameter set, perform the following operations:

[0034] Determine the flow corresponding to the parameter, the corresponding flow is one of material flow, information flow, and energy flow, determine the number of the parameter in the corresponding flow parameter set, and calculate the fifth weight of the parameter in the flow:

[0035]

[0036] Among them, w 物质流,Ei1 represents the fifth weight of the i1th parameter in the material flow parameter set in the material flow, w 信息流,Ei1 represents the fifth weight of the i2th parameter in the information flow parameter set in the information flow, w 能量流,Ei1 represents the fifth weight of the i3th parameter in the energy flow parameter set in the energy flow; H 物质流,i1 represents the information entropy of the i1th parameter in the material flow parameter set, H 信息流,i2 represents the information entropy of the i2th parameter in the information flow parameter set, H 能量流,i3 represents the information entropy of the i3th parameter in the energy flow parameter set; N 物质流 Indicates the number of parameters in the material flow parameter set, N 信息流 Indicates the number of parameters in the information flow parameter set, N 能量流 Indicates the number of parameters in the energy flow parameter set; N物质流 +N 信息流 +N 能量流 =N;

[0037] Calculate the second weight w of the parameter in the unmanned ship intelligent cabin system parameter set Bi :

[0038]

[0039] Step S323: For each parameter in the unmanned ship intelligent cabin system parameter set, perform the following calculation: Let the first weight of the parameter in the unmanned ship intelligent cabin system parameter set be w Ai , the second weight is w Bi ,

[0040] like Then Otherwise, let ω′ i =w Bi ;

[0041] After all parameters in the unmanned ship intelligent cabin system parameter set are calculated, a third weight w of each parameter in the unmanned ship intelligent cabin system parameter set is calculated. Ci :

[0042]

[0043] The third weight of each parameter in the unmanned ship intelligent cabin system parameter set satisfies:

[0044]

[0045] Step S324: For each parameter in the unmanned ship intelligent cabin system parameter set, perform the following operations:

[0046] Determine a flow corresponding to the parameter, wherein the corresponding flow is one of a material flow, an information flow, and an energy flow;

[0047] If the parameter is a material flow parameter, assume that the parameter is the i1th parameter in the material flow parameter set, and record the fourth weight of the parameter in the material flow parameter set as w 物质流,Di1 , the fifth weight of this parameter in the material flow parameter set is w 物质流,Ei1 ,like Then Otherwise, let ω′ 物质流,i1 =w 物质流,Ei1 ;

[0048] If the parameter is an information flow parameter, assuming that the parameter is the i2th parameter in the information flow parameter set, the fourth weight of the parameter in the information flow parameter set is w 信息流,Di2, the fifth weight of this parameter in the information flow parameter set is w 信息流,Ei2 ,like Then

[0049]

[0050] If the parameter is an energy flow parameter, assuming that the parameter is the i3th parameter in the energy flow parameter set, the fourth weight of the parameter in the energy flow parameter set is w 能量流,Di3 , the fifth weight of this parameter in the energy flow parameter set is w 能量流,Ei3 ,like Then

[0051]

[0052] Step S325: After calculating the fifth weights corresponding to all parameters, calculate the sixth weight of the parameter in the flow parameter set:

[0053] If the parameter is a material flow parameter, assuming that the parameter is the i1th parameter in the material flow parameter set, then the sixth weight w of the parameter in the material flow parameter set is 物质流,Fi1 :

[0054]

[0055] If the parameter is an information flow parameter, assuming that the parameter is the i2th parameter in the information flow parameter set, then the sixth weight w of the parameter in the information flow parameter set is 信息流,Fi2 :

[0056]

[0057] If the parameter is an energy flow parameter, assuming that the parameter is the i3th parameter in the energy flow parameter set, then the sixth weight w of the parameter in the energy flow parameter set is 能量流,Fi3 :

[0058]

[0059] Step S326: Obtain the corresponding flow parameter set weights for the material flow parameter set, information flow parameter set, and energy flow parameter set, respectively, and record them as W 物质流 , W 信息流 , W 能量流 ; Among them, the flow parameter set weight W of the material flow parameter set 物质流 =W is equal to the arithmetic sum of the third weights of each parameter in the material flow parameter set in the unmanned ship intelligent cabin system parameter set; the flow parameter set weight W of the information flow parameter set 信息流 = equal to the arithmetic sum of the third weights of each parameter in the information flow parameter set in the unmanned ship intelligent cabin system parameter set; the flow parameter set weight W of the energy flow parameter set 能量流It is equal to the arithmetic sum of the third weights of each parameter in the energy flow parameter set in the unmanned ship intelligent cabin system parameter set.

[0060] Preferably, the step S4: extracting parameter values ​​corresponding to various parameters from the current state data of the unmanned ship intelligent cabin system, and determining the task execution capability of the unmanned ship intelligent cabin system in combination with the third weight and the sixth weight of each parameter, comprises:

[0061] Step S41: extracting the parameter values ​​corresponding to each parameter from the current state data of the unmanned ship intelligent cabin system, and establishing the current efficacy value vector X of the parameter set of the unmanned ship intelligent cabin system c :

[0062]

[0063] Among them, x c,i It represents the efficacy value of the current value of the i-th parameter in the system parameter set, and its calculation formula is

[0064]

[0065] in, Take the maximum value of the i-th parameter in S observation samples, Take the minimum value of the i-th parameter in S observation samples; v c,i The calculation method is

[0066]

[0067] Among them, c c,i represents the current observed value of the i-th parameter in the system parameter set; K c,i Represents the theoretical target value corresponding to the current observed value of the i-th parameter in the parameter set;

[0068] Step S42: normalize the current efficacy value vector:

[0069]

[0070] Get the current evaluation vector X c ′:

[0071]

[0072] Among them, x c ' ,i represents the current evaluation value of the i-th parameter in the system parameter set;

[0073] Step S43: Based on the historical evaluation matrix X′ S And the sixth weight of each parameter in the corresponding flow parameter set, calculate the historical order of each flow, the calculation method is

[0074]

[0075] Among them, OD 物质流,j OD 信息流,j OD 能量流,j They represent the historical order of material flow, information flow, and energy flow corresponding to the jth historical observation sample among the S historical observation samples; w 物质流,Fi1 represents the sixth weight of the i1th parameter in the material flow parameter set, w 信息流,Fi2 represents the sixth weight of the i2th parameter in the information flow parameter set, w 能量流,Fi3 represents the sixth weight of the i3th parameter in the energy flow parameter set; the corresponding number of the i1th parameter in the material flow parameter set in the unmanned ship intelligent cabin system parameter set is m1, the corresponding number of the i2th parameter in the information flow parameter set in the unmanned ship intelligent cabin system parameter set is m2, and the corresponding number of the i3th parameter in the energy flow parameter set in the unmanned ship intelligent cabin system parameter set is m3; on this basis, x′ m1,j That is, the historical evaluation value of the i1th parameter in the material flow parameter set in the jth historical observation sample, x′ m2,j That is, the historical evaluation value of the i2th parameter in the information flow parameter set in the jth historical observation sample, x′ m3,j That is, the historical evaluation value of the i3th parameter in the energy flow parameter set in the jth historical observation sample;

[0076] Step S44: Based on the current evaluation vector X c ′ and the sixth weight of each parameter in the corresponding flow parameter set, calculate the current order of each flow, and the calculation method is:

[0077]

[0078] Among them, OD 物质流,c OD 信息流,c OD 能量流,c They represent the current order of material flow, the current order of information flow, and the current order of energy flow respectively. The corresponding number of the i1th parameter in the material flow parameter set in the unmanned ship intelligent cabin system parameter set is m1, the corresponding number of the i2th parameter in the information flow parameter set in the unmanned ship intelligent cabin system parameter set is m2, and the corresponding number of the i3th parameter in the energy flow parameter set in the unmanned ship intelligent cabin system parameter set is m3. On this basis, x c ' ,m1 That is, the current evaluation value of the i1th parameter in the material flow parameter set, x c ',m2 That is, the current evaluation value of the i2th parameter in the information flow parameter set, x c ' ,m3 That is, the current evaluation value of the i3th parameter in the energy flow parameter set;

[0079] Step S45: Calculate the system order corresponding to the jth historical observation sample in the S historical observation samples and the current order of the unmanned ship intelligent cabin system respectively, and the calculation method is:

[0080]

[0081] Among them, W 物质流 , W 信息流 , W 能量流 The flow parameter set weights corresponding to the material flow parameter set, information flow parameter set, and energy flow parameter set respectively; SOD j SOD represents the historical order of the unmanned ship intelligent engine room system corresponding to the jth historical observation sample among the S historical observation samples; c Indicates the current orderliness of the unmanned ship intelligent engine room system;

[0082] Step S46:

[0083] SOD max is the maximum value of the system order corresponding to each historical observation sample in S historical observation samples;

[0084] Step S47: According to the current order degree SOD of the unmanned ship intelligent engine room system c , calculate and determine the current task execution capability SE of the unmanned ship intelligent cabin system as

[0085]

[0086] Wherein, R represents the design performance redundancy ratio of the unmanned ship intelligent cabin system.

[0087] The present invention provides a device for evaluating the task execution capability of an unmanned ship intelligent cabin system based on the three-stream coordination theory, comprising:

[0088] Parameter determination module: configured to determine various parameters representing material flow, energy flow, and information flow supporting the operation of the unmanned ship intelligent cabin system, and all parameters constitute a parameter set of the unmanned ship intelligent cabin system;

[0089] A weight module: configured to input the historical data of the operation of the unmanned ship intelligent cabin system and each parameter in the parameter set of the unmanned ship intelligent cabin system into the trained neural network model, and obtain the first weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fourth weight in the parameter set of the flow represented by each parameter;

[0090] The weight correction module is configured to determine the second weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fifth weight of each parameter in the parameter set of the flow represented by each parameter based on the historical data of the operation of the unmanned ship intelligent cabin system; correct the second weight based on the first weight of the parameter to obtain the third weight; correct the fifth weight based on the fourth weight of the parameter to obtain the sixth weight;

[0091] Calculation module: configured to extract parameter values ​​corresponding to various parameters from the current state data of the unmanned ship intelligent cabin system, and determine the task execution capability of the unmanned ship intelligent cabin system in combination with the third weight and the sixth weight of each parameter.

[0092] From the perspective of supporting the execution of unmanned ship intelligent cabin system tasks, this paper proposes a method for evaluating the task execution capability of unmanned ship intelligent cabin system based on the three-flow synergy theory. This method is based on the historical data of the man-ship intelligent cabin system, determines the mutual influence of material flow, energy flow, and information flow, and determines a comprehensive and integrated task execution capability evaluation index system and weights. This paper provides a basis for subsequent instruction issuance, material supply, task content planning and optimization, and adjustment of operation mode.

[0093] Beneficial effects:

[0094] (1) The present invention can improve the ability of the unmanned ship's intelligent engine room system to ensure the stable and reliable operation of the power system and enhance the unmanned ship's mission completion capability;

[0095] (2) The present invention can improve the real-time monitoring capability of the overall healthy operation level of the intelligent cabin system based on the mission requirements of the unmanned ship, and enhance the autonomous perception capability of the unmanned ship;

[0096] (3) The present invention can improve the ability to evaluate the overall healthy operation level of the unmanned ship's intelligent cabin system and the degree of matching with the mission support, and reduce direct asset losses and indirect mission losses caused by mission failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] Figure 1 It is a flow chart of a method for evaluating the task execution capability of an unmanned ship intelligent engine room system based on the three-stream synergy theory of the present invention;

[0098] Figure 2 This is a structural block diagram of the task execution capability evaluation device of the unmanned ship intelligent cabin system based on the three-stream collaboration theory of the present invention. DETAILED DESCRIPTION

[0099] The present invention is described in detail below in conjunction with the accompanying drawings and embodiments.

[0100] The present invention proposes a method for evaluating the task execution capability of an unmanned ship intelligent engine room system based on the three-stream collaboration theory.

[0101] like Figure 1 As shown, the method for evaluating the task execution capability of the unmanned ship intelligent cabin system based on the three-stream synergy theory provided by the present invention comprises the following steps:

[0102] Step S1: Determine various parameters representing material flow, energy flow, and information flow that support the operation of the unmanned ship intelligent cabin system, and form an unmanned ship intelligent cabin system parameter set with all the parameters;

[0103] Step S2: inputting the historical data of the operation of the unmanned ship intelligent cabin system and the various parameters in the parameter set of the unmanned ship intelligent cabin system into the trained neural network model, and obtaining the first weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fourth weight of each parameter in the parameter set of the flow represented by each parameter;

[0104] Step S3: Based on the historical data of the operation of the unmanned ship intelligent cabin system, determine the second weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fifth weight of each parameter in the parameter set of the flow represented by each parameter; based on the first weight of the parameter, correct the second weight to obtain the third weight; based on the fourth weight of the parameter, correct the fifth weight to obtain the sixth weight;

[0105] Step S4: extracting parameter values ​​corresponding to various parameters from the current state data of the unmanned ship intelligent cabin system, and determining the task execution capability of the unmanned ship intelligent cabin system in combination with the third weight and the sixth weight of each parameter.

[0106] The material flow, energy flow, and information flow of the unmanned ship intelligent cabin system are mutually coupled, mutually influential, and mutually coordinated. In the unmanned ship intelligent cabin system, the relevant power, mechanical, electrical, and electronic equipment cooperate under the control of the command information to convert fuel substances into energy forms such as electrical energy and mechanical energy and transmit them to the designated user equipment on the unmanned ship side, accompanied by corresponding material emissions. In order to ensure the reliable, stable, and high-quality operation and operation of the above-mentioned main process, on the one hand, through the control of the control instructions and the drive of the energy flow, cooling, lubrication and other materials can be circulated to provide operating conditions for the main process related equipment; on the other hand, based on the real-time generated environment, status, and alarm monitoring information feedback, the operating mode and status of the relevant equipment are adjusted in real time to provide sufficient, reliable, and high-quality operating conditions for the main process related equipment.

[0107] (1) Material flow

[0108] Information flow mainly refers to the flow and circulation of fuel, cooling medium, lubricating medium, combustion-supporting oxidant medium and other substances in the unmanned ship intelligent cabin system. The material flow parameters of the unmanned ship intelligent cabin system mainly include fuel pressure / flow, lubricating oil pressure / flow, cooling fresh water pressure / flow / temperature difference before and after cooling, cooling seawater pressure / flow / temperature difference before and after cooling, and internal combustion engine intake boost air pressure / exhaust temperature.

[0109] (2) Energy flow

[0110] Energy flow mainly refers to the conversion, transmission, absorption and release of various types of energy such as fuel chemical energy, electrical energy, and mechanical energy in the unmanned ship intelligent cabin system. The reliable, high-quality, and uninterrupted flow of energy flow is the core requirement and ultimate goal of the unmanned ship intelligent cabin system. The energy flow parameters of the unmanned ship intelligent cabin system mainly include the output shaft power of the prime mover, the output shaft power of the propulsion shaft, and the output electrical power of the generator.

[0111] (3) Information Flow

[0112] Information flow mainly refers to the issuance of various control commands in the unmanned ship intelligent cabin system and the feedback of system, equipment, and environmental monitoring signals. The information flow parameters of the unmanned ship intelligent cabin system mainly include the prime mover speed control command and monitoring signal, propulsion shaft speed control command and monitoring signal, ambient temperature, etc.

[0113] The step S1: determining various parameters representing material flow, energy flow, and information flow that support the operation of the unmanned ship intelligent cabin system, and all the parameters constitute a parameter system that characterizes the unmanned ship intelligent cabin system.

[0114] Among them, the parameters representing the material flow include the pressure of the fuel, the flow of the fuel, the pressure of the lubricating oil, the flow of the lubricating oil, the pressure of the cooling fresh water, the flow of the cooling fresh water, the temperature difference before and after the cooling of the cooling fresh water, the pressure of the cooling seawater, the flow of the cooling seawater, the temperature difference before and after the cooling of the cooling seawater, the intake boost air pressure of the internal combustion engine, and the exhaust temperature of the internal combustion engine; the parameters representing the energy flow include the output shaft power of the prime mover, the output shaft power of the propulsion shaft, and the output electrical power of the generator; the parameters representing the information flow include the prime mover speed control command, the prime mover speed monitoring signal, the propulsion shaft speed control command, the propulsion shaft speed monitoring signal, and the ambient temperature.

[0115] The step S2 includes: forming a material flow parameter set with parameters representing material flow, forming an energy flow parameter set with parameters representing energy flow, and forming an information flow parameter set with parameters representing information flow; all parameters in the material flow parameter set, the information flow parameter set, and the energy flow parameter set together form the unmanned ship intelligent cabin system parameter set; inputting the historical data of the operation of the unmanned ship intelligent cabin system and each parameter in the unmanned ship intelligent cabin system parameter set into the trained neural network model to obtain the first weight of each parameter in the unmanned ship intelligent cabin system parameter set and the fourth weight in the parameter set of the flow represented by each parameter.

[0116] The neural network model is an RNN network model, an LSTM network model or a WaveNet network model.

[0117] The step S3: based on the historical data of the operation of the unmanned ship intelligent cabin system, determining the second weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fifth weight of each parameter in the parameter set of the flow represented by each parameter; based on the first weight of the parameter, correcting the second weight to obtain the third weight; based on the fourth weight of the parameter, correcting the fifth weight to obtain the sixth weight, including:

[0118] Step S31: constructing a historical efficacy matrix of the unmanned ship intelligent cabin system based on the historical data of the operation of the unmanned ship intelligent cabin system, and constructing a historical evaluation matrix based on the historical efficacy matrix;

[0119] Step S32: Determine the second weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fifth weight of each parameter in the parameter set of the flow it represents based on the historical evaluation matrix; correct the second weight based on the first weight of the parameter in the parameter set of the unmanned ship intelligent cabin system to obtain the third weight of the parameter in the parameter set of the unmanned ship intelligent cabin system; correct the fifth weight based on the fourth weight of the parameter in the parameter set of the flow to obtain the sixth weight of the parameter in the parameter set of the flow.

[0120] The step S31 comprises:

[0121] Step S311: Obtain S historical observation samples from the historical data, and construct a historical efficacy value matrix X based on the S historical observation samples. S :

[0122]

[0123] Wherein, S represents the number of historical observation samples, N represents the number of parameters in the parameter set of the unmanned ship intelligent cabin system; x ij It represents the power value of the observed value of the i-th parameter in the parameter set in the j-th observation sample, and its calculation formula is

[0124]

[0125] in, Take the maximum value of the i-th parameter in S historical observation samples, Take the minimum value of the i-th parameter in S historical observation samples; v i,j The calculation method is

[0126]

[0127] Among them, c i,j represents the observed value of the i-th parameter in the parameter set of the unmanned ship intelligent cabin system in the j-th observation sample; K i,j represents the theoretical target value corresponding to the i-th parameter in the parameter set of the unmanned ship intelligent cabin system in the j-th observation sample;

[0128] Step S312: Calculate the historical efficacy value matrix X S Perform normalization:

[0129]

[0130] Then we get the historical evaluation matrix X′ S :

[0131]

[0132] Among them, x i ' ,j It represents the historical evaluation value of the i-th parameter in the parameter set of the unmanned ship intelligent cabin system in the j-th historical observation sample.

[0133] Step S32: determining the second weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fifth weight of each parameter in the parameter set of the stream represented by each parameter based on the historical evaluation matrix; correcting the second weight based on the first weight of the parameter in the parameter set of the unmanned ship intelligent cabin system to obtain the third weight of the parameter in the parameter set of the unmanned ship intelligent cabin system; correcting the fifth weight based on the fourth weight of the parameter in the parameter set of the stream to obtain the sixth weight of the parameter in the parameter set of the stream, including:

[0134] Step S321: Based on the historical evaluation matrix X′ S , calculate the information entropy of each parameter:

[0135]

[0136] Where J = 1 / ln(S); only when x′ ij = 0, take H i Represents the information entropy of the i-th parameter in the parameter set of the unmanned ship intelligent cabin system;

[0137] Step S322: For each parameter in the unmanned ship intelligent cabin system parameter set, perform the following operations:

[0138] Determine the flow corresponding to the parameter, the corresponding flow is one of material flow, information flow, and energy flow, determine the number of the parameter in the corresponding flow parameter set, and calculate the fifth weight of the parameter in the flow:

[0139]

[0140] Among them, w 物质流,Ei1 represents the fifth weight of the i1th parameter in the material flow parameter set in the material flow, w 信息流,Ei1 represents the fifth weight of the i2th parameter in the information flow parameter set in the information flow, w 能量流,Ei1 represents the fifth weight of the i3th parameter in the energy flow parameter set in the energy flow; H 物质流,i1 represents the information entropy of the i1th parameter in the material flow parameter set, H 信息流,i2 represents the information entropy of the i2th parameter in the information flow parameter set, H 能量流,i3 represents the information entropy of the i3th parameter in the energy flow parameter set; N 物质流 Indicates the number of parameters in the material flow parameter set, N 信息流 Indicates the number of parameters in the information flow parameter set, N 能量流 Indicates the number of parameters in the energy flow parameter set; N 物质流 +N 信息流 +N 能量流 =N;

[0141] Calculate the second weight w of the parameter in the unmanned ship intelligent cabin system parameter set Bi :

[0142]

[0143] Step S323: For each parameter in the unmanned ship intelligent cabin system parameter set, perform the following calculation: Let the first weight of the parameter in the unmanned ship intelligent cabin system parameter set be w Ai , the second weight is w Bi ,

[0144] like Then Otherwise, let ω′ i =w Bi ;

[0145] After all parameters in the unmanned ship intelligent cabin system parameter set are calculated, a third weight w of each parameter in the unmanned ship intelligent cabin system parameter set is calculated. Ci :

[0146]

[0147] The third weight of each parameter in the unmanned ship intelligent cabin system parameter set satisfies:

[0148]

[0149] Step S324: For each parameter in the unmanned ship intelligent cabin system parameter set, perform the following operations:

[0150] Determine a flow corresponding to the parameter, wherein the corresponding flow is one of a material flow, an information flow, and an energy flow;

[0151] If the parameter is a material flow parameter, assume that the parameter is the i1th parameter in the material flow parameter set, and record the fourth weight of the parameter in the material flow parameter set as w 物质流,Di1 , the fifth weight of this parameter in the material flow parameter set is w 物质流,Ei1 ,like Then

[0152]

[0153] If the parameter is an information flow parameter, assuming that the parameter is the i2th parameter in the information flow parameter set, the fourth weight of the parameter in the information flow parameter set is w 信息流,Di2 , the fifth weight of this parameter in the information flow parameter set is w 信息流,Ei2 ,like Then

[0154]

[0155] If the parameter is an energy flow parameter, assuming that the parameter is the i3th parameter in the energy flow parameter set, the fourth weight of the parameter in the energy flow parameter set is w 能量流,Di3 , the fifth weight of this parameter in the energy flow parameter set is w 能量流,Ei3 ,like Then

[0156]

[0157] Step S325: After calculating the fifth weights corresponding to all parameters, calculate the sixth weight of the parameter in the flow parameter set:

[0158] If the parameter is a material flow parameter, assuming that the parameter is the i1th parameter in the material flow parameter set, then the sixth weight w of the parameter in the material flow parameter set is 物质流,Fi1 :

[0159]

[0160] If the parameter is an information flow parameter, assuming that the parameter is the i2th parameter in the information flow parameter set, then the sixth weight w of the parameter in the information flow parameter set is 信息流,Fi2 :

[0161]

[0162] If the parameter is an energy flow parameter, assuming that the parameter is the i3th parameter in the energy flow parameter set, then the sixth weight w of the parameter in the energy flow parameter set is 能量流,Fi3 :

[0163]

[0164] Further:

[0165]

[0166] Step S326: Obtain the corresponding flow parameter set weights for the material flow parameter set, information flow parameter set, and energy flow parameter set, respectively, and record them as W 物质流 , W 信息流 , W 能量流 ; Among them, the flow parameter set weight W of the material flow parameter set 物质流 =W is equal to the arithmetic sum of the third weights of each parameter in the material flow parameter set in the unmanned ship intelligent cabin system parameter set; the flow parameter set weight W of the information flow parameter set 信息流 = equal to the arithmetic sum of the third weights of each parameter in the information flow parameter set in the unmanned ship intelligent cabin system parameter set; the flow parameter set weight W of the energy flow parameter set 能量流 It is equal to the arithmetic sum of the third weights of each parameter in the energy flow parameter set in the unmanned ship intelligent cabin system parameter set.

[0167] Furthermore, W 物质流 +W 信息流 +W 能量流 =1.

[0168] In the present invention, the analysis of historical data by a neural network model is combined to correct the weights of the parameters, which can combine the advantages of entropy value calculation and neural network calculation.

[0169] The step S4: extracting parameter values ​​corresponding to various parameters from the current state data of the unmanned ship intelligent cabin system, and determining the task execution capability of the unmanned ship intelligent cabin system in combination with the third weight and the sixth weight of each parameter, including:

[0170] Step S41: extracting the parameter values ​​corresponding to each parameter from the current state data of the unmanned ship intelligent cabin system, and establishing the current efficacy value vector X of the parameter set of the unmanned ship intelligent cabin system c :

[0171]

[0172] Among them, x c,i It represents the efficacy value of the current value of the i-th parameter in the system parameter set, and its calculation formula is

[0173]

[0174] in, Take the maximum value of the i-th parameter in S observation samples, Take the minimum value of the i-th parameter in S observation samples; v c,i The calculation method is

[0175]

[0176] Among them, c c,i represents the current observed value of the i-th parameter in the system parameter set; K c,i Represents the theoretical target value corresponding to the current observed value of the i-th parameter in the parameter set;

[0177] Step S42: normalize the current efficacy value vector:

[0178]

[0179] Get the current evaluation vector X c ′:

[0180]

[0181] Among them, x c ' ,i represents the current evaluation value of the i-th parameter in the system parameter set;

[0182] Step S43: Based on the historical evaluation matrix X′ S And the sixth weight of each parameter in the corresponding flow parameter set, calculate the historical order of each flow, the calculation method is

[0183]

[0184] Among them, OD 物质流,j OD 信息流,j OD 能量流,jThey represent the historical order of material flow, information flow, and energy flow corresponding to the jth historical observation sample among the S historical observation samples; w 物质流,Fi1 represents the sixth weight of the i1th parameter in the material flow parameter set, w 信息流,Fi2 represents the sixth weight of the i2th parameter in the information flow parameter set, w 能量流,Fi3 represents the sixth weight of the i3th parameter in the energy flow parameter set; the corresponding number of the i1th parameter in the material flow parameter set in the unmanned ship intelligent cabin system parameter set is m1, the corresponding number of the i2th parameter in the information flow parameter set in the unmanned ship intelligent cabin system parameter set is m2, and the corresponding number of the i3th parameter in the energy flow parameter set in the unmanned ship intelligent cabin system parameter set is m3; on this basis, x′ m1,j That is, the historical evaluation value of the i1th parameter in the material flow parameter set in the jth historical observation sample, x′ m2,j That is, the historical evaluation value of the i2th parameter in the information flow parameter set in the jth historical observation sample, x′ m3,j That is, the historical evaluation value of the i3th parameter in the energy flow parameter set in the jth historical observation sample;

[0185] Step S44: Based on the current evaluation vector X c ′ and the sixth weight of each parameter in the corresponding flow parameter set, calculate the current order of each flow, and the calculation method is:

[0186]

[0187] Among them, OD 物质流,c OD 信息流,c OD 能量流,c They represent the current order of material flow, the current order of information flow, and the current order of energy flow respectively; the corresponding number of the i1th parameter in the material flow parameter set in the unmanned ship intelligent cabin system parameter set is m1, the corresponding number of the i2th parameter in the information flow parameter set in the unmanned ship intelligent cabin system parameter set is m2, and the corresponding number of the i3th parameter in the energy flow parameter set in the unmanned ship intelligent cabin system parameter set is m3; on this basis, x′ c,m1 That is, the current evaluation value of the i1th parameter in the material flow parameter set, x′ c,m2 That is, the current evaluation value of the i2th parameter in the information flow parameter set, x′ c,m3 That is the current evaluation value of the i3th parameter in the energy flow parameter set.

[0188] Step S45: Calculate the system order corresponding to the jth historical observation sample in the S historical observation samples and the current order of the unmanned ship intelligent cabin system respectively, and the calculation method is:

[0189]

[0190] Among them, W 物质流 , W 信息流 , W 能量流 The flow parameter set weights corresponding to the material flow parameter set, information flow parameter set, and energy flow parameter set respectively; SOD j SOD represents the historical order of the unmanned ship intelligent engine room system corresponding to the jth historical observation sample among the S historical observation samples; c Indicates the current orderliness of the unmanned ship intelligent engine room system;

[0191] Step S46:

[0192] SOD max is the maximum value of the system order corresponding to each historical observation sample in S historical observation samples;

[0193] Step S47: According to the current order degree SOD of the unmanned ship intelligent engine room system c , calculate and determine the current task execution capability SE of the unmanned ship intelligent cabin system as

[0194]

[0195] Wherein, R represents the design performance redundancy ratio of the unmanned ship intelligent cabin system.

[0196] In the present invention, R is the system performance redundancy reserved in the early design stage to compensate for the decline in system coordination caused by factors such as aging and loss during the long-term operation of the physical system. Usually, the value of R can be 0.05 to 0.1.

[0197] Furthermore, the method includes step S6: based on the current task execution capability of the unmanned ship intelligent cabin system, planning and adjusting subsequent tasks of the unmanned ship intelligent cabin system, the subsequent tasks may include reconnaissance, patrolling, special operations, ferrying, entering and exiting narrow waterways, entering and exiting ports, and leaving and docking at piers.

[0198] The present invention is based on S historical observation samples collected in the early stage (the more historical observation samples there are, the more accurate the various statistical calculation results based on the historical observation samples are. The number of historical observation samples S in the calculation method described above can take a value of 1000 to 2000) to establish a parameter set of the unmanned ship intelligent cabin system.

[0199] The present invention also provides a task execution capability evaluation device for an unmanned ship intelligent cabin system based on the three-stream synergy theory, such as Figure 2 As shown, the device comprises:

[0200] Parameter determination module: configured to determine various parameters representing material flow, energy flow, and information flow supporting the operation of the unmanned ship intelligent cabin system, and all parameters constitute a parameter set of the unmanned ship intelligent cabin system;

[0201] A weight module: configured to input the historical data of the operation of the unmanned ship intelligent cabin system and each parameter in the parameter set of the unmanned ship intelligent cabin system into the trained neural network model, and obtain the first weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fourth weight in the parameter set of the flow represented by each parameter;

[0202] The weight correction module is configured to determine the second weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fifth weight of each parameter in the parameter set of the flow represented by each parameter based on the historical data of the operation of the unmanned ship intelligent cabin system; correct the second weight based on the first weight of the parameter to obtain the third weight; correct the fifth weight based on the fourth weight of the parameter to obtain the sixth weight;

[0203] Calculation module: configured to extract parameter values ​​corresponding to various parameters from the current state data of the unmanned ship intelligent cabin system, and determine the task execution capability of the unmanned ship intelligent cabin system in combination with the third weight and the sixth weight of each parameter.

[0204] The present invention does not elaborate on some of the well-known technologies that belong to those skilled in the art.

[0205] The above specific embodiments only describe the design principle of the present invention. The shapes and names of the components in the description may be different and are not limited. Therefore, those skilled in the art in the field of the present invention may modify or replace the technical solutions recorded in the above embodiments; and these modifications and replacements do not deviate from the creative purpose and technical solutions of the present invention and should all fall within the protection scope of the present invention.

Claims

1. A method for evaluating the task execution capability of an unmanned ship intelligent engine room system based on the three-stream collaboration theory, characterized in that: include: Step S1: Determine various parameters representing material flow, energy flow, and information flow that support the operation of the unmanned ship intelligent cabin system, and form an unmanned ship intelligent cabin system parameter set with all the parameters; Step S2: inputting the historical data of the operation of the unmanned ship intelligent cabin system and the various parameters in the parameter set of the unmanned ship intelligent cabin system into the trained neural network model, and obtaining the first weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fourth weight of each parameter in the parameter set of the flow represented by each parameter; Step S3: Based on the historical data of the operation of the unmanned ship intelligent cabin system, determine the second weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fifth weight of each parameter in the parameter set of the flow represented by each parameter; The second weight is modified based on the first weight of the parameter to obtain a third weight; The fifth weight is modified based on the fourth weight of the parameter to obtain a sixth weight; Step S4: extracting parameter values ​​corresponding to various parameters from the current state data of the unmanned ship intelligent cabin system, and determining the task execution capability of the unmanned ship intelligent cabin system in combination with the third weight and the sixth weight of each parameter.

2. The method according to claim 1, characterized in that The step S2 includes: forming a material flow parameter set with parameters representing material flow, forming an energy flow parameter set with parameters representing energy flow, and forming an information flow parameter set with parameters representing information flow; all parameters in the material flow parameter set, the information flow parameter set, and the energy flow parameter set together form the unmanned ship intelligent cabin system parameter set; inputting the historical data of the operation of the unmanned ship intelligent cabin system and each parameter in the unmanned ship intelligent cabin system parameter set into the trained neural network model to obtain the first weight of each parameter in the unmanned ship intelligent cabin system parameter set and the fourth weight in the parameter set of the flow represented by each parameter.

3. The method according to any one of claims 1 to 2, characterized in that: The step S3: based on the historical data of the operation of the unmanned ship intelligent cabin system, determining the second weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fifth weight of each parameter in the parameter set of the flow represented by each parameter; The second weight is modified based on the first weight of the parameter to obtain a third weight; The fifth weight is modified based on the fourth weight of the parameter to obtain a sixth weight, including: Step S31: constructing a historical efficacy matrix of the unmanned ship intelligent cabin system based on the historical data of the operation of the unmanned ship intelligent cabin system, and constructing a historical evaluation matrix based on the historical efficacy matrix; Step S32: Determine the second weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fifth weight of each parameter in the parameter set of the flow it represents based on the historical evaluation matrix; correct the second weight based on the first weight of the parameter in the parameter set of the unmanned ship intelligent cabin system to obtain the third weight of the parameter in the parameter set of the unmanned ship intelligent cabin system; correct the fifth weight based on the fourth weight of the parameter in the parameter set of the flow to obtain the sixth weight of the parameter in the parameter set of the flow.

4. The method according to claim 3, characterized in that The step S31 comprises: Step S311: Obtain S historical observation samples from the historical data, and construct a historical efficacy value matrix X based on the S historical observation samples. S : Wherein, S represents the number of historical observation samples, N represents the number of parameters in the parameter set of the unmanned ship intelligent cabin system; x ij It represents the power value of the observed value of the i-th parameter in the parameter set in the j-th observation sample, and its calculation formula is in, Take the maximum value of the i-th parameter in S historical observation samples, Take the minimum value of the i-th parameter in S historical observation samples; v i,j The calculation method is Among them, c i,j represents the observed value of the i-th parameter in the parameter set of the unmanned ship intelligent cabin system in the j-th observation sample; K i,j represents the theoretical target value corresponding to the i-th parameter in the parameter set of the unmanned ship intelligent cabin system in the j-th observation sample; Step S312: Calculate the historical efficacy value matrix X S Perform normalization: Then we get the historical evaluation matrix X′ S : Among them, x i ' ,j represents the historical evaluation value of the i-th parameter in the j-th historical observation sample of the unmanned ship intelligent cabin system parameter set; The step S32 comprises: Step S321: Based on the historical evaluation matrix X′ S , calculate the information entropy of each parameter: Where J = 1 / ln(S); only when x′ ij = 0, take H i Represents the information entropy of the i-th parameter in the parameter set of the unmanned ship intelligent cabin system; Step S322: For each parameter in the unmanned ship intelligent cabin system parameter set, perform the following operations: Determine the flow corresponding to the parameter, the corresponding flow is one of material flow, information flow, and energy flow, determine the number of the parameter in the corresponding flow parameter set, and calculate the fifth weight of the parameter in the flow: Among them, w 物质流,Ei1 represents the fifth weight of the i1th parameter in the material flow parameter set in the material flow, w 信息流,Ei1 represents the fifth weight of the i2th parameter in the information flow parameter set in the information flow, w 能量流,Ei1 represents the fifth weight of the i3th parameter in the energy flow parameter set in the energy flow; H 物质流,i1 represents the information entropy of the i1th parameter in the material flow parameter set, H 信息流,i2 represents the information entropy of the i2th parameter in the information flow parameter set, H 能量流,i3 represents the information entropy of the i3th parameter in the energy flow parameter set; N 物质流 Indicates the number of parameters in the material flow parameter set, N 信息流 Indicates the number of parameters in the information flow parameter set, N 能量流 Indicates the number of parameters in the energy flow parameter set; N 物质流 +N 信息流 +N 能量流 =N; Calculate the second weight w of the parameter in the unmanned ship intelligent cabin system parameter set Bi : Step S323: For each parameter in the unmanned ship intelligent cabin system parameter set, perform the following calculation: Let the first weight of the parameter in the unmanned ship intelligent cabin system parameter set be w Ai , the second weight is w Bi , like Then Otherwise, let ω′ i =w Bi ; After all parameters in the unmanned ship intelligent cabin system parameter set are calculated, a third weight w of each parameter in the unmanned ship intelligent cabin system parameter set is calculated. Ci : The third weight of each parameter in the unmanned ship intelligent cabin system parameter set satisfies: Step S324: For each parameter in the unmanned ship intelligent cabin system parameter set, perform the following operations: Determine a flow corresponding to the parameter, wherein the corresponding flow is one of a material flow, an information flow, and an energy flow; If the parameter is a material flow parameter, assume that the parameter is the i1th parameter in the material flow parameter set, and record the fourth weight of the parameter in the material flow parameter set as w 物质流,Di1 , the fifth weight of this parameter in the material flow parameter set is w 物质流,Ei 1. If Then Otherwise, let ω′ 物质流,i1 =w 物质流,Ei1 ; If the parameter is an information flow parameter, assuming that the parameter is the i2th parameter in the information flow parameter set, the fourth weight of the parameter in the information flow parameter set is w 信息流,Di2 , the fifth weight of this parameter in the information flow parameter set is w 信息流,Ei2 ,like Then Otherwise, let ω′ 信息流,i2 =w 信息流,Ei2 ; If the parameter is an energy flow parameter, assuming that the parameter is the i3th parameter in the energy flow parameter set, the fourth weight of the parameter in the energy flow parameter set is w 能量流,Di3 , the fifth weight of this parameter in the energy flow parameter set is w 能量流,Ei3 ,like Then Otherwise, let ω′ 能量流,i3 =w 能量流,Ei3 ; Step S325: After calculating the fifth weights corresponding to all parameters, calculate the sixth weight of the parameter in the flow parameter set: If the parameter is a material flow parameter, assuming that the parameter is the i1th parameter in the material flow parameter set, then the sixth weight w of the parameter in the material flow parameter set is 物质流,Fi1 : If the parameter is an information flow parameter, assuming that the parameter is the i2th parameter in the information flow parameter set, then the sixth weight w of the parameter in the information flow parameter set is 信息流,Fi2 : If the parameter is an energy flow parameter, assuming that the parameter is the i3th parameter in the energy flow parameter set, then the sixth weight w of the parameter in the energy flow parameter set is 能量流,Fi3 : Step S326: Obtain the corresponding flow parameter set weights for the material flow parameter set, information flow parameter set, and energy flow parameter set, respectively, and record them as W 物质流 , W 信息流 , W 能量流 ; Among them, the flow parameter set weight W of the material flow parameter set 物质流 =W is equal to the arithmetic sum of the third weights of each parameter in the material flow parameter set in the unmanned ship intelligent cabin system parameter set; the flow parameter set weight W of the information flow parameter set 信息流 = equal to the arithmetic sum of the third weights of each parameter in the information flow parameter set in the unmanned ship intelligent cabin system parameter set; the flow parameter set weight W of the energy flow parameter set 能量流 It is equal to the arithmetic sum of the third weights of each parameter in the energy flow parameter set in the unmanned ship intelligent cabin system parameter set.

5. The method according to claim 4, characterized in that The step S4: extracting parameter values ​​corresponding to various parameters from the current state data of the unmanned ship intelligent cabin system, and determining the task execution capability of the unmanned ship intelligent cabin system in combination with the third weight and the sixth weight of each parameter, including: Step S41: extracting the parameter values ​​corresponding to each parameter from the current state data of the unmanned ship intelligent cabin system, and establishing the current efficacy value vector X of the parameter set of the unmanned ship intelligent cabin system c : Among them, x c,i It represents the efficacy value of the current value of the i-th parameter in the system parameter set, and its calculation formula is in, Take the maximum value of the i-th parameter in S observation samples, Take the minimum value of the i-th parameter in S observation samples; v c,i The calculation method is Among them, c c,i represents the current observed value of the i-th parameter in the system parameter set; K c,i Represents the theoretical target value corresponding to the current observed value of the i-th parameter in the parameter set; Step S42: normalize the current efficacy value vector: Get the current evaluation vector X c ′: Among them, x c ' ,i represents the current evaluation value of the i-th parameter in the system parameter set; Step S43: Based on the historical evaluation matrix X′ S And the sixth weight of each parameter in the corresponding flow parameter set, calculate the historical order of each flow, the calculation method is Among them, OD 物质流,j OD 信息流,j OD 能量流,j They represent the historical order of material flow, information flow, and energy flow corresponding to the jth historical observation sample among the S historical observation samples; w 物质流,Fi1 represents the sixth weight of the i1th parameter in the material flow parameter set, w 信息流,Fi2 represents the sixth weight of the i2th parameter in the information flow parameter set, w 能量流,Fi3 represents the sixth weight of the i3th parameter in the energy flow parameter set; the corresponding number of the i1th parameter in the material flow parameter set in the unmanned ship intelligent cabin system parameter set is m1, the corresponding number of the i2th parameter in the information flow parameter set in the unmanned ship intelligent cabin system parameter set is m2, and the corresponding number of the i3th parameter in the energy flow parameter set in the unmanned ship intelligent cabin system parameter set is m3; on this basis, x′ m1,j That is, the historical evaluation value of the i1th parameter in the material flow parameter set in the jth historical observation sample, x′ m2,j That is, the historical evaluation value of the i2th parameter in the information flow parameter set in the jth historical observation sample, x′ m3,j That is, the historical evaluation value of the i3th parameter in the energy flow parameter set in the jth historical observation sample; Step S44: Based on the current evaluation vector X c ′ and the sixth weight of each parameter in the corresponding flow parameter set, calculate the current order of each flow, and the calculation method is: Among them, OD 物质流,c OD 信息流,c OD 能量流,c They represent the current order of material flow, the current order of information flow, and the current order of energy flow respectively; the corresponding number of the i1th parameter in the material flow parameter set in the unmanned ship intelligent cabin system parameter set is m1, the corresponding number of the i2th parameter in the information flow parameter set in the unmanned ship intelligent cabin system parameter set is m2, and the corresponding number of the i3th parameter in the energy flow parameter set in the unmanned ship intelligent cabin system parameter set is m3; on this basis, x′ c,m1 That is, the current evaluation value of the i1th parameter in the material flow parameter set, x′ c,m2 That is, the current evaluation value of the i2th parameter in the information flow parameter set, x′ c,m3 That is, the current evaluation value of the i3th parameter in the energy flow parameter set; Step S45: Calculate the system order corresponding to the jth historical observation sample in the S historical observation samples and the current order of the unmanned ship intelligent cabin system respectively, and the calculation method is: Among them, W 物质流 , W 信息流 , W 能量流 The flow parameter set weights corresponding to the material flow parameter set, information flow parameter set, and energy flow parameter set respectively; SOD j SOD represents the historical order of the unmanned ship intelligent engine room system corresponding to the jth historical observation sample among the S historical observation samples; c Indicates the current orderliness of the unmanned ship intelligent engine room system; Step S46: SOD max is the maximum value of the system order corresponding to each historical observation sample in S historical observation samples; Step S47: According to the current order degree SOD of the unmanned ship intelligent cabin system c , calculate and determine the current task execution capability SE of the unmanned ship intelligent cabin system as Wherein, R represents the design performance redundancy ratio of the unmanned ship intelligent cabin system.

6. A device for evaluating the task execution capability of an unmanned ship intelligent engine room system based on the three-stream collaboration theory, characterized in that: include: Parameter determination module: configured to determine various parameters representing material flow, energy flow, and information flow supporting the operation of the unmanned ship intelligent cabin system, and all parameters constitute a parameter set of the unmanned ship intelligent cabin system; A weight module: configured to input the historical data of the operation of the unmanned ship intelligent cabin system and each parameter in the parameter set of the unmanned ship intelligent cabin system into the trained neural network model, and obtain the first weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fourth weight in the parameter set of the flow represented by each parameter; A weight correction module: configured to determine the second weight of each parameter in the parameter set of the unmanned ship intelligent cabin system and the fifth weight of each parameter in the parameter set of the flow represented by each parameter based on the historical data of the operation of the unmanned ship intelligent cabin system; The second weight is modified based on the first weight of the parameter to obtain a third weight; The fifth weight is modified based on the fourth weight of the parameter to obtain a sixth weight; Calculation module: configured to extract parameter values ​​corresponding to various parameters from the current state data of the unmanned ship intelligent cabin system, and determine the task execution capability of the unmanned ship intelligent cabin system in combination with the third weight and the sixth weight of each parameter.

7. A computer-readable storage medium, characterized in that: The storage medium stores a plurality of instructions; the plurality of instructions are used for a processor to load and execute the method as described in any one of claims 1 to 5.

8. An electronic device, characterized in that: The electronic device comprises: A processor, which is used to execute multiple instructions; A memory for storing a plurality of instructions; The plurality of instructions are used to be stored in the memory and loaded and executed by the processor according to any one of claims 1 to 5.

Images