Multi-domain control system collaborative network model construction method and system

Abstract

The invention discloses a multi-domain control system collaborative network model construction method and system, and relates to the technical field of data processing, and the method comprises the following steps: S1, carrying out the clustering of existing control elements, dividing the existing control elements into a plurality of domains, obtaining a domain set # imgabs0 #, and constructing an initial network model with the control elements as nodes and the relation between the nodes as edges; according to the multi-domain control system collaborative network model construction method and system, the efficiency of establishing a control system collaborative network model can be improved, and the established control system collaborative network model is relatively high in correlation, so that the efficiency of control decision is improved, the contribution degree of nodes selected by an HL is fully considered, the efficiency of collaborative control is further improved, and the method and system are suitable for popularization and application. By reasonably configuring the HL, the waste of the HL is avoided, the cost is saved, and the sent information is sent through a plurality of carriers, so that the confidentiality is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for constructing a collaborative network model of a multi-domain control system. Background Art

[0002] The number of component systems that constitute the collaborative network model of a multi-domain control system is large, and the interconnections and interactions are complex. Under the condition of limited resources, there are situations of mutual cooperation and competition. When there are problems in the cooperation between the component systems, the interaction between the component systems may change under the pressure of competition, which will cause changes in the system architecture and then cause changes in the system behavior. On the other hand, the future environment is uncertain. When the environment changes, the system must adapt to the new changes, which requires the system to make corresponding structural and behavioral changes. Therefore, a method and system for constructing a collaborative network model of a multi-domain control system is proposed. Summary of the invention

[0003] In view of the deficiencies in the prior art, the present invention provides a method and system for constructing a collaborative network model of a multi-domain control system, which solves the problems raised in the above-mentioned background technology.

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for constructing a collaborative network model of a multi-domain control system, comprising the following steps: S1: Cluster the existing control elements into multiple domains to obtain domain sets , construct the initial network model with control elements as nodes and the relationships between nodes as edges; S2: Calculate newly discovered control factors Combine with existing domain Each domain in If the domain set Each domain in Both repel each other and execute ; If there are non-exclusive domains, the set of non-exclusive domains is denoted by , then calculate the newly discovered control factor v i The similarity of each non-exclusive domain in the set of non-exclusive domains ; S3: If Less than the threshold, execute ;like If it is greater than or equal to the threshold, the newly discovered control factor Place The largest domain, calculate the newly discovered control elements The topological association with existing control elements in the domain and connected by edges; S4: Based on the newly discovered control factors Create a new domain , and the domain Join Domain Collection middle; S5: Repeat S2, S3 and S4 until all newly discovered control elements are Clustering is completed and a collaborative network model of the control system is formed.

[0005] Optionally, the control elements include control monitoring nodes, decision nodes, HL selected nodes and target nodes; The control monitoring node obtains the information of the target node in real time and transmits it to the decision node through the encrypted communication network; The decision node includes an information fusion module and an intelligent decision module; The information fusion module aggregates the information provided by multiple control monitoring nodes, and generates control targets based on the aggregated information; The intelligent decision-making module includes a data selection module, a graph attention mechanism model layer and a BP neural network; The data selection module Select from the control system collaborative network model according to the control target at any time entities, Each entity consists of a target node and HL selected nodes, HL selected nodes form a HL node set ;Will HL selected nodes The feature vector of the target at each moment is input into each graph attention mechanism model in the graph attention mechanism model layer; The graph attention mechanism model layer includes The graph attention mechanism model, The graph attention mechanism model is Output the completion vector of the target at all times , so the output vector of the graph attention mechanism model layer is ; BP neural network based on The input vector at time generate Moment control indicator items.

[0006] Optionally, according to the above content: (1) In formula (1), is the activation function, Select the node set for HL The HL selects nodes, and the feature vector of the selected target For The feature vector of the target selected by the HL selected node Contribution of is the activation function; Parameters from the input layer to the hidden layer of the graph attention mechanism model; represents the parameter matrix; Indicates that and Put it together.

[0007] Optionally, S4: based on the newly discovered control element Create a new domain , and the domain Join Domain Collection The node set selected by HL middle The selection of a HL selected node includes the following steps: S41: ; S42: Calculate the HL selected node set according to formula (2) To target Achievement value: (2) In the formula, Select the node set for HL HL selected node in To target Ability to achieve; S43: Judgement, if , then the HL node set is considered Not enough to achieve the goal , , and then returns to S42; if , then the target is considered selected The HL node set Enough to achieve the goal , and then execute S44, where, For the goal The completion value of S44: Output HL selected node set And the set corresponds to the selected target .

[0008] Optionally, the control monitoring node, decision node and HL selected node all include a communication device, and the communication device includes a wireless transmitter and a wireless receiver; The wireless transmitter comprises: a first measuring unit, a sending controller and a sending unit; The first measuring unit measures the electromagnetic wave environment between a wireless transmitter of a first node and a wireless receiver of a second node that communicate with each other based on wireless resources; The transmission controller determines the wireless resources and parameters used in transmitting the bit information sequence based on the measurement result of the first measurement unit; The sending unit selects a frequency combination according to the wireless resource, and generates a bit group symbol according to the frequency combination; The wireless receiver comprises: a second measuring unit, a receiving controller, a receiving unit and a decoding unit; The second measuring unit measures the electromagnetic wave environment between the wireless transmitter of the first node and the wireless receiver of the second node which communicate with each other according to the wireless resources; The receiving controller estimates a frequency combination based on a measurement result of the second measuring unit; The receiving unit receives a bit group special number; The decoding unit decodes the received bit group symbol based on the frequency combination.

[0009] Optionally, the sending unit includes a source input module, a bit grouping module, a mapper and a modulator; The information source input module is used to receive the bit information sequence to be modulated after information source coding; The bit grouping module divides the bit information sequence into groups of K bits and provides them to the symbol mapper. The bit sequence is Combination of The mapper maps a combination into a bit group symbol according to an agreed confidentiality rule; The modulator selects from the wireless resources measured by the first measurement unit carrier frequency and modulate the adjacent 4 symbols to On the four phases of a carrier frequency.

[0010] Optionally, the decoding unit includes a plurality of receiving modules, a multi-channel demodulation module and a calculation module; Each of the receiving modules converts the signal received by the receiving antenna into electrical data; The multi-channel demodulation module includes a multiplication module, an integration module and a modulus module; The multiplication module is used to multiply each electrical data with the complex conjugate value of the bit group symbol and send it to the integration module; The integration module integrates the received signal within a symbol length in the time domain, and then sends it to the modulo module to obtain its absolute value to obtain the received value, and the calculation module obtains the bit confidence probability according to the received value.

[0011] Optionally, the calculation module includes a probabilistic neural network, which includes an input layer, a hidden layer and an output layer, the input layer inputs the received value of the multi-channel demodulation module, and the output layer outputs the bit confidence probability.

[0012] A multi-domain control system collaborative network model construction system includes a storage medium and several processors, the storage medium stores computer program code, and the processor calls the computer program code in the storage medium to implement the above-mentioned method.

[0013] The present invention provides a method and system for constructing a collaborative network model of a multi-domain control system, which has the following beneficial effects: The method and system for constructing a collaborative network model of a multi-domain control system can improve the efficiency of establishing a collaborative network model of a control system, and the established collaborative network model of a control system has a strong correlation, thereby improving the efficiency of control decision-making, fully considering the contribution of the nodes selected by HL, and further improving the efficiency of collaborative control. By reasonably configuring HL, there is no waste of HL, saving costs, and the information to be transmitted is sent through multiple carriers, thereby improving confidentiality. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a flow chart of the control system collaborative network model construction method of the present invention; Figure 2 It is a block diagram of the composition of the intelligent decision-making module of the decision node of the present invention; Figure 3 is a flow chart of the HL configuration method of the present invention; Figure 4 It is a block diagram of the composition of the wireless transmitter of each node of the present invention; Figure 5 It is a block diagram of the composition of the wireless receiver of each node of the present invention. DETAILED DESCRIPTION

[0015] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0016] Embodiment 1 See also Figures 1 to 5 The present invention provides a technical solution: a method for constructing a collaborative network model of a multi-domain control system, comprising the following steps: S1: Cluster the existing control elements into multiple domains to obtain domain sets , construct the initial network model with control elements as nodes and the relationships between nodes as edges; S2: Calculate newly discovered control factors Combine with existing domain Each domain in If the domain set Each domain in are mutually exclusive, execute S4; if there are non-exclusive domains, the non-exclusive domain set is recorded as , then calculate the newly discovered control factor v i The similarity of each non-exclusive domain in the set of non-exclusive domains ; S3: If Less than the threshold, execute ;like If it is greater than or equal to the threshold, the newly discovered control factor Place The largest domain, calculate the newly discovered control elements The topological association with existing control elements in the domain and connected by edges; S4: Based on the newly discovered control factors Create a new domain , and the domain Join Domain Collection middle; S5: Repeat S2, S3 and S4 until all new findings have control elements Clustering is completed and a collaborative network model of the control system is formed.

[0017] Through the technical solution proposed in the present invention, the efficiency of establishing a collaborative network model of a control system is improved, and the established collaborative network model of the control system has strong correlation, which improves the efficiency of control decision-making.

[0018] Among them, the control elements include control monitoring nodes, decision nodes, HL selected nodes and target nodes; The control monitoring node obtains the information of the target node in real time and transmits it to the decision node through the encrypted communication network; The decision node includes an information fusion module and an intelligent decision module; The information fusion module aggregates the information provided by multiple control monitoring nodes, and generates control targets based on the aggregated information; like Figure 2 As shown, the intelligent decision-making module includes a data selection module, a graph attention mechanism model layer and a BP neural network; The data selection module is Select from the control system collaborative network model according to the control target at any time entities, Each entity consists of a target node and HL selected nodes, HL selected nodes form a HL node set ;Will HL selected nodes The feature vector of the target at each moment is input into each graph attention mechanism model in the graph attention mechanism model layer; The graph attention mechanism model layer includes The graph attention mechanism model, The graph attention mechanism model is Output the completion vector of the target at all times , so the output vector of the graph attention mechanism model layer is ; BP neural network based on The input vector at time generate Moment Control indicator items; From the above we can get: (1) In the formula, is the activation function, Select the node set for HL The HL selects nodes, and the feature vector of the selected target For The feature vector of the target selected by the HL selected node Contribution of is the activation function; Parameters from the input layer to the hidden layer of the graph attention mechanism model; represents the parameter matrix; Indicates that and Put it together.

[0019] The proposed scheme fully considers the contribution between the nodes selected by HL, thereby improving the control efficiency of collaborative control; like Figure 3 As shown, S4: Based on the newly discovered control factors Create a new domain , and the domain Join Domain Collection The node set selected by HL middle The selection of a HL selected node includes the following steps: S41: ; S42: Calculate the HL selected node set according to formula (2) To target Achievement value: (2) In the formula, Select the node set for HL HL selected node in To target Ability to achieve; S43: Judgement, if , then the HL node set is considered Not enough to achieve the goal , , and then returns to S42; if , then the target is considered selected The HL node set Enough to achieve the goal , and then execute S44, where, For the goal The completion value of S44: Output HL selected node set And the set corresponds to the selected target .

[0020] Through the proposed solution, HL is reasonably configured, which will avoid waste of HL and save costs.

[0021] Wherein, the control monitoring node, the decision node and the HL selected node all include a communication device, and the communication device all includes a wireless transmitter and a wireless receiver; like Figure 4 As shown, the wireless transmitter includes: a first measuring unit, a sending controller and a sending unit; A first measuring unit, measuring an electromagnetic wave environment between a wireless transmitter of a first node and a wireless receiver of a second node that communicate with each other according to wireless resources; A transmission controller, which determines the radio resources and parameters used in transmitting the bit information sequence based on the measurement result of the first measurement unit; The sending unit selects a frequency combination according to wireless resources and generates a bit group symbol according to the frequency combination.

[0022] The sending unit includes a source input module, a bit grouping module, a mapper and a modulator; The information source input module is used to receive the bit information sequence to be modulated after information source coding; The bit grouping module divides the bit information sequence into groups of K bits and provides them to the symbol mapper. The bit sequence is Combination of A mapper maps a combination into a bit group symbol according to an agreed confidentiality rule; A modulator selects from the wireless resources measured by the first measurement unit carrier frequency and modulate the adjacent 4 symbols to On the four phases of a carrier frequency.

[0023] like Figure 5 As shown, the wireless receiver includes: a second measuring unit, a receiving controller, a receiving unit and a decoding unit; a second measuring unit, measuring an electromagnetic wave environment between a wireless transmitter of a first node and a wireless receiver of a second node that communicate with each other according to wireless resources; a receiving controller that estimates a frequency combination based on a measurement result of the second measurement unit, A receiving unit, receiving a bit group signal according to a wireless resource; The decoding unit decodes the received bit group symbol based on the frequency combination.

[0024] The decoding unit includes: multiple receiving modules, a multi-channel demodulation module and a calculation module. Each receiving module converts the signal received by the receiving antenna into electrical data, and each demodulation module includes a multiplication module, an integration module and a modulus module; The multiplication module is used for multiplying each electrical data with the complex conjugate value of the bit group symbol and sending the result to the integration module; The integration module integrates the received signal within a symbol length in the time domain, and then sends it to the modulo module to obtain its absolute value to obtain the received value; the calculation module obtains the bit confidence probability based on the received value.

[0025] The calculation module includes a probabilistic neural network, which includes an input layer, a hidden layer and an output layer. The input layer inputs the received value of the multi-channel demodulation module; the output layer outputs the bit confidence probability.

[0026] This scheme can send the information through multiple carriers, thereby improving confidentiality.

[0027] Embodiment 2 The present invention also provides a multi-domain control system collaborative network model construction system, including a storage medium and a plurality of processors, the storage medium stores computer program code, and the processor calls the computer program code in the storage medium to implement the above-mentioned proposed method.

[0028] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for constructing a collaborative network model of a multi-domain control system, characterized in that: The following steps are involved: S1: Cluster the existing control elements into multiple domains to obtain domain sets , construct the initial network model with control elements as nodes and the relationships between nodes as edges; S2: Calculate newly discovered control factors Combine with existing domain Each domain in If the domain set Each domain in Both repel each other and execute ; If there are non-exclusive domains, the set of non-exclusive domains is denoted by , then calculate the newly discovered control factor v i The similarity of each non-exclusive domain in the set of non-exclusive domains ; S3: If Less than the threshold, execute ;like If it is greater than or equal to the threshold, the newly discovered control factor Place The largest domain, calculate the newly discovered control elements The topological association with existing control elements in the domain and connected by edges; S4: Based on the newly discovered control factors Create a new domain , and the domain Join Domain Collection middle; S5: Repeat S2, S3 and S4 until all newly discovered control elements are Clustering is completed and a collaborative network model of the control system is formed.

2. A method for constructing a collaborative network model of a multi-domain control system according to claim 1, characterized in that: The control elements include control monitoring nodes, decision nodes, HL selected nodes and target nodes; The control monitoring node obtains the information of the target node in real time and transmits it to the decision node through the encrypted communication network; The decision node includes an information fusion module and an intelligent decision module; The information fusion module aggregates the information provided by multiple control monitoring nodes, and generates control targets based on the aggregated information; The intelligent decision-making module includes a data selection module, a graph attention mechanism model layer and a BP neural network; The data selection module Select from the control system collaborative network model according to the control target at any time entities, Each entity consists of a target node and HL selected nodes, HL selected nodes form a HL node set ;Will HL selected nodes The feature vector of the target at each moment is input into each graph attention mechanism model in the graph attention mechanism model layer; The graph attention mechanism model layer includes The graph attention mechanism model, The graph attention mechanism model is Output the completion vector of the target at all times , so the output vector of the graph attention mechanism model layer is ; BP neural network based on The input vector at time generate Moment control indicator items.

3. The method for constructing a collaborative network model of a multi-domain control system according to claim 1, characterized in that: According to the above content, we can get: （1） In formula (1), is the activation function, Select the node set for HL The HL selects nodes, and the feature vector of the selected target For The feature vector of the target selected by the HL selected node Contribution of is the activation function; Parameters from the input layer to the hidden layer of the graph attention mechanism model; represents the parameter matrix; Indicates that and Put it together.

4. The method for constructing a collaborative network model of a multi-domain control system according to claim 1, characterized in that: S4: Based on the newly discovered control elements Create a new domain , and the domain Join Domain Collection The node set selected by HL middle The selection of a HL selected node includes the following steps: S41： ； S42: Calculate the HL selected node set according to formula (2) To target Achievement value: (2) In the formula, Select the node set for HL HL selected node in To target Ability to achieve; S43: Judgement, if , then the HL node set is considered Not enough to achieve the goal , , and then returns to S42; if , then the target is considered selected The HL node set Enough to achieve the goal , and then execute S44, where, For the goal The completion value of S44: Output HL selected node set And the set corresponds to the selected target .

5. The method for constructing a collaborative network model of a multi-domain control system according to claim 1, characterized in that: The control monitoring node, decision node and HL selected node all include a communication device, and the communication device includes a wireless transmitter and a wireless receiver; The wireless transmitter comprises: a first measuring unit, a sending controller and a sending unit; The first measuring unit measures the electromagnetic wave environment between a wireless transmitter of a first node and a wireless receiver of a second node that communicate with each other based on wireless resources; The transmission controller determines the wireless resources and parameters used in transmitting the bit information sequence based on the measurement result of the first measurement unit; The sending unit selects a frequency combination according to the wireless resource, and generates a bit group symbol according to the frequency combination; The wireless receiver comprises: a second measuring unit, a receiving controller, a receiving unit and a decoding unit; The second measuring unit measures the electromagnetic wave environment between the wireless transmitter of the first node and the wireless receiver of the second node which communicate with each other according to the wireless resources; The receiving controller estimates a frequency combination based on a measurement result of the second measuring unit; The receiving unit receives a bit group special number; The decoding unit decodes the received bit group symbol based on the frequency combination.

6. The method for constructing a collaborative network model of a multi-domain control system according to claim 1, characterized in that: The sending unit includes a source input module, a bit grouping module, a mapper and a modulator; The information source input module is used to receive the bit information sequence to be modulated after information source coding; The bit grouping module divides the bit information sequence into groups of K bits and provides them to the symbol mapper. The bit sequence is Combination of The mapper maps a combination into a bit group symbol according to an agreed confidentiality rule; The modulator selects from the wireless resources measured by the first measurement unit carrier frequency and modulate the adjacent 4 symbols to On the four phases of a carrier frequency.

7. The method for constructing a collaborative network model of a multi-domain control system according to claim 1, characterized in that: The decoding unit includes a plurality of receiving modules, a multi-channel demodulation module and a calculation module; Each of the receiving modules converts the signal received by the receiving antenna into electrical data; The multi-channel demodulation module includes a multiplication module, an integration module and a modulus module; The multiplication module is used to multiply each electrical data with the complex conjugate value of the bit group symbol and send it to the integration module; The integration module integrates the received signal within a symbol length in the time domain, and then sends it to the modulo module to obtain its absolute value to obtain the received value, and the calculation module obtains the bit confidence probability according to the received value.

8. The method for constructing a collaborative network model of a multi-domain control system according to claim 1, characterized in that: The calculation module includes a probabilistic neural network, which includes an input layer, a hidden layer and an output layer. The input layer inputs the received value of the multi-channel demodulation module, and the output layer outputs the bit confidence probability.

9. A multi-domain control system collaborative network model construction system, characterized by: The method comprises a storage medium and several processors, wherein the storage medium stores computer program codes, and the processors call the computer program codes in the storage medium to implement any of the methods described in claims 1-4.

Images