Loosely coupled federated system alignment method, device, equipment and storage medium

Abstract

The present application relates to a loosely coupled federal system alignment method, device, equipment and storage medium. The loosely coupled federal system alignment method comprises: in each state transition process of the federal system, state alignment is performed according to a pre-selected federal member benchmark state; when aligning the benchmark state, the state section of each attribute state of each federal member in the federal system is determined according to a pre-built federal system state space model. The present application selects a certain state of a federal member as a comparison benchmark. Under this state alignment, other attribute states of the federal members are calculated and compared to approximate the continuous system behavior. Compared with the clock alignment method, selecting a benchmark state with actual physical significance for alignment is more in line with actual engineering applications. At the same time, it effectively overcomes the shortcomings of the existing clock alignment method based on a single time variable that cannot fully and flexibly explain the evolution of the behavior of the loosely coupled federal system.

Description

Technical Field

[0001] The present application relates to the field of industrial Internet, and in particular to a loosely coupled federated system alignment method, device, equipment and storage medium. Background Art

[0002] With the in-depth application of the industrial Internet, all industrial elements such as machines, materials, products, tooling, people and software systems will break the heterogeneous constraints to carry out information circulation, interconnection and interoperation. The future industrial Internet must be a CPS (cyber-physical system) that integrates virtuality and reality, and the loosely coupled federated system can better represent CPS. The federated system consists of multiple federated members. Federated members can be physical objects, such as industrial elements such as equipment, systems, and tooling in the real world, or virtual objects, such as models, algorithms, and software. A loosely coupled federated system refers to a federated system that is connected and flexibly customized on demand, has a dynamic variable structure, and can meet the application requirements of dynamic joining and exiting of industrial elements. The loosely coupled federated system is data-centric. The state data of each federated member collected constitutes a state aspect of the federated system, and massive data is combined into a discrete state space. In order to ensure the logical correctness and causal relationship of data flow between federated members, the data needs to be under the same comparison benchmark to have practical significance. Therefore, it is necessary to study the state alignment technology of loosely coupled federated systems to ensure that federated members interoperate at the right "location" at the right time, ensure the accuracy of federated member state changes, and drive the evolution of federated system behavior.

[0003] At present, the clock alignment method is generally used. In discrete event simulation, a fixed clock advancement step is set, synchronization points are declared and registered, clock advancement is requested, and instructions (including clock information) are sent. After all federation members complete simulation advancement, the simulation clock is declared, registered, applied for, and advanced again, so that the simulation clocks of each distributed federation member remain consistent.

[0004] In a loosely coupled federated system with a dynamic variable structure, the physical system and the virtual system are deeply integrated, and the system behavior evolution is driven by data. In this case, data is not always based on time. In this case, the clock alignment method has the following shortcomings:

[0005] 1) The clock alignment method cannot well explain the evolution of system behavior. On the one hand, there are cases where the data of federated members are not all based on time, and choosing the actual physical state is more meaningful; on the other hand, the time scale of the physical system and the virtual system is quite different. In this case, the clock alignment method cannot well explain the evolution of system behavior.

[0006] 2) The clock alignment method lacks flexibility and is inefficient. Since the federated system is a dynamically variable structure, the member connection matrix is ​​sparse, and the timeliness of data flow between members is different. The clock alignment method sets a fixed clock step size, and all federated members must reach the clock synchronization point before the next clock advance. At the same time, the efficiency is low, and federated members cannot dynamically join and exit, and cannot flexibly cope with the dynamic variable structure of the loosely coupled system.

[0007] In view of the shortcomings of the above clock alignment methods, a state alignment method is proposed. State alignment refers to selecting a certain state of a federation member as a comparison benchmark. Under this state alignment, other attribute states of the federation members are calculated and compared to approximate the behavior of the continuous system. Compared with the clock alignment method, selecting states with actual physical significance for alignment is more in line with actual engineering applications. In addition, for dynamic variable structures, the reference state is flexibly selected. This method is proposed to overcome the shortcomings of the existing clock alignment method based on a single time variable, which cannot fully explain the behavior evolution mechanism of the loosely coupled federation system and lacks flexibility for dynamic real-time variable structures. Summary of the invention

[0008] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides a loosely coupled federated system alignment method, apparatus, device and storage medium.

[0009] In a first aspect, the present application provides a loosely coupled federated system alignment method, the loosely coupled federated system alignment method comprising:

[0010] During each state transition of the federation system, state alignment is performed according to a pre-selected federation member benchmark state; the federation system is composed of a plurality of federation members;

[0011] When aligning the baseline state, the state slice of each attribute state of each federation member in the federation system is determined according to the pre-built federation system state space model.

[0012] Optionally, the loosely coupled federated system alignment method further includes:

[0013] Constructing a connection matrix A according to the data interaction relationship between the federation members in the federation system;

[0014] According to the connection matrix A, a federation member state space model for reflecting the state information of each federation member is constructed; the federation member state information is composed of a plurality of attribute states;

[0015] Constructing the federation system state space model according to the state space models of each federation member;

[0016] The data interaction relationship is:

[0017]

[0018] Where m represents the number of federation members in the federation system.

[0019] Optionally, constructing a federation member state space model for reflecting state information of each federation member according to the connection matrix A includes:

[0020] For each federation member, determining a plurality of attribute states possessed by the federation member;

[0021] Determine the own state variables corresponding to each attribute state and the input state data of the associated member according to the connection matrix A;

[0022] Constructing a first state equation only related to the attribute state of the federation member itself according to the self state variable;

[0023] A second state equation related to the attribute state of the federation member itself and the control of the input state data is constructed according to the input state data; wherein the first state equation and the second state equation constitute a state space model of the federation member.

[0024] Optionally, according to the state space model of each federation member, the federation system state space model is constructed using the following formula:

[0025]

[0026] in, Indicates the (k+1) state of the federated system, k indicates the state transition iteration order index, The state transfer matrix of the federated system representing the first state equation, represents the state transfer matrix of the federated system of the second state equation, the symbol ⊙ represents the Hadamard product of the two matrices, and W(k) represents the state space error.

[0027] Optionally, the loosely coupled federated system alignment method further includes:

[0028] According to the data interaction conditions and / or data interaction frequency of the federation members, the same attribute state among the federation members is selected as the benchmark state.

[0029] Optionally, the states are aligned according to the pre-selected federation member benchmark states in the following manner:

[0030] When the value of the federation member benchmark state is a certain value, mapping and aligning the federation member benchmark state;

[0031] When the value of the federation member reference state is an uncertain value, parameter polynomial alignment is performed on the federation member reference state.

[0032] In a second aspect, the present application provides a loosely coupled federated system alignment device, the loosely coupled federated system alignment device comprising:

[0033] A state space module, used to construct the state space model of the federation system according to the state space models of each federation member;

[0034] A state alignment module, used for performing state alignment according to a pre-selected reference state of a federation member during each state transition of a federation system; the federation system is composed of a plurality of federation members;

[0035] When aligning the baseline state, the state slice of each attribute state of each federation member in the federation system is determined according to the pre-built federation system state space model.

[0036] Optionally, the state space module is specifically used to construct a connection matrix A according to the data interaction relationship between the federation members in the federation system; construct a federation member state space model for reflecting the state information of each federation member according to the connection matrix A; and construct the federation system state space model according to the state space models of each federation member;

[0037] The data interaction relationship is:

[0038]

[0039] Where m represents the number of federation members in the federation system.

[0040] In a third aspect, the present application provides a loosely coupled federated system alignment device, the loosely coupled federated system alignment device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor;

[0041] When the computer program is executed by the processor, the steps of the loosely coupled federated system alignment method as described in any one of the above items are implemented.

[0042] In a fourth aspect, the present application provides a computer-readable storage medium, on which a loosely coupled federal system alignment program is stored. When the federal system alignment program is executed by a processor, the steps of the loosely coupled federal system alignment method as described in any of the above items are implemented.

[0043] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art:

[0044] Each embodiment of the present application performs state alignment according to a pre-selected federal member reference state during each state transition of the federal system; the federal system is composed of multiple federal members, and when the reference state is aligned, the state section of each attribute state of each federal member in the federal system is determined according to the pre-constructed federal system state space model, so as to select a certain state of the federal member as a comparison benchmark. Under this state alignment, other attribute states of the federal members are calculated and compared to approximate the continuous system behavior. Compared with the clock alignment method, selecting a reference state with actual physical significance for alignment is more in line with actual engineering applications. In addition, for dynamically variable structures, the reference state can also be flexibly selected. At the same time, it effectively overcomes the shortcomings of the existing clock alignment method based on a single time variable that cannot fully explain the behavior evolution mechanism of the loosely coupled federal system and lacks flexibility for dynamic real-time variable structures. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0047] Figure 1 A main flow chart of a loosely coupled federated system state alignment method provided by an embodiment of the present invention;

[0048] Figure 2 A flowchart of a method for aligning states of an optionally loosely coupled federated system provided by an embodiment of the present invention;

[0049] Figure 3 A schematic diagram of a process flow provided by an embodiment of the present invention;

[0050] Figure 4 A federation member connection relationship diagram provided for an embodiment of the present invention;

[0051] Figure 5 A federation member state space diagram provided for an embodiment of the present invention;

[0052] Figure 6 A schematic diagram of the federated system state alignment provided by an embodiment of the present invention;

[0053] Figure 7 A schematic diagram of the structure of a loosely coupled federated system state alignment device provided by an embodiment of the present invention;

[0054] Figure 8 A schematic diagram of an optional structure of a loosely coupled federated system state alignment device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0056] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present invention, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0057] Embodiment 1

[0058] The embodiment of the present invention provides a loosely coupled federated system alignment method, such as Figure 1 As shown, the loosely coupled federated system alignment method includes:

[0059] S101, in each state transition process of the federation system, aligning the state according to a pre-selected federation member benchmark state; the federation system is composed of a plurality of federation members;

[0060] S102, when aligning the reference state, determine the state slice of each attribute state of each federation member in the federation system according to the pre-built federation system state space model.

[0061] Among them, the federation system: a distributed system that defines different federations according to different purposes to achieve specific purposes. A federation is composed of multiple federation members. Federation members: constitute a federation system, and federation members can be equipment, systems, tooling, models, algorithms, software, etc. Loose coupling: federation members are loosely connected, and there is a data flow relationship between members, but they are not directly connected and have no mutual restrictions. The disconnection of any federation member has no effect on other members. System behavior evolution: the process of federation member state change and the effective operation of the federation system.

[0062] The embodiment of the present invention performs state alignment according to a pre-selected federal member reference state during each state transition of the federal system; the federal system is composed of multiple federal members, and when the reference state is aligned, the state section of each attribute state of each federal member in the federal system is determined according to a pre-constructed federal system state space model, so that a certain state of the federal member is selected as a comparison benchmark. Under this state alignment, other attribute states of the federal members are calculated and compared to approximate the continuous system behavior. Compared with the clock alignment method, selecting a reference state with actual physical significance for alignment is more in line with actual engineering applications. In addition, for dynamic variable structures, the reference state can also be flexibly selected. At the same time, it effectively overcomes the shortcomings of the existing clock alignment method based on a single time variable that cannot fully explain the behavior evolution mechanism of the loosely coupled federal system and lacks flexibility for dynamic real-time variable structures.

[0063] The embodiments of the present invention can effectively solve the problem of consistent representation of spatiotemporal data calculation of federation members, can better explain the evolution of loosely coupled system behavior, and flexibly respond to the dynamic variable structure of the loosely coupled system.

[0064] The following uses the CPS (Cyber-Physical Systems) application that links virtual space with physical space as an example to explain the loosely coupled federated system state alignment method and device. The optional embodiment of the present invention is a part of a complex product production process, which includes a total of 4 processes. Each process establishes a corresponding virtual prototype for simulation calculation, and the material flow between the processes is operated by a handling robot. Figure 2 As shown, the specific process is as follows:

[0065] 1. First, a connection matrix A is constructed based on the data interaction relationship between the federation members in the federation system. For example, based on the loosely coupled federation system, the data interaction relationship between the federation members is defined through the publish / subscribe mode, and the interaction relationship between the members is represented by the connection matrix. In this embodiment, there are 5 federation members, and the connection matrix is ​​represented by A(R 5×5 ) means, let element a ij ∈A indicates that federation member i and j have data interaction. When member i sends data to j, a ij =1, otherwise 0;

[0066]

[0067] The data interaction between federation members is loosely coupled, and data transmission is directional, so the matrix A is a 5×5 square matrix. The connection matrix changes with the changes in the composition structure of the federation system. The data interaction between federation members is local, and data transmission is directional, so the connection matrix A is a sparse matrix. When the structure of the loosely coupled federation system changes, the connection matrix A also changes accordingly.

[0068] The process flow of this embodiment is shown as follows Figure 3 As shown in the figure, the workpiece is moved from federation member 1 to federation member 2 by the robot according to the processing order, then flows to federation member 3 and federation member 4, and finally placed at the finished product by the robot. The system state is mainly driven and controlled by the action state of federation member robot 5. The publish / subscribe relationship of the federation member is shown in the figure. Figure 4 The connection matrix is:

[0069]

[0070] 2. According to the connection matrix A, a federation member state space model is constructed to reflect the state information of each federation member; according to each federation member state space model, the federation system state space model is constructed. Specifically, for each federation member, multiple attribute states of the federation member state information are determined; according to the connection matrix A, the own state variables and input state data corresponding to each attribute state are determined; according to the own state variables, a first state equation related only to the attribute state of the federation member itself is constructed; this type of state model is only related to the member's own state and is not affected by the state data of other members. According to the input state data, a second state equation controlled by the attribute state of the federation member itself and the input state data of the associated members is constructed; this type is a state space model controlled by combining its own state and subscribed state data.

[0071] For example, a state space model of each federation member is constructed, and then the state space model of each federation member is used to form a state space model of the federation system; wherein, the state space model of the federation system is constructed according to the composition of the federation system; and the implementation steps are: analyzing the movement mechanism of the federation members, obtaining the state equations of the federation members, and for the federation members with interactive relationships, their state equations are functions of their own state variables and input state data.

[0072] In this embodiment, the state equation of the federation member is calculated as follows: Assume that the state variable of one of the federation members is X = [x, y, u, v], and the member subscribes to the data state variables X of the federation members j and k. j ,X k , and as the input of state variables u, v. Then the state space equation of a single federation member is expressed as:

[0073]

[0074] where f iis the state equation of the i-th state. In this embodiment, the value of i is 1 to 4. The state equation of attribute state x, y is a function of the member's own state and is not affected by the state data of other federated members. The state equation of attribute state u, v is a function of the member's own state and the subscribed member state as the control variable. The state of u, v is affected by the input state variable (input state data). In detail, formula (3) is the robot's four-degree-of-freedom equation, where x represents the lateral distance, y represents the longitudinal distance, u represents the lateral speed, and v represents the longitudinal speed. It means taking the derivative of variable x, the derivative of distance is velocity, and the derivative of velocity is acceleration. j Represents the input state data of federation member j, that is, X j =[x j ,y j ,u j ,v j ], member X k =[x k ,y k ,u k ,v k ].

[0075] Now we describe the federation member state space model in a unified format. The unified format description is to write the input states of different members together, such as X j , X k Use the same X to represent X J =[x J ,y J ,u J ,v J ]J=k,j; the federation member status information is symbolized by X i Indicates that X i ∈R n is an n-dimensional vector, and the input vector is the member status information X J Since each federation member has its own clock, let the time of the i-th member be T i , then the federation member state space model is expressed as

[0076]

[0077] T represents time, X i (T i ) indicates that the i-th member at time T i Status X i =[x i ,y i ,u i ,v i ], and X J (T J ) means that the jth member is at time Tj Status X j =[x j ,y j ,u j ,v j ], and the kth member at time T k Status X k =[x k ,y k ,u k ,v k ].

[0078] The subscript i = 1, 2, ..., m, represents the federation member. F is the state equation. Depending on the actual federation members, the function may be linear or nonlinear. J (T J ) is the control variable of the state equation of the ith federation member, which is the set of topic messages subscribed by the member, with subscript J = {j|a ji =1,j=1,…,m,a ji ∈A}, that is, the row subscript corresponding to the value of 1 in the i-th column of the connection matrix. After expanding equation (4), it can be written as

[0079]

[0080] The variables Represents X i The approximation of The error is ω i Indicates that C i , D i is the state transition matrix.

[0081] The state transfer matrix Where D i Each element in is a matrix. i is the state space error.

[0082] When there is no other member status data as input, it is only related to its own status, D i = 0, when the state of other members is used as the control variable, assuming there are two members j and k, then the state matrix D i ∈R n×(n×J) The calculation is

[0083]

[0084] The continuous state space model is converted into a discrete state space. Since each federation member has its own clock mechanism, the time interval Δt is set according to the data accuracy requirements. i =t k -t k-1, then the discrete state space is expressed as:

[0085] X i (k+1)=C i,k X i (k)+D i,k X J (k)+ω i (k) (7)

[0086] Among them C i,k =E+Δt i C i , D i,k =Δt i D i

[0087] Here k is the iteration order index of the state transition, k = 1, 2, ..., E represents the unit matrix, the diagonal is 1, and the other positions are 0.

[0088] The single member state space model is expanded to the federated system state space model as follows:

[0089]

[0090] in, Indicates the (k+1) state of the federated system, k indicates the state transition iteration order index, The state transfer matrix of the federated system representing the first state equation, represents the state transfer matrix of the federated system of the second state equation, W(k) represents the state space error symbol ⊙ represents the Hadamard product (dot product) of the two matrices, that is, (A⊙B) ij =a ij ×b ij .

[0091] Figure 5 The state space diagram of the federation member of the embodiment of the present invention is shown in FIG. The horizontal axis is the time axis. According to the time interval, the state space model is discretized to obtain the state section of the federation member. The massive data constitutes the state space.

[0092] 3. During each state transition of the federated system, state alignment is performed according to the pre-selected federal member benchmark state; the federal system is composed of multiple federal members; when aligning the benchmark state, the state section of each attribute state of each federal member in the federal system is determined according to the pre-constructed federal system state space model. For example, according to the data interaction conditions and data interaction frequency of the federal members, a certain attribute state in the federal members is determined as the benchmark state, and state alignment is performed. The state alignment method is selected according to whether the value of the benchmark state is determined. When the value of the federal member benchmark state is a definite value, the federal member benchmark state is mapped and aligned; when the value of the federal member benchmark state is an uncertain value, the federal member benchmark state is parametrically aligned. For example, when the value of the selected benchmark state is definite, a mapping alignment method is selected, and the benchmark state of the federal member is mapped and aligned, and the mapping function is a constant; when the value of the selected benchmark state is uncertain and fluctuates within a certain range according to the conditions, a parametric polynomial alignment method is selected, and the parameter determination method includes but is not limited to polynomial fitting, empirical estimation, and interpolation calculation. At this time, the federal member state equation under state alignment is converted to

[0093] X i (z+1)=C i,k X i (z)+D i,k X J (z)+ω i (z) (9)

[0094] Where z is the reference state.

[0095] In this embodiment, the same attribute state in the federation member is selected as the reference state according to the data interaction conditions and / or data interaction frequency of the federation member. For example, before the start of production, each federation member takes the position and motion of the federation member robot 5 (the robot is in the handling position and stationary) as the initial reference state. At the beginning of the processing operation, according to the processing process path, each federation member has mutual state information feedback. Each federation member updates its own operation state according to the interactive information, the motion and processing conditions of the reference robot. For example, when the state of the federation member 2 changes, the robot and other federation members will update the state (self-motion) according to the state of the device 2 (the position of the device 2, the position of the workpiece, the motion data of the device 2, etc.). After each state change, it is necessary to ensure that the reference state of each federation member is aligned, that is, the state of the federation member robot itself, the relative position of the federation member robot and other federation members, and the mutual motion state are consistent. At this time, the state alignment function is the relative position of the robot and the federation member 2, which is a fixed value and a constant. After the state is aligned, the state of the robot is returned to zero (the robot is at the zero point position and each joint returns to the zero position state). During the simulation process, the federation member maintains the consistency of its own state with the federation system to achieve system state alignment. Figure 6 This is a state alignment principle diagram of this embodiment.

[0096] Furthermore, the state section where the other attribute states of each federation member are located under the condition of baseline state alignment is determined, and according to each state change, the discrete points of state data are obtained under the condition of baseline state alignment to evolve the system behavior. In other words, according to the data interaction conditions and data interaction frequency of the federation members, the same attribute state in the federation members is determined as the baseline state, so that data calculation and comparison are performed when the baseline state is aligned. Determine the state section where the other attribute states of each federation member are located under the condition of baseline state alignment, and evolve the system behavior according to the discrete points of state data. When the structure of the loosely coupled federation system changes, return to step 1, recalculate the connection matrix, and reconstruct the system state space model. If the structure of the federation system has not changed, re-match the baseline state, perform the next state alignment calculation, obtain the state data section, and repeat this cycle to ensure accurate and effective deduction of the federation system state.

[0097] The loosely coupled federated system state alignment method provided by the present invention constructs a federated system state space model based on a connection matrix, analyzes federated members with data flow, determines a baseline state, and calculates and compares the state sections of each federated member under state alignment, thereby solving the problem of consistent representation of spatiotemporal data calculation of multidisciplinary federated members, enabling federated members to perform data calculations at the correct locations, and better explaining the evolution of federated system behavior.

[0098] For dynamically changing structures, the base state can be flexibly selected. The state alignment method for loosely coupled federated systems is more flexible and more suitable for loosely coupled CPSs, as federated members dynamically join and exit and dynamically change structures.

[0099] Embodiment 2

[0100] An embodiment of the present invention provides a loosely coupled federated system alignment device, the loosely coupled federated system alignment device comprising:

[0101] A state space module, used to construct the state space model of the federation system according to the state space models of each federation member;

[0102] A state alignment module is used to perform state alignment according to a pre-selected federal member benchmark state during each state transition of a federated system; the federated system is composed of multiple federal members; when aligning the benchmark state, the state section of each attribute state of each federal member in the federated system is determined according to a pre-constructed federal system state space model.

[0103] Optionally, the state space module is specifically used to construct a connection matrix A according to the data interaction relationship between the federation members in the federation system; construct a federation member state space model for reflecting the state information of each federation member according to the connection matrix A; and construct the federation system state space model according to the state space models of each federation member;

[0104] The data interaction relationship is:

[0105]

[0106] Where m represents the number of federation members in the federation system.

[0107] The embodiment of the present invention selects a certain state of a federation member as a comparison benchmark. Under the state alignment, other attribute states of the federation members are calculated and compared to approximate the continuous system behavior. Compared with the clock alignment method, selecting a reference state with actual physical significance for alignment is more in line with actual engineering applications. In addition, for dynamic variable structures, the reference state can also be flexibly selected. At the same time, it effectively overcomes the shortcomings of the existing clock alignment method based on a single time variable that cannot fully explain and lacks flexibility for dynamic real-time variable structures.

[0108] The following describes the embodiment of the present invention in detail using a specific example.

[0109] like Figure 7 , Figure 8 As shown, a loosely coupled federated system state alignment method device of this example includes:

[0110] A federation system composition module, used to form a loosely coupled federation system, and obtain a connection matrix between federation members according to the data interaction relationship between federation members in the federation system;

[0111] A state space module is used to construct a state space model of the federation system according to the composition of the federation system and the movement mechanism of the federation members, and obtain a discrete data set of the federation system state;

[0112] A state alignment module, which matches the reference state of the federation member for state data comparison and calculation according to the federation system state space model, performs state alignment, and obtains the state slice of each federation member during state alignment;

[0113] The federal system component modules include:

[0114] The connection matrix unit is used to obtain the connection matrix of the loosely coupled federated system based on the publish / subscribe relationship of the federated members. Since data publishing is directional, the connection matrix is ​​an asymmetric sparse square matrix.

[0115] Optionally, the state space module includes:

[0116] The state space model unit is used to analyze the movement mechanism of federation members and build the state space model of federation members based on the connection matrix according to the loosely coupled federation system structure;

[0117] The state equation evolution unit is used to perform the evolution of the federated system state space based on the state characteristics after state alignment and the alignment of the federated member states. Specifically, it is used for each state transition, and the federated system state space evolution is performed after the baseline state is aligned.

[0118] Optionally, the state alignment module includes:

[0119] The judgment unit is used to judge whether the structure of the loosely coupled federated system has changed. If so, the federation member definition is updated to obtain a new connection matrix. Otherwise, the federation member states are aligned and the state space equation evolution is performed.

[0120] The reference state matching unit is used to obtain a reference state that meets the data calculation conditions when the federation members interact with each other.

[0121] The state alignment unit is used to align the baseline state after obtaining the baseline state, and determine the state slice where other attribute states of each federation member are located.

[0122] Of course, for the specific implementation process of this example, please refer to Example 1.

[0123] Embodiment 3

[0124] An embodiment of the present invention provides a loosely coupled federated system alignment device, the loosely coupled federated system alignment device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor;

[0125] When the computer program is executed by the processor, the steps of the loosely coupled federated system alignment method as described in any one of the first embodiments are implemented.

[0126] Embodiment 4

[0127] An embodiment of the present invention provides a computer-readable storage medium, on which a loosely coupled federated system alignment program is stored. When the federated system alignment program is executed by a processor, the steps of the loosely coupled federated system alignment method described in any one of the first embodiments are implemented.

[0128] The specific implementation of Embodiments 2 to 4 may refer to Embodiment 1, and have corresponding technical effects.

[0129] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0130] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0131] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of the present invention. Of course, it can also be embodied in the form of program code, and the methods described in the various embodiments of the present invention are executed by a firmware (such as a chip) that solidifies the program code.

[0132] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A loosely coupled federated system alignment method, characterized in that: The loosely coupled federated system is used to characterize a virtual-real integrated cyber-physical system, and the loosely coupled federated system alignment method includes: During each state transition of the federated system, state alignment is performed according to a pre-selected federated member benchmark state; the federated system is composed of multiple federated members; the state alignment refers to selecting a certain state of a federated member as a comparison benchmark, under which other attribute states of the federated members are calculated and compared to approximate continuous system behavior; When aligning the baseline state, the state slice of each attribute state of each federation member in the federation system is determined according to the pre-built federation system state space model.

2. The loosely coupled federated system alignment method according to claim 1, characterized in that: The loosely coupled federated system alignment method further includes: Constructing a connection matrix A according to the data interaction relationship between the federation members in the federation system; According to the connection matrix A, a federation member state space model for reflecting the state information of each federation member is constructed; the federation member state information is composed of a plurality of attribute states; Constructing the federation system state space model according to the state space models of each federation member; The data interaction relationship is: Where m represents the number of federation members in the federation system.

3. The loosely coupled federated system alignment method according to claim 2, characterized in that: The step of constructing a federation member state space model for reflecting the state information of each federation member according to the connection matrix A includes: For each federation member, determining a plurality of attribute states of the federation member state information; Determine the own state variables corresponding to each attribute state and the input state data of the associated member according to the connection matrix A; Constructing a first state equation only related to the attribute state of the federation member itself according to the self state variable; A second state equation related to the attribute state of the federation member itself and the control of the input state data is constructed according to the input state data; wherein the first state equation and the second state equation constitute a state space model of the federation member.

4. The loosely coupled federated system alignment method according to claim 2, characterized in that: According to the state space model of each federation member, the state space model of the federation system is constructed using the following formula: in, Indicates the (k+1) state of the federated system, k indicates the state transition iteration order index, The state transfer matrix of the federated system representing the first state equation, represents the state transfer matrix of the federated system of the second state equation, the symbol ⊙ represents the Hadamard product of the two matrices, and W(k) represents the state space error.

5. The loosely coupled federated system alignment method according to claim 1, characterized in that: The loosely coupled federated system alignment method further includes: According to the data interaction conditions and / or data interaction frequency of the federation members, the same attribute state among the federation members is selected as the benchmark state.

6. The method for aligning a loosely coupled federated system according to any one of claims 1 to 5, characterized in that: The following methods are used to align the states based on the pre-selected federation member benchmark states: When the value of the federation member benchmark state is a certain value, mapping and aligning the federation member benchmark state; When the value of the federation member reference state is an uncertain value, parameter polynomial alignment is performed on the federation member reference state.

7. A loosely coupled federated system alignment device, characterized in that: The loosely coupled federated system is used to characterize a virtual-real fusion cyber-physical system, and the loosely coupled federated system alignment device includes: A state space module, used to construct the state space model of the federation system according to the state space models of each federation member; A state alignment module is used to perform state alignment according to a pre-selected federation member benchmark state during each state transition of the federation system; the federation system is composed of multiple federation members; the state alignment refers to selecting a certain state of the federation member as a comparison benchmark, under which other attribute states of the federation member are calculated and compared to approximate continuous system behavior; The state alignment module is also used to determine the state slice of each attribute state of each federation member in the federation system according to the pre-built federation system state space model when aligning the baseline state.

8. The loosely coupled federated system alignment device according to claim 7, characterized in that: The state space module is specifically used to: construct a connection matrix A according to the data interaction relationship between the federation members in the federation system; construct a federation member state space model for reflecting the state information of each federation member according to the connection matrix A; and construct the federation system state space model according to the state space models of each federation member; The data interaction relationship is: Where m represents the number of federation members in the federation system.

9. A loosely coupled federated system alignment device, characterized in that: The loosely coupled federated system alignment device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor; When the computer program is executed by the processor, the steps of the loosely coupled federated system alignment method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a loosely coupled federated system alignment program, and when the federated system alignment program is executed by a processor, the steps of the loosely coupled federated system alignment method according to any one of claims 1 to 8 are implemented.

Images