Parameter optimization method and system for dynamic coupling of roller press

Abstract

The invention discloses a parameter optimization method and system for dynamic coupling of a roller press, and the method comprises the steps: constructing the interaction among all parts through a knowledge graph in the dynamic coupling process of the roller press; establishing a synchronous link between nodes in the knowledge graph by using a Bayesian algorithm to obtain an optimized knowledge graph; in the working process of the roller press, matching corresponding coupling parameters in the optimized knowledge graph by setting output parameters of the roller press; when any coupling parameter fluctuates, other coupling parameters are optimized and adjusted through the optimized knowledge graph, so that the fluctuating parameter is compensated; and parameter optimization in the dynamic coupling process of the roller press is realized. According to the method, the coordination and response speed of parameter adjustment are improved, the problems of quality fluctuation and high energy consumption caused by coupling imbalance are remarkably reduced, intelligent, high-precision and high-stability operation of the rolling process is achieved, and the method has good engineering practical value and popularization prospects.

Description

Technical Field

[0001] The present invention relates to the technical field of dynamic optimization of mechanical parameters, and specifically to a method and system for optimizing parameters of dynamic coupling of a roller press. Background Art

[0002] Roller presses are widely used in industrial scenarios such as powder compaction, sheet forming, lithium battery pressing, and metallurgical granulation, and are important equipment for realizing efficient and continuous pressing of materials. In the traditional control mode, the operating parameters of the roller press, such as pressure, speed, roller gap, tension, temperature, etc., are all adjusted by independent control systems, and there is no effective linkage mechanism between the parameters, resulting in difficulties in achieving dynamic coordinated adjustment when the equipment faces complex working condition changes, thus resulting in problems such as poor product consistency, high energy consumption, and structural response lag.

[0003] In addition, existing technologies mostly rely on a single model for optimization control, and it is difficult to adapt to the complex characteristics of multi-parameter coupling, non-linear response, and time-series fluctuations in the actual rolling process. Especially when key parameters fluctuate, it is impossible to achieve linkage compensation of other coupled parameters, resulting in untimely or even unstable system responses, seriously affecting product quality and equipment life.

[0004] With the development of multi-source sensing and machine learning technologies, the correlation relationships between parameters can be modeled in a graph structure. However, in current methods, the graph spectra are mostly static topologies, lacking the ability to model synchronous change relationships within a time window, and it is difficult to support adaptive compensation strategies under parameter fluctuation conditions. Summary of the Invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] To solve the above technical problems, the present invention provides the following technical solution: A method for optimizing parameters of dynamic coupling of a roller press, including:

[0007] Construct the interactions between components during the dynamic coupling process of the roller press through a knowledge graph;

[0008] Use the Bayesian algorithm to establish synchronous links between nodes in the knowledge graph to obtain an optimized knowledge graph;

[0009] During the working process of the roller press, by setting the output parameters of the roller press, match the corresponding coupled parameters in the optimized knowledge graph;

[0010] When any coupled parameter fluctuates, through the optimized knowledge graph, optimize and adjust other coupled parameters to compensate for the fluctuating parameter; achieve parameter optimization during the dynamic coupling process of the roller press.

[0011] As a preferred solution of the parameter optimization method for the dynamic coupling of the roller press according to the present invention, wherein: the knowledge graph includes constructing a graph structure regarding the relationships between the components of the roller press by taking the physical parameters of each component as nodes and the relationships between the physical parameters as edges;

[0012] The relationships between the physical parameters include the relationships between different parameters within each component and the coupling relationships between parameters of different components.

[0013] As a preferred solution of the parameter optimization method for the dynamic coupling of the roller press according to the present invention, wherein: the synchronous link includes assuming that there is no connection relationship between link i and link j in the knowledge graph;

[0014] By using the Bayesian algorithm, calculate whether the physical parameters in link j change when the physical parameters in link i change; and output the corresponding occurrence probability;

[0015] Assume that the changes between link i and link j are reflected by the parameter changes between the initial nodes of the links; under the assumption that the occurrence probability of link i affecting link j is 1, fit the relationship between the initial node of link i and the initial node of link j;

[0016] Take the fitting function and occurrence probability of link i affecting link j and embed them between the initial node of link i and the initial node of link j as a link.

[0017] As a preferred solution of the parameter optimization method for the dynamic coupling of the roller press according to the present invention, wherein: the optimized knowledge graph includes adding the synchronous link to the knowledge graph as a new knowledge graph.

[0018] As a preferred solution of the parameter optimization method for the dynamic coupling of the roller press according to the present invention, wherein: the output parameters include the parameters directly manifested when the roller press is working;

[0019] The coupling parameters include coupling parameter 1: the physical parameters other than the output parameters in the link where the output parameters exist; coupling parameter 2: all the physical parameters in the links having synchronous links with the link where the output parameters exist;

[0020] In the knowledge graph before optimization, according to the set values of the output parameters, synchronously calculate the values of the coupling parameter 1 to obtain the target values of each coupling parameter 1 in the knowledge graph before optimization.

[0021] As a preferred solution of the parameter optimization method for the dynamic coupling of the roller press according to the present invention, wherein: the compensation for the fluctuating parameters includes synchronizing the target values of each coupling parameter 1 in the knowledge graph before optimization;

[0022] When any coupling parameter deviates in the optimized knowledge graph, adjust the coupling parameter by any step size, so as to minimize the influence of the parameter fluctuation on the output parameter;

[0023] During the compensation process, it is completed through the objective function and constraint conditions.

[0024] As a preferred solution of the parameter optimization method for the dynamic coupling of the roller press according to the present invention, wherein: the objective function is: taking the minimum value of the sum of the products of the ratio of the adjustment amount of each coupling parameter to the maximum adjustable amount and the influence coefficient; wherein, coupling parameter 2 only uses one coupling parameter directly connected by a synchronous link to compensate the output parameter;

[0025] The influence coefficient includes: if it is a direct connection line in the knowledge graph, take 1; if it is a synchronous link, take the probability output by the Bayesian algorithm;

[0026] The constraint conditions include: the output parameter after completion of compensation is within the fluctuation range of the set value; the adjustment of each parameter is within the adjustable range.

[0027] A parameter optimization system for the dynamic coupling of a roller press, wherein:

[0028] An association unit constructs the interaction between components during the dynamic coupling of the roller press through a knowledge graph; uses the Bayesian algorithm to establish synchronous links between nodes in the knowledge graph to obtain an optimized knowledge graph;

[0029] A control unit, during the working process of the roller press, matches the corresponding coupling parameters in the optimized knowledge graph by setting the output parameters of the roller press;

[0030] A compensation unit, when any coupling parameter fluctuates, optimally adjusts other coupling parameters through the optimized knowledge graph, so as to compensate for the fluctuating parameters; realizing parameter optimization during the dynamic coupling process of the roller press.

[0031] A computer device includes: a memory and a processor; the memory stores a computer program, wherein: when the processor executes the computer program, it implements the steps of the method described in any one of the present invention.

[0032] A computer-readable storage medium stores a computer program thereon, wherein: when the computer program is executed by a processor, the steps of any one of the methods of the present invention are implemented.

[0033] Advantages of the present invention: The parameter optimization method for dynamic coupling of a roller press provided by the present invention can construct a dynamically evolving knowledge graph model for the complex coupling relationships among multiple components and multiple parameters of the roller press. By introducing the Bayesian algorithm to establish synchronous links, the response probability modeling and function relationship fitting between cross-component parameters are realized, effectively enhancing the adaptive ability of the knowledge graph to changes in the operating state. By setting the target of the output parameters, the optimal coupling parameter combination can be quickly matched in the graph, and when the key parameters fluctuate, the linkage compensation of other parameters can be realized based on the jump logic. This method improves the coordination and response speed of parameter adjustment, significantly reduces the quality fluctuations and high energy consumption problems caused by coupling imbalance, realizes the intelligent, high-precision and high-stability operation of the rolling process, and has good engineering practical value and promotion prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0035] Figure 1 It is the overall flowchart of a parameter optimization method for dynamic coupling of a roller press provided by the first embodiment of the present invention;

[0036] Figure 2 It is the working principle diagram of a roller press in a parameter optimization method for dynamic coupling of a roller press provided by the second embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] In order to make the above objects, features and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0038] Example 1, referring to Figure 1 This is an embodiment of the present invention, providing a parameter optimization method for dynamic coupling of a roller press, including:

[0039] S1: The interaction between components in the dynamic coupling process of the roller press is constructed through a knowledge graph.

[0040] The knowledge graph includes constructing a graph structure regarding the relationships between the components of the roller press by taking the physical parameters of each component as nodes and the relationships between the physical parameters as edges. The relationships between the physical parameters include the relationships between different parameters within each component and the coupling relationships between parameters of different components. The coupling relationships generated by the assembly method of each component are direct relationships, so the coupling relationships of the parameters are generally linear relationships.

[0041] Since there are definite mechanical connections between the components of the roller press (such as the upper and lower rollers, bearings, drive devices, etc.), there are stable and predictable linear function relationships between the physical parameters corresponding to these structural connections (such as pressure, speed, gap), which are suitable for constructing the initial edges of the knowledge graph.

[0042] S2: Use the Bayesian algorithm to establish synchronous links between the nodes in the knowledge graph to obtain an optimized knowledge graph.

[0043] The synchronous links include assuming that there is no connection relationship between link i and link j in the knowledge graph. Through the Bayesian algorithm, calculate whether the physical parameters in link j change when the physical parameters in link i change; and output the corresponding occurrence probability.

[0044] Suppose: The changes between link i and link j are reflected by the parameter changes between the initial nodes of the links; under the assumption that the occurrence probability of link i affecting link j is 1, fit the relationship between the initial nodes of link i and the initial nodes of link j. Take the fitting function and occurrence probability of link i affecting link j and embed them as a link between the initial nodes of link i and the initial nodes of link j.

[0045] It should be noted that the initial nodes are generally preset, and generally the nodes with the strongest correlation are preset as the initial nodes in each link (which can respond the fastest during calculation). In addition, the selection of this node has certain constraints. The parameter change of this node must be a continuous process and cannot be a "threshold type" phased change process (after reaching a value, with the change of other parameters, the parameter of this node does not change or changes jumpily).

[0046] When analyzing whether there is a relationship between two links, in this embodiment, it is divided into two types of link relationships: threshold type synchronous link and continuous type synchronous link.

[0047] The threshold - type synchronization link (i.e., there is a piece - wise function modeling relationship between the initial nodes of two links) includes analyzing the relationship between the initial nodes of link i and link j within a set time window: Let the initial nodes be physical parameters x and y respectively. When the change amplitude of physical parameter x exceeds any threshold u, physical parameter y undergoes a response change within the synchronization window, then the relationship between physical parameter x and physical parameter y under threshold u is established. The threshold u can be one or multiple. The thresholds y include: u1, u2,..., un; n represents the number of thresholds between physical parameter x and physical parameter y. un represents the nth threshold between physical parameter x and physical parameter y. As physical parameter x changes, between every two adjacent thresholds, physical parameter y can change continuously (there is a fit - able change curve between physical parameter x and physical parameter y), and at the same time satisfy: before and after a threshold, the fit - able change curves between physical parameter x and physical parameter y are different. It is also possible that as physical parameter x changes, between every two adjacent thresholds, physical parameter y is a constant value, but before and after a threshold, the magnitudes of the constant values of physical parameter y are different.

[0048] The continuous - type synchronization link includes that in a continuous time series, if there is a fit - able change curve between physical parameter x and physical parameter y, then the relationship between the two physical parameters is established through function fitting.

[0049] In the knowledge graph, add the synchronization link as a new knowledge graph.

[0050] Based on the established initial knowledge graph structure, further explore the potential dynamic response relationships between different links, and construct the synchronization link relationship between the nodes in the graph through the Bayesian algorithm to achieve enhanced modeling of complex coupling paths and improve the system's linkage response ability under parameter fluctuations.

[0051] Since the initial knowledge graph only depicts the direct physical connection relationships between components and cannot reflect the "indirect coupling" or "synchronization response" characteristics shown by multiple parameters in the system during sequential operation. The present invention remedies the problem of the traditional graph lacking dynamic expansion ability by adding synchronization link paths to the graph, enabling the graph structure to have the ability to model dynamic linkage paths for "cross - link" and "cross - component".

[0052] Specifically, in this step, the initial node of each link is set as the modeling entry. This node must be a preset parameter with the fastest response speed and have a continuously observable change process to avoid affecting the modeling stability due to threshold mutations. The conditional influence probability of link i on link j is calculated through the Bayesian algorithm, and combined with the fitting function between the initial nodes, a synchronous connection relationship between the links is established. The synchronous links are divided into two structures: threshold type and continuous type, which are respectively applicable to physical quantities with piecewise change characteristics and continuous trend characteristics.

[0053] Finally, by embedding the constructed synchronous links into the knowledge graph, the upgrade from the structural connection model to the dynamic response model is realized, forming an optimized knowledge graph structure that can support parameter jump, collaborative compensation, and path selection, providing a key basis for subsequent adaptive control and refined compensation strategies.

[0054] S3: During the working process of the roller press, by setting the output parameters of the roller press, the corresponding coupling parameters are matched in the optimized knowledge graph.

[0055] The output parameters include the parameters directly presented during the operation of the roller press, including but not limited to the pressure, rotation speed of the upper or lower roller, the gap between the upper and lower rollers, the nip temperature, the discharge tension, the feeding speed, and the discharge speed, etc. These parameters usually reflect the "apparent characteristics" under the combined action of a certain link or multiple components, and can be used to evaluate control objectives such as whether the operation is stable and whether the production line meets the standards. In the knowledge graph, the output parameters usually are in the position of the observed nodes and exist as the target constraint items of the jump logic or optimization path.

[0056] The coupling parameters include: Coupling parameter 1: Among the physical parameters in the link where the output parameter exists, except for the output parameter; Coupling parameter 2: All the physical parameters in the links that have synchronous links with the link where the output parameter exists.

[0057] In the knowledge graph before optimization, according to the set value of the output parameter, the value of the coupling parameter 1 is synchronously calculated to obtain the target value of each coupling parameter 1 in the knowledge graph before optimization. The coupling parameter 1 is the structural physical parameter in the link where the output parameter is located. These parameters are the direct regulation quantities in the system control process, and their adjustment will directly affect the state of the output parameter and belong to the main participating variables in the core adjustment path of the controller.

[0058] The structural connection relationship represented by the knowledge graph before optimization reflects the deterministic mapping relationship directly established between the various components of the equipment through mechanical structure, electrical drive, or process logic, and has repeatability, reversibility, and engineering controllability. Therefore, it can be used as a reliable basis for calculating the target value of the coupling parameter 1.

[0059] In contrast, although the optimized knowledge graph introduces "synchronous links" and jump relationships between multiple links through the Bayesian algorithm, which can express the dynamic response potential between parameters, most of these paths are non-control paths or indirect influence paths, and do not have stable control constraints. Therefore, it is not suitable as a basis for accurately solving the target value of coupling parameter 1.

[0060] In summary, for the sake of control accuracy and execution feasibility, the present invention prioritizes directly calculating the target value of coupling parameter 1 based on the structural link in the knowledge graph before optimization; and the optimized knowledge graph is only used as a compensation path reference or strategy jump basis after parameter disturbance.

[0061] S4: When any coupling parameter fluctuates, other coupling parameters are optimized and adjusted through the optimized knowledge graph to compensate for the fluctuating parameters; thus realizing parameter optimization in the dynamic coupling process of the roller press.

[0062] When the roller press is working, the target value of each coupling parameter 1 in the knowledge graph before optimization is synchronized. When any coupling parameter is offset in the knowledge graph after optimization, the coupling parameter is adjusted with any step length, so as to minimize the influence of the parameter fluctuation on the output parameter.

[0063] In the compensation process, it is completed through objective function and constraints.

[0064] First, during the initialization and initial operation of the system, the target value of coupling parameter 1 is synchronized through the knowledge graph before optimization. This is because the parameter relationship in the graph comes from the direct mapping of the device structure connection and functional role, and has the characteristics of controllability, traceability, and unambiguity, and can provide accurate reference targets for each adjustment parameter.

[0065] During the operation of the system, as the material state, environmental conditions or equipment state fluctuates, some parameters may deviate from the preset state. At this time, the newly added "synchronous link" in the optimized knowledge graph can timely identify potential coupling pathways and capture the response trend of non-structural paths in the system. On this basis, the system can make multi-scale adjustments to all coupling parameters with arbitrary step lengths to quickly respond to external disturbances and minimize their impact on output parameters.

[0066] By linking the main structural diagram (diagram before optimization) with the dynamic response diagram (diagram after optimization), this step realizes a fine control and flexible compensation mechanism for process disturbances, which significantly improves the stability, anti-interference ability and coupling adaptability level of roller pressure control.

[0067] The objective function is: the sum of the products of the ratio of the adjustment amount of each coupling parameter to the maximum adjustable amount and the influence coefficient is minimized; among them, coupling parameter 2 only uses a coupling parameter directly connected through a synchronous link to compensate the output parameter. The influence coefficient includes: if it is a direct connection line in the knowledge graph, take 1; if it is a synchronous link, take the probability output by the Bayesian algorithm.

[0068] For each coupling parameter x i :

[0069] There is an adjustment amount Δx i ; The maximum adjustable range (the remaining value of the adjustable amount); the influence coefficient α i , value rule: if from the structural link (the original edge of the knowledge graph) → α i = 1; · if from the synchronous link (the probability output by the Bayesian algorithm).

[0070] Let n represent the number of all coupling parameters participating in the compensation.

[0071]

[0072] The objective function is:

[0073]

[0074] The constraint conditions include that the output parameter after compensation is within the fluctuation range of the set value; the adjustment of each parameter is within the adjustable range.

[0075] On the other hand, this embodiment also provides a parameter optimization system for the dynamic coupling of a roller press, which includes:

[0076] An association unit, which constructs the interaction between components during the dynamic coupling of the roller press through a knowledge graph; uses the Bayesian algorithm to establish synchronous links between nodes in the knowledge graph to obtain an optimized knowledge graph.

[0077] A control unit, during the working process of the roller press, matches the corresponding coupling parameters in the optimized knowledge graph by setting the output parameters of the roller press.

[0078] A compensation unit, when any coupling parameter fluctuates, optimally adjusts other coupling parameters through the optimized knowledge graph to compensate for the fluctuating parameter; realizes parameter optimization during the dynamic coupling process of the roller press.

[0079] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0080] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device.

[0081] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection part with one or more wirings (electronic device), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or otherwise processing it as appropriate, and then storing it in a computer memory.

[0082] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits with logic gate circuits for implementing logic functions on data signals, application specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0083] Example 2, referring to Figure 2 , which is an embodiment of the present invention, provides a method for optimizing parameters of dynamic coupling of a roller press. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0084] When the device is in an operating state, as Figure 2 shown, the material enters from the middle feed port, and the fixed roller and the movable roller rotate relative to each other to form a pressing area.

[0085] The movable roller can generate displacement in the horizontal direction, and its pressure is set by the control unit and accurately applied through a hydraulic device. During actual operation, if the system detects that the "outlet tension" in the output parameters abnormally increases (such as the tension exceeding the set value), the control system first, based on the knowledge graph before optimization, inversely deduces the coupling parameter on the structural path directly connected to this output parameter - that is, the pressure of the movable roller.

[0086] Through the established linear structure model, the system calculates the pressure value that the movable roller should apply as its target value under the current tension target. At this time, if it is found that there is an offset in the pressure of the movable roller, the present invention further calls the optimized knowledge graph, retrieves other links that are synchronously linked to the tension, and identifies that there is a probabilistic synchronous response relationship between parameters such as the rotational speed of the movable roller and the tension. Then the system performs a joint compensation calculation based on the objective function, and determines the optimal combined adjustment amount of the pressure and rotational speed of the movable roller on the premise of meeting the target value of the output parameter, so as to complete the dynamic recovery of the tension at the minimum adjustment cost and realize the coupling optimization adjustment mechanism of structural path control and synchronous jump compensation.

[0087] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A parameter optimization method for dynamic coupling of a roller press, characterized in that, Including: During the dynamic coupling process of the roller press, the interactions between various components are constructed through a knowledge graph; Using the Bayesian algorithm to establish synchronous links between nodes in the knowledge graph to obtain an optimized knowledge graph; During the working process of the roller press, by setting the output parameters of the roller press, matching the corresponding coupling parameters in the optimized knowledge graph; When any coupling parameter fluctuates, through the optimized knowledge graph, other coupling parameters are optimized and adjusted to compensate for the fluctuating parameter; Realize parameter optimization during the dynamic coupling process of the roller press.

2. The parameter optimization method for dynamic coupling of a roller press according to claim 1, characterized in that: The knowledge graph includes constructing a graph structure about the relationships between components of the roller press by taking the physical parameters of each component as nodes and the relationships between the physical parameters as edges; The relationships between the physical parameters include the relationships between different parameters within each component and the coupling relationships between parameters of different components.

3. The parameter optimization method for dynamic coupling of a roll press according to claim 2, characterized in that: The synchronous link includes assuming that there is no connection relationship between link i and link j in the knowledge graph; Through the Bayesian algorithm, calculate whether the physical parameters in link j change when the physical parameters in link i change; and output the corresponding occurrence probability; Assume that the change between link i and link j is reflected by the parameter change between the initial nodes of the links; under the assumption that the occurrence probability of link i affecting link j is 1, fit the relationship between the initial node of link i and the initial node of link j; Take the fitting function and occurrence probability of link i affecting link j and embed them as a link between the initial node of link i and the initial node of link j.

4. The parameter optimization method for dynamic coupling of a roll press according to claim 3, characterized in that: The optimized knowledge graph includes adding the synchronous link to the knowledge graph as a new knowledge graph.

5. The parameter optimization method for dynamic coupling of a roller press according to claim 4, characterized in that: The output parameters include the parameters that directly show during the operation of the roller press; The coupling parameters include: Coupling parameter 1: the physical parameters other than the output parameter in the link where the output parameter exists; Coupling parameter 2: all the physical parameters in the links that have synchronous links with the link where the output parameter exists; In the knowledge graph before optimization, according to the set value of the output parameter, synchronously calculate the values of the coupling parameter 1 to obtain the target values of each coupling parameter 1 in the knowledge graph before optimization.

6. The parameter optimization method for dynamic coupling of a roller press according to claim 5, characterized in that: Compensating for the fluctuating parameter includes synchronizing the data of the target values of each coupling parameter 1 in the knowledge graph before optimization; When any coupling parameter in the optimized knowledge graph deviates, adjust the coupling parameter by any step size so that the influence of the parameter fluctuation on the output parameter is minimized; During the compensation process, it is completed through the objective function and constraint conditions.

7. The parameter optimization method for dynamic coupling of a roll press according to claim 6, characterized in that: The objective function is: taking the minimum value of the sum of the products of the ratio of the adjustment amount of each coupling parameter to the maximum adjustable amount and the influence coefficient; among them, coupling parameter 2 only uses one coupling parameter directly connected through a synchronous link to compensate for the output parameter; The influence coefficient includes taking 1 if it is a direct connection in the knowledge graph, and taking the probability output by the Bayesian algorithm if it is a synchronous link. The constraint conditions include that the output parameter after compensation is within the fluctuation range of the set value; the adjustment of each parameter is within the adjustable range.

8. A parameter optimization system for dynamic coupling of a roller press adopting the method according to any one of claims 1-7, characterized in that: An association unit constructs the interaction between components during the dynamic coupling of the roller press through a knowledge graph; a synchronous link between nodes in the knowledge graph is established by using a Bayesian algorithm to obtain an optimized knowledge graph; A control unit, during the working process of the roller press, matches corresponding coupling parameters in the optimized knowledge graph by setting the output parameters of the roller press; A compensation unit, when any coupling parameter fluctuates, optimizes and adjusts other coupling parameters through the optimized knowledge graph so as to compensate for the fluctuating parameter; Realize parameter optimization during the dynamic coupling process of the roller press.

9. A computer device, comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the method according to any one of claims 1-7 are realized.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the method according to any one of claims 1-7 are realized.

Images