An intelligent manufacturing system and a method for resolving cross-domain conflicts in manufacturing tasks thereof

Abstract

The present invention relates to the technical field of intelligent manufacturing, and proposes an intelligent manufacturing system and a method for resolving cross-domain conflicts in manufacturing tasks thereof, comprising: an upper-layer computing module and a lower-layer physical module; the upper-layer computing module comprises a database, a computing unit, a blockchain and a contract unit; the lower-layer physical module comprises a manufacturing unit and a communication module; the database is used to store data to be stored in the upper-layer computing module; the computing unit is used to analyze and process the data and generate a work dispatching plan; the communication module is used to upload the data of the manufacturing unit to the computing unit, and to send the work dispatching plan issued by the computing unit to the manufacturing unit; the manufacturing unit comprises production equipment and is used to execute the work dispatching plan; the contract unit comprises a smart contract, and the smart contract is deployed on a blockchain node; the blockchain is used to use the manufacturing unit to perform conflict detection on the work dispatching plan during the execution of the work dispatching plan, and to use the contract unit to perform conflict resolution on the work dispatching plan in which conflicts are detected.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent manufacturing, and more specifically, to an intelligent manufacturing system and a method for resolving cross-domain conflicts in manufacturing tasks. Background Art

[0002] An intelligent manufacturing system is a two-tiered system, with the upper tier consisting of an intelligent algorithm engine and the lower tier consisting of physical manufacturing units. The overall operational logic of an intelligent manufacturing system can be described as follows: the upper tier responds to external orders and the production environment in both time and space, relying on an internal algorithm engine to solve and dispatch work and schedule the lower tier physical manufacturing units to achieve overall efficiency in the production process.

[0003] In the current intelligent manufacturing system's two-layer intelligent framework, information exchange between the upper and lower layers requires computational time for upper-layer coupled optimization, leading to non-instantaneous information asymmetry and manufacturing task conflicts. Consequently, if a bottleneck resource fails during upper-layer computation, causing process flow stagnation, and the plan continues to be issued, this can cause some processes to deadlock. The lack of a compensation mechanism for instructions makes it impossible to ensure the timeliness of production instructions. Furthermore, the lack of an adaptive mechanism for instructions that lack a certain degree of timeliness (causing process deadlocks during execution) can easily lead to intermittent production downtime in the manufacturing system.

[0004] In summary, the existing intelligent manufacturing system has the defect of task conflict problem under the condition of information asymmetry, which leads to intermittent shutdown of the intelligent manufacturing system. Summary of the Invention

[0005] In order to overcome the defect of intermittent production suspension in the intelligent manufacturing system existing in the above-mentioned prior art, the present invention provides an intelligent manufacturing system capable of continuous and stable production and a method for resolving cross-domain conflicts in manufacturing tasks.

[0006] To solve the above technical problems, the intelligent manufacturing system of the present invention includes:

[0007] Upper-level computing module and lower-level physical module;

[0008] The upper computing module includes: a database, a computing unit, a blockchain, and a contract unit;

[0009] The lower-level physical module includes: several manufacturing units and communication modules;

[0010] The database is used to store data that needs to be stored in the upper computing module;

[0011] The computing unit is used to analyze and process the data in the database and generate a work dispatch plan;

[0012] The communication module is used to upload the data of the manufacturing unit to the computing unit, and send the work dispatch plan issued by the computing unit to the manufacturing unit;

[0013] The manufacturing unit includes a plurality of production equipment, and the manufacturing unit is used to execute the work dispatch plan;

[0014] The contract unit includes several smart contracts, which are deployed on blockchain nodes;

[0015] The blockchain is used to use the manufacturing unit to perform conflict detection on the work dispatching plan during the execution of the work dispatching plan, and to use the contract unit to resolve conflicts in the work dispatching plan that are detected to be in conflict.

[0016] The present invention also proposes a method for resolving cross-domain conflicts in manufacturing tasks of an intelligent manufacturing system. Applying the above-mentioned intelligent manufacturing system, the method comprises the following steps:

[0017] Acquire equipment data from production equipment in manufacturing units;

[0018] using the communication module to transmit the device data to the computing unit;

[0019] The calculation unit predicts the tolerable load of the production equipment based on the equipment data, performs error compensation calculation on the predicted tolerable load of the production equipment, obtains the compensated capacity prediction value, and solves the work dispatch plan based on the compensated capacity prediction value;

[0020] The work dispatch plan is sent to the manufacturing unit using the communication module, and the manufacturing unit executes the work dispatch plan;

[0021] During the execution of the work dispatch plan, the blockchain uses the manufacturing unit to detect conflicts in the work dispatch plan, and uses the contract unit to resolve conflicts in the work dispatch plan that are detected to be in conflict.

[0022] The present invention also proposes a computer device comprising a memory and a processor, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor executes the steps of the above-mentioned method for resolving cross-domain conflicts in manufacturing tasks of the intelligent manufacturing system.

[0023] Compared with the prior art, the beneficial effects of the technical solution of the present invention are:

[0024] Based on the equipment data, the computing unit is used to solve the dispatching plan after error compensation, so as to reduce the probability of conflicts in the dispatching plan; the dispatching plan is executed by the manufacturing unit. During the execution of the dispatching plan, the manufacturing unit is used to detect conflicts in the dispatching plan through the blockchain, and the contract unit is used to resolve conflicts in the dispatching plan that are detected to be in conflict, so as to solve the problem of inconsistency between the global plan and the local execution, so that the intelligent manufacturing system can achieve continuous and stable production. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is the overall framework diagram of the intelligent manufacturing system proposed in Example 1;

[0026] Figure 2 This is a flow chart of the method for resolving cross-domain conflicts in manufacturing tasks of an intelligent manufacturing system proposed in Example 2;

[0027] Figure 3 This is a logical diagram of the mapping between random disturbance events and smart contracts proposed in Example 2. DETAILED DESCRIPTION

[0028] The accompanying drawings are for illustrative purposes only and are not to be construed as limiting the present embodiment;

[0029] In order to better illustrate this embodiment, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product size;

[0030] It is understandable to those skilled in the art that some well-known structures and descriptions thereof may be omitted in the drawings.

[0031] The technical solution of the present invention is further described below with reference to the accompanying drawings and embodiments.

[0032] Example 1

[0033] This embodiment proposes an intelligent manufacturing system. Figure 1 This is the overall framework diagram of the intelligent manufacturing system of this embodiment;

[0034] The intelligent manufacturing system includes:

[0035] Upper-level computing module and lower-level physical module;

[0036] The upper computing module includes: a database, a computing unit, a blockchain, and a contract unit;

[0037] The lower-level physical module includes: several manufacturing units and communication modules;

[0038] The database is used to store data that needs to be stored in the upper computing module;

[0039] The computing unit is used to analyze and process the data in the database and generate a work dispatch plan;

[0040] The communication module is used to upload the data of the manufacturing unit to the computing unit, and send the work dispatch plan issued by the computing unit to the manufacturing unit;

[0041] The manufacturing unit includes a plurality of production equipment, and the manufacturing unit is used to execute the work dispatch plan;

[0042] The contract unit includes several smart contracts, which are deployed on blockchain nodes;

[0043] The blockchain is used to use the manufacturing unit to perform conflict detection on the work dispatching plan during the execution of the work dispatching plan, and to use the contract unit to resolve conflicts in the work dispatching plan that are detected to be in conflict.

[0044] Example 2

[0045] This embodiment proposes a method for resolving cross-domain conflicts in manufacturing tasks of an intelligent manufacturing system, and applies the intelligent manufacturing system proposed in Example 1;

[0046] Figure 2 Schematic diagram of the process of resolving cross-domain conflicts in manufacturing tasks of the intelligent manufacturing system of this embodiment;

[0047] The method for resolving cross-domain conflicts in manufacturing tasks of an intelligent manufacturing system proposed in this embodiment includes the following steps:

[0048] S1: Obtain equipment data from the production equipment of the manufacturing unit;

[0049] S2: Using the communication module to transmit the device data to the computing unit;

[0050] S3: The calculation unit predicts the tolerable load of the production equipment based on the equipment data, performs error compensation calculation on the predicted tolerable load of the production equipment, obtains a compensated capacity prediction value, and solves a work dispatch plan based on the compensated capacity prediction value;

[0051] S4: Using the communication module, the work dispatch plan is sent to the manufacturing unit, and the manufacturing unit executes the work dispatch plan;

[0052] S5: During the execution of the work dispatch plan, the blockchain uses the manufacturing unit to detect conflicts in the work dispatch plan, and uses the contract unit to resolve conflicts in the work dispatch plan that are detected to be in conflict.

[0053] During the specific implementation process, based on the equipment data, the computing unit is used to solve the dispatching plan after error compensation, so as to reduce the probability of conflicts in the dispatching plan; the dispatching plan is executed by the manufacturing unit, and in the process of the dispatching plan being executed, the blockchain is used to detect conflicts in the dispatching plan by using the manufacturing unit, and the conflict of the dispatching plan detected is resolved by using the contract unit, so as to solve the problem of inconsistency between the global plan and the local execution, so that the intelligent manufacturing system can achieve continuous and stable production.

[0054] In an optional embodiment, the expression of the device data is:

[0055] D up ={Op,Ind new , P acc , Layout}

[0056] Where D up Indicates device data, Op is a binary value indicating whether the device is in a working state, Ind new Indicates the various operating indicators of the equipment, P acc Indicates the actual capacity of the equipment in the last round of operation, and Layout indicates the layout of the equipment.

[0057] In an optional embodiment, the D up 、Op、Ind new 、P acc and Layout are both expressed in the form of matrices, and D up 、Op、Ind new 、P acc The matrix sizes of and Layout are: n×(n+m+2), n×1, n×m, n×1 and n×n, where n represents the number of devices and m represents the total number of types of device operation indicators.

[0058] In this optional embodiment, the matrix size of the above data is convenient for data processing and extraction, and is convenient for subsequent numerical fitting and calculation.

[0059] In an optional embodiment, when the calculation unit predicts the tolerable load of the production equipment based on the equipment data, the Ind new Data is input into the machine learning model, and the machine learning model outputs the tolerable load of the production equipment in this round of prediction Among them, the predicted tolerable load of each production equipment obtained by the machine learning model is stored in the database.

[0060] In an optional embodiment, the calculation unit performs error compensation calculation on the predicted tolerable load of the production equipment to obtain a compensated capacity prediction value, and the step of solving the work dispatch plan based on the compensated capacity prediction value includes:

[0061] Get the P in the device data of this round acc Data and Op data, call out the last round of predicted production equipment's tolerable load from the database Based on P acc Data, Op Data, Data and The data calculates the capacity forecast value after compensation. The calculation unit uses a preset algorithm to solve the work dispatch plan based on the capacity forecast value after compensation.

[0062] The expression of the production capacity prediction value after compensation is:

[0063]

[0064]

[0065] Where, P pred Indicates the predicted capacity after compensation; Op T Represents the transposed matrix of Op.

[0066] As an exemplary illustration, the preset algorithm includes a heuristic algorithm; as an exemplary illustration, the present application uses the annealing algorithm, a heuristic algorithm, as the preset algorithm of the present application solution;

[0067] As an example, the production capacity forecast value after compensation P pred The upper-level algorithm engine will use it as the calculation basis for solving the work dispatch plan. Once the work dispatch plan is solved, it will be assigned to the corresponding manufacturing unit according to the processing flow characteristics. This error compensation method can improve the data matching rate between the execution conditions of the work dispatch plan and scheduling plan generated by the upper-level system based on equipment capacity data and the actual physical environment to a certain extent, thereby reducing the probability of policy conflicts.

[0068] In this optional embodiment, for the cumulative inconsistency conflicts in the upper system, a conflict resolution method based on cumulative error compensation priority evaluation is adopted to improve the timeliness of the upper system's dispatching and scheduling plans, reduce the probability of policy conflict events, and propose a conflict resolution method based on cumulative error compensation priority evaluation; the core idea of ​​the conflict resolution method based on cumulative error compensation is to use the cumulative compensation method to correct the data errors in the upper and lower layer information alignment, and reduce the probability of triggering system policy conflict events caused by cumulative inconsistency conflicts from the data transmission link; the upper algorithm engine relies on the production capacity of each manufacturing unit in the lower system for solving the dispatch plan. Layout characteristics between levels and units; however, limited by the bottleneck of solution time, the upper-level algorithm has a probability of different lower-level system production states before and after solution, and this phenomenon is called data error in upper- and lower-level information registration; In response to this situation, the present application proposes a conflict resolution method based on cumulative error compensation priority evaluation; This method acts on the process of the upper-level algorithm engine obtaining information from the actual physical environment, and aims to obtain the current production state of the lower-level system while calculating and obtaining the error between the production state of the lower-level system used in the previous round of solution and the production state of the lower-level system used in this round of solution to correct and compensate for the currently solved predicted production capacity.

[0069] In an optional embodiment, the conflict includes: an immediate conflict and a non-immediate conflict;

[0070] When a system failure causes the local production capacity of the intelligent manufacturing system to drop to a preset threshold, the dispatch plan will generate an immediate conflict;

[0071] When the products produced in the current round need to be rescheduled before the next round of production, the dispatch plan will have a non-immediate conflict;

[0072] During the execution of the work dispatch plan, the blockchain uses the manufacturing unit to perform conflict detection on the work dispatch plan, including the following steps:

[0073] Based on blockchain and manufacturing units, a directed graph for conflict detection is constructed;

[0074] The proxy nodes of the blockchain correspond one-to-one to the manufacturing units;

[0075] The directed graph uses the manufacturing units corresponding to the blockchain proxy nodes as graph nodes, is arranged according to the production process of the manufacturing units, and uses the relationship between the previous and next steps in the production process between different manufacturing units as the edges between the graph nodes;

[0076] The manufacturing execution system is used to perform non-instantaneous conflict detection on the execution process of the dispatch plan. If the manufacturing execution system detects the delivery of a temporary processing order, the dispatch plan will generate non-instantaneous conflict monitoring during the execution process. The manufacturing execution system traces the delivery information back to the blockchain node that generated the temporary order.

[0077] The execution process of the dispatch plan is subject to real-time conflict detection using the manufacturing execution system and a directed graph. If the number of parts in the parts buffer of the manufacturing execution system increases or decreases to a preset threshold, the dispatch plan will generate real-time conflict detection during execution, and the directed graph reverse solution is required to locate the blockchain proxy node corresponding to the faulty manufacturing unit.

[0078] In this optional embodiment, for node failure and deadlock scenarios in the lower-level system, a directed graph conflict detection model is established to perform conflict detection; for detected conflict events, a search-based composite strategy is used to resolve the conflict, solving the inconsistency problem between global planning and local execution;

[0079] In this optional embodiment, during the operation of the intelligent manufacturing system, the phenomenon that the actual production plan that needs to be carried out conflicts with the dispatch plan originally solved by the upper-level algorithm engine due to emergencies (such as equipment failure, supplementary injection and insertion, etc.) is called a strategy conflict; different conflicts require different detection methods, and conflicts can be divided into two types according to the cause of the conflict: immediate conflict and non-immediate conflict; among them, non-immediate conflict refers to the conflict type in which the rework of workpieces, supplementary injection and insertion, etc. in the production process require rescheduling before the next round of production of the current product, thereby conflicting with the dispatch plan solved by the upper-level algorithm engine; and immediate conflict is caused by the rapid decline of local production capacity of the system due to failure or deadlock of the manufacturing unit inside the system, resulting in the failure of the original dispatch plan to be executed normally; compared with immediate conflict, non-immediate conflict is easier to diagnose, because the occurrence of non-immediate conflict is often accompanied by a clear demand document; based on this feature, by controlling the manufacturing execution system (manufacturing execution system) of the system to control production scheduling, the system can automatically detect the conflict caused by the production schedule of the original work plan. Non-immediate conflicts can be effectively detected by using a manufacturing execution system (MES). However, immediate conflicts require a special conflict detection method because they are often caused by failures in internal nodes of the system. Establishing a fault diagnosis system for all manufacturing units would incur high system construction costs.

[0080] To address this problem, the present application adopts a conflict detection model; the principle of this model is the inverse solution of the directed graph model, and the specific process can be described as follows: in the context of the conflict monitoring model supported by a composite strategy, the manufacturing system is defined as a blockchain combination between multiple agent nodes; wherein, each agent node is a manufacturing unit, and each unit consists of a physical system and an information system; the physical system undertakes the actual processing task, and the information system undertakes the two-way communication function between the system and the contract engine and the upper-level algorithm engine; thanks to the process characteristics in the manufacturing process, the production process can be regarded as a directed flow of production objects between different manufacturing unit nodes; therefore, we abstract the manufacturing system into a directed graph model; by detecting whether the number of parts in the node represented by the part buffer (Buffer area) has abnormal increases or decreases (under normal circumstances, the number of parts in the Buffer area should fluctuate periodically within a certain range), if the number of parts increases or decreases abnormally, it means that there is a conflict in the system's production scheduling strategy, and then the specific fault node is located by inverse solution of the directed graph; through this method, the location of the node failure can be located quickly and effectively.

[0081] In an optional embodiment, the step of using the contract unit to resolve the conflict of the work dispatching plan detected includes:

[0082] The contract unit selects a smart contract based on the cause of the fault in the faulty manufacturing unit. After determining the smart contract, the contract unit opens a bidding channel and sends a signal to the blockchain agent node k corresponding to the faulty manufacturing unit, prompting agent node k to bid. The winning agent node reaches a work allocation transaction with agent node k, broadcasts the updated transaction to the entire blockchain, and synchronously updates the information of all nodes through the blockchain.

[0083] In this optional embodiment, the above-mentioned conflict resolution scheme using a combination of multiple strategies is proposed. With the assistance of the conflict detection model, immediate strategy conflicts can use the graph model to obtain the fault point; and non-immediate conflicts can be detected through the system's MES system; on the basis of conflict detectability, this application solves the inconsistency problem between global planning and local execution by applying a conflict resolution scheme using a combination of multiple strategies; the core of the conflict resolution method using a combination of multiple strategies is to adopt different smart contracts for conflict events with different characteristics to obtain the best conflict resolution scheme; therefore, the conflict events are characterized and formal verification methods are used to check the accessibility and deadlock possibility of smart contracts under different conflict events to solve the inconsistency problem that may exist in the smart contract system itself;

[0084] As an example, Figure 3 This is a logical diagram of the mapping between random disturbance events and smart contracts proposed in this embodiment; Figure 3As shown in Figure 2, when the system detects a conflict event, it diagnoses the conflict type based on the conflict characteristics. Figure 3 The conflict types displayed include: workpiece rework, supplementary plug-in, equipment failure, equipment recovery and other types of disturbances; when a new process is added or a single / multiple processes are inserted to destroy the original process, the conflict type generated is workpiece rework; when a new work order or a sequential multi-process is inserted to destroy the original process, the conflict type generated is supplementary plug-in; when the faulty equipment dispatch is withdrawn and allocated to other equipment, the conflict type generated is equipment failure; when other dispatches are selectively moved to the recovery equipment, the conflict type generated is equipment recovery; after the conflict type is determined, the intelligent decision-making system or engineer selects the intelligent contract algorithm based on the conflict characteristics; after the intelligent contract algorithm is determined, the contract system opens the bidding channel and sends a signal to the agent in the conflict event to prompt the agent node to bid, among which, Figure 3 The optional smart contract algorithms displayed include: one-time bidding smart contract, iterative bidding smart contract, auction type smart contract, resource sharing Crowd-X smart contract, competitive negotiation smart contract, job exchange coordination smart contract, master-slave Stackelbeng smart contract, subcontract smart contract, iterative refinement smart contract and other smart contracts; among them, Figure 3 The box in the upper left corner shows the mechanism for resolving device recovery conflict events using the Vickrey-Clarke-Croves Auction-type smart contract.

[0085] In an optional embodiment, the step of proxy node k conducting bidding includes:

[0086] Agent node k creates a work allocation proposal for bidding based on the cause of the manufacturing unit's failure and sends a bidding message to the contract unit. The work allocation proposal requests the transfer of a work quantity of size a to other manufacturing units to resolve the failure. When a is a non-zero positive number, it indicates that agent node k intends to transfer a work quantity of the absolute value of a to other manufacturing units. When a is a non-zero negative number, it indicates that agent node k intends to receive a work quantity of the absolute value of a from other manufacturing units.

[0087] After receiving the bidding information, the contract unit sends a bidding request for work allocation to other agent nodes. Other agent nodes choose whether to bid based on the load of the corresponding production unit;

[0088] If the allocatable workload of proxy node j is equal to zero, then proxy node j sends a signal to the contract unit to reject the bid;

[0089] Otherwise, the proxy node j sends a signal to the contract unit to accept the bid. At this time:

[0090] When a is a non-zero positive number and the allocable workload of the agent node i with the largest transferable workload is greater than or equal to a, the contract algorithm comprehensively considers the allocable workload of all bidding agent nodes to determine whether the winning bid of agent node i can maximize the benefits of the intelligent manufacturing system. If so, the bidding information of agent node i is sent to agent node k. Agent node k confirms the proposal content in the transaction information and sends the confirmation information and the transaction information of the work allocation to agent node i through the contract algorithm. After receiving the confirmation information and the transaction information of the work allocation from agent node k, agent node i broadcasts the updated transaction to the entire blockchain and synchronously updates the information of all nodes through the blockchain. Otherwise, the contract algorithm facilitates the work allocation transaction between agent node k and the agent node that can maximize the benefits of the intelligent manufacturing system, and synchronously updates the information of all nodes through the blockchain.

[0091] When a is a non-zero negative number and the allocatable workload of proxy node i is less than a, proxy node i generates a proposal based on its current allocatable workload and submits it to the contract unit for bidding. The contract unit performs a balance calculation among the bidding proxy nodes, obtains a balance result of having proxy node j assume part of the workload of proxy node k, and determines whether proxy node k can accept the balance result.

[0092] If the contract unit determines that the proxy node k cannot accept the balance result, the contract unit updates the proposal status of the proxy node k to the rejected status and returns it to the proxy node k. The proxy node k formulates a new tender and starts the tender again.

[0093] Otherwise, the contract unit updates the proposal of proxy node k to a partially accepted state and sends it to proxy node k together with the proposal of proxy node i. Proxy node k generates transaction information of work assignment based on the proposal of proxy node i, and sends the transaction and confirmation information of proxy k to proxy node i through the contract unit. After proxy node i receives the confirmation information of proxy node k and the transaction information of work assignment, it broadcasts the updated transaction to the entire blockchain and synchronously updates the information of all nodes through the blockchain.

[0094] Example 3

[0095] This embodiment also proposes a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor executes the steps of the method for resolving cross-domain conflicts in manufacturing tasks of the intelligent manufacturing system described in Example 1.

[0096] It can be understood that the computer device of this embodiment improves the method of Example 2. The options in the above-mentioned Example 2 are also applicable to this embodiment, so they will not be described again here.

[0097] The same or similar reference numerals correspond to the same or similar components;

[0098] The terms used in the drawings to describe positional relationships are for illustrative purposes only and should not be construed as limiting the present embodiment.

[0099] Obviously, the above embodiments of the present invention are merely examples for the purpose of clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Those skilled in the art will appreciate that other variations or modifications can be made based on the above description. It is not necessary and impossible to enumerate all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the claims of the present invention.

Claims

1. An intelligent manufacturing system, characterized in that: include: Upper-level computing module and lower-level physical module; The upper computing module includes: a database, a computing unit, a blockchain, and a contract unit; The lower-level physical module includes: several manufacturing units and communication modules; The database is used to store data that needs to be stored in the upper computing module; The computing unit is used to analyze and process the data in the database and generate a work dispatch plan; The communication module is used to upload the data of the manufacturing unit to the computing unit, and send the work dispatch plan issued by the computing unit to the manufacturing unit; The manufacturing unit includes a plurality of production equipment, and the manufacturing unit is used to execute the work dispatch plan; The contract unit includes several smart contracts, which are deployed on blockchain nodes; The blockchain is used to detect conflicts in the dispatching plans using the manufacturing unit during the execution of the dispatching plans, and to resolve conflicts in the dispatching plans detected using the contract unit; The conflicts include: immediate conflicts and non-immediate conflicts; When a system failure causes the local production capacity of the intelligent manufacturing system to drop to a preset threshold, the dispatch plan will generate an immediate conflict; When the products produced in the current round need to be rescheduled before the next round of production, the dispatch plan will have a non-immediate conflict; During the execution of the work dispatch plan, the blockchain uses the manufacturing unit to perform conflict detection on the work dispatch plan, including the following steps: Based on blockchain and manufacturing units, a directed graph for conflict detection is constructed; The proxy nodes of the blockchain correspond one-to-one to the manufacturing units; The directed graph uses the manufacturing units corresponding to the blockchain proxy nodes as graph nodes, is arranged according to the production process of the manufacturing units, and uses the relationship between the previous and next steps in the production process between different manufacturing units as the edges between the graph nodes; The manufacturing execution system is used to perform non-immediate conflict detection on the execution process of the dispatch plan. If the manufacturing execution system detects the delivery of a temporary processing order, a non-immediate conflict monitoring will be generated during the execution of the dispatch plan. The manufacturing execution system will trace the delivery information back to the blockchain node that generated the temporary order. The execution process of the dispatch plan is subject to real-time conflict detection using the manufacturing execution system and a directed graph. If the number of parts in the parts buffer of the manufacturing execution system increases or decreases to a preset threshold, the dispatch plan will generate real-time conflict detection during execution, and the directed graph reverse solution is required to locate the blockchain proxy node corresponding to the faulty manufacturing unit.

2. A method for resolving cross-domain conflicts in manufacturing tasks of an intelligent manufacturing system, applying the intelligent manufacturing system according to claim 1, characterized in that: The following steps are involved: Acquire equipment data from production equipment in manufacturing units; using the communication module to transmit the device data to the computing unit; The calculation unit predicts the tolerable load of the production equipment based on the equipment data, performs error compensation calculation on the predicted tolerable load of the production equipment, obtains the compensated capacity prediction value, and solves the work dispatch plan based on the compensated capacity prediction value; The work dispatch plan is sent to the manufacturing unit using the communication module, and the manufacturing unit executes the work dispatch plan; During the execution of the work dispatch plan, the blockchain uses the manufacturing unit to detect conflicts in the work dispatch plan, and uses the contract unit to resolve conflicts in the work dispatch plan that are detected to be in conflict.

3. The method for resolving cross-domain conflicts in manufacturing tasks of an intelligent manufacturing system according to claim 2, characterized in that: The expression of the device data is: Where, Represents device data, A binary value indicating whether the device is in a working state. Indicates various operating indicators of the equipment. Indicates the actual production capacity of the equipment in the last round of operation. Indicates the layout of the device.

4. The method for resolving cross-domain conflicts in manufacturing tasks of an intelligent manufacturing system according to claim 3, characterized in that: described 、 、 、 and are expressed in the form of matrices, and 、 、 、 and The matrix sizes are: 、 、 、 and , where n represents the number of devices and m represents the total number of types of equipment operation indicators.

5. The method for resolving cross-domain conflicts of manufacturing tasks in an intelligent manufacturing system according to claim 4, characterized in that: When the calculation unit predicts the tolerable load of the production equipment based on the equipment data, the equipment data corresponding to the current production round Data is input into the machine learning model, and the machine learning model outputs the tolerable load of the production equipment in this round of prediction , wherein the predicted tolerable load of each production equipment obtained by the machine learning model is stored in the database.

6. The method for resolving cross-domain conflicts in manufacturing tasks of an intelligent manufacturing system according to claim 5, characterized in that: The calculation unit performs error compensation calculation on the predicted tolerable load of the production equipment to obtain a compensated capacity forecast value. The steps of solving the work dispatch plan based on the compensated capacity forecast value include: Get the device data of this round Data and Data, call out the last round of predicted production equipment's tolerable load from the database ,based on data, data, Data and The data calculates the capacity forecast value after compensation. The calculation unit uses a preset algorithm to solve the work dispatch plan based on the capacity forecast value after compensation. The expression of the production capacity prediction value after compensation is: Where, Indicates the predicted capacity value after compensation; express The transposed matrix of .

7. The method for resolving cross-domain conflicts in manufacturing tasks of an intelligent manufacturing system according to any one of claims 2 to 6, characterized in that: The steps for using the contract unit to resolve conflicts in the detected conflicting work dispatching plans include: The contract unit selects a smart contract based on the cause of the fault in the faulty manufacturing unit. After determining the smart contract, the contract unit opens a bidding channel and sends a signal to the blockchain agent node k corresponding to the faulty manufacturing unit, prompting agent node k to bid. The winning agent node reaches a work allocation transaction with agent node k, broadcasts the updated transaction to the entire blockchain, and synchronously updates the information of all nodes through the blockchain.

8. The method for resolving cross-domain conflicts of manufacturing tasks in an intelligent manufacturing system according to claim 7, characterized in that: The steps for proxy node k to conduct bidding include: Agent node k creates a work allocation proposal for bidding based on the cause of the manufacturing unit's failure and sends a bidding message to the contract unit. The work allocation proposal requests the transfer of a work quantity of size a to other manufacturing units to resolve the failure. When a is a non-zero positive number, it indicates that agent node k intends to transfer a work quantity of the absolute value of a to other manufacturing units. When a is a non-zero negative number, it indicates that agent node k intends to receive a work quantity of the absolute value of a from other manufacturing units. After receiving the bidding information, the contract unit sends a bidding request for work allocation to other agent nodes. Other agent nodes choose whether to bid based on the load of the corresponding production unit; If the allocatable workload of proxy node j is equal to zero, then proxy node j sends a signal to the contract unit to reject the bid; Otherwise, the proxy node j sends a signal to the contract unit to accept the bid. At this time: When a is a non-zero positive number and the allocable workload of the agent node i with the largest transferable workload is greater than or equal to a, the contract algorithm comprehensively considers the allocable workload of all bidding agent nodes to determine whether the winning bid of agent node i can maximize the benefits of the intelligent manufacturing system. If so, the bidding information of agent node i is sent to agent node k. Agent node k confirms the proposal content in the transaction information and sends the confirmation information and the transaction information of the work allocation to agent node i through the contract algorithm. After receiving the confirmation information and the transaction information of the work allocation from agent node k, agent node i broadcasts the updated transaction to the entire blockchain and synchronously updates the information of all nodes through the blockchain. Otherwise, the contract algorithm facilitates the work allocation transaction between agent node k and the agent node that can maximize the benefits of the intelligent manufacturing system, and synchronously updates the information of all nodes through the blockchain. When a is a non-zero negative number and the allocatable workload of proxy node i is less than a, proxy node i generates a proposal based on its current allocatable workload and submits it to the contract unit for bidding. The contract unit performs a balance calculation among the bidding proxy nodes, obtains a balance result of having proxy node j assume part of the workload of proxy node k, and determines whether proxy node k can accept the balance result. If the contract unit determines that the proxy node k cannot accept the balance result, the contract unit updates the proposal status of the proxy node k to the rejected status and returns it to the proxy node k. The proxy node k formulates a new tender and starts the tender again. Otherwise, the contract unit updates the proposal of proxy node k to a partially accepted state and sends it to proxy node k together with the proposal of proxy node i. Proxy node k generates transaction information of work assignment based on the proposal of proxy node i, and sends the transaction and confirmation information of proxy k to proxy node i through the contract unit. After proxy node i receives the confirmation information of proxy node k and the transaction information of work assignment, it broadcasts the updated transaction to the entire blockchain and synchronously updates the information of all nodes through the blockchain.

9. A computer device comprising a memory and a processor, wherein the memory stores computer-readable instructions, wherein: When the computer-readable instructions are executed by the processor, the processor executes the steps of the method for resolving cross-domain conflicts of manufacturing tasks in an intelligent manufacturing system according to any one of claims 2 to 8.

Images