Supply chain full-process traceability system based on digital twinning and block chain

Abstract

The invention discloses a supply chain full-process traceability system based on digital twinning and block chains, and belongs to the technical field of digital twinning and block chains, and the system comprises a data collection layer which obtains original data from each link in real time, and carries out the preprocessing of the original data through an edge computing device; the twinborn model building layer is used for building digital twinborn models corresponding to all links of the supply chain respectively and generating link-level optimization parameters through simulation analysis; the block chain network layer is used for verifying and storing shared data and key traceability information among the digital twin models; the collaborative optimization module is used for dynamically adjusting a cross-link collaborative strategy based on a multi-agent reinforcement learning algorithm; and the data traceability layer responds to an external traceability query request and generates a full-link visual traceability map. By means of the collaborative algorithm based on multi-agent reinforcement learning, automation and intellectualization of information interaction among all link models are guaranteed, and personalized and multi-terminal traceability service can be provided for users.

Description

Technical Field

[0001] The present invention relates to the technical fields of digital twin and blockchain, and particularly to a full-process traceability system for the supply chain based on digital twin and blockchain. Background Art

[0002] The supply chain management field, as a comprehensive management category, integrates multidisciplinary knowledge and covers the efficient overall planning of the entire process from raw material procurement, production operation to product delivery to the final customer. However, the traditional supply chain management model has many deficiencies in aspects such as data collection, storage and sharing, process monitoring, and quality traceability, and it is difficult to meet the requirements of modern enterprises for the efficiency, transparency, and collaboration of the supply chain.

[0003] Firstly, in terms of data collection, traditional supply chain management mainly relies on manual records or simple information system input. Manual records are limited by manpower and time, making it difficult to collect data in real-time and comprehensively, and prone to human errors. At the same time, the existing information systems have limited functions and are difficult to be deeply integrated with production equipment, logistics systems, etc., resulting in limited data collection scope and frequency, information lag, and affecting the overall decision-making efficiency and response ability.

[0004] Secondly, in terms of data storage and sharing, traditional technologies mainly rely on a centralized database architecture. This architecture has the risk of node failures. Once the core node has problems, it may lead to the paralysis of the entire system. In addition, the centralized management method lacks effective security mechanisms to ensure the authenticity and integrity of data. Data is vulnerable to human tampering and has low credibility. More seriously, the data formats and standards between different enterprises or departments are not unified, and the informatization construction is carried out independently, resulting in the widespread existence of the "information island" phenomenon, which hinders the efficient collaboration and information interaction between the upstream and downstream of the supply chain.

[0005] Thirdly, in terms of product quality traceability and problem tracking, traditional means usually rely on paper records or limited electronic records, and the information is scattered in different departments or business processes. There is a lack of a unified integration mechanism. Paper documents are easy to lose and damage, and inconvenient to query; while electronic records, due to problems such as inconsistent formats and fragmented data, make the traceability process cumbersome, time-consuming, and inaccurate, and it is difficult to quickly locate the root cause of quality problems, seriously affecting the enterprise's emergency response ability and customer satisfaction.

[0006] In summary, the traditional supply chain management model has been difficult to adapt to the current complex and changeable market environment and the needs of the high-quality development of enterprises, and there is an urgent need for system optimization and technology upgrading. Summary of the Invention

[0007] The purpose of the present invention is to provide a full-process traceability system for the supply chain based on digital twin and blockchain, so as to solve the deficiencies existing in aspects such as data collection, storage and sharing, process monitoring, and quality traceability in the traditional supply chain management mode.

[0008] To achieve the above object, the present application adopts the following technical solutions:

[0009] A full-process traceability system for the supply chain based on digital twin and blockchain of the present application, the system includes a data collection layer, a twin model construction layer, a blockchain network layer, a collaborative optimization module, and a data traceability layer, wherein:

[0010] The data collection layer, based on sensors and data collection devices deployed in each link of the supply chain, obtains raw data from each link in real time, and uses edge computing devices to preprocess the raw data;

[0011] The twin model construction layer is used to construct digital twin models corresponding to each link of the supply chain according to the preprocessed data. Each digital twin model is updated based on real-time data to dynamically reflect the operating state of the physical entity of the corresponding link, and generates link-level optimization parameters through simulation analysis;

[0012] The blockchain network layer is configured as a consortium chain network composed of each participant in the supply chain as nodes, and adopts a hierarchical consensus mechanism to verify and store the shared data and key traceability information between each digital twin model, and associates cross-link data through a globally unique identifier;

[0013] The collaborative optimization module is coupled between the twin model construction layer and the blockchain network layer. Based on the multi-agent reinforcement learning algorithm, it drives each digital twin model to interact state information and optimization parameters through the blockchain network, and dynamically adjusts the cross-link collaborative strategy according to the on-chain consensus result;

[0014] The data traceability layer is used to respond to external traceability query requests, retrieve cross-link data associated with the target globally unique identifier in the blockchain network, and generate a full-link visual traceability map in combination with each digital twin model.

[0015] Preferably, each link of the supply chain includes a production link and a transportation link;

[0016] Each participant in the supply chain includes a core enterprise and a supplier as the main nodes, and a logistics provider and a distributor as the secondary nodes.

[0017] Preferably, the twin model construction layer includes:

[0018] A virtual production equipment model, constructed based on the initialization data of the production process, is used to simulate the operating state of the production equipment, and autonomously optimize the production parameters using a reinforcement learning algorithm, and transfer the production parameters to the collaborative optimization module;

[0019] A transportation process twin model, which integrates geographical information and real-time transportation data, is used to simulate the vehicle position and transportation route, and generates an alternative route based on road condition prediction and uploads it to the collaborative optimization module;

[0020] A model collaboration interface, which realizes real-time data exchange between the production and transportation models based on the collaborative optimization module, and shares the optimized parameters and policy execution results through a blockchain network.

[0021] Preferably, the collaborative optimization module includes:

[0022] A state perception unit, which is used to receive the historical optimized parameters, real-time operating state and simulation analysis results of the virtual production equipment model and the transportation process twin model;

[0023] A policy learning unit, based on the learning and updating rules in the reinforcement learning mechanism, takes each digital twin model as an agent, and calculates the optimal behavior policy of each agent according to the received data;

[0024] A on-chain feedback unit, which is used to encapsulate the optimal behavior policy into a blockchain transaction, and write it into the on-chain ledger after being verified by a hierarchical consensus mechanism.

[0025] Preferably, the blockchain network layer includes:

[0026] An intelligent contract module, which includes a transaction settlement contract and a goods handover contract, and is used to automatically execute the contract terms when the supply chain business meets the preset conditions;

[0027] An identifier management module, which is used to generate a globally unique identifier, and bind the globally unique identifier to the first blockchain transaction to form a data association anchor point.

[0028] Preferably, the intelligent contract module further includes:

[0029] A cross-model collaboration response unit, which is used to automatically call the target model interface to generate a collaborative processing plan when an abnormal event is detected in any digital twin model, and write the event processing record into the blockchain network.

[0030] Preferably, the hierarchical consensus mechanism includes the Byzantine Fault Tolerance consensus algorithm adopted among the primary nodes, and the improved Practical Byzantine Fault Tolerance algorithm adopted between the secondary nodes and the primary nodes.

[0031] Preferably, the improved Practical Byzantine Fault Tolerance algorithm includes the following steps:

[0032] Select a part of the primary nodes as the verification node subset, and set the quick verification threshold K and the synchronization period S;

[0033] When a secondary node generates data, generate a message and submit the message to the verification node subset in the primary nodes for preliminary verification;

[0034] If within a short period of time, K nodes in the verification node subset verify the message successfully, send a quick confirmation message to the secondary node;

[0035] After receiving the quick confirmation message, the secondary node directly writes the data into the local ledger;

[0036] When the synchronization period S arrives, the secondary node synchronizes the ledger with the primary node and repairs the differences.

[0037] Preferably, the method of data traceability includes the following steps:

[0038] Receive a traceability query request sent by the user, and the request contains a globally unique identifier;

[0039] Retrieve the corresponding historical transaction data in the blockchain network according to the globally unique identifier, and distribute the historical transaction data to the corresponding digital twin model;

[0040] Use each digital twin model to perform reverse simulation on the historical transaction data to generate a visual map of the entire supply chain process;

[0041] Dynamically filter data according to the user role to customize and display the traceability information.

[0042] Preferably, the key traceability information includes the product completion time, production batch, and quality inspection results in the production link, as well as the real-time location of the vehicle and the vehicle transportation route in the transportation link.

[0043] The present invention has the following beneficial effects:

[0044] The present invention realizes the efficient acquisition and preprocessing of raw data by deploying various sensors and devices in all links of the supply chain; also uses advanced technologies such as industrial Internet of Things edge intelligence collaboration, digital twin and geographic information system integration to create an intelligent model with real-time self-learning and optimization and active intervention capabilities, realizing the comprehensive digital mapping of the physical entities in the supply chain; and with the help of a collaborative algorithm based on multi-agent reinforcement learning, it ensures the automation and intelligence of information interaction between models in each link; at the same time, in the construction of the blockchain network, based on the design of a hierarchical consensus mechanism and targeted smart contracts, it ensures the consistency, reliability of data and the automated processing of business processes; it can also provide users with personalized and multi-terminal traceability services, realizing the transparent and traceable management of the entire supply chain process. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0046] Figure 1 is a schematic structural diagram of a full-process traceability system for the supply chain based on digital twin and blockchain provided by an embodiment of the present application;

[0047] Figure 2 is a flowchart of the Byzantine fault tolerance consensus algorithm in an embodiment of the present application;

[0048] Figure 3 is a flowchart of the improved practical Byzantine fault tolerance algorithm in an embodiment of the present application;

[0049] Figure 4 is a flowchart of the data traceability method in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] To make the technical solutions of the present application clearer, the following further elaborates on the present invention in detail with reference to the accompanying drawings and specific embodiments. The terms "first", "second", etc. in the claims and the description of the present application are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances. This is only a way of distinguishing objects with the same attributes when describing the embodiments of the present application. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, so that a process, method, system, product or device including a series of units does not have to be limited to those units, but may include other units not clearly listed or inherent to these processes, methods, products or devices.

[0051] This embodiment provides a full-process traceability system for the supply chain based on digital twin and blockchain, as Figure 1 shown. The system includes a data acquisition layer, a twin model construction layer, a blockchain network layer, a collaborative optimization module, and a data traceability layer.

[0052] Among them, the data acquisition layer is based on sensors and data acquisition devices deployed in each link of the supply chain, and real-time obtains the original data from each link, and uses edge computing devices to preprocess the original data.

[0053] Specifically, a variety of sensors and data acquisition devices are deployed in each link of the supply chain, including but not limited to temperature sensors and humidity sensors for recording product production link parameters, GPS positioning devices for recording logistics transportation locations, and radio frequency identification tag readers for recording product raw material information, etc., to collect the original data of supply chain links such as production, transportation, warehousing, and sales in real time, such as raw material sources, production progress, output, product offline time, batch numbers, transportation trajectories, inventory quantities, etc., and preliminarily sort and classify all the collected original data. At the same time, industrial Internet of Things (IIoT) technology is used to connect these sensors and data acquisition devices to edge computing devices, and the edge computing devices are used to preprocess the data after preliminary sorting and classification. The preprocessing specifically includes data cleaning, duplicate removal, feature extraction, and format standardization, etc., aiming to eliminate invalid noise data and duplicate records, thereby significantly reducing the data transmission load and effectively improving the overall quality of the data.

[0054] Among them, the twin model construction layer is used to construct digital twin models corresponding to each link of the supply chain according to the preprocessed data. Each digital twin model is updated based on real-time data to dynamically reflect the operating state of the physical entity of the corresponding link, and generates link-level optimization parameters through simulation analysis.

[0055] Furthermore, the twin model construction layer includes:

[0056] A virtual production equipment model, constructed based on the initialization data of the production link, used to simulate the operating state of the production equipment, and autonomously optimize the production parameters using a reinforcement learning algorithm, and transmit the production parameters to the collaborative optimization module;

[0057] A transportation process twin model, which integrates geographical information and real-time transportation data, used to simulate vehicle positions and transportation routes, and generates alternative routes based on road condition predictions and uploads them to the collaborative optimization module;

[0058] A model collaboration interface, which realizes real-time data exchange between the production and transportation models based on the collaborative optimization module, and shares optimization parameters and policy execution results through the blockchain network.

[0059] In this embodiment, digital twin models for the production and transportation links are mainly established.

[0060] Specifically, for the production link, a virtual production equipment model is constructed based on the production equipment parameters and process data included in the preprocessed data. This model can not only simulate the equipment operation status, production efficiency, and product quality fluctuations during the actual production process, but also simulate the production progress, output, and product off-line time in real time.

[0061] By simulating the operation status of the equipment in the actual production process, such as startup, stop, and failure, this model can predict potential problems of the equipment in advance, optimize the equipment maintenance plan, and reduce the downtime; by simulating the production process to evaluate the production efficiency and identify production bottlenecks, it can optimize the production process, improve the overall production efficiency, and reduce the production cost; by simulating the product quality fluctuations during the production process, it can predict the defective rate, adjust the production parameters in advance, reduce the defective rate, and improve the product quality; by simulating the production progress in real time, it can master the product progress in real time and ensure the smooth execution of the production plan; by predicting the output in advance, it can optimize the resource allocation to meet the market demand; by accurately predicting the product off-line time, it can optimize the supply chain management, reduce the inventory backlog, and improve the customer satisfaction.

[0062] At the same time, the virtual production equipment model also has the adaptive control ability based on reinforcement learning. It trains and optimizes the production parameters through the reinforcement learning algorithm and real-time data, and dynamically adjusts the production strategy. Specifically, it continuously receives the latest equipment operation data, uses the comparative analysis technology based on the generative adversarial network to conduct in-depth comparative analysis with its own simulated operation results. When it finds that there is a deviation between the actual data and the simulated results, it starts the self-learning mechanism and uses the deep transfer learning algorithm to optimize and adjust the model parameters. Suppose the actual production efficiency is lower than the model expectation, then it deeply analyzes the complex connections between multi-source information such as equipment operation and raw material quality data with the help of the knowledge graph technology, finds out the key factors affecting the production efficiency, and adjusts the equipment performance parameters, production process parameters, etc. in the model through the intelligent decision-making system, so that the model can more accurately reflect the actual production situation, or autonomously adjusts the production strategy according to the real-time monitored equipment operation data.

[0063] For the logistics transportation link, by using the integrated technology of digital twin and geographic information system, based on the transportation vehicle information, route planning information, real-time transportation data, etc. contained in the data preprocessed by the edge computing device, a twin model of the transportation process is constructed. This model is used to display in real time information such as the location of the transportation vehicle, driving speed, estimated arrival time, etc. And through the introduced spatio-temporal big data analysis algorithm, factors such as road condition changes and weather impacts during the transportation process are predicted in real time. Suppose it is predicted that there will be congestion on a certain section of the road, then the quantum-inspired optimization algorithm is used to quickly plan an alternative route for the transportation vehicle, and at the same time, coordinate the surrounding vehicle resources to achieve dynamic allocation and collaborative scheduling of transportation tasks, improve transportation efficiency. It also predicts the vehicle failure risk through the deep learning of historical transportation data and real-time environmental data, arranges maintenance plans in advance, and reduces transportation delays caused by vehicle failures, thus providing guarantee for the reliability of logistics transportation.

[0064] By constructing digital twin models for each link of the supply chain, a comprehensive digital mapping of the physical entities of the supply chain is realized, providing an intuitive and visual basis for full-process traceability.

[0065] Among them, the blockchain network layer is configured as a consortium chain network composed of nodes of each participant in the supply chain. A hierarchical consensus mechanism is adopted to verify and store the shared data and key traceability information between digital twin models, and cross-link data is associated through a globally unique identifier.

[0066] The key traceability information includes the product completion time, production batch, and quality inspection results in the production link, as well as the real-time location of the vehicle and the vehicle transportation route in the transportation link.

[0067] In this embodiment, a blockchain network with multi-party participation is designed using the consortium chain architecture. The core enterprises, suppliers, distributors, and logistics providers in the supply chain are added to the network as nodes of the consortium chain. Among them, the core enterprises and suppliers are the main nodes, and the distributors and logistics providers are the secondary nodes. Each node has independent data storage and processing capabilities, and a hierarchical consensus mechanism is used to ensure the consistency and reliability of data between nodes. At the same time, the data processed and verified by the digital twin model will also be packaged into blocks and stored on the blockchain according to a specific format and time stamp.

[0068] The blockchain uses asymmetric encryption technology to ensure the security and immutability of data, and any modification of data by a node requires verification by a hierarchical consensus mechanism, ensuring the authenticity and integrity of the full-process data of the supply chain.

[0069] Among them, the hierarchical consensus mechanism includes the Byzantine fault-tolerant consensus algorithm adopted between the main nodes, and the improved practical Byzantine fault-tolerant algorithm adopted between the secondary nodes and the main nodes.

[0070] Specifically, as Figure 2 shown, the Byzantine fault-tolerant consensus algorithm mainly includes the following steps:

[0071] S110. Parameter setting: Specify the specific number of main nodes such as the core enterprise and the public key supplier. The specific number N is determined according to the actual scale and business complexity of the supply chain. Considering the network condition, set the maximum allowable delay time T for message propagation between nodes to control the time range for consensus reaching. For example, in a high-speed and stable enterprise internal network environment, T is set to a relatively small value, such as 100 milliseconds. If there are many unstable factors in the network, T needs to be appropriately increased. According to the reliability evaluation of the main nodes, set the tolerable proportion f of faulty or malicious nodes, such as f = N / 3 (rounded down), to ensure that the consensus mechanism can still operate normally when a certain number of nodes have problems;

[0072] S111. Message broadcasting: When a main node generates new key data (such as the core enterprise determines a new raw material procurement plan), encapsulate the data and related transaction information into a message in a specific format and broadcast it to all other main nodes;

[0073] S112. Message verification: Each receiving node verifies the legality of the received message, including whether the data format is correct and whether the signature is valid. If the verification passes, the node stores the message in the local cache and sends an acknowledgment message to other nodes;

[0074] S113. Consensus reaching: When a node receives more than 2f + 1 acknowledgment messages (including the message sent by itself), it considers that the message has reached a consensus, writes the relevant data into the local ledger, and updates the blockchain state.

[0075] The Byzantine fault-tolerant consensus algorithm ensures that consensus can still be quickly reached in the case of a large number of nodes and the existence of some node failures or malicious attacks, guaranteeing the consistency and reliability of key data.

[0076] As Figure 3 shown, the improved Practical Byzantine Fault Tolerance (PBFT) algorithm mainly includes the following steps:

[0077] S210. Parameter setting: Select a part of the main nodes as the verification node subset M; Set a message quantity threshold for fast verification, that is, the fast verification threshold K. When a secondary node receives K identical messages from the verification node subset, it directly considers that a consensus has been reached and enters the data processing process; Define the time interval for data synchronization between the secondary node and the main node, such as synchronizing every 5 minutes, to ensure the real-time nature of the secondary node data;

[0078] S211. Message submission: After a secondary node (such as a logistics provider) generates data (such as a transportation status update), submit the message to the verification node subset in the main nodes;

[0079] S212, Quick verification: After receiving the message, the verification node conducts preliminary verification. If within a short period (such as 1 second), K nodes in the subset of verification nodes verify the same message successfully, a quick confirmation message is sent to the secondary node. After receiving the quick confirmation message, the secondary node can directly write the data to the local ledger;

[0080] S213, Periodic synchronization: When the synchronization period S arrives, the secondary node synchronizes all data with the primary node, compares the differences in the ledger, and repairs the inconsistent data to ensure data consistency.

[0081] The improved Practical Byzantine Fault Tolerance algorithm improves the data transmission and storage efficiency by reducing unnecessary consensus verification links. It also significantly improves the system's efficiency and fault tolerance by introducing a quick verification mechanism and a periodic synchronization mechanism. This improvement is particularly suitable for distributed systems that require quick response and high throughput, such as logistics and supply chain management. Through these optimizations, the system can improve the overall performance and user experience while maintaining data consistency.

[0082] Specifically, the blockchain network layer includes:

[0083] The smart contract module, which includes a transaction settlement contract and a goods handover contract, is used to automatically execute the contract terms when the supply chain business meets the preset conditions;

[0084] The identifier management module is used to generate a globally unique identifier and bind the globally unique identifier to the first blockchain transaction to form a data association anchor point.

[0085] The blockchain network layer also sets up a smart contract module. For business processes such as transaction settlement and goods handover in the supply chain, smart contract code is written. When the smart contract meets the preset conditions, the smart contract is automatically triggered to execute, realizing the automated processing of business processes, reducing manual intervention, improving the efficiency and transparency of supply chain business processing, and further ensuring the safe and efficient transfer of the entire supply chain process data on the blockchain.

[0086] Among them, the transaction settlement contract includes parameters such as defining the two parties to the transaction (such as the supplier and the core enterprise), the settlement amount, the settlement conditions (such as settlement within X days after product acceptance), and the payment method (such as the digital currency payment address). When the settlement conditions are met, the contract execution is automatically triggered to transfer the corresponding funds from the payer's account to the payee's account.

[0087] The goods handover contract includes parameters such as clearly defining the two parties for goods handover, goods information (such as name, quantity, specifications, etc.), handover address, handover time, etc. When the goods are transported to the designated handover location and the time complies with the contract regulations, and at the same time the receiving party confirms that the goods are correct, the contract automatically records the handover completion information and updates the goods status in the supply chain.

[0088] The smart contract module also includes:

[0089] A cross-model collaborative response unit, which is used to automatically call the target model interface to generate a collaborative processing plan when an abnormal event is detected in any digital twin model, and write the event processing record into the blockchain network.

[0090] Suppose the virtual production equipment model predicts through the reinforcement learning algorithm that the equipment Machine-001 will malfunction in 30 minutes. Then it first generates an abnormal event {GUID: "PROD-20250421-002", failure type: "equipment downtime risk", remaining normal operation time: 25 minutes}, and then calls the "transportation resource reallocation" interface of the transportation process twin model through the smart contract to notify that the production of batch PROD-20250421-002 originally planned to be produced by Machine-001 will be completed 2 hours later; after receiving the notice, the transportation process twin model immediately adjusts the route of the transport vehicle TRUCK-008 (originally planned to arrive at the factory at 15:00), delays the departure to 17:00, and temporarily allocates the vehicle during the idle period to other urgent tasks.

[0091] Suppose the transportation process twin model predicts through spatio-temporal big data analysis that a certain section (such as 3 kilometers of Highway X) will be congested in 1 hour (probability > 80%). Then it first generates a congestion warning event {GUID: "PROD-20250421-001", congestion period: 16:00~18:00, recommended detour route: Route Y}, and then sends a request "whether to adjust the loading time of batch PROD-20250421-001 to after 17:30" to the production model through the multi-agent reinforcement learning algorithm. After receiving the request, the virtual production equipment model combines the current production progress (expected to be completed at 16:30), and through knowledge graph analysis, concludes that "delaying the loading by 1 hour will not affect the subsequent processes", so it returns an approval instruction, and the transportation process digital twin model re-plans the departure time of vehicle TRUCK-007 accordingly.

[0092] The blockchain network layer is also provided with an identifier management module, which assigns a unique identification code, i.e., the globally unique identifier (GUID), to each batch or single product during the product production process. This GUID serves as the "digital ID card" throughout the entire supply chain. The GUID is associated with data such as raw material batches and process parameters in the production process, stored in the initial blockchain transaction of the production process, and synchronized to the blockchain nodes in links such as logistics and warehousing as the product flows, realizing cross-link data association and anchoring. For example, in the production process, a transaction Tx-Production is generated, including fields {GUID: "PROD-20250421-001", raw material batch: "RM-202504-05", process version: "V3.2", production time: "2025-04-21 09:00"}; in the logistics process, a transaction Tx-Logistics is generated, containing fields {GUID: "PROD-20250421-001", transportation period: "2025-04-21 14:00~2025-04-22 08:00", temperature and humidity data: "[22℃,55%RH]", vehicle ID: "TRUCK-007"}.

[0093] The hash chain association of cross-link data is also realized through the GUID to ensure that the data is immutable and traceable. Specifically, when constructing the digital twin virtual model, the virtual device operation data in the production process (such as device numbers, process parameters, etc.) and the transportation model in the logistics process (such as vehicle numbers, route nodes, etc.) are mapped through the GUID. For example, the product batch produced by a certain device Machine-001 in the production model corresponds to the GUID PROD-20250421-001; the GUID of the goods transported by vehicle TRUCK-007 in the logistics model is PROD-20250421-001. Through the cross-verification of spatio-temporal data (production time, transportation period), the accuracy of data association is ensured. When the product comes off the production line in the production process, the edge computing device synchronizes the GUID and production data to the digital twin model in the logistics transportation process through a smart contract, triggers the transportation resource scheduling of the transportation model, and the data collected in the logistics transportation process will be written into the blockchain network through the edge computing node device and associated with the transaction corresponding to the GUID. If the production time is later than the transportation time, it is determined that there is a data error or process problem.

[0094] Among them, the collaborative optimization module is coupled between the twin model construction layer and the blockchain network layer. Based on the multi-agent reinforcement learning algorithm, it drives each digital twin model to interact state information and optimization parameters through the blockchain network, and dynamically adjusts the cross-link collaborative strategy according to the on-chain consensus result.

[0095] Specifically, the collaborative optimization module includes:

[0096] A state perception unit, configured to receive historical optimization parameters, real-time operating states, and simulation analysis results of the virtual production equipment model and the transportation process twin model;

[0097] A policy learning unit, based on the learning and updating rule in the reinforcement learning mechanism, takes each digital twin model as an agent, and calculates the optimal behavior policy for each agent according to the received data;

[0098] A feedback unit on the chain, configured to encapsulate the optimal behavior policy as a blockchain transaction, and write it into the ledger on the chain after being verified by a hierarchical consensus mechanism.

[0099] To meet the automation and intelligence requirements for information interaction among digital twin models in each link, this embodiment also adopts a collaborative algorithm based on multi-agent reinforcement learning. Specifically, in the collaborative algorithm based on multi-agent reinforcement learning, the digital twin model corresponding to each supply chain link is an agent. For example, the virtual production equipment model is the production link agent, and the transportation process twin model is the logistics transportation link agent, and the learning and updating rule in the reinforcement learning mechanism is introduced for policy optimization, which is expressed as follows:

[0100] ,

[0101] where, represents the current value estimate of taking action in state , corresponding to the value of the production link agent or the logistics transportation link agent executing a certain action in a specific state. For example, when the production link agent has a device failure (state ), it chooses to send a failure message to the logistics transportation link (action ), and the value; represents "update to" or "replace with".

[0102] is the learning rate, and its value range is usually between 0 and 1. It determines the degree of update of the newly obtained information to the original value. For example, indicates that the new information has a relatively small impact on the update of the value, and it is more dependent on historical experience.

[0103] is the reward obtained from the environment after executing action , which is related to the design of the reward mechanism. For example, the production link agent obtains a reward of +10 for reasonably adjusting the production speed to avoid goods backlog. At this time, .

[0104] is the discount factor, whose value range is also between 0 and 1, and is used to balance the importance of current rewards and future rewards. For example, means attaching more importance to future rewards and tending to choose actions that can bring long-term benefits.

[0105] is the executed action after which the new state is transferred to. For example, after the intelligent agent in the logistics transportation link reallocates vehicle resources (action ), changes occur in the vehicle location, transportation task allocation, etc., forming a new state .

[0106] represents the one with the maximum value among all possible actions in the new state . That is, the intelligent agent's estimate of the optimal action value for the future, representing the optimal choice. For example, in the new transportation task allocation state , the intelligent agent in the logistics transportation link can choose actions such as optimizing the transportation route and adjusting the vehicle load. Among them, the action corresponding to the maximum value of is the value of . .

[0107] By continuously repeating this update process, the intelligent agents in the production link and the logistics transportation link can gradually learn, based on the real-time collected data and business rules, what actions (such as adjusting the production rate, choosing the optimal distribution route, etc.) to take in different states (such as inventory level, order quantity, traffic conditions, etc.) to maximize the cumulative reward, thus realizing the automation and intelligence of information interaction in each link of the digital twin model. For example, the intelligent agents in the production link and the logistics transportation link calculate and find that notifying the logistics in advance to make transportation preparations a certain time before the product is completed can maximize the cumulative reward. Then, through the information interaction mechanism and collaborative process established between these two links, when the production link predicts that a certain batch of products is about to be completed, it will synchronize the information to the transportation process digital twin model. This model, based on the vehicle location, transportation capacity, and real-time conditions of the transportation route, arranges appropriate vehicles to standby in advance, optimizes the transportation route planning, ensures that the products can be quickly loaded and shipped after completion, reduces the waiting time of the products in the warehouse, and thereby improves the overall efficiency of the supply chain. Among them, the business rules refer to the operation specifications set within the enterprise, such as quality control standards, safety regulations, etc.

[0108] In this embodiment, the purpose of calculating the maximized cumulative reward is to guide the agents in each link to find the behavioral strategies that are most conducive to improving the overall efficiency of the supply chain. In a complex supply chain system, different links are interconnected and face various dynamic changes, such as equipment failures and traffic congestion. By maximizing the cumulative reward, the agents can determine the action plan that is most beneficial to the overall supply chain benefit in the long run among numerous possible behavioral choices. For example, if the production link agent can obtain a high cumulative reward through behaviors such as reasonably adjusting the production speed and timely communicating and coordinating with the logistics and transportation link, it indicates that these behaviors contribute to improving the overall operation efficiency of the supply chain, including reducing inventory backlogs, lowering transportation costs, and increasing the on-time delivery rate.

[0109] Among them, the data traceability layer is used to respond to external traceability query requests, retrieve cross-link data associated with the target globally unique identifier in the blockchain network, and generate a full-link visual traceability map in combination with each digital twin model.

[0110] Specifically, the method of data traceability includes the following steps:

[0111] Receive the traceability query request sent by the user, where the request contains the globally unique identifier;

[0112] Retrieve the corresponding historical transaction data in the blockchain network according to the globally unique identifier, and distribute the historical transaction data to the corresponding digital twin model;

[0113] Use each digital twin model to perform reverse simulation on the historical transaction data to generate a visual map of the entire supply chain process;

[0114] Dynamically filter the data according to the user role to customize the display of traceability information.

[0115] Such as Figure 4As shown, when a data query or traceability is required in a certain link of the supply chain, the user sends a traceability query request to the blockchain network through the client of the traceability system. Further, the user inputs or scans the GUID of a product through the front-end interface to send a traceability query request. This request contains the GUID and user identity information (such as consumers, regulatory agencies, internal enterprise personnel, etc.). Using the GUID as an index to query in the blockchain network, the corresponding block data can be located. Each piece of data is pushed to the digital twin model of the corresponding link according to the event type. The digital twin model starts from the final state based on the received data and reversely traces back the supply chain process of Zhen Gege. Through the collaborative work of each digital twin model, the whole process of the product from birth to the present can be restored. Then, a visualization map of the whole process is constructed using a graph database such as Neo4j. The actual status and historical data changes of each link in the supply chain are shown in this visualization map. Through interactive operations, the user can view in detail the whole process information of the product from raw material procurement to final sales, including the specific time, location, operation content, and responsible person of each link, realizing the transparent and traceable management of the entire supply chain process.

[0116] The data traceability layer can also select different display methods and information focuses according to the user role. For example, for production enterprises, it can focus on showing the changes in process parameters and quality inspection data during the product production process; for consumers, the display interface can be simplified to highlight the raw material source, production date, shelf life, and quality certification information of the product. At the same time, the client supports multi-terminal access, including but not limited to the PC side, mobile side, and smart wearable devices, etc.

[0117] Based on the data collection layer, this embodiment realizes the efficient collection and preprocessing of raw data by deploying various sensors and devices in each link of the supply chain. In the digital twin model construction link, advanced technologies such as industrial Internet of Things edge intelligence collaboration, digital twin and geographic information system integration are used to create an intelligent model with real-time self-learning and optimization and active intervention capabilities, realizing the comprehensive digital mapping of the physical entities in the supply chain. Also, with the collaborative algorithm based on multi-agent reinforcement learning, the automation and intelligence of information interaction between models in each link are guaranteed. At the same time, in terms of building the blockchain network, the design of the hierarchical consensus mechanism and targeted smart contracts ensures the consistency, reliability of data and the automated processing of business processes. Finally, the data interaction and traceability process provides users with personalized and multi-terminal traceability services, realizing the transparent and traceable management of the entire supply chain process.

[0118] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

Claims

1. A full-process traceability system for the supply chain based on digital twin and blockchain, characterized in that, The system includes a data acquisition layer, a digital twin model construction layer, a blockchain network layer, a collaborative optimization module, and a data traceability layer, where: The data acquisition layer, based on sensors and data acquisition devices deployed in each link of the supply chain, obtains raw data from each link in real time, and uses edge computing devices to preprocess the raw data; The digital twin model construction layer is used to construct digital twin models corresponding to each link of the supply chain according to the preprocessed data. Each digital twin model is updated based on real-time data to dynamically reflect the operating state of the physical entity in the corresponding link, and generates link-level optimization parameters through simulation analysis; The blockchain network layer is configured as a consortium chain network composed of each participant in the supply chain as nodes, and uses a hierarchical consensus mechanism to verify and store the shared data and key traceability information between each digital twin model, and associates cross-link data through a globally unique identifier; The collaborative optimization module is coupled between the digital twin model construction layer and the blockchain network layer. Based on the multi-agent reinforcement learning algorithm, it drives each digital twin model to interact state information and optimization parameters through the blockchain network, and dynamically adjusts the cross-link collaborative strategy according to the consensus result on the chain; The data traceability layer is used to respond to external traceability query requests, retrieve cross-link data associated with the target globally unique identifier in the blockchain network, and generate a full-link visual traceability map in combination with each digital twin model.

2. The whole-process traceability system for the supply chain based on digital twin and blockchain according to claim 1, characterized in that, Each link of the supply chain includes a production link and a transportation link; Each participant in the supply chain includes a core enterprise and a supplier as the main nodes, and a logistics provider and a distributor as the secondary nodes.

3. A full-process traceability system for the supply chain based on digital twin and blockchain according to claim 2, characterized in that, The digital twin model construction layer includes: A virtual production equipment model, constructed based on the initialization data of the production link, used to simulate the operating state of the production equipment, and autonomously optimize the production parameters using the reinforcement learning algorithm, and transmit the production parameters to the collaborative optimization module; A transportation process digital twin model, which integrates geographic information and real-time transportation data, is used to simulate vehicle positions and transportation routes, and generates alternative routes based on road condition predictions and uploads them to the collaborative optimization module; A model collaboration interface, which realizes real-time data exchange between the production and transportation models based on the collaborative optimization module, and shares optimization parameters and policy execution results through the blockchain network.

4. The whole-process traceability system for the supply chain based on digital twin and blockchain according to claim 3, characterized in that, The collaborative optimization module includes: A state perception unit, used to receive the historical optimization parameters, real-time operating state, and simulation analysis results of the virtual production equipment model and the transportation process digital twin model; The policy learning unit, based on the learning update rule, takes each digital twin model as an agent and calculates the optimal behavior policy for each agent according to the received data; An on-chain feedback unit, used to encapsulate the optimal behavior strategy as a blockchain transaction, and write it into the on-chain ledger after being verified by the hierarchical consensus mechanism.

5. The whole-process traceability system of the supply chain based on digital twin and blockchain according to claim 2, characterized in that The blockchain network layer includes: An intelligent contract module, including a transaction settlement contract and a goods handover contract, used to automatically execute the contract terms when the supply chain business meets the preset conditions; An identifier management module, used to generate a globally unique identifier, and bind the globally unique identifier to the first blockchain transaction to form a data association anchor point.

6. The whole-process traceability system for supply chain based on digital twin and blockchain according to claim 5, characterized in that, The intelligent contract module also includes: Cross-model collaborative response unit, which is used to automatically call the target model interface to generate a collaborative processing solution when an abnormal event is detected in any digital twin model, and write the event processing record into the blockchain network.

7. The full-process traceability system for the supply chain based on digital twin and blockchain according to claim 2, characterized in that, The hierarchical consensus mechanism includes the Byzantine fault tolerance consensus algorithm adopted among the primary nodes, and the improved practical Byzantine fault tolerance algorithm adopted between the secondary nodes and the primary nodes.

8. A whole-process traceability system for a supply chain based on digital twin and blockchain according to claim 7, characterized in that, The improved practical Byzantine fault tolerance algorithm includes the following steps: Select a part of the primary nodes as the verification node subset, and set the fast verification threshold K and the synchronization period S; When the secondary node generates data, generate a message and submit the message to the verification node subset in the primary nodes for preliminary verification; If within a short period of time, K nodes in the verification node subset verify the message passed, send a fast confirmation message to the secondary node; After receiving the fast confirmation message, the secondary node directly writes the data into the local ledger; When the synchronization period S arrives, the secondary node synchronizes the ledger with the primary node and repairs the differences.

9. The whole-process traceability system for supply chain based on digital twin and blockchain according to claim 1, characterized in that, The method of data traceability includes the following steps: Receive the traceability query request sent by the user, and the request contains a globally unique identifier; Retrieve the corresponding historical transaction data in the blockchain network according to the globally unique identifier, and distribute the historical transaction data to the corresponding digital twin models; Use each digital twin model to perform reverse simulation on the historical transaction data to generate a visual map of the entire supply chain process; Dynamically filter data according to the user role to customize the display of traceability information.

10. The whole-process traceability system of the supply chain based on digital twin and blockchain according to claim 2, characterized in that, The key traceability information includes the product completion time, production batch, and quality inspection results in the production link, as well as the real-time location of the vehicle and the vehicle transportation route in the transportation link.

Images