Blockchain-based rail transit distributed intelligent operation and maintenance system and its operation method

Through the coordinated work of blockchain network and edge nodes, a unified rail transit operation and maintenance model is built, which solves the problems of equipment data transmission security and workload in the existing technology, and realizes an efficient and secure intelligent operation and maintenance system.

CN111859465BActive Publication Date: 2024-11-22TRAFFIC CONTROL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010608559.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-06-29
Publication Date
2024-11-22
Estimated Expiration
2040-06-29

AI Technical Summary

Technical Problem

Due to the limitations of distributed data collection and storage, privacy and security, each type of equipment needs to be trained separately, which increases the workload of developers, and data is easily intercepted and intercepted during transmission. Tampering, lack of effective privacy protection.

Method used

Adopt a distributed intelligent operation and maintenance system based on blockchain, train and update a unified local operation and maintenance model through communication connection between blockchain network and edge nodes, only transmit model parameters rather than device data, and utilize aggregation nodes and blocks. The consensus mechanism of chain nodes builds and updates the model to ensure the security and integrity of model parameters.

Benefits of technology

All edge nodes use the same operation and maintenance model, reduce the workload of developers and algorithm complexity, avoid repeated training, improve the reliability and information security of the intelligent operation and maintenance system, and prevent device data from being intercepted and tampered. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN111859465B_ABST
    Figure CN111859465B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention provides a distributed intelligent operation and maintenance system for rail transit based on blockchain and its operation method. All edge nodes in the system use the same local operation and maintenance model to operate and maintain the carried rail transit operation equipment. Since the same local operation and maintenance model is used, the workload of developers is greatly reduced, the algorithm complexity of the intelligent operation and maintenance system is reduced, and a single model can be used to complete related tasks for all operating characteristics and line characteristics of a certain type of rail transit operation equipment, avoiding repeated training, thereby reducing the workload of the intelligent operation and maintenance system. At the same time, the same local operation and maintenance model is used to determine the model parameters through the blockchain network. During the determination process, only the interactive transmission of model parameters between the edge nodes and the blockchain network is required, and the transmission of device data is not required, which prevents the possibility of device data being intercepted and tampered with, and improves the reliability of the intelligent operation and maintenance system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of urban rail transit operation and maintenance technology, and more specifically, to a distributed intelligent operation and maintenance system for rail transit based on blockchain and an operation method thereof. Background Art

[0002] At present, the level of rail transit intelligent operation and maintenance system is still in its infancy, with low levels of intelligence and safety. In the process of using AI technology (such as machine learning, deep learning, etc.) to implement intelligent operation and maintenance for a certain type of equipment, due to restrictions such as distributed data collection and storage, privacy security, and training mechanisms, an operation and maintenance model is usually trained separately for each line, each type of equipment, and even each type of working condition. At the same time, due to the limitations of existing collection conditions and differences in project implementation, such as the inability to install wireless transmission modules in some on-site environments and the inability to add sensors to some equipment, the data feature space of the same type of equipment is very different, resulting in many different operation and maintenance models with duplicate functions running simultaneously in the current intelligent operation and maintenance system, which increases the workload of developers and also leads to a huge workload for the intelligent operation and maintenance system.

[0003] In addition, the data collected by the terminals lack effective privacy protection measures, and the data is mostly transmitted in plain text or with weak private protocols. Under public networks or large-scale local area networks, the data can be easily intercepted and tampered with. Summary of the invention

[0004] In order to overcome the above problems or at least partially solve the above problems, an embodiment of the present invention provides a distributed intelligent operation and maintenance system for rail transit based on blockchain and an operation method thereof.

[0005] In a first aspect, an embodiment of the present invention provides a distributed intelligent operation and maintenance system for rail transit based on blockchain, including: a blockchain network and a plurality of edge nodes, wherein the blockchain network and the edge nodes are communicatively connected;

[0006] Each edge node is used to collect device data and transmit model parameters of a local operation and maintenance model trained based on the device data to the blockchain network;

[0007] The blockchain network is used to receive the model parameters transmitted by each edge node, build an aggregate model based on the received model parameters, and send the model parameters of the aggregate model to each edge node, so that each edge node updates the model parameters of the local operation and maintenance model based on the received model parameters.

[0008] Preferably, the blockchain network specifically includes an aggregation node and a plurality of blockchain nodes, and the blockchain nodes and the edge nodes correspond one to one and are communicatively connected;

[0009] Each blockchain node is used to receive the model parameters transmitted by the corresponding edge node, and after the blockchain network generates a transaction block for storing the model parameters received by all blockchain nodes, all blockchain nodes determine the blockchain node with the right to generate blocks based on the operation consensus mechanism, and broadcast the generated transaction block to the blockchain network through the blockchain node with the right to generate blocks;

[0010] The aggregation node is used to build the aggregation model based on the model parameters stored in the received transaction block, and send the model parameters of the aggregation model to each edge node through the blockchain node with the block production right, so that each edge node updates the local operation and maintenance model based on the received model parameters.

[0011] Preferably, the aggregation node is specifically used for:

[0012] Creating an encrypted pair and sending the public key in the encrypted pair to each blockchain node, so that each blockchain node calculates the encrypted gradient and loss function and sends the encrypted value to the aggregation node based on the public key;

[0013] The aggregation node decrypts the encrypted value and calculates the target loss function, calculates partial derivatives of the decrypted encrypted gradient and loss function for each blockchain node, and sends the corresponding partial derivative results to the corresponding blockchain nodes, so that each blockchain node updates the local operation and maintenance model based on the received partial derivative results;

[0014] The aggregation node iteratively interacts with each blockchain node until the target loss function converges to obtain the aggregation model.

[0015] Preferably, each edge node is further used for: performing standardized alignment processing on the device data based on a data standard structure.

[0016] Preferably, each edge node is further used to: encrypt the device data after the standardization alignment process.

[0017] In a second aspect, an embodiment of the present invention provides an operation method of a distributed intelligent operation and maintenance system for rail transit based on blockchain, including:

[0018] The edge node collects current device data;

[0019] Perform equipment operation and maintenance based on the local operation and maintenance model;

[0020] Among them, the model parameters of the local operation and maintenance model are determined and issued based on the blockchain network of the rail transit distributed intelligent operation and maintenance system.

[0021] In the third aspect, the embodiment of the present invention provides an operating device of a distributed intelligent operation and maintenance system for rail transit based on blockchain, including: a data acquisition module and an equipment operation and maintenance module.

[0022] The data acquisition module is used to collect current equipment data;

[0023] The equipment operation and maintenance module is used to perform equipment operation and maintenance based on the local operation and maintenance model;

[0024] Among them, the model parameters of the local operation and maintenance model are determined and issued based on the blockchain network of the rail transit distributed intelligent operation and maintenance system.

[0025] In a fourth aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the operating method of the distributed intelligent operation and maintenance system for rail transit based on blockchain as described in the second aspect are implemented.

[0026] In the fifth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the operation method of the blockchain-based distributed intelligent operation and maintenance system for rail transit as described in the first aspect are implemented.

[0027] The embodiment of the present invention provides a distributed intelligent operation and maintenance system for rail transit based on blockchain and its operation method, in which all edge nodes in the system use the same local operation and maintenance model to realize the operation and maintenance of the carried rail transit operation equipment. Since the same local operation and maintenance model is adopted, the workload of developers is greatly reduced, and the algorithm complexity of the intelligent operation and maintenance system is reduced. The intelligent operation and maintenance system can use a single model to complete related tasks for all operating characteristics and line characteristics of a certain type of rail transit operation equipment, avoid repeated training, and thus reduce the workload of the intelligent operation and maintenance system. At the same time, the same local operation and maintenance model is used to determine the model parameters through the blockchain network. In the determination process, only the interactive transmission of model parameters between the edge nodes and the blockchain network is required, and the transmission of device data is not required, which prevents the possibility of device data being intercepted and tampered with, and improves the reliability of the intelligent operation and maintenance system. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 A schematic diagram of the structure of a distributed intelligent operation and maintenance system for rail transit based on blockchain provided by an embodiment of the present invention;

[0030] Figure 2 A schematic diagram of the structure of a blockchain system in a distributed intelligent operation and maintenance system for rail transit based on blockchain provided by an embodiment of the present invention;

[0031] Figure 3 A flowchart of an operation method of a distributed intelligent operation and maintenance system for rail transit based on blockchain provided by an embodiment of the present invention;

[0032] Figure 4 A schematic diagram of the structure of an operating device of a distributed intelligent operation and maintenance system for rail transit based on blockchain provided by an embodiment of the present invention;

[0033] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] The embodiment of the present invention provides a distributed intelligent operation and maintenance system for rail transit based on blockchain, including: a blockchain network and a plurality of edge nodes, wherein the blockchain network and the edge nodes are communicatively connected;

[0036] Each edge node is used to collect device data and transmit model parameters of a local operation and maintenance model trained based on the device data to the blockchain network;

[0037] The blockchain network is used to receive the model parameters transmitted by each edge node, build an aggregate model based on the received model parameters, and send the model parameters of the aggregate model to each edge node, so that each edge node updates the model parameters of the local operation and maintenance model based on the received model parameters.

[0038] Specifically, Figure 1As shown, the distributed intelligent operation and maintenance system for rail transit based on blockchain provided in the embodiment of the present invention includes a blockchain network 1 and an edge node 2, and the blockchain network 1 and the edge node 2 are communicatively connected. The operation mechanism of the distributed intelligent operation and maintenance system for rail transit supports simultaneous access of multiple rail transit agencies, and builds a more complete intelligent operation and maintenance system on the basis of expanding the amount of data and data dimensions. Figure 1 Only the case where two edge nodes 2 are included in the rail transit distributed intelligent operation and maintenance system is shown. Among them, each edge node 2 carries multiple rail transit operation equipment according to its own computing power, and all rail transit operation equipment carried by each edge node 2 can come from one rail transit organization or from several different rail transit organizations. Figure 1 Each edge node carries three rail transit operation equipment, which are respectively recorded as equipment A, equipment B, equipment C and equipment A', B', and equipment C'. Each edge node 2 collects the equipment data of all the rail transit operation equipment it carries in real time, and uses the loss function to train the local operation and maintenance model based on the collected equipment data, so that the trained local operation and maintenance model can operate and maintain the rail transit operation equipment carried by the edge node, that is, to determine whether the carried rail transit operation equipment has a fault and whether maintenance is required. The training process can specifically be a process of minimizing the corresponding loss function by finding the model parameters of the local operation and maintenance model through an algorithm based on gradient descent. After the local operation and maintenance model is trained, the model parameters of the local operation and maintenance model are transmitted to the blockchain network.

[0039] The blockchain network receives the model parameters transmitted by each edge node, and authenticates, encrypts, stores and broadcasts the parameters through the consensus protocol. The core is to build an aggregate model. This process is to build an aggregate model that can be applied to all edge nodes based on the model parameters of each edge node, so as to facilitate the maintenance of the model in the later stage. After the aggregate model is built, the model parameters of the aggregate model are transferred to each edge node, that is, the model parameters of the aggregate model are migrated to the local operation and maintenance model of each edge node to update the local operation and maintenance model. After that, the local operation and maintenance models of all edge nodes are the same, and the edge nodes operate and maintain the rail transit operation equipment they carry through the local operation and maintenance model. The introduction of the blockchain system can ensure the security and integrity of the model parameter transmission process. Moreover, in the blockchain system, only the model parameters are transmitted, which reduces the performance requirements of the blockchain system, reduces the risk of privacy exposure of rail transit agencies, and improves the information security protection capability of the data-driven intelligent operation and maintenance system.

[0040] In the distributed intelligent operation and maintenance system for rail transit based on blockchain provided in the embodiment of the present invention, all edge nodes in the system use the same local operation and maintenance model to realize the operation and maintenance of the rail transit operating equipment carried. Since the same local operation and maintenance model is adopted, the workload of developers is greatly reduced, and the algorithm complexity of the intelligent operation and maintenance system is reduced. The intelligent operation and maintenance system can use a single model to complete related tasks for all operating characteristics and line characteristics of a certain type of rail transit operating equipment, avoid repeated training, and thus reduce the workload of the intelligent operation and maintenance system. At the same time, the same local operation and maintenance model is used to determine the model parameters through the blockchain network. During the determination process, only the interactive transmission of model parameters between the edge nodes and the blockchain network is required, and the transmission of device data is not required, which prevents the possibility of device data being intercepted and tampered with, and improves the reliability of the intelligent operation and maintenance system.

[0041] On the basis of the above-mentioned embodiment, in the distributed intelligent operation and maintenance system for rail transit based on blockchain provided in the embodiment of the present invention, the blockchain network specifically includes an aggregation node and a plurality of blockchain nodes, and the blockchain nodes and the edge nodes correspond one to one and are communicatively connected;

[0042] Each blockchain node is used to receive the model parameters transmitted by the corresponding edge node, and after the blockchain network generates a transaction block for storing the model parameters received by all blockchain nodes, all blockchain nodes determine the blockchain node with the right to generate blocks based on the operation consensus mechanism, and broadcast the generated transaction block to the blockchain network through the blockchain node with the right to generate blocks;

[0043] The aggregation node is used to build the aggregation model based on the model parameters stored in the received transaction block, and send the model parameters of the aggregation model to each edge node through the blockchain node with the block production right, so that each edge node updates the local operation and maintenance model based on the received model parameters.

[0044] Specifically, in the embodiment of the present invention, Figure 2 As shown, the blockchain network specifically includes an aggregation node and multiple blockchain nodes. The blockchain nodes and edge nodes correspond one to one and are communicatively connected, that is, the number of blockchain nodes is equal to the number of edge nodes and they are communicatively connected. Figure 2 Only the situation that the blockchain network includes 4 edge nodes and 1 aggregation node is shown in the figure. The 4 blockchain nodes are blockchain node-A, blockchain node-B, blockchain node-C, and blockchain node-D. The 4 edge nodes corresponding to the communication connection are edge node A, edge node B, edge node C, and edge node D.

[0045] The model parameters of the local operation and maintenance model obtained by edge node training are transmitted to the blockchain network through the wireless network and stored in each blockchain node in the form of transactions.

[0046] Each blockchain node is used to receive the model parameters transmitted by the corresponding edge node, and after the blockchain network generates a transaction block for storing the model parameters received by all blockchain nodes, the received model parameters are packaged into the transaction block through encryption and signature. All blockchain nodes run the consensus mechanism to determine the blockchain node with the right to generate blocks, that is, to determine who has the right to generate blocks. The generated transaction block is broadcast to the blockchain network by the blockchain node with the right to generate blocks, that is, the blockchain node that obtains the right to generate blocks broadcasts the transaction block containing the model parameters received by each blockchain node to the entire blockchain network, and joins the blockchain after authentication.

[0047] The aggregation node collects the model parameters received by each blockchain node based on the records on the blockchain, and builds an aggregation model applicable to all edge nodes based on the target loss function and / or model accuracy. The basis for the successful construction of the aggregation model can be the convergence of the loss function, the model accuracy reaching the preset threshold, or the convergence of the loss function and the model accuracy reaching the preset threshold and meeting the requirements at the same time. The model parameters of the aggregation model are then sent to each edge node through the blockchain node with the right to generate blocks, so that each edge node updates the local operation and maintenance model based on the received model parameters.

[0048] It should be noted that the process of building an aggregation model by an aggregation node is an iterative process combined with the training process of the local operation and maintenance model of the edge node.

[0049] Based on the above embodiment, the aggregation node in the embodiment of the present invention is specifically used for:

[0050] Creating an encrypted pair and sending the public key in the encrypted pair to each blockchain node, so that each blockchain node calculates the encrypted gradient and loss function and sends the encrypted value to the aggregation node based on the public key;

[0051] The aggregation node decrypts the encrypted value and calculates the target loss function, calculates partial derivatives of the decrypted encrypted gradient and loss function for each blockchain node, and sends the corresponding partial derivative results to the corresponding blockchain nodes, so that each blockchain node updates the local operation and maintenance model based on the received partial derivative results;

[0052] The aggregation node iteratively interacts with each blockchain node until the target loss function converges to obtain the aggregation model.

[0053] Specifically, when the aggregation node constructs the aggregation model, the gradient descent method can be used. The specific process is as follows:

[0054] 1) The aggregation node creates an encrypted pair, which includes a public key and a private key. Then, the public key is sent to each blockchain node.

[0055] 2) Each blockchain node encrypts and exchanges the intermediate results required for gradient and loss function calculations, calculates the encrypted gradient and loss function respectively, and sends the encrypted values ​​to the aggregation node based on the received public key;

[0056] 3) The aggregation node decrypts and calculates the total target loss function, and takes partial derivatives of the decrypted gradients and loss functions for each blockchain node respectively, and sends the corresponding partial derivative results back to each node. Each node updates the model parameters of the local operation and maintenance model accordingly.

[0057] On this basis, the training steps of the local operation and maintenance model and the construction steps of the aggregate model are iterated until the target loss function converges and / or the accuracy of the aggregate model reaches the preset threshold, thus completing the entire training process. During the entire training process, the device data of each edge node is retained locally, and the interaction of model parameters during the training process will not lead to the leakage of device data.

[0058] The above architecture based on blockchain and distributed AI training complements the security and trustworthiness of blockchain and the intelligence and data privacy protection of distributed architecture, improving the overall security of the system and building a more intelligent blockchain mechanism. At the same time, because the data interacted with the blockchain system is limited to model parameters, the performance of the blockchain system is no longer a bottleneck for engineering applications.

[0059] In the embodiment of the present invention, based on the distributed algorithm architecture, the intelligent operation and maintenance system is guaranteed to complete the algorithm training process without exposing the privacy of user data.

[0060] On the basis of the above-mentioned embodiments, in the distributed intelligent operation and maintenance system for rail transit based on blockchain provided in the embodiments of the present invention, each edge node is also used to: perform standardized alignment processing on the device data based on the data standard structure.

[0061] Specifically, since the equipment data structures of different rail transit agencies are not necessarily completely consistent, the data features are not completely overlapping. Therefore, in an embodiment of the present invention, after collecting the equipment data, the edge node performs standardized alignment processing on the collected equipment data according to the data standard structure. It should be noted that each edge node uses the same data standard structure. The data standard structure has a uniform data volume and a uniform device data type. Device data types may include data and pictures, etc. Under the premise that each rail transit agency does not disclose its own equipment data, the same equipment type is confirmed to each other so that all the equipment data features obtained can be jointly modeled.

[0062] Based on the above embodiment, each edge node is further used to: encrypt the device data after the standardization alignment processing.

[0063] Specifically, in the embodiment of the present invention, after the edge node performs the standardization and alignment processing on the device data, it may also perform encryption processing on the device data after the standardization and alignment processing to prevent leakage of the device data.

[0064] The blockchain-based distributed intelligent operation and maintenance system for rail transit provided in the embodiment of the present invention introduces an incentive mechanism to promote various rail transit agencies to fully participate in the operation of the distributed intelligent operation and maintenance system, expand the data volume of the intelligent operation and maintenance system, and improve system performance.

[0065] Based on the above embodiments, Figure 3 As shown, an embodiment of the present invention provides an operation method of a distributed intelligent operation and maintenance system for rail transit based on blockchain, including:

[0066] S31, the edge node collects current device data;

[0067] S32, equipment operation and maintenance based on the local operation and maintenance model;

[0068] Among them, the model parameters of the local operation and maintenance model are determined and issued based on the blockchain network of the rail transit distributed intelligent operation and maintenance system.

[0069] Specifically, the operation method of the rail transit distributed intelligent operation system provided in the embodiment of the present invention is executed by an edge node, and the operation process of the rail transit distributed intelligent operation system is explained from the perspective of the edge node.

[0070] First, step S31 is executed. The collection action can be performed in real time, and the edge node can be any edge node in the distributed intelligent operation and maintenance system of rail transit based on blockchain.

[0071] Then execute step S32. Among them, the local operation and maintenance model refers to the local operation and maintenance model obtained after the model parameters of the fusion model under the blockchain network are updated, and the equipment operation and maintenance is realized through the model and the current equipment data collected. The construction process of the fusion model and the transmission of the model parameters are specifically referred to the role of the edge node in the embodiment of the distributed intelligent operation and maintenance system for rail transit based on blockchain.

[0072] In the operation method provided in the embodiment of the present invention, all edge nodes use the same local operation and maintenance model for equipment operation and maintenance, which can greatly reduce the workload of developers when developing a distributed intelligent operation and maintenance system for rail transit based on blockchain, thereby reducing the workload of the intelligent operation and maintenance system. At the same time, the same local operation and maintenance model is used to determine the model parameters through the blockchain network. During the determination process, only the interactive transmission of model parameters between the edge nodes and the blockchain network is required, and the transmission of device data is not required, which prevents the possibility of device data being intercepted and tampered with, and improves the reliability of the intelligent operation and maintenance system.

[0073] Based on the above embodiments, Figure 4 As shown, an embodiment of the present invention provides an operating device of a distributed intelligent operation and maintenance system for rail transit based on blockchain, including: a data acquisition module 41 and an equipment operation and maintenance module 42. Among them,

[0074] The data acquisition module 41 is used to collect current device data;

[0075] The equipment operation and maintenance module 42 is used to perform equipment operation and maintenance based on the local operation and maintenance model;

[0076] Among them, the model parameters of the local operation and maintenance model are determined and issued based on the blockchain network of the rail transit distributed intelligent operation and maintenance system.

[0077] Specifically, the operating device of the rail transit distributed intelligent operation system provided in the embodiment of the present invention is equivalent to an edge node, that is, it can be understood that the edge node includes a data acquisition module 41 and an equipment operation and maintenance module 42.

[0078] The functions of each module in the operating device correspond one-to-one to the operations of each step in the above-mentioned operating method embodiment, and the effects achieved are also consistent, which will not be repeated here in the embodiment of the present invention.

[0079] In summary, in the embodiments of the present invention, in view of the fact that the intelligent operation and maintenance system of the cross-device data feature space based on AI technology cannot be realized in the prior art, the acquisition terminal cannot be identified whether it has been attacked or tampered with, the data transmission process lacks security protection, and the privacy and integrity cannot be guaranteed, and the workload of the central system is large, the computing power of the edge nodes is not fully utilized, the data transmission volume between the central system and the underlying equipment is too large, and data loss and communication blockage often occur, a set of distributed intelligent operation and maintenance system for rail transit based on blockchain is formulated, and the distributed intelligent operation and maintenance system is enabled by blockchain. Through the authorization mechanism and identity management of blockchain, mutually untrustworthy operation and maintenance terminals are integrated as participants to establish a safe and reliable cooperation mechanism. In addition, the algorithm parameters of the distributed operation and maintenance system of rail transit can be stored in the blockchain network, which ensures the security and reliability of the model parameters. Moreover, in the embodiments of the present invention, a low-energy application-based blockchain system is created to solve the contradiction between the limited storage capacity of nodes and the large storage requirements of the blockchain network in the traditional blockchain system. Through the processing of raw data by edge nodes, the blockchain system only transmits model parameters and stores calculation results, which can reduce resource overhead.

[0080] Figure 5 As shown, based on the above embodiment, an electronic device is provided in an embodiment of the present invention, including: a processor (processor) 501, a memory (memory) 502, a communication interface (Communications Interface) 503 and a communication bus 504; wherein,

[0081] The processor 501, the memory 502, and the communication interface 503 communicate with each other through the communication bus 504. The memory 502 stores program instructions that can be executed by the processor 501, and the processor 501 is used to call the program instructions in the memory 502 to execute the operation method of the distributed intelligent operation and maintenance system of rail transit based on blockchain provided by the above-mentioned method embodiments.

[0082] It should be noted that the electronic device in this embodiment can be a server, a PC, or other devices in specific implementation, as long as its structure includes the following: Figure 5 The processor 501, communication interface 503, memory 502 and communication bus 504 are shown, wherein the processor 501, communication interface 503 and memory 502 communicate with each other through the communication bus 504, and the processor 501 can call the logic instructions in the memory 502 to execute the above method. This embodiment does not limit the specific implementation form of the electronic device.

[0083] The logic instructions in the memory 502 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0084] Furthermore, an embodiment of the present invention discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the operation method of the blockchain-based distributed intelligent operation and maintenance system for rail transit provided by the above-mentioned method embodiments.

[0085] On the basis of the above embodiments, an embodiment of the present invention further provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the operation method of the blockchain-based distributed intelligent operation and maintenance system for rail transit provided in the above embodiments.

[0086] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0087] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A distributed intelligent operation and maintenance system for rail transit based on blockchain, characterized in that: include: A blockchain network and a plurality of edge nodes, wherein the blockchain network and the edge nodes are communicatively connected; Each edge node is used to collect device data and transmit model parameters of a local operation and maintenance model trained based on the device data to the blockchain network; The blockchain network is used to receive the model parameters transmitted by each edge node, build an aggregate model based on the received model parameters, and send the model parameters of the aggregate model to each edge node, so that each edge node updates the model parameters of the local operation and maintenance model based on the received model parameters; The blockchain network specifically includes an aggregation node and a plurality of blockchain nodes, and the blockchain nodes and the edge nodes correspond to each other one by one and are communicatively connected; Each blockchain node is used to receive the model parameters transmitted by the corresponding edge node, and after the blockchain network generates a transaction block for storing the model parameters received by all blockchain nodes, all blockchain nodes determine the blockchain node with the right to generate blocks based on the operation consensus mechanism, and broadcast the generated transaction block to the blockchain network through the blockchain node with the right to generate blocks; The aggregation node is used to construct the aggregation model based on the model parameters stored in the received transaction block, and send the model parameters of the aggregation model to each edge node through the blockchain node with the block generation right, so that each edge node updates the local operation and maintenance model based on the received model parameters; The aggregation node is specifically used for: Creating an encrypted pair and sending the public key in the encrypted pair to each blockchain node, so that each blockchain node calculates the encrypted gradient and loss function and sends the encrypted value to the aggregation node based on the public key; The aggregation node decrypts the encrypted value and calculates the target loss function, calculates partial derivatives of the decrypted encrypted gradient and loss function for each blockchain node, and sends the corresponding partial derivative results to the corresponding blockchain nodes, so that each blockchain node updates the local operation and maintenance model based on the received partial derivative results; The aggregation node iteratively interacts with each blockchain node until the target loss function converges to obtain the aggregation model.

2. According to claim 1, the distributed intelligent operation and maintenance system for rail transit based on blockchain is characterized in that: Each edge node is further used to: perform standardized alignment processing on the device data based on a data standard structure.

3. According to claim 2, the distributed intelligent operation and maintenance system for rail transit based on blockchain is characterized in that: Each edge node is further used to encrypt the device data after the standardization and alignment processing.

4. An operation method of a distributed intelligent operation and maintenance system for rail transit based on blockchain as described in any one of claims 1 to 3, characterized in that: include: The edge node collects current device data; Perform equipment operation and maintenance based on the local operation and maintenance model; Among them, the model parameters of the local operation and maintenance model are determined and issued based on the blockchain network of the rail transit distributed intelligent operation and maintenance system.

5. An operating device of a distributed intelligent operation and maintenance system for rail transit based on blockchain as described in any one of claims 1 to 3, characterized in that: include: Data acquisition module, used to collect current equipment data; Equipment operation and maintenance module, used to perform equipment operation and maintenance based on the local operation and maintenance model; Among them, the model parameters of the local operation and maintenance model are determined and issued based on the blockchain network of the rail transit distributed intelligent operation and maintenance system.

6. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the operation method of the distributed intelligent operation and maintenance system for rail transit based on blockchain as described in claim 4 are implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the operation method of the blockchain-based distributed intelligent operation and maintenance system for rail transit are implemented as described in claim 4.