Mobile operation and maintenance job monitoring system and method based on blockchain technology

Abstract

The application discloses a mobile operation and maintenance job monitoring system and method based on a blockchain technology, and relates to the technical field of big data analysis.The hardware unique identifier of a mobile maintenance operation and maintenance job site is associated with a blockchain node public key verified by a chain authorized node for validity, and an associated binding mapping table is generated, thereby laying a foundation for the authenticity of maintenance data.The block height and hash value of broadcast data are compared in advance by a consensus layer pre-verification logic to detect conflicts, effective data is screened from the conflict data and is de-duplicated, invalid consumption of node resources is reduced, and consensus delay caused by conflict data in the existing blockchain technology is avoided;by optimizing a transaction pool queue, a prediction model is trained by combining an LSTM model to control the data broadcast submission time, off-peak submission is realized, the real-time performance of monitoring data is greatly improved, and the overall effectiveness and reliability of mobile operation and maintenance job monitoring are ensured.

Description

Technical Field

[0001] This invention relates to the field of big data analytics, specifically to a mobile operation and maintenance monitoring system and method based on blockchain technology. Background Technology

[0002] In mobile maintenance scenarios for infrastructure such as power poles, communication base stations, and traffic signal equipment, the work sites are widely distributed and the processes are highly dynamic. The quality of maintenance directly determines the stability and safety of infrastructure operation. Traditional monitoring relies heavily on manual recording or centralized systems, which are prone to problems such as data lag, information tampering, and difficulty in tracing responsibility. Inadequate monitoring can lead to incomplete maintenance, unresolved hidden dangers, and infrastructure shutdowns, affecting public services and social production order. Therefore, mobile maintenance monitoring is a key link in ensuring that the maintenance process is traceable, the quality of the work is verifiable, and the infrastructure continues to operate reliably, avoiding economic losses and safety risks caused by maintenance oversights. It is of great significance for ensuring the stable operation of critical infrastructure and supporting the normal operation of society.

[0003] In mobile operation and maintenance monitoring scenarios based on blockchain technology, operation sites are widely distributed and numerous, and operation and maintenance often require multiple detection and maintenance teams to carry out operations and maintenance in parallel. When two or more operation sites submit operation and maintenance data at the same time, broadcast conflicts can easily occur when blockchain nodes update data via broadcast. These conflicts can lead to the deletion of multiple invalid broadcast data, resulting in the ineffective consumption of node storage and computing resources, reducing node data synchronization efficiency, increasing consensus mechanism processing latency, and extending the block confirmation cycle. This can further lead to insufficient timeliness of real-time data in mobile operation and maintenance monitoring, decreased accuracy of operation site maintenance status tracing, and ultimately affect the overall effectiveness and reliability of mobile operation and maintenance monitoring. Summary of the Invention

[0004] The purpose of this invention is to provide a mobile operation and maintenance monitoring system and method based on blockchain technology to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a mobile operation and maintenance operation monitoring method based on blockchain technology, the mobile operation and maintenance operation monitoring method comprising the following steps: Step S1: Associate and bind the unique identifier of the mobile maintenance work station with the corresponding blockchain node identity to obtain the association and binding mapping table between each work station and the blockchain node. Step S1-1: Obtain the unique hardware identifier of the mobile maintenance and repair work station. The mobile maintenance and repair work station refers to the object carrier that needs to be inspected, troubleshooted, and maintained in the infrastructure operation scenario. The unique hardware identifier is an immutable code pre-stored in the built-in chip of the work station equipment. Obtain the digital certificate of the blockchain node. The digital certificate contains the node's public key and the node's maintenance and repair permission identifier. The validity of the digital certificate is verified by the chain authorization node. Step S1-2: The verified work site hardware unique identifier and the blockchain node public key are associated and mapped through a smart contract. The association mapping includes the hardware unique identifier, the node public key and the binding timestamp. The smart contract writes the association mapping into the blockchain distributed ledger to generate an association binding mapping table. The association binding mapping table supports bidirectional querying using the hardware unique identifier or the node public key. By mapping the immutable hardware unique identifier of the work site to the blockchain node digital certificate verified by the chain-authorized node through a smart contract, a binding mapping table that supports two-way query is generated. This establishes a unique and trustworthy association between the work site and the blockchain node from the source, solving the problem of the ambiguous correspondence between the work site identity and the data source in traditional monitoring. It provides an identity binding basis for the subsequent traceability and tamper-proof verification of maintenance data.

[0006] Step S2: Monitor each work site. After the work site completes maintenance, broadcast data to the maintenance work site according to the association binding mapping table, and perform broadcast conflict detection on each node in the blockchain. Step S2-1: Based on the blockchain API interface, monitor the maintenance completion status of each work site in real time. When any work site is found to have completed maintenance, determine the corresponding blockchain node based on the unique identifier of the work site and the association binding mapping table, and broadcast the maintenance data to the entire blockchain network through the P2P network. The maintenance data includes the unique hardware identifier of the work site, the maintenance data hash and the block height at the time of broadcast initiation. Step S2-2: When receiving maintenance data, the underlying blockchain node extracts multiple maintenance data corresponding to the same unique hardware identifier through the consensus layer pre-verification logic, and compares the block height and data hash value at the time of broadcast initiation of each maintenance data. If there are two or more broadcast data with a block height difference of less than 1 and inconsistent data hash values, it is determined to be a broadcast conflict. If the block height difference of all data is greater than or equal to 1, or the block height difference is less than 1 but the data hash values ​​are consistent, it is determined to be no broadcast conflict. Based on the blockchain API interface, the system enables real-time monitoring and targeted broadcasting of the maintenance completion status of work sites. By comparing the block height and data hash value of the broadcast data corresponding to the same hardware unique identifier, conflict detection is completed. This allows for accurate identification of broadcast conflicts caused by concurrent submissions before the data enters the consensus layer, avoiding the invalid propagation of conflicting data throughout the blockchain network and reducing the consumption of node storage and computing resources caused by the deletion of invalid data.

[0007] Step S3: Based on the broadcast conflict detection results, obtain the information data of the accounting node by calling the blockchain node API interface; and analyze the obtained information data to obtain the real-time data of the transaction pool in the blockchain, which is recorded as the blockchain real-time transaction pool data. Step S3-1: The blockchain network determines the current accounting node through a consensus mechanism. The accounting node refers to the node in the blockchain network that has obtained the right to record transactions through the consensus mechanism and is responsible for verifying, packaging, and writing transactions in the network into new blocks. If the broadcast conflict detection result is no conflict, the blockchain node API interface is directly called, and an information data acquisition request is sent to the accounting node. If the broadcast conflict detection result is a conflict, the broadcast data with the highest block height and unique data hash is first filtered out through the consensus layer pre-verification logic. At the same time, duplicate broadcast data is removed by deduplication using the transaction ID. Based on the filtered broadcast data, the blockchain node API interface is called to send an information data acquisition request to the accounting node. Step S3-2: Receive the information data returned by the accounting node, extract the hash value of the unconfirmed maintenance transaction, maintenance data and transaction submission time in the transaction pool of the accounting node, as well as the current block height and network communication address of the accounting node, to form a structured dataset containing transaction identifier, data content, time parameters and node information. The structured dataset represents the blockchain real-time transaction pool data. A differentiated strategy for obtaining accounting node information is adopted in response to broadcast conflict detection results. For conflict data, the highest block height and unique hash are selected as valid data and deduplicated. Then, the structured data in the transaction pool is extracted to form the real-time blockchain transaction pool data. This ensures that the maintenance data entering the transaction pool is all valid and complete core data, avoids the redundant processing of invalid and duplicate data by the consensus mechanism, reduces the processing burden of the consensus layer, and improves the accuracy of transaction data and the efficiency of subsequent processing.

[0008] Step S4: Analyze the real-time transaction pool data of the blockchain and set the transaction pool queue sorting threshold; obtain the submission time of data broadcasting of each work site, and sort the transaction pool queue based on the submission time of data broadcasting and the transaction pool queue sorting threshold to obtain the first transaction pool queue sorting; process the first transaction pool queue sorting by calling the consensus mechanism of the blockchain to obtain the second transaction pool queue sorting. Step S4-1: parse the blockchain real-time transaction pool data, extract the submission timestamps of the data broadcasts of each work site, and control the number of queues in the transaction pool based on the transaction pool queue sorting threshold, where the transaction pool queue sorting threshold is the maximum number of transactions allowed to enter the first sort. Step S4-2: Sort the unconfirmed maintenance transactions in the transaction pool according to the submission timestamps of the data broadcasts of each work site from earliest to latest, and select the number of transactions in the sorting results that are equal to the sorting threshold of the transaction pool queue to form the first transaction pool queue sorting. Step S4-3: Call the priority queue data structure built into the blockchain consensus mechanism, and perform a second sorting on the transactions in the first transaction pool queue to obtain the second transaction pool queue sorting. By setting a transaction pool queue sorting threshold to control the initial sorting scale, and after completing the initial sorting by submission timestamp, the consensus mechanism priority queue is invoked for secondary sorting. This constructs a two-layer sorting logic that prioritizes time and adapts to consensus, optimizes the processing order of unconfirmed maintenance transactions in the transaction pool, ensures the priority processing of early valid transactions, and adapts to the inherent scheduling rules of the consensus mechanism, significantly improving the efficiency of the consensus layer in packaging transactions and shortening the block confirmation cycle.

[0009] Step S5: Obtain the number of online nodes through the blockchain API interface, analyze the data broadcast logs of the accounting nodes to obtain the relationship between data broadcast speed and the number of online nodes, train the data using a neural network model to obtain a processing time prediction model, sort the second transaction pool queue according to the processing time prediction model, predict the time required to complete a transaction, and record it as the transaction pool completion prediction time; control the submission time of data broadcasting for each work site in the blockchain according to the transaction pool completion prediction time. Step S5-1: Obtain the broadcast logs of the nodes with accounting rights through the blockchain node API interface. Extract the time from the start of broadcasting each transaction to the consensus confirmation of all nodes in the blockchain and the time written into the block, and record it as the single broadcast completion time. At the same time, obtain the number of online nodes in the blockchain during the broadcast period of each transaction to form a related dataset containing the single broadcast completion time and the corresponding number of online nodes. Step S5-2: Input the associated dataset into the neural network model for training. The neural network model selects the number of online nodes as the input parameter and the completion time of a single broadcast as the output parameter. After training, a processing time prediction model is obtained. Step S5-3: Obtain time series data of the number of online nodes within a preset time period through the blockchain node API interface, analyze the time series data through the LSTM time series model, and predict the predicted value of the number of online nodes within the future preset time period; input the predicted value into the processing time prediction model to obtain the predicted time for processing a single transaction in the second transaction pool queue sorting, which is recorded as the transaction pool completion prediction time. The calculation formula for the LSTM time series model is as follows: ; In the formula, Y new (t+T) represents the predicted number of online nodes at time T obtained through the LSTM time series model; LSTM() represents the mapping function of the LSTM time series model, which is used to process the input historical time series data and output the prediction result; Y(t) represents the number of online nodes at time t, which is the value of the latest time in the historical time series data input to the LSTM time series model; Y(t-1), ..., Y(tn-1) represent the number of online nodes corresponding to times t-1 to tn-1 respectively; n represents the window length of the historical time series data input to the LSTM time series model, which is the time step of the historical data involved in the prediction; T represents the future time step of the prediction.

[0010] Step S5-4: Sort the newly submitted data to be broadcast by each work site in the blockchain from earliest to latest according to the broadcast submission time, and mark the data to be broadcast at the first position as the data to be entered into the transaction pool; set the transaction pool entry time for the data to be entered into the transaction pool, which is set as the current time plus the transaction pool completion prediction time; when the accounting node completes the packaging of the current block and generates a new block, when the new accounting node is determined through the consensus mechanism, add the data to be entered into the transaction pool to the transaction pool, and at the same time, re-execute steps S5-1 to S5-3 based on the broadcast log of the new accounting node to obtain a new transaction pool completion prediction time, set the transaction pool entry time for the next ranked data to be broadcast, and synchronously process the broadcasts submitted by subsequent nodes to complete the mobile maintenance and operation monitoring.

[0011] A processing time prediction model is trained based on the broadcast logs of the accounting right node and the associated dataset. The model is combined with an LSTM model to predict the number of online nodes to obtain the transaction pool completion prediction time. This allows for dynamic control of the broadcast submission time of new data, enabling staggered submission of data broadcasts from work sites. This reduces broadcast conflicts caused by concurrent submissions at the source and ensures that newly submitted data can enter the transaction pool and be processed in a timely manner, significantly improving the real-time performance and reliability of mobile operation and maintenance monitoring data.

[0012] Furthermore, a mobile operation and maintenance monitoring system based on blockchain technology includes a node association module, a broadcast monitoring module, a transaction pool data module, a transaction sorting module, and a time prediction control module. The node association module is used to associate and bind the unique identifier of the mobile maintenance and repair work site with the blockchain node identity to obtain an association binding mapping table; the broadcast monitoring module is used to monitor the work site, broadcast data according to the association binding mapping table after maintenance is completed, and detect broadcast conflicts; the transaction pool data module is used to obtain the accounting right node information based on the broadcast conflict results and analyze it to obtain the real-time blockchain transaction pool data; the transaction sorting module is used to analyze the real-time transaction pool data, set a sorting threshold, and sort the data based on the submission time and consensus mechanism to obtain two types of transaction pool queues; the time prediction control module is used to obtain the number of online nodes and broadcast logs, train a prediction model, and control the data broadcast submission time. The node association module includes an identifier verification unit and a mapping generation unit; the identifier verification unit is used to obtain the unique identifier of the work site hardware and the blockchain node digital certificate, and verify the validity of the digital certificate through the chain authorized node; the mapping generation unit is used to associate and map the verified unique identifier of the work site hardware with the blockchain node public key through a smart contract, and write it into the ledger to generate an association binding mapping table. The broadcast monitoring module includes a broadcast initiation unit and a conflict detection unit; the broadcast initiation unit is used to monitor the maintenance completion status of the work site and broadcast maintenance data to the entire blockchain network through the P2P network; the conflict detection unit is used to extract broadcast data with the same unique hardware identifier and compare the block height and hash value to determine broadcast conflicts. The transaction pool data module includes a node information acquisition unit and a data extraction unit; the node information acquisition unit is used to send an information acquisition request to the accounting node by calling the interface according to the broadcast conflict result; the data extraction unit is used to receive the accounting node information and extract the data to form a structured dataset of blockchain real-time transaction pool data. The transaction sorting module includes an initial sorting unit and a consensus sorting unit; the initial sorting unit is used to extract the broadcast submission timestamp, sort by time, and select a threshold number of transactions to form a first transaction pool queue; the consensus sorting unit is used to call the consensus mechanism priority queue to sort the first transaction pool queue a second time to obtain a second transaction pool queue. The time prediction control module includes a prediction model training unit and a submission time control unit. The prediction model training unit is used to extract data to train a processing time prediction model, and uses LSTM to predict the number of online nodes to obtain the transaction pool completion prediction time. The submission time control unit is used to sort the data to be broadcast, set the entry time, update the prediction time, and process subsequent broadcasts. The output of the node association module is electrically connected to the input of the broadcast monitoring module; the output of the broadcast monitoring module is electrically connected to the input of the transaction pool data module; the output of the transaction pool data module is electrically connected to the input of the transaction sorting module; and the output of the transaction sorting module is electrically connected to the input of the time prediction control module.

[0013] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention establishes a unique and trusted association between a mobile maintenance and repair work site and a blockchain node's public key, verified by authorized blockchain nodes, through a smart contract. This association is mapped to generate a bidirectional query-enabled mapping table. Compared to traditional manual records or centralized systems, this invention effectively solves the problems of ambiguous data sources, susceptibility to tampering, and difficulty in tracing responsibility, providing an underlying guarantee for the authenticity and traceability of maintenance data.

[0014] 2. This invention utilizes consensus layer pre-verification logic to compare the block height and data hash value of broadcast data corresponding to the same hardware unique identifier, thereby enabling early detection of broadcast conflicts. For conflicting data, it filters out valid data with the highest block height and unique hash, removes duplicates, and then requests information from the accounting node. Compared to existing blockchain technologies where conflicting data directly enters the consensus layer, this reduces the ineffective consumption of node storage and computing resources, improves data synchronization efficiency, and lowers consensus processing latency.

[0015] 3. This invention optimizes the transaction pool queue and combines the logs of the accounting node with an LSTM model to train a processing time prediction model, dynamically controlling the data broadcast submission time of the work site. Compared with the existing technology where disordered data submissions cause repeated conflicts, this invention achieves staggered data submission, improves the real-time performance of monitoring data, and ensures the overall effectiveness and reliability of mobile operation and maintenance monitoring. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a mobile operation and maintenance monitoring method based on blockchain technology according to the present invention. Figure 2 This is a schematic diagram of the structure of a mobile operation and maintenance monitoring system based on blockchain technology according to the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1: As Figure 1 As shown, this invention provides a technical solution: a mobile operation and maintenance monitoring method based on blockchain technology. The mobile operation and maintenance monitoring method includes the following steps: Step S1: Associate and bind the unique identifier of the mobile maintenance work station with the corresponding blockchain node identity to obtain the association and binding mapping table between each work station and the blockchain node. Step S1-1: Obtain the unique hardware identifier of the mobile maintenance and repair work station. The mobile maintenance and repair work station refers to the object carrier that needs to be inspected, troubleshooted, and maintained in the infrastructure operation scenario. The unique hardware identifier is an immutable code pre-stored in the built-in chip of the work station equipment. Obtain the digital certificate of the blockchain node. The digital certificate contains the node's public key and the node's maintenance and repair permission identifier. The validity of the digital certificate is verified by the chain authorization node. Step S1-2: The verified work site hardware unique identifier and the blockchain node public key are associated and mapped through a smart contract. The association mapping includes the hardware unique identifier, the node public key and the binding timestamp. The smart contract writes the association mapping into the blockchain distributed ledger to generate an association binding mapping table. The association binding mapping table supports bidirectional querying using the hardware unique identifier or the node public key. In practical implementation, core work sites such as main transformers and high-voltage switchgear within the power plant are targeted. Their unique hardware identifiers are based on unrewritable codes embedded in the main control chip at the time of equipment manufacturing. The unique correspondence between work sites and physical equipment is established based on the physical immutability of the codes. When obtaining blockchain node digital certificates, the certificates must be issued by the chain-authorized nodes of the power plant's operation and maintenance management department. The node operation and maintenance permission identifiers in the certificates must accurately match the scope of power plant equipment operation and maintenance that the node is responsible for, preventing operation and maintenance chaos caused by overstepping of permissions. Before the smart contract association mapping, logical vulnerability detection must be completed through the power plant's dedicated security audit tools to avoid abnormal binding relationships caused by contract defects. The two-way query function of the association binding mapping table must be adapted to the distributed storage architecture of the power plant's blockchain to ensure that operation and maintenance personnel can quickly locate the corresponding node or perform reverse queries through the equipment identifier, thereby improving operation and maintenance efficiency.

[0019] Step S2: Monitor each work site. After the work site completes maintenance, broadcast data to the maintenance work site according to the association binding mapping table, and perform broadcast conflict detection on each node in the blockchain. Step S2-1: Based on the blockchain API interface, monitor the maintenance completion status of each work site in real time. When any work site is found to have completed maintenance, determine the corresponding blockchain node based on the unique identifier of the work site and the association binding mapping table, and broadcast the maintenance data to the entire blockchain network through the P2P network. The maintenance data includes the unique hardware identifier of the work site, the maintenance data hash and the block height at the time of broadcast initiation. Step S2-2: When receiving maintenance data, the underlying blockchain node extracts multiple maintenance data corresponding to the same unique hardware identifier through the consensus layer pre-verification logic, and compares the block height and data hash value at the time of broadcast initiation of each maintenance data. If there are two or more broadcast data with a block height difference of less than 1 and inconsistent data hash values, it is determined to be a broadcast conflict. If the block height difference of all data is greater than or equal to 1, or the block height difference is less than 1 but the data hash values ​​are consistent, it is determined to be no broadcast conflict. In practical implementation, when broadcasting maintenance data via P2P network, it is necessary to adapt to the industrial Ethernet environment within the power plant area and adopt a transmission protocol with anti-electromagnetic interference capabilities to avoid interference from electromagnetic signals generated during the operation of high-voltage equipment in the power plant on data transmission. Before the consensus layer pre-verification logic determines a broadcast conflict, it synchronizes the latest block height confirmed by the entire power plant blockchain network to avoid block height lag caused by network delays of maintenance nodes at the edge of the plant area, which could lead to misjudgments of conflicts. At the same time, the hash value of maintenance data must be calculated using a unified encryption algorithm to ensure that the hash results of maintenance data for the same equipment submitted by different maintenance teams are consistent, thus ensuring the accuracy of conflict detection.

[0020] Step S3: Based on the broadcast conflict detection results, obtain the information data of the accounting node by calling the blockchain node API interface; and analyze the obtained information data to obtain the real-time data of the transaction pool in the blockchain, which is recorded as the blockchain real-time transaction pool data. Step S3-1: The blockchain network determines the current accounting node through a consensus mechanism. The accounting node refers to the node in the blockchain network that has obtained the right to record transactions through the consensus mechanism and is responsible for verifying, packaging, and writing transactions in the network into new blocks. If the broadcast conflict detection result is no conflict, the blockchain node API interface is directly called, and an information data acquisition request is sent to the accounting node. If the broadcast conflict detection result is a conflict, the broadcast data with the highest block height and unique data hash is first filtered out through the consensus layer pre-verification logic. At the same time, duplicate broadcast data is removed by deduplication using the transaction ID. Based on the filtered broadcast data, the blockchain node API interface is called to send an information data acquisition request to the accounting node. Step S3-2: Receive the information data returned by the accounting node, extract the hash value of the unconfirmed maintenance transaction, maintenance data and transaction submission time in the transaction pool of the accounting node, as well as the current block height and network communication address of the accounting node, to form a structured dataset containing transaction identifier, data content, time parameters and node information. The structured dataset represents the blockchain real-time transaction pool data. In practice, the nodes with the right to record transactions must be selected from the core server nodes of the power plant operation and maintenance center, and must pass the equipment operation and maintenance qualification review and node security protection assessment to ensure the credibility of the nodes. When the broadcast conflict detection result is negative, the broadcast data with the highest block height should be selected based on the block height confirmed by more than a majority of authorized nodes in the power plant blockchain to avoid the block height abnormality of a single operation and maintenance team node affecting the accuracy of the selection results. When deduplicating transactions by transaction ID, the transaction ID should be generated by combining the equipment asset number of the power plant operation site and the maintenance initiation timestamp to ensure the uniqueness of each transaction ID.

[0021] Step S4: Analyze the real-time transaction pool data of the blockchain and set the transaction pool queue sorting threshold; obtain the submission time of data broadcasting of each work site, and sort the transaction pool queue based on the submission time of data broadcasting and the transaction pool queue sorting threshold to obtain the first transaction pool queue sorting; process the first transaction pool queue sorting by calling the consensus mechanism of the blockchain to obtain the second transaction pool queue sorting. Step S4-1: parse the blockchain real-time transaction pool data, extract the submission timestamps of the data broadcasts of each work site, and control the number of queues in the transaction pool based on the transaction pool queue sorting threshold, where the transaction pool queue sorting threshold is the maximum number of transactions allowed to enter the first sort. Step S4-2: Sort the unconfirmed maintenance transactions in the transaction pool according to the submission timestamps of the data broadcasts of each work site from earliest to latest, and select the number of transactions in the sorting results that are equal to the sorting threshold of the transaction pool queue to form the first transaction pool queue sorting. Step S4-3: Call the priority queue data structure built into the blockchain consensus mechanism, and perform a second sorting on the transactions in the first transaction pool queue to obtain the second transaction pool queue sorting. In practical implementation, the transaction pool queue sorting threshold is dynamically set according to the periodic characteristics of power plant maintenance operations. For example, the threshold is adjusted at different times such as annual overhaul and quarterly inspection of the power plant to make the threshold compatible with the amount of maintenance data in the current period. When extracting the submission timestamp of the data broadcast from the work site, time calibration is required based on the high-precision time synchronization system uniformly deployed by the power plant to prevent sorting chaos caused by local time deviations of nodes from different maintenance teams. When calling the priority queue built into the PoA consensus mechanism for secondary sorting, the importance of the equipment at the power plant work site must be included in the sorting logic to avoid conflicts with the priority requirements of the actual operation and maintenance of the power plant and to ensure the timeliness of the operation and maintenance of key equipment.

[0022] Step S5: Obtain the number of online nodes through the blockchain API interface, analyze the data broadcast logs of the accounting nodes to obtain the relationship between data broadcast speed and the number of online nodes, train the data using a neural network model to obtain a processing time prediction model, sort the second transaction pool queue according to the processing time prediction model, predict the time required to complete a transaction, and record it as the transaction pool completion prediction time; control the submission time of data broadcasting for each work site in the blockchain according to the transaction pool completion prediction time. Step S5-1: Obtain the broadcast logs of the nodes with accounting rights through the blockchain node API interface. Extract the time from the start of broadcasting each transaction to the consensus confirmation of all nodes in the blockchain and the time written into the block, and record it as the single broadcast completion time. At the same time, obtain the number of online nodes in the blockchain during the broadcast period of each transaction to form a related dataset containing the single broadcast completion time and the corresponding number of online nodes. Step S5-2: Input the associated dataset into the neural network model for training. The neural network model selects the number of online nodes as the input parameter and the completion time of a single broadcast as the output parameter. After training, a processing time prediction model is obtained. Step S5-3: Obtain time series data of the number of online nodes within a preset time period through the blockchain node API interface; analyze the time series data through the LSTM time series model to predict the predicted value of the number of online nodes within the future preset time period; input the predicted value into the processing time prediction model to obtain the predicted time for processing a single transaction in the second transaction pool queue sorting, which is recorded as the transaction pool completion prediction time. Step S5-4: Sort the newly submitted data to be broadcast by each work site in the blockchain from earliest to latest according to the broadcast submission time, and mark the data to be broadcast at the first position as the data to be entered into the transaction pool; set the transaction pool entry time for the data to be entered into the transaction pool, which is set as the current time plus the transaction pool completion prediction time; when the accounting node completes the packaging of the current block and generates a new block, when the new accounting node is determined through the consensus mechanism, add the data to be entered into the transaction pool to the transaction pool, and at the same time, re-execute steps S5-1 to S5-3 based on the broadcast log of the new accounting node to obtain a new transaction pool completion prediction time, set the transaction pool entry time for the next ranked data to be broadcast, and synchronously process the broadcasts submitted by subsequent nodes to complete the mobile maintenance and operation monitoring.

[0023] In practical implementation, a fully connected neural network model can be used to train the processing time prediction model. The associated dataset used for training needs to be extracted from the historical broadcast logs of the power plant's accounting nodes, and abnormal broadcast time data caused by extreme weather such as thunderstorms and blizzards must be removed to ensure the validity of the dataset. When analyzing the time series data of the number of online nodes using the LSTM time series model, the time series window length needs to match the power plant's maintenance cycle so that the model can accurately capture the changing patterns of the number of online nodes within different maintenance cycles. Before setting the entry time of the transaction pool for data to be entered into the transaction pool, the network transmission delay between the new accounting node and the work site needs to be obtained first. The transaction pool completion prediction time is corrected based on the delay data to improve the prediction accuracy. When sorting the newly submitted data to be broadcast by each work site according to the submission time, the submission timestamp recorded on the blockchain must be strictly used as the standard. Operations by maintenance personnel attempting to improve the data sorting priority by modifying the local time of the nodes must be rejected to ensure the fairness and standardization of power plant maintenance data processing.

[0024] Example 2, as Figure 2 As shown, the present invention provides a mobile operation and maintenance monitoring system based on blockchain technology. The mobile operation and maintenance monitoring system includes a node association module, a broadcast monitoring module, a transaction pool data module, a transaction sorting module, and a time prediction control module. The node association module is used to associate and bind the unique identifier of the mobile maintenance and repair work site with the blockchain node identity to obtain an association binding mapping table; the broadcast monitoring module is used to monitor the work site, broadcast data according to the association binding mapping table after maintenance is completed, and detect broadcast conflicts; the transaction pool data module is used to obtain the accounting right node information based on the broadcast conflict results and analyze it to obtain the real-time blockchain transaction pool data; the transaction sorting module is used to analyze the real-time transaction pool data, set a sorting threshold, and sort the data based on the submission time and consensus mechanism to obtain two types of transaction pool queues; the time prediction control module is used to obtain the number of online nodes and broadcast logs, train a prediction model, and control the data broadcast submission time. The node association module includes an identifier verification unit and a mapping generation unit; the identifier verification unit is used to obtain the unique identifier of the work site hardware and the blockchain node digital certificate, and verify the validity of the digital certificate through the chain authorized node; the mapping generation unit is used to associate and map the verified unique identifier of the work site hardware with the blockchain node public key through a smart contract, and write it into the ledger to generate an association binding mapping table. The broadcast monitoring module includes a broadcast initiation unit and a conflict detection unit; the broadcast initiation unit is used to monitor the maintenance completion status of the work site and broadcast maintenance data to the entire blockchain network through the P2P network; the conflict detection unit is used to extract broadcast data with the same unique hardware identifier and compare the block height and hash value to determine broadcast conflicts. The transaction pool data module includes a node information acquisition unit and a data extraction unit; the node information acquisition unit is used to send an information acquisition request to the accounting node by calling the interface according to the broadcast conflict result; the data extraction unit is used to receive the accounting node information and extract the data to form a structured dataset of blockchain real-time transaction pool data. The transaction sorting module includes an initial sorting unit and a consensus sorting unit; the initial sorting unit is used to extract the broadcast submission timestamp, sort by time, and select a threshold number of transactions to form a first transaction pool queue; the consensus sorting unit is used to call the consensus mechanism priority queue to sort the first transaction pool queue a second time to obtain a second transaction pool queue. The time prediction control module includes a prediction model training unit and a submission time control unit. The prediction model training unit is used to extract data to train a processing time prediction model and use LSTM to predict the number of online nodes to obtain the transaction pool completion prediction time. The submission time control unit is used to sort the data to be broadcast, set the entry time, update the prediction time, and process subsequent broadcasts. The output of the node association module is electrically connected to the input of the broadcast monitoring module; the output of the broadcast monitoring module is electrically connected to the input of the transaction pool data module; the output of the transaction pool data module is electrically connected to the input of the transaction sorting module; and the output of the transaction sorting module is electrically connected to the input of the time prediction control module.

[0025] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, it is intended that all variations falling within the meaning and scope of equivalents of the claims be included within the present invention.

Claims

1. A mobile operation and maintenance monitoring method based on blockchain technology, characterized in that: The mobile operation and maintenance monitoring method includes the following steps: Step S1: Associate and bind the unique identifier of the mobile maintenance work station with the corresponding blockchain node identity to obtain the association and binding mapping table between each work station and the blockchain node. Step S2: Monitor each work site. After the work site completes maintenance, broadcast data to the maintenance work site according to the association binding mapping table, and perform broadcast conflict detection on each node in the blockchain. Step S3: Based on the broadcast conflict detection results, obtain the information data of the accounting node by calling the blockchain node API interface; and analyze the obtained information data to obtain the real-time data of the transaction pool in the blockchain, which is recorded as the blockchain real-time transaction pool data. Step S4: Analyze the real-time transaction pool data of the blockchain and set the transaction pool queue sorting threshold; obtain the submission time of data broadcasting of each work site, and sort the transaction pool queue based on the submission time of data broadcasting and the transaction pool queue sorting threshold to obtain the first transaction pool queue sorting; process the first transaction pool queue sorting by calling the consensus mechanism of the blockchain to obtain the second transaction pool queue sorting. Step S5: Obtain the number of online nodes through the blockchain API interface, analyze the data broadcast logs of the accounting nodes to obtain the relationship between data broadcast speed and the number of online nodes, train the data using a neural network model to obtain a processing time prediction model, sort the second transaction pool queue according to the processing time prediction model, predict the time required to complete a transaction, and record it as the transaction pool completion prediction time; control the submission time of data broadcasting for each work site in the blockchain according to the transaction pool completion prediction time. The specific steps of step S2 are as follows: Step S2-1: Based on the blockchain API interface, monitor the maintenance completion status of each work site in real time. When any work site is found to have completed maintenance, determine the corresponding blockchain node based on the unique identifier of the work site and the association binding mapping table, and broadcast the maintenance data to the entire blockchain network through the P2P network. The maintenance data includes the unique hardware identifier of the work site, the maintenance data hash and the block height at the time of broadcast initiation. Step S2-2: When receiving maintenance data, the underlying blockchain node extracts multiple maintenance data corresponding to the same unique hardware identifier through the consensus layer pre-verification logic, and compares the block height and data hash value at the time of broadcast initiation of each maintenance data. If there are two or more broadcast data with a block height difference of less than 1 and inconsistent data hash values, it is determined to be a broadcast conflict. If the block height difference of all data is greater than or equal to 1, or the block height difference is less than 1 but the data hash values ​​are consistent, it is determined to be no broadcast conflict. The specific steps of step S3 are as follows: Step S3-1: The blockchain network determines the current accounting node through a consensus mechanism. The accounting node refers to the node in the blockchain network that has obtained the right to record transactions through the consensus mechanism and is responsible for verifying, packaging, and writing transactions in the network into new blocks. If the broadcast conflict detection result is no conflict, the blockchain node API interface is directly called, and an information data acquisition request is sent to the accounting node. If the broadcast conflict detection result is a conflict, the broadcast data with the highest block height and unique data hash is first filtered out through the consensus layer pre-verification logic. At the same time, duplicate broadcast data is removed by deduplication using the transaction ID. Based on the filtered broadcast data, the blockchain node API interface is called to send an information data acquisition request to the accounting node. Step S3-2: Receive the information data returned by the accounting node, extract the unconfirmed maintenance transaction hash value, maintenance data and transaction submission time in the transaction pool of the accounting node, as well as the current block height and network communication address of the accounting node, to form a structured dataset containing transaction identifier, data content, time parameters and node information. The structured dataset represents the blockchain real-time transaction pool data.

2. The mobile operation and maintenance monitoring method based on blockchain technology according to claim 1, characterized in that: The specific steps of step S1 are as follows: Step S1-1: Obtain the unique hardware identifier of the mobile maintenance and repair work station. The mobile maintenance and repair work station refers to the object carrier that needs to be inspected, troubleshooted and maintained in the infrastructure operation scenario. The unique hardware identifier is an unalterable code pre-stored in the built-in chip of the work station equipment. Obtain a digital certificate for a blockchain node, the digital certificate containing the node's public key and node operation and maintenance permission identifier, and verify the validity of the digital certificate through a chain-authorized node; Step S1-2: The verified work site hardware unique identifier and the blockchain node public key are associated and mapped through a smart contract. The association mapping includes the hardware unique identifier, the node public key and the binding timestamp. The smart contract writes the association mapping into the blockchain distributed ledger to generate an association binding mapping table. The association binding mapping table supports bidirectional querying using the hardware unique identifier or the node public key.

3. The mobile operation and maintenance monitoring method based on blockchain technology according to claim 1, characterized in that: The specific steps of step S4 are as follows: Step S4-1: parse the blockchain real-time transaction pool data, extract the submission timestamps of the data broadcasts of each work site, and control the number of queues in the transaction pool based on the transaction pool queue sorting threshold, where the transaction pool queue sorting threshold is the maximum number of transactions allowed to enter the first sort. Step S4-2: Sort the unconfirmed maintenance transactions in the transaction pool according to the submission timestamps of the data broadcasts of each work site from earliest to latest, and select the number of transactions in the sorting results that are equal to the sorting threshold of the transaction pool queue to form the first transaction pool queue sorting. Step S4-3: Call the priority queue data structure built into the blockchain consensus mechanism, and perform a secondary sorting on the transactions in the first transaction pool queue to obtain the second transaction pool queue sorting.

4. The mobile operation and maintenance monitoring method based on blockchain technology according to claim 3, characterized in that: The specific steps of step S5 are as follows: Step S5-1: Obtain the broadcast log of the node with accounting rights through the blockchain node API interface. Extract the time from the start of broadcasting for each transaction to the time it is confirmed by the consensus of all nodes in the blockchain and written into the block, and record it as the single broadcast completion time. At the same time, the number of online nodes in the blockchain during the broadcast period of each transaction is obtained, forming a related dataset containing the completion time of a single broadcast and the corresponding number of online nodes; Step S5-2: Input the associated dataset into the neural network model for training. The neural network model selects the number of online nodes as the input parameter and the completion time of a single broadcast as the output parameter. After training, a processing time prediction model is obtained.

5. The mobile operation and maintenance monitoring method based on blockchain technology according to claim 4, characterized in that: Step S5 also includes: Step S5-3: Obtain time series data of the number of online nodes within a preset time period through the blockchain node API interface; analyze the time series data through the LSTM time series model to predict the predicted value of the number of online nodes within the future preset time period; input the predicted value into the processing time prediction model to obtain the predicted time for processing a single transaction in the second transaction pool queue sorting, which is recorded as the transaction pool completion prediction time. Step S5-4: Sort the newly submitted data to be broadcast by each work site in the blockchain from earliest to latest according to the broadcast submission time, and mark the data to be broadcast at the first position as the data to be entered into the transaction pool; set the transaction pool entry time for the data to be entered into the transaction pool, which is set as the current time plus the transaction pool completion prediction time; when the accounting node completes the packaging of the current block and generates a new block, when the new accounting node is determined through the consensus mechanism, add the data to be entered into the transaction pool to the transaction pool, and at the same time, re-execute steps S5-1 to S5-3 based on the broadcast log of the new accounting node to obtain a new transaction pool completion prediction time, set the transaction pool entry time for the next ranked data to be broadcast, and synchronously process the broadcasts submitted by subsequent nodes to complete the mobile maintenance and operation monitoring.

6. A mobile operation and maintenance monitoring system based on blockchain technology, which is applied to the mobile operation and maintenance monitoring method based on blockchain technology as described in any one of claims 1-5, characterized in that: The mobile operation and maintenance monitoring system includes a node association module, a broadcast monitoring module, a transaction pool data module, a transaction sorting module, and a time prediction and control module. The node association module is used to associate and bind the unique identifier of the mobile maintenance and repair work site with the blockchain node identity to obtain an association binding mapping table; the broadcast monitoring module is used to monitor the work site, broadcast data according to the association binding mapping table after maintenance is completed, and detect broadcast conflicts; the transaction pool data module is used to obtain the accounting right node information based on the broadcast conflict results and analyze it to obtain the real-time blockchain transaction pool data; the transaction sorting module is used to analyze the real-time transaction pool data, set a sorting threshold, and sort the data based on the submission time and consensus mechanism to obtain two types of transaction pool queues; the time prediction control module is used to obtain the number of online nodes and broadcast logs, train a prediction model, and control the data broadcast submission time. The output of the node association module is electrically connected to the input of the broadcast monitoring module; the output of the broadcast monitoring module is electrically connected to the input of the transaction pool data module; the output of the transaction pool data module is electrically connected to the input of the transaction sorting module; and the output of the transaction sorting module is electrically connected to the input of the time prediction control module. The node association module includes an identifier verification unit and a mapping generation unit; the identifier verification unit is used to obtain the unique identifier of the work site hardware and the blockchain node digital certificate, and to verify the validity of the digital certificate through the chain-authorized node. The mapping generation unit is used to associate and map the verified unique identifier of the work site hardware with the public key of the blockchain node through a smart contract, and write it into the ledger to generate an association binding mapping table. The broadcast monitoring module includes a broadcast initiation unit and a conflict detection unit; the broadcast initiation unit is used to monitor the maintenance completion status of the work site and broadcast maintenance data to the entire blockchain network through the P2P network; the conflict detection unit is used to extract broadcast data with the same unique hardware identifier and compare the block height and hash value to determine broadcast conflicts. The transaction pool data module includes a node information acquisition unit and a data extraction unit. The node information acquisition unit is used to send an information acquisition request to the accounting node by calling the interface according to the broadcast conflict result. The data extraction unit is used to receive the accounting node information and extract the data to form a structured dataset of blockchain real-time transaction pool data.

7. A mobile operation and maintenance monitoring system based on blockchain technology according to claim 6, characterized in that: The transaction sorting module includes an initial sorting unit and a consensus sorting unit; the initial sorting unit is used to extract the broadcast submission timestamp, sort by time, and select a threshold number of transactions to form a first transaction pool queue; the consensus sorting unit is used to call the consensus mechanism priority queue to sort the first transaction pool queue a second time to obtain a second transaction pool queue. The time prediction control module includes a prediction model training unit and a submission time control unit. The prediction model training unit is used to extract data to train a processing time prediction model and use LSTM to predict the number of online nodes to obtain the transaction pool completion prediction time. The submission time control unit is used to sort the data to be broadcast, set the entry time, update the prediction time, and process subsequent broadcasts.

Images