Power transmission hidden danger intelligent alarm method and system based on intelligent contract

Abstract

The invention discloses a power transmission hidden danger intelligent alarm method and system based on an intelligent contract. The method comprises the steps of receiving sensing data from a multi-source heterogeneous sensor, performing feature extraction on the sensing data in different forms, and performing fusion on extracted multi-dimensional features; performing correlation analysis on the fused sensor data, wherein the correlation analysis comprises correlation analysis of the sensor data and historical data thereof, and data correlation analysis among a plurality of sensors; according to a preset intelligent contract rule, carrying out parallel analysis processing on the sensor data in a plurality of different nodes, generating an alarm signal when a power transmission hidden danger is identified, and executing a corresponding operation based on the intelligent contract rule; and sending alarm information according to the generated alarm signal. According to the scheme, safe operation of the power transmission equipment is guaranteed, and the safety and reliability of the system are improved.

Description

Technical Field

[0001] The present invention belongs to the field of integration and intelligent processing of multi-source heterogeneous sensor data, and in particular to a method and system for intelligent alarm of power transmission hidden dangers based on smart contracts. Background Art

[0002] With the continuous development of sensing technology, the fusion of multi-source heterogeneous sensor data has become an important means to achieve comprehensive perception and comprehensive decision-making. However, in traditional heterogeneous sensor systems, the integration and processing of multi-source heterogeneous data usually requires manual intervention, which is inefficient and easily affected by misoperation. Therefore, a smart contract engine that can be automatically executed and does not require trust is needed to improve the efficiency and accuracy of data fusion.

[0003] For example, in the specific field of power transmission, the power transmission monitoring center usually deploys a variety of different types of sensors to monitor the temperature of the transmission line, the construction of the transmission line channel, etc. The data generated by these sensors are of various types, which is quite cumbersome to manage, and each sensor may send out an alarm signal. Due to abnormal functions of sensor equipment or misunderstanding of data, false alarms often occur, reducing the reliability and efficiency of the system. The existing technology does not uniformly perform intelligent perception and processing. Summary of the invention

[0004] In order to solve the deficiencies in the prior art, the present invention provides a method and system for intelligent alarm of power transmission hidden dangers based on smart contracts to solve the problems existing in the sensor alarm mechanism, including data errors caused by false alarms and sensor failures.

[0005] In order to solve the above technical problems, the present invention adopts the following technical solutions.

[0006] The present invention first discloses a power transmission hidden danger intelligent alarm method based on a smart contract, which comprises the following steps:

[0007] Step 1: receiving sensor data from multi-source heterogeneous sensors, extracting features from sensor data in different forms, and fusing the extracted multi-dimensional features;

[0008] Step 2, performing association analysis on the fused sensor data, wherein the association analysis includes association analysis between the sensor data and its historical data, and association analysis between data of multiple sensors;

[0009] Step 3: According to the pre-set smart contract rules, the sensor data is analyzed and processed in parallel in multiple different nodes, an alarm signal is generated when a power transmission hidden danger is identified, and corresponding operations are executed based on the smart contract rules;

[0010] Step 4: Send alarm information according to the generated alarm signal.

[0011] The present invention further includes the following preferred embodiments:

[0012] The feature extraction of different forms of sensor data further includes:

[0013] For text data, its word frequency, sentiment, and theme features are extracted; for image data, its color, texture, and shape features are extracted; for audio data, its rhythm, pitch, and tone features are extracted.

[0014] The fusing of the extracted multi-dimensional features further includes:

[0015] Calculate the mean of the monitoring data at time N as: where y i is the actual sensor detection value;

[0016] Calculate the standard deviation of the monitoring data at time N and estimate it as δ y for: For any positive number n>0, the probability that y is at least n standard deviations from its expected value μ does not exceed δ 2 / ε 2 , δ represents any δ y , y represents any y i , for any transmission line monitoring process parameter y, P(|y-μ|≥ε)≤δ 2 / ε 2 , let ε=nδ, P(|y-μ|≥ε)=P(|y-μ|≥nδ)≤1 / n 2 , get the normal spatial range of y [μ yN -nδ y , μ yN +nδ y ]; P is probability;

[0017] Set the normal interval of sensor i to [a i,min , a i,max ], when the data exceeds the normal range, the sensor triggers an alarm condition; at the same time, combined with the daily monitoring data of the sensor, the data safety and stability interval range of the sensor's stable operation is determined [μ yN -nδ y , μ yN +nδ y ], when the monitoring data exceeds the safe and stable range of operation, the sensor prompt message is triggered to determine that the sensor data is in an unsafe and stable range.

[0018] The performing correlation analysis on the fused sensor data further includes:

[0019] The correlation coefficient R is used to determine the degree of correlation between the two sensor data:

[0020] R=∑(x N -μ N )×(y N -μ N ) / δ x ×δ y

[0021] x N and N Represent the observed data values ​​of the two sensors, μ N represents the mean of sensor data, δ x ,δ y Represents the standard deviation of the monitoring data.

[0022] The method of performing parallel analysis and processing of sensor data in multiple different nodes according to the pre-set smart contract rules further includes:

[0023] Divide the sensor data into multiple fragments, and each node processes one or more fragments. Through parallel computing, multiple data fragments are processed simultaneously.

[0024] Define the rules of data exchange and collaboration through smart contracts, and share analysis results and transfer tasks between nodes;

[0025] Automatically adjust task allocation based on node availability and performance. If a node fails or performance degrades, the system automatically reallocates tasks to other nodes.

[0026] Based on the data anomalies of a single sensor or the status of data fusion from multiple sensors, the trigger conditions for the execution of the smart contract are set. When it is detected that the set conditions are met, the corresponding operations are automatically performed, including generating alarm information, adjusting system parameters, and sending instructions to other devices.

[0027] The present invention also discloses a power transmission hidden danger intelligent alarm system based on smart contracts using the above-mentioned power transmission hidden danger intelligent alarm method based on smart contracts, comprising:

[0028] The sensor interface acquisition module is used to receive sensor data from multi-source heterogeneous sensors, extract features from sensor data in different forms, and fuse the extracted multi-dimensional features;

[0029] A sensor data analysis module, used to perform correlation analysis on the fused sensor data, wherein the correlation analysis includes correlation analysis between the sensor data and its historical data, and correlation analysis between data of multiple sensors;

[0030] A smart contract engine module, which is used to analyze and process sensor data in parallel in multiple different nodes according to pre-set smart contract rules, generate an alarm signal when a power transmission hazard is identified, and execute corresponding operations based on the smart contract rules;

[0031] The alarm module is used to send alarm information according to the generated alarm signal.

[0032] Accordingly, the present application also discloses a terminal, including a processor and a storage medium;

[0033] The storage medium is used to store instructions;

[0034] The processor is used to operate according to the instructions to execute the steps of the aforementioned power transmission hidden danger intelligent alarm method based on smart contracts.

[0035] Correspondingly, the present application also discloses a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the aforementioned smart contract-based power transmission hazard intelligent alarm method are implemented.

[0036] The beneficial effect of the present invention is that, compared with the prior art, the present invention provides a method and system for intelligent alarm of power transmission hidden dangers based on smart contracts, which realizes comprehensive monitoring of power transmission equipment and environment through the fusion of multi-source heterogeneous sensor data and the autonomous execution of smart contracts. When the conditions are met, the smart contract is autonomously executed, data anomalies are discovered in time and corresponding measures are taken, power transmission hidden dangers are discovered quickly and accurately, and alarms are issued in time without human intervention, thereby improving data processing and monitoring efficiency, avoiding errors caused by a single data source, improving the monitoring and early warning accuracy of the system, eliminating the need to trust a third party, ensuring the safe operation of power transmission equipment, improving the safety and reliability of the system, reducing the risk of accidents, as well as economy and sustainability, and having broad application prospects and economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the sensor threshold data acquisition process in the present invention.

[0038] Figure 2 It is a flow chart of the intelligent alarm scheme for power transmission hidden dangers based on smart contracts in the present invention. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present invention more clear, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0040] The embodiments described in this application are only some embodiments of the present invention, not all embodiments. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the protection scope of the present invention.

[0041] In view of the shortcomings of the prior art, the present invention proposes a method and system for intelligent alarm of power transmission hidden dangers based on smart contracts. Taking temperature sensors, micro-meteorological sensors, and video monitoring sensors as examples, the present invention realizes data integration and automatic execution of hidden danger alarms for various types of sensors deployed in the power transmission monitoring center. Through smart contracts, seamless fusion of multi-source sensor data is achieved, and corresponding operations are automatically triggered when specific conditions are met without manual intervention, solving the problems existing in the sensor alarm mechanism, including data errors caused by false alarms and sensor failures, thereby optimizing the sensor alarm mechanism and data processing method.

[0042] The power transmission hidden danger alarm system based on smart contracts disclosed in the present invention includes a sensor interface acquisition module, a sensor data analysis module, a smart contract engine module and an alarm module. The power transmission hidden danger intelligent alarm method based on smart contracts disclosed in the present invention includes the following steps:

[0043] Step 1: Receive sensor data from multi-source heterogeneous sensors, extract features from sensor data in different forms, and fuse the extracted multi-dimensional features.

[0044] The sensor interface acquisition module receives the alarm level data standards of multi-source heterogeneous sensors from different manufacturers and types through a standard interface, including visual monitoring sensors, temperature sensors, drone visible light sensors, etc. It converts them into a standardized data format to facilitate subsequent data processing.

[0045] Different feature extractions are required for various data forms such as text, images, audio, and video. For example, for text data, features such as word frequency, sentiment, and theme can be extracted; for image data, features such as color, texture, and shape can be extracted; and for audio data, features such as rhythm, pitch, and tone can be extracted.

[0046] In order to obtain more complete and accurate data through comprehensive analysis, various data features are fused after feature extraction, and the fused features are processed for dimensionality reduction. The modal data that is easy to collect and easy to label is used to guide the pre-training and fine-tuning methods of the modal data that is difficult to collect and label. The fast regional convolutional neural network method based on image content can quickly locate text and efficiently extract text information from high-noise images in complex environments; a carousel data recognition model based on convolutional recurrent neural networks is constructed, and an end-to-end indefinite-length text sequence recognition algorithm is proposed. The convolutional neural network and the deep neural network are combined, and the connection time series classification loss function is introduced to solve the problem of repeated sequence recognition, improve the text recognition rate, and realize the real-time and automatic collection of sensor data and monitoring data, such as Figure 1 shown.

[0047] The end-to-end variable-length text sequence recognition algorithm includes steps, namely image preprocessing, feature extraction, sequence modeling, connection temporal classification (CTC) loss calculation, and a final decoding step.

[0048] 1. Image preprocessing

[0049] Before text recognition, the input image needs to be preprocessed to improve the accuracy and efficiency of recognition. Preprocessing includes the following steps:

[0050] Grayscale: Convert a color image to a grayscale image to reduce computational complexity.

[0051] Normalization: Normalize the grayscale image so that the pixel values ​​are distributed between 0 and 1.

[0052] Resize: Resizes the image to a fixed height, maintaining the aspect ratio and adding padding if necessary.

[0053] 2. Feature extraction

[0054] Use convolutional neural network (CNN) for feature extraction. The typical network architecture includes multiple layers of convolutional layers and pooling layers. The following is a typical CNN feature extraction architecture:

[0055] Convolutional layer: Use multiple convolutional layers to extract local features of the image and use the ReLU activation function for nonlinear transformation.

[0056] Pooling layer: Reduce the size of the feature map through the maximum pooling or average pooling layer to retain important features.

[0057] Batch Normalization: Batch normalization is performed after the convolutional layer to stabilize the training process.

[0058] 3. Sequence Modeling

[0059] The extracted features are modeled using a recurrent neural network (RNN). Bidirectional long short-term memory network (BiLSTM) is a commonly used RNN architecture that can capture the dependencies between sequences.

[0060] 4. Connection Temporal Classification (CTC) loss calculation

[0061] The CTC loss function is used to solve the alignment problem of indefinite length sequences. CTC allows the length of the input sequence and the output sequence to not match, and calculates the most likely alignment path through dynamic programming.

[0062] 5. Decoding steps

[0063] In the inference phase, the probability distribution output by the model needs to be decoded into the final character sequence. Common decoding methods include greedy decoding and beam search decoding.

[0064] The algorithm combines convolutional neural networks for feature extraction, recurrent neural networks for sequence modeling, and CTC loss function for variable-length sequence alignment to build an end-to-end variable-length text sequence recognition system. This system can effectively handle complex text recognition tasks and improve the accuracy and efficiency of text recognition.

[0065] Assume that the normal interval of sensor i data is [a i,min , a i,max ], when the interval is exceeded, an alarm is generated, and an alarm threshold function H[(a i,max -x)∩(xa i,min )], H[Θ] is a step activation function, where H[Θ] = 1 when Θ > 0; H[Θ] = 0 when Θ < 0, and when the sensor data is less than the minimum value a of the normal range i,min , or the sensor data is greater than the maximum value a of the normal range i,max When the alarm signal is triggered, the system alarms.

[0066] Calculate the mean of the monitoring data at time N as: where y i is the actual sensor detection value.

[0067] Calculate the standard deviation of the monitoring data at time N and estimate it as δ y for: According to Chebyshev's inequality, the probability of detecting data deviating from its expected value is characterized. For any positive number n>0, the inequality shows that the probability that y is at least n standard deviations away from its expected value μ does not exceed δ 2 / ε 2 , δ represents any δ y , y represents any y i For any transmission line monitoring process parameter y, we can obtain P(|y-μ|≥ε)≤δ2 / ε 2 , let ε=nδ, P(|y-μ|≥ε)=P(|y-μ|≥nδ)≤1 / n 2 , and then we can get the normal spatial range of y [μ yN -nδ y , μ yN +nδ y ]. P is the probability.

[0068] The normal interval of sensor i [a i,min , a i,max ], when the monitoring data exceeds the normal range, the sensor triggers the alarm condition; at the same time, combined with the daily monitoring data of the sensor, the data safety and stability interval range of the sensor's stable operation is determined [μ yN -nδ y , μ yN +nδ y ], when the monitoring data exceeds the safe and stable range of operation, the sensor prompt message is triggered, indicating that the sensor data is in an unsafe and stable range and requires special attention.

[0069] The initial coefficients are constantly adjusted during the training process, and the coefficients are corrected using the steepest descent method. N+1 =n N +ηe N , where e N is the correction value at time N, η is the adjustment coefficient, satisfying 0<η<1 / y N ,and,

[0070]

[0071] Step 2: Perform association analysis on the fused sensor data, including association analysis between the sensor data and its historical data, and data association analysis between multiple sensors.

[0072] The sensor data analysis module obtains standardized sensor data from the database, integrates and correlates the data to obtain more comprehensive and accurate monitoring results. The correlation analysis between sensors includes the correlation between current sensor data and historical data. The current state of the target is estimated by obtaining the estimated state of the target observed previously and the measured value of the current state. For example, if the mean value of the temperature sensor is significantly higher than the historical data, the sensor alarms. It also includes the correlation between the data of multiple sensors.

[0073] The correlation coefficient R is used to determine the degree of association between the two sensor data:

[0074] R=∑(x N -μ xN)×(y N -μ yN ) / δ x ×δ y

[0075] x N and N Represent the observed data values ​​of the two sensors, μ xN ,μ yN represents the mean of sensor data, δ x ,δ y Represents the standard deviation of the monitoring data.

[0076] Based on the integration and analysis of sensor data, the sensor data analysis module uses a pre-set hidden danger identification algorithm to identify potential power transmission hidden danger events, such as abnormal power equipment and excessive temperature. Take micro-meteorological sensors and hardware temperature sensors as examples:

[0077] The detailed parameters of the hardware temperature sensor are:

[0078] Temperature measurement range: -40℃~+125℃;

[0079] Temperature measurement accuracy: ±0.5~2℃;

[0080] Working environment temperature: -40℃~+100℃;

[0081] The detailed parameters of the micro-meteorological sensor are:

[0082] Temperature measurement range: -40℃~+60℃;

[0083] Temperature measurement error: ≤0.5℃;

[0084] (1) Single sensor alarm:

[0085] Taking the temperature sensor as an example, the alarm function is set as:

[0086] The temperature range is between 20℃ and 40℃, which is normal;

[0087] When the temperature range is between 60℃ and 70℃, it is in alert state and alarms are sounded;

[0088] If the temperature exceeds 70℃, it is an emergency and an alarm is issued;

[0089] Taking the micro-meteorological sensor as an example, the alarm function is set as:

[0090] Temperatures below 0°C are considered extremely low temperatures;

[0091] When the temperature range is between 0℃ and 10℃, it is a low temperature environment;

[0092] When the temperature range is between 10℃ and 30℃, it is a normal temperature environment;

[0093] When the temperature range is 30℃~35℃, it is a high temperature environment;

[0094] When the temperature range is between 35℃ and 45℃, it is an extremely high temperature environment and an alarm is triggered;

[0095] (2) Correlate sensor data to identify false alarms:

[0096] The sensor false alarm scenario is judged by using the data of two sensors jointly, calculating the difference between the two sensor data and comparing it with the pre-set threshold.

[0097] Assume there are two sensors, hardware temperature sensor A and micro-meteorological sensor B, and the data they collect are A data and B data . Calculate the absolute difference between them |A data -B data |, and then compared with the threshold and the alarm mechanism is triggered. This difference value is compared with the pre-set threshold to determine whether there is an abnormality. If the difference value exceeds the threshold, there is an abnormality.

[0098] The trigger processing mechanism of the system triggering the abnormal data processing module:

[0099] 1) Micro-meteorological sensor B is in extremely low temperature. If A data <B data , then the hardware temperature sensor A is reporting a false alarm;

[0100] 2) Micro-meteorological sensor B is in a low temperature environment. If the difference value = |A data -B data | If it exceeds 60℃, the temperature of the transmission line is abnormal, it is in a warning state, and an alarm is issued;

[0101] 3) Micro-meteorological sensor B is in a normal temperature environment. If the difference value = |A data -B data | If it exceeds 30℃, the temperature of the transmission line is abnormal, it is in a warning state, and an alarm is issued;

[0102] 4) Micro-meteorological sensor B is in a high temperature environment. If the difference value = |A data -B data | If it exceeds 25℃, the temperature of the transmission line is abnormal, it is in a warning state, and an alarm is issued;

[0103] 5) Micro-meteorological sensor B is in an extremely high temperature environment. If the difference value = |A data -B data| If it exceeds 20℃, the temperature of the transmission line is abnormal, it is in a warning state, and an alarm is issued;

[0104] In another embodiment, taking the video surveillance sensor monitoring the transmission line channel crane as an example:

[0105] (1) Single sensor alarm:

[0106] The distance between the transmission line and the crane is more than 100m, which is considered normal;

[0107] When the distance between the transmission line and the crane is between 20m and 100m, it is in alert state and alarm is sounded;

[0108] If the distance between the transmission line and the crane is within 20m, it is in an emergency state and an alarm is sounded;

[0109] (2) Correlate sensor data to identify false alarms:

[0110] The sensor false alarm scenario is determined by jointly using the data from the two sensors, calculating the correlation between the two sensor data and comparing it with a pre-set threshold.

[0111] Assume that there are video surveillance sensors C and system note information D. The latter mainly collects the announcement information of the construction in the transmission line channel reported by the transportation, fire and other departments to the power department. The collected data are C data and D data . Design alarm trigger mechanism:

[0112] 1) D data With / without the transmission line channel construction information; if C data >100m, which is the normal range, the video surveillance sensor will not alarm;

[0113] 2) D data No transmission line channel construction information is noted; if 20m<C data ≤100m, it is in alert state and the video surveillance sensor alarms;

[0114] 3) D data There are notes on the construction information of the transmission line channel; if 20m<C data ≤100m, it is in alert state and the video surveillance sensor does not alarm;

[0115] 4) D data With / without the transmission line channel construction information; if C data If the distance is less than 20m, it is in an emergency state and the video surveillance sensor will sound an alarm.

[0116] Step 3: According to the pre-set smart contract rules, the sensor data is analyzed and processed in parallel in multiple different nodes, an alarm signal is generated when a power transmission hazard is identified, and corresponding operations are performed based on the smart contract rules.

[0117] The smart contract engine module analyzes and processes sensor data in parallel in multiple different nodes according to pre-set rules. When the system detects a power transmission hazard, the smart contract will automatically generate an alarm signal and perform corresponding operations. The following is an example of a smart contract rule:

[0118] Rule name: Temperature anomaly detection and alarm

[0119] Objective: Detect temperature anomalies in power transmission lines and generate alarm signals.

[0120] Participating nodes: All nodes equipped with hardware temperature sensors.

[0121] Data collection: Each node reports the data of micro-meteorological sensors and hardware temperature sensors once a minute.

[0122] Conditional triggering: Refer to step 2 for the trigger processing mechanism of the system triggering the abnormal data processing module.

[0123] Post-trigger operation: Generate and broadcast alarm information to notify relevant maintenance personnel.

[0124] Abnormal temperature data and alarm information are recorded on the blockchain to ensure that the data cannot be tampered with. The smart contract engine module processes and judges the data after fusion and correlation analysis according to the pre-set smart contract rules, and automatically triggers alarms or other corresponding operations when power transmission hazards are found.

[0125] The smart contract engine module achieves decentralized and efficient analysis of sensor data through distributed computing and smart contract technology. The decentralized system includes multiple nodes, each of which runs a smart contract. These nodes can be the sensor device itself, an IoT device connected to the sensor, or a dedicated server. Such a distributed structure allows the system to better adapt to the processing needs of large-scale data.

[0126] Through smart contracts, data analysis tasks are assigned to different nodes for processing. Each node is responsible for analyzing sensor data within its own range, reducing the computing burden of a single central node and improving the overall efficiency of the system.

[0127] Divide the sensor data into small pieces (fragments), and each node processes one or more fragments. Through parallel computing, multiple data fragments are processed at the same time, thereby improving the speed of data analysis and dealing with sensor data of different scales and complexities. The nodes work together through smart contracts. Smart contracts can define the rules for data exchange and collaboration, ensuring that the analysis results and tasks can be effectively shared and transferred between nodes, and the consistency of the system can be maintained to avoid single point failures and improve the robustness of the system. Automatically adjust task allocation according to the availability and performance of the nodes. If a node fails or its performance degrades, the system can automatically reallocate tasks to other nodes to ensure the high availability and stability of the system. Use cryptography and blockchain technology to ensure data security. Implement encryption and decryption of data to ensure data privacy.

[0128] Efficiently utilize multi-source heterogeneous sensor data to achieve real-time monitoring and intelligent alarm, while having stronger scalability and robustness.

[0129] The smart contract engine module includes conditional triggers, which are used to set the trigger conditions for smart contract execution based on the data anomalies of a single sensor or the status of the fusion data of multiple sensors; executors, which are used to automatically perform corresponding operations when the conditional trigger detects that the set conditions are met, such as generating alarm information, adjusting system parameters, sending instructions to other devices, etc. Figure 2 shown.

[0130] In a preferred embodiment, the specific steps of conditional triggering and execution are as follows:

[0131] Step 3.1: Designate a contract owner. Usually the creator of the contract, the contract owner has the highest authority and can perform key management operations of the contract.

[0132] Step 3.2: Determine the nodes authorized to participate in data exchange and task delivery. That is, the list of authorized nodes, which are nodes that have been authenticated by the contract owner and are allowed to participate in specific operations.

[0133] Step 3.3:

[0134] When the analysis result is shared, event 1 is triggered, and event 1 is used to solve the situation of frequent signaling and obvious false alarms. When the task is delivered, event 2 is triggered. Event 2 is triggered when the task is delivered, and is used to record the event of task delivery.

[0135] Step 3.4: Determine two permission modifiers Owner-Only Modifier and Authorized-NodeModifier. Some functions can only be called by the contract owner or authorized nodes.

[0136] The purpose of determining the two permission modifiers is to control the access rights of the function and ensure that only the contract owner or authorized nodes can perform specific operations:

[0137] Owner-Only Modifier: This modifier ensures that only the contract owner can call certain key functions, such as adding authorized nodes and deleting authorized nodes. Its role is to protect the core management functions of the contract and prevent unauthorized operations.

[0138] Authorized-Node Modifier: This modifier ensures that only authorized nodes can call certain data exchange and task transfer functions, such as sharing analysis results and transferring tasks. Its role is to protect the process of data exchange and task transfer and ensure that only trusted nodes participate in these operations.

[0139] Step 3.5: The contract owner adds authorized nodes to the contract by calling the addAuthorizedNode function so that they can participate in data exchange and task delivery. This step ensures that only the contract owner can manage the authorized node list, enhancing the security of the system.

[0140] Step 3.6: The authorized node calls the shareAnalysisResult and transferTask functions to share the analysis results with other nodes or transfer tasks to other nodes. These operations are protected by permission modifiers to ensure that only authorized nodes can perform them.

[0141] The code example is as follows:

[0142]

[0143] emit AnalysisResultShared(msg.sender, to, result);

[0144] / / The logic of actually sharing the analysis results

[0145] }

[0146] function transferTask(address to, string memory task)externalonlyAuthorizedNode{

[0147] emit TaskTransferred(msg.sender, to, task);

[0148] / / The logic of actually passing the task

[0149] }

[0150] / / You can add more functions and logic to meet specific needs

[0151] }

[0152] Among them, the event keyword is used to declare events; AnalysisResult Shared and TaskTransferred are the names of two events, which respectively represent the events of analysis results being shared and tasks being transferred. The indexed keyword is used to mark parameters for easy query and filtering in the blockchain browser. In the above code, from and to are marked as indexed to improve query efficiency. When the emit statement is called in the contract function, the corresponding event is triggered and the value of the parameter is passed to the event. The parameter from represents the address of the initiator of the event; to represents the address of the receiver of the event; result and task represent the shared analysis results and transfer respectively.

[0153] The smart contract engine can be implemented in environments such as the Internet of Things platform and blockchain network, and the contract rules are defined through the contract programming language. In practical applications, customized configuration can be performed according to different sensor data characteristics and requirements.

[0154] Step 4: Send alarm information according to the generated alarm signal.

[0155] The alarm module receives the alarm signal triggered by the smart contract engine and sends the alarm information to the power transmission monitoring center or relevant staff through voice, SMS, email, etc., for timely processing.

[0156] The power transmission hidden danger alarm scheme of the present invention can be widely used in the monitoring and early warning of power transmission equipment such as power transmission lines and substations, and can also be applied to other fields, such as smart factories, environmental monitoring and other multi-source sensor data fusion and intelligent processing scenarios. Through the preset rules of the smart contract engine, automated data processing and alarm can be achieved.

[0157] The beneficial effect of the present invention is that, compared with the prior art, the present invention provides a method and system for intelligent alarm of power transmission hidden dangers based on smart contracts, which realizes comprehensive monitoring of power transmission equipment and environment through the fusion of multi-source heterogeneous sensor data and the autonomous execution of smart contracts. When the conditions are met, the smart contract is autonomously executed, data anomalies are discovered in time and corresponding measures are taken, power transmission hidden dangers are discovered quickly and accurately, and alarms are issued in time without human intervention, thereby improving data processing and monitoring efficiency, avoiding errors caused by a single data source, improving the monitoring and early warning accuracy of the system, eliminating the need to trust a third party, ensuring the safe operation of power transmission equipment, improving the safety and reliability of the system, reducing the risk of accidents, as well as economy and sustainability, and having broad application prospects and economic benefits.

[0158] The present invention may be a system, a method and / or a computer program product. The present invention also discloses a power transmission hidden danger intelligent alarm system based on a smart contract based on the aforementioned power transmission hidden danger intelligent alarm method based on a smart contract, comprising:

[0159] The sensor interface acquisition module is used to receive sensor data from multi-source heterogeneous sensors, extract features from sensor data in different forms, and fuse the extracted multi-dimensional features;

[0160] A sensor data analysis module, used to perform correlation analysis on the fused sensor data, wherein the correlation analysis includes correlation analysis between the sensor data and its historical data, and correlation analysis between data of multiple sensors;

[0161] A smart contract engine module, which is used to analyze and process sensor data in parallel in multiple different nodes according to pre-set smart contract rules, generate an alarm signal when a power transmission hazard is identified, and execute corresponding operations based on the smart contract rules;

[0162] The alarm module is used to send alarm information according to the generated alarm signal.

[0163] Based on the spirit of the present invention, those skilled in the art can easily think that a computer program product can be obtained based on the aforementioned intelligent alarm method for power transmission hazards based on smart contracts. The computer program product may include a computer-readable storage medium on which computer-readable program instructions are loaded for enabling a processor to implement various aspects of the present disclosure. That is, the present application also includes a terminal, including a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the aforementioned intelligent alarm method for power transmission hazards based on smart contracts.

[0164] Computer readable storage medium can be a tangible device that can keep and store the instructions used by the instruction execution device. Computer readable storage medium can be, for example, - but not limited to - electrical storage device, magnetic storage device, optical storage device, electromagnetic storage device, semiconductor storage device or any suitable combination of the above. More specific examples (non-exhaustive list) of computer readable storage medium include: portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, for example, punch card or groove protrusion structure with instructions stored thereon and any suitable combination of the above. Computer readable storage medium used here is not interpreted as instantaneous signal itself, such as radio wave or other free propagating electromagnetic wave, electromagnetic wave propagated by waveguide or other transmission medium (for example, light pulse by optical fiber cable) or electrical signal transmitted by wire.

[0165] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0166] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages-such as Smalltalk, C++, etc., and conventional procedural programming languages-such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network-including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA) may be personalized by utilizing the state information of a computer-readable program instruction, and the electronic circuit may execute a computer-readable program instruction, thereby realizing various aspects of the present disclosure.

[0167] 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 above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for intelligent alarm of power transmission hidden dangers based on smart contracts, characterized in that: The following steps are involved: Step 1: receiving sensor data from multi-source heterogeneous sensors, extracting features from sensor data in different forms, and fusing the extracted multi-dimensional features; Step 2, performing association analysis on the fused sensor data, wherein the association analysis includes association analysis between the sensor data and its historical data, and association analysis between data of multiple sensors; Step 3: According to the pre-set smart contract rules, the sensor data is analyzed and processed in parallel in multiple different nodes, an alarm signal is generated when a power transmission hidden danger is identified, and corresponding operations are executed based on the smart contract rules; Step 4: Send alarm information according to the generated alarm signal.

2. The intelligent alarm method for power transmission hidden dangers based on smart contracts according to claim 1 is characterized in that: The feature extraction of different forms of sensor data further includes: For text data, its word frequency, sentiment, and theme features are extracted; for image data, its color, texture, and shape features are extracted; for audio data, its rhythm, pitch, and tone features are extracted.

3. The intelligent alarm method for power transmission hidden dangers based on smart contracts according to claim 2 is characterized in that: The fusing of the extracted multi-dimensional features further includes: Calculate the mean of the monitoring data at time N as: where y i is the actual sensor detection value; Calculate the standard deviation of the monitoring data at time N and estimate it as δ y for: For any positive number n>0, the probability that y is at least n standard deviations from its expected value μ does not exceed δ 2 / ε 2 , δ represents any δ y , y represents any y i , for any transmission line monitoring process parameter y, P(|y-μ|≥ε)≤δ 2 / ε 2 , let ε=nδ, P(|y-μ|≥ε)=P(|y-μ|≥nδ)≤1 / n 2 , get the normal spatial range of y [μ yN -nδ y , μ yN +nδ y ]; P is probability; Set the normal interval of sensor i to [a i,min , a i,max ], when the data exceeds the normal range, the sensor triggers an alarm condition; at the same time, combined with the daily monitoring data of the sensor, the data safety and stability interval range of the sensor's stable operation is determined [μ yN -nδ y , μ yN +nδ y ], when the monitoring data exceeds the safe and stable range of operation, the sensor prompt message is triggered to determine that the sensor data is in an unsafe and stable range.

4. The intelligent alarm method for power transmission hidden dangers based on smart contracts according to claim 3 is characterized in that: The performing correlation analysis on the fused sensor data further includes: The correlation coefficient R is used to determine the degree of correlation between the two sensor data: R=∑(x N -m N )×(y N -m N ) / δx×δy x N and N Represent the observed data values ​​of the two sensors, μ N represents the mean of sensor data, δ x ,δ y Represents the standard deviation of the monitoring data.

5. The method for intelligent alarm of power transmission hidden dangers based on smart contracts according to claim 4 is characterized in that: The method of performing parallel analysis and processing of sensor data in multiple different nodes according to the pre-set smart contract rules further includes: Divide the sensor data into multiple fragments, and each node processes one or more fragments. Through parallel computing, multiple data fragments are processed simultaneously. Define the rules of data exchange and collaboration through smart contracts, and share analysis results and transfer tasks between nodes; Automatically adjust task allocation based on node availability and performance. If a node fails or performance degrades, the system automatically reallocates tasks to other nodes. Based on the data anomalies of a single sensor or the status of data fusion from multiple sensors, the trigger conditions for the execution of the smart contract are set. When it is detected that the set conditions are met, the corresponding operations are automatically performed, including generating alarm information, adjusting system parameters, and sending instructions to other devices.

6. A power transmission hidden danger intelligent alarm system based on smart contracts, characterized in that: include: The sensor interface acquisition module is used to receive sensor data from multi-source heterogeneous sensors, extract features from sensor data in different forms, and fuse the extracted multi-dimensional features; A sensor data analysis module, used to perform correlation analysis on the fused sensor data, wherein the correlation analysis includes correlation analysis between the sensor data and its historical data, and correlation analysis between data of multiple sensors; A smart contract engine module, which is used to analyze and process sensor data in parallel in multiple different nodes according to pre-set smart contract rules, generate an alarm signal when a power transmission hazard is identified, and execute corresponding operations based on the smart contract rules; The alarm module is used to send alarm information according to the generated alarm signal.

7. The intelligent alarm system for power transmission hidden dangers based on smart contracts according to claim 6 is characterized in that: The sensor interface acquisition module is further used for: For text data, its word frequency, sentiment, and theme features are extracted; for image data, its color, texture, and shape features are extracted; for audio data, its rhythm, pitch, and tone features are extracted.

8. The intelligent alarm system for power transmission hidden dangers based on smart contracts according to claim 7 is characterized in that: The sensor data analysis module is further used to: Calculate the mean of the monitoring data at time N as: where y i is the actual sensor detection value; Calculate the standard deviation of the monitoring data at time N and estimate it as δ y for: For any positive number n>0, the probability that y is at least n standard deviations from its expected value μ does not exceed δ 2 / ε 2 , δ represents any δ y , y represents any y i , for any transmission line monitoring process parameter y, P(|y-μ|≥ε)≤δ 2 / ε 2 , let ε=nδ, P(|y-μ|≥ε)=P(|y-μ|≥nδ)≤1 / n 2 , get the normal spatial range of y [μ yN -nδ y , μ yN +nδ y ]; P is probability; Set the normal interval of sensor i to [a i,min , a i,max ], when the data exceeds the normal range, the sensor triggers an alarm condition; at the same time, combined with the daily monitoring data of the sensor, the data safety and stability interval range of the sensor's stable operation is determined [μ yN -nδ y , μ yN +nδ y ], when the monitoring data exceeds the safe and stable range of operation, the sensor prompt message is triggered to determine that the sensor data is in an unsafe and stable range.

9. The intelligent alarm system for power transmission hidden dangers based on smart contracts according to claim 8 is characterized in that: The smart contract engine module is further used to: The correlation coefficient R is used to determine the degree of correlation between the two sensor data: R=∑(x N -m N )×(y N -m N ) / d x ×d y x N and N Represent the observed data values ​​of the two sensors, μ N represents the mean of sensor data, δ x ,δ y Represents the standard deviation of the monitoring data.

10. The intelligent alarm system for power transmission hidden dangers based on smart contracts according to claim 9 is characterized in that: The alarm module is further used for: Divide the sensor data into multiple fragments, and each node processes one or more fragments. Through parallel computing, multiple data fragments are processed simultaneously. Define the rules of data exchange and collaboration through smart contracts, and share analysis results and transfer tasks between nodes; Automatically adjust task allocation based on node availability and performance. If a node fails or performance degrades, the system automatically reallocates tasks to other nodes. Based on the data anomalies of a single sensor or the status of data fusion from multiple sensors, the trigger conditions for the execution of the smart contract are set. When it is detected that the set conditions are met, the corresponding operations are automatically performed, including generating alarm information, adjusting system parameters, and sending instructions to other devices.

11. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the power transmission hidden danger intelligent alarm method based on smart contract according to any one of claims 1-5.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the intelligent alarm method for power transmission hazards based on smart contracts as described in any one of claims 1 to 5 are implemented.

Images