Power transmission line on-line safety monitoring method, system and device based on quantum communication and storage medium

Abstract

The invention relates to the technical field of power system safety monitoring, in particular to a power transmission line online safety monitoring method, system and device based on quantum communication and a storage medium. The multi-modal fusion sensor synchronously collects multi-parameter electric signal data such as current, voltage and temperature of the power transmission line, and performs quantum encryption instantaneous recording on the data; based on quantum encryption instantaneous record extraction data, a deep learning adaptive Kalman filtering algorithm is combined with a neural network to predict the operation state of the power transmission line; generating a new Manchester code according to the multi-parameter electric signal data and the operation state predicted value, and encrypting by adopting quantum key distribution to generate a ciphertext; and transmitting the ciphertext to a client based on a terahertz communication channel, decrypting and recovering the data through the quantum key, and carrying out safety early warning. Theoretically uncracked data security assurance is realized by using the unclonable characteristic of the quantum state, high-rate data transmission is realized by terahertz communication, and the transformation from passive monitoring to active early warning is realized by a prediction algorithm.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system safety monitoring, and in particular to a power transmission line online safety monitoring method, system and device based on quantum communication and a storage medium. BACKGROUND

[0002] With the rapid advancement of smart grid construction and the continuous improvement of the automation level of the power system, real-time monitoring of the power transmission line becomes increasingly important. Traditional power transmission line monitoring mainly relies on manual inspection and simple sensor monitoring, which is not only inefficient, but also difficult to achieve accurate prediction and timely warning of the operating state of the power transmission line.

[0003] Although existing power transmission line online monitoring technology can collect basic parameters such as current, voltage and temperature, there are many deficiencies in data transmission and processing. On the one hand, the traditional data transmission method is susceptible to external interference, and the reliability and security of data transmission are difficult to guarantee; on the other hand, the existing data processing algorithm is mostly static analysis, lacking dynamic prediction ability for the operating state of the power transmission line, and unable to timely discover potential fault hidden dangers.

[0004] More importantly, in terms of data security, the existing technology has serious defects. Wireless communication signals can be illegally intercepted, access control at the data storage link is not strict enough, and encryption measures are insufficient, resulting in sensitive data being easily stolen and tampered with. These security risks not only affect the accuracy of the monitoring data, but also may threaten the safe and stable operation of the entire power system. SUMMARY

[0005] In view of the problems existing in the prior art, the present application is proposed.

[0006] Therefore, the problem to be solved by the present application is how to solve the problem that the power transmission line data is easily stolen and tampered with in the prior art, resulting in difficulty in guaranteeing data security, while improving the reliability of data transmission and the accuracy of monitoring and prediction, and realizing intelligent real-time monitoring and safety warning of the operating state of the power transmission line.

[0007] To solve the above technical problems, the present application provides the following technical solutions:

[0008] In a first aspect, the present application provides a power transmission line online safety monitoring method based on quantum communication, which comprises synchronously collecting multi-parameter electric signal data of the power transmission line by a multi-modal fusion sensor, and performing quantum encryption instantaneous recording on the multi-parameter electric signal data;

[0009] Based on the quantum encryption instantaneous recording, the multi-parameter electric signal data is extracted, and the operating state of the power transmission line is predicted by a deep learning self-adaptive Kalman filtering algorithm combined with a neural network;

[0010] A new Manchester code is generated according to the multi-parameter electric signal data and the predicted value of the operating state, and quantum key distribution is used for encryption to generate ciphertext;

[0011] The ciphertext is transmitted to the client based on a terahertz communication channel, and the data is recovered by quantum key decryption and security warning is performed.

[0012] As a preferred scheme of the power transmission line online safety monitoring method based on quantum communication, the multi-modal fusion sensor includes a current sensing unit, a voltage sensing unit and a temperature sensing unit.

[0013] The multi-parameter electric signal data includes real-time monitoring data of current value, voltage value and temperature value.

[0014] As a preferred scheme of the power transmission line online safety monitoring method based on quantum communication, the quantum encryption instantaneous record includes:

[0015] A quantum bit sequence is generated by a quantum random number generator, and the quantum bits are in different quantum states.

[0016] The quantum bit sequence is sent to a cloud platform and measured using a random measurement basis.

[0017] Eavesdropping is detected by measuring basis consistency, and data is encrypted and stored using a quantum encryption key.

[0018] As a preferred scheme of the power transmission line online safety monitoring method based on quantum communication, the deep learning adaptive Kalman filtering algorithm includes:

[0019] A state prediction model based on a neural network is established, and multi-parameter electric signal data at the current time is input.

[0020] State estimation is performed by Kalman filtering prediction equation and updating equation.

[0021] Neural network parameters are optimized by minimizing mean square error to achieve accurate prediction of the operating state.

[0022] As a preferred scheme of the power transmission line online safety monitoring method based on quantum communication, the new Manchester code generation process includes:

[0023] The original signal is sampled at a fixed frequency and quantized to a discrete digital value.

[0024] According to the level value, high level is encoded as 10 and low level is encoded as 01.

[0025] Based on bit parity, check bits are inserted to generate an encoded signal with error detection capability.

[0026] As a preferred scheme of the power transmission line online safety monitoring method based on quantum communication provided by the application, wherein: the terahertz communication channel transmission comprises:

[0027] Check if the terahertz communication transmission rate reaches the set standard;

[0028] Convert the new Manchester code into the form of analog signal of terahertz channel transmission;

[0029] Achieve high-rate data transmission through amplitude and phase modulation.

[0030] As a preferred scheme of the power transmission line online safety monitoring method based on quantum communication provided by the application, wherein: the safety warning comprises:

[0031] The client uses the same quantum key to decrypt the ciphertext;

[0032] Restore the new Manchester code and restore the multi-parameter electric signal data and the operation state prediction value;

[0033] Trigger the alarm mechanism and store the monitoring data when the operation state prediction value exceeds the set threshold.

[0034] In a second aspect, the embodiments of the application provide a power transmission line online safety monitoring system based on quantum communication, which comprises a parameter acquisition module, which is used for synchronously acquiring multi-parameter electric signal data of the power transmission line through a multi-modal fusion sensor and performing quantum encryption instantaneous recording on the multi-parameter electric signal data;

[0035] A signal cloud processing module is used for extracting the multi-parameter electric signal data based on the quantum encryption instantaneous recording, and predicting the operation state of the power transmission line through a deep learning self-adaptive Kalman filtering algorithm combined with a neural network;

[0036] A data cloud encryption communication module is used for generating a new Manchester code according to the multi-parameter electric signal data and the operation state prediction value, and performing encryption to generate a ciphertext by using quantum key distribution;

[0037] A safety transmission module is used for transmitting the ciphertext to a client based on a terahertz communication channel, restoring data by quantum key decryption, and performing safety warning.

[0038] In a third aspect, the embodiments of the application provide a computer device, which comprises a memory and a processor, and the memory stores a computer program, wherein: the computer program instructions are executed by the processor to realize the steps of the power transmission line online safety monitoring method based on quantum communication provided by the first aspect of the application.

[0039] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium having stored thereon a computer program, wherein the computer program instructs a processor to implement the steps of the power transmission line online security monitoring method based on quantum communication as described in the first aspect of the present application.

[0040] The present application has the following beneficial effects: The present application synchronously collects multi-parameter electric signal data such as current, voltage, and temperature through a multi-modal fusion sensor, breaks through the limitation of incomplete monitoring information of a traditional single sensor, realizes comprehensive perception of the operating state of a power transmission line, provides a rich data basis for subsequent intelligent analysis, and thus significantly improves the comprehensiveness and accuracy of the monitoring system. The collected data is encrypted through quantum encryption instantaneous recording technology, a theoretically unbreakable security protection mechanism is constructed by using the uncertainty and unclonable characteristics of quantum states, the security risks of data being easily stolen and tampered with in the traditional monitoring system are solved, and the effect of absolute security guarantee in the data collection stage is achieved. An intelligent prediction model is established by combining a deep learning self-adaptive Kalman filtering algorithm with a neural network, the nonlinear modeling capability of deep learning and the optimal estimation characteristics of Kalman filtering are fused, the fundamental change from traditional passive monitoring to active early warning is realized, potential fault risks can be identified in advance, and the significant effect of preventive maintenance is achieved. An encoding signal with error detection and correction capability is generated through the new Manchester encoding technology, and secondary encryption is performed in combination with quantum key distribution, the security protection of the data in the whole life cycle is realized while the reliability of data transmission is ensured, the problem of insufficient anti-interference capability of the traditional encoding technology is solved, and the dual protection effects of security and reliability in the data transmission process are achieved. High-speed data transmission is performed through a terahertz communication channel, the super-large bandwidth and strong directivity characteristics of the terahertz frequency band are used, real-time transmission of large-capacity data and natural secure communication are realized, the bandwidth limitation and delay problem of the traditional communication mode are broken through, and the communication effects of high efficiency, low delay, and high security are achieved. The whole technical scheme realizes the organic fusion of quantum communication, terahertz transmission, intelligent prediction, and other frontier technologies, and constructs a complete closed-loop system from data collection to security early warning, which solves the core problem of difficult data security guarantee in the prior art. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0042] Figure 1 The flowchart of the power transmission line online security monitoring method based on quantum communication;

[0043] Figure 2 A flowchart of a computer device for a power transmission line online safety monitoring method based on quantum communication;

[0044] Figure 3 Another flowchart of a power transmission line online safety monitoring method based on quantum communication. DETAILED DESCRIPTION

[0045] In order to make the above objectives, characteristics and advantages of the present application more apparent, specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0046] In the following description, a large number of specific details are set forth in order to facilitate a thorough understanding of the present application, but the present application can also be implemented in other ways different from the description, and those skilled in the art can make similar extensions without departing from the concept of the present application, so the present application is not limited to the specific embodiments disclosed below.

[0047] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. "In one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an embodiment that is separate or selectively excluded from other embodiments.

[0048] Embodiment 1

[0049] Reference Figure 1-Figure 2 For the first embodiment of the present application, the embodiment provides a power transmission line online safety monitoring method based on quantum communication, comprising,

[0050] S100: synchronously collecting multi-parameter electric signal data of the power transmission line by a multi-modal fusion sensor, and performing quantum encryption instantaneous recording on the multi-parameter electric signal data;

[0051] S200: extracting the multi-parameter electric signal data based on the quantum encryption instantaneous recording, and predicting the operation state of the power transmission line by a deep learning self-adaptive Kalman filtering algorithm combined with a neural network;

[0052] S300: generating a new Manchester code according to the multi-parameter electric signal data and the operation state prediction value, and performing encryption to generate ciphertext by quantum key distribution;

[0053] S400: transmitting the ciphertext to a client based on a terahertz communication channel, recovering the data by quantum key decryption, and performing safety warning.

[0054] Traditional transmission line monitoring systems face multiple technical challenges in actual operation. First, in the data acquisition link, existing sensors are mostly single type, which cannot synchronously acquire multi-parameter data such as current, voltage and temperature, resulting in incomplete monitoring information and difficulty in fully reflecting the operation state of the transmission line. Second, in terms of data security, traditional monitoring systems use plaintext transmission or simple encryption methods, and data is easily intercepted and tampered with during transmission, seriously threatening the information security of the power grid. Third, in terms of data processing, existing algorithms are mostly static analysis mode, lacking dynamic prediction ability of the operation state of the transmission line, and unable to identify potential fault risks in advance. Fourth, in terms of communication transmission, the traditional communication method has limited bandwidth and high delay, which is difficult to meet the demand of large capacity and real-time data transmission. Finally, in terms of system integration, there is a lack of effective coordination mechanism between various subsystems, and the data flow efficiency is low, affecting the overall monitoring effect.

[0055] The transmission line online safety monitoring method based on quantum communication according to claim 1 of the present application solves the above technical problems by constructing a complete intelligent monitoring system through four core technical steps. The method first realizes the synchronous acquisition of multi-parameter electric signal data of the transmission line through a multi-modal fusion sensor, and uses quantum encryption instantaneous recording technology to ensure the security of the data acquisition stage, and uses the uncertainty and unclonable characteristics of quantum states to provide theoretically unbreakable security for the data. Then, through the deep learning self-adaptive Kalman filtering algorithm combined with neural network, the collected data is intelligently analyzed to accurately predict the operation state of the transmission line, and the passive monitoring is changed to active early warning. Then, the data and prediction results are encoded by using the new Manchester coding technology, and are encrypted twice by using the quantum key distribution technology to form ciphertext, realizing the security protection of the whole life cycle of the data. Finally, through the terahertz communication channel, the data is transmitted at high speed and safety, and the client restores the original data by quantum key decryption, realizing real-time safety warning. The whole technical scheme forms a closed-loop system from data acquisition, security encryption, intelligent processing, safe transmission to early warning response, and comprehensively improves the safety, accuracy and real-time performance of the transmission line monitoring.

[0056] Embodiment 2

[0057] Reference Figure 1-Figure 3 The second embodiment of the present application.

[0058] In the embodiment of the present application, the multi-modal fusion sensor is used to synchronously acquire the multi-parameter electric signal data of the transmission line in step S100, and the multi-parameter electric signal data is recorded by quantum encryption instantaneous recording, including the following steps A1-A2:

[0059] A1: The multi-modal fusion sensor includes a current sensing unit, a voltage sensing unit and a temperature sensing unit.

[0060] The multi-parameter electric signal data includes real-time monitoring data of current value, voltage value and temperature value.

[0061] The current sensing unit is used to accurately obtain the current value by measuring the voltage change of the Hall element in the magnetic field. Assuming that the current through the Hall element is I, the magnetic field strength is B, and the sensitivity of the Hall element is K, the Hall voltage is: V = K*I*B. By measuring V, the current value in the line is calculated. H H The current value in the line is calculated.

[0062] The voltage sensing unit is used to convert high voltage into low voltage allowed to be measured according to a set proportion. Assuming that the voltage sensing unit is composed of a voltage divider resistor R1 and a voltage divider resistor R2 connected in series, the input voltage is V in , and the output voltage is V out , the output voltage acquisition formula is:

[0063]

[0064] The temperature sensing unit is used to calculate the temperature by measuring the resistance value R T . According to the resistance-temperature characteristic curve of the thermistor, the resistance value R T is measured, and the temperature T r is calculated by using the following formula:

[0065]

[0066] wherein Q is the material constant of the thermistor, R0 is the resistance value at temperature T0, and R T is the resistance value at temperature T.

[0067] Specifically, the current sensing unit adopts Hall effect sensor technology, and accurately obtains the current value by measuring the voltage change of the Hall element in the magnetic field. When the current passes through the conductor, a magnetic field is generated around the conductor, and the Hall sensor detects the change of the magnetic field strength and converts it into a corresponding voltage signal. The Hall voltage is proportional to the current passing through the conductor, and the actual current value in the line can be accurately calculated through calibration. The sensor has the advantages of non-contact measurement, fast response speed, high precision, etc., and can realize real-time continuous monitoring of the current of the power transmission line.

[0068] ​The voltage sensing unit adopts a resistance voltage division principle. A high-precision voltage division resistor network converts high voltage into a low voltage signal suitable for measurement according to a set ratio. The voltage division resistor uses a high-stability, low-temperature-coefficient precision resistor to ensure that the voltage division ratio remains stable under various environmental conditions. The output voltage signal is filtered and amplified by a signal conditioning circuit to eliminate noise interference and improve measurement accuracy. The unit is also equipped with an overvoltage protection circuit that automatically disconnects the measurement circuit when the input voltage exceeds the safe range, protecting the subsequent circuit.

[0069] The temperature sensing unit uses high-precision thermistor technology to measure temperature by utilizing the characteristic that the resistance of a thermistor changes with temperature. The thermistor is of the NTC (Negative Temperature Coefficient) type, whose resistance changes exponentially with temperature, with high sensitivity and fast response. The temperature measurement circuit uses a constant current source driving method to calculate the temperature value by measuring the voltage across the thermistor. To improve measurement accuracy, the system is also equipped with a reference temperature compensation circuit to automatically correct the influence of ambient temperature on the measurement results.

[0070] In an alternative embodiment, the multi-modal fusion sensor can also include a vibration sensor and a humidity sensor for monitoring the mechanical vibration state of the transmission line and the change of environmental humidity. The vibration sensor uses a piezoelectric accelerometer that can detect the vibration frequency and amplitude of the transmission conductor under the action of wind load and electromagnetic force, providing data support for the fatigue life assessment of the transmission line. The humidity sensor uses a capacitive humidity sensitive element to monitor the influence of environmental humidity change on insulation performance.

[0071] In another alternative embodiment, the sensor data acquisition system is also equipped with a GPS clock synchronization module to ensure that the data acquisition timestamps of each sensor remain highly accurate and synchronized. The GPS module receives satellite clock signals to provide the system with a nanosecond-level time reference, ensuring accurate alignment of multi-channel sensor data in the time dimension and providing a reliable time basis for subsequent data fusion analysis.

[0072] It should be noted that the design of the multi-modal fusion sensor adopts a modular structure, and each sensing unit can be flexibly configured according to actual monitoring needs. The sensor housing adopts an IP67 protection level design, with good waterproof and dustproof performance, capable of working stably in harsh outdoor environments for a long time. The sensor is also equipped with a self-diagnosis function that can monitor its working state in real time and report alarm information in a timely manner when a fault occurs.

[0073] A2: Quantum encryption instantaneous recording includes:

[0074] Generating a sequence of quantum bits by a quantum random number generator, the quantum bits being in different quantum states;

[0075] The sequence of quantum bits is sent to a cloud platform and measured using a random measurement basis;

[0076] The eavesdropping phenomenon is detected by measurement basis consistency, and the data is encrypted and stored using a quantum encryption key.

[0077] Specifically, the quantum random number generator uses quantum optical noise source technology to generate a truly random number sequence using the quantum noise of a laser or the dark count of a single-photon detector. Based on the basic principles of quantum mechanics, the random numbers generated have unpredictability and irreproducibility, providing a theoretically absolutely secure random source for quantum key generation. Each bit in the quantum bit sequence carries specific quantum state information, including polarization state, phase state, or spin state, etc., which forms the basis of quantum key distribution.

[0078] The generation process of quantum bits uses a polarization encoding scheme to encode quantum information by controlling the polarization direction of the photons output by the laser. The system uses four polarization states: horizontal polarization (0°), vertical polarization (90°), 45° polarization, and 135° polarization, corresponding to binary 00, 01, 10, and 11 states, respectively. The polarization state of the photon has quantum superposition characteristics and is in a superposition state of multiple states before being measured, and only collapses to a certain eigenstate when measured.

[0079] The selection of the measurement basis uses a randomization strategy, with the sending end and the receiving end independently selecting the measurement basis randomly. The measurement basis includes straight-line polarization measurement bases (0° / 90°) and diagonal polarization measurement bases (45° / 135°). When the sending end and the receiving end use the same measurement basis, the measurement results have complete correlation; when different measurement bases are used, the measurement results are completely random. This randomness of the measurement basis is an important guarantee for the security of quantum key distribution.

[0080] The eavesdropping detection mechanism is based on the quantum no-cloning theorem, and any eavesdropping on the quantum state will inevitably change the statistical properties of the quantum state. The system compares the measurement results of the sending end and the receiving end under the same measurement basis and calculates the quantum bit error rate (QBER). When the QBER exceeds the theoretical threshold, it indicates that there is eavesdropping behavior in the transmission process, and the system will immediately terminate the current key distribution process and issue a security alert. Under normal circumstances, the QBER should be below the theoretical safety threshold of 11%.

[0081] In an alternative embodiment, quantum key distribution can also use a phase encoding scheme to encode quantum information by controlling the phase of the optical pulse. The phase encoding scheme has better stability in the optical fiber transmission environment, which can reduce the impact of polarization disturbance on system performance. The system uses a Mach-Zehnder interferometer structure to control the phase difference of the optical pulse through a phase modulator to achieve encoding of 0, π / 2, π, and 3π / 2 phase states.

[0082] In another alternative embodiment, the system can also integrate a quantum key pool management mechanism, pre-generate and store a large number of quantum keys, and dynamically allocate and use them according to the data transmission requirements. The quantum key pool adopts a hierarchical management strategy, including three levels of master key, session key and data key, and realizes the secure conversion between different levels of keys through key derivation algorithm.

[0083] It should be noted that the core advantage of quantum encryption instantaneous recording technology lies in its security guarantee based on physical laws. Unlike traditional mathematical encryption algorithms, the security of quantum encryption is based on the basic principles of quantum mechanics, and does not rely on computational complexity assumptions, which is theoretically unconditionally secure. At the same time, the quantum encryption process has the characteristics of instantaneousness, and the key generation and distribution can be completed within milliseconds, meeting the response requirements of real-time monitoring systems.

[0084] In the embodiments of the present application, the multi-parameter electric signal data is extracted based on quantum encryption instantaneous recording in step S200, and the power line operation state is predicted by combining deep learning adaptive Kalman filtering algorithm with neural network, including the following steps B1:

[0085] B1: The deep learning adaptive Kalman filtering algorithm includes:

[0086] A state prediction model based on neural network is established, and the current multi-parameter electric signal data is inputted;

[0087] State estimation is performed through Kalman filtering prediction equation and updating equation;

[0088] The neural network parameters are optimized by minimizing the mean square error to realize accurate prediction of the operation state.

[0089] Specifically, the neural network state prediction model adopts a deep feedforward network structure, including an input layer, multiple hidden layers and an output layer. The number of nodes in the input layer is equal to the dimension of the multi-parameter electric signal data, including real-time values and historical sequences of parameters such as current, voltage and temperature. The hidden layer adopts a multi-layer structure design, the first hidden layer contains 128 neurons, the second hidden layer contains 64 neurons, and the third hidden layer contains 32 neurons, and each layer is connected through full connection. The activation function adopts ReLU function, which has the advantages of simple calculation and fast convergence. The output layer contains the predicted power line operation state parameters, such as load rate, temperature rise trend and fault probability.

[0090] The input data preprocessing of neural network includes three steps: normalization, denoising and feature extraction. The normalization process maps the different dimensional electrical signal data to the interval [0, 1], eliminating the influence of data dimension on network training. The denoising process uses wavelet transform technology to decompose the signal into different frequency domains, filter out high-frequency noise components, and retain useful signal features. The feature extraction uses principal component analysis (PCA) method to extract the main feature components from high-dimensional original data, reduce the data dimension, and improve the network training efficiency.

[0091] The Kalman filter prediction equation establishes the dynamic evolution model of the system state. The system state vector includes the current values and change rates of current, voltage and temperature, and the state transition matrix describes the linear relationship between the state quantities. The prediction equation is:

[0092]

[0093] where, is the prediction value of the transmission line operating state at time k based on the multi-parameter electrical signal data at time k-1, A is the state transition matrix, and for a simple linear system, the state transition matrix can be expressed as:

[0094]

[0095] Here Δt is the sampling time interval, and this matrix represents the linear change relationship of the multi-parameter electrical signal data between adjacent sampling time points.

[0096] is the optimal estimation value of the transmission line operating state at time k-1, D is the control matrix, and u k-1 is the external control input at time k-1;

[0097] The prediction value of the transmission line operating state at time k is updated as follows:

[0098]

[0099] where, K k is the Kalman gain, Z k is the measurement value of the multi-parameter electrical signal data at time k, H is the observation matrix, for example, when only the current and voltage can be directly observed, the observation matrix is:

[0100]

[0101] which means only the current and voltage parts of the state vector are observed.

[0102] The neural network parameters θ are optimized by minimizing the mean square error;

[0103] The method for obtaining the mean square error is:

[0104]

[0105] where L is the mean square error, k is the time index, and N is the number of samples of the multi-parameter telecommunication signal data;

[0106] The optimization formula of the neural network parameter θ is:

[0107]

[0108] where θ m+1 is the neural network parameter of the m+1th iteration, θ m is the neural network parameter of the mth iteration, and α is the learning rate, is the gradient of the mean square error L with respect to the neural network parameter θ at θ m ;

[0109] The neural network parameter θ in f(X k , θ) is updated to θ m+1 .

[0110] The adaptive mechanism dynamically adjusts the network parameters through an online learning strategy, enabling the model to adapt to changes in the operating state of the power transmission line. When a new operating mode or abnormal mode is detected, the system triggers the model update mechanism, retraining the network parameters using the latest data to maintain the prediction accuracy of the model.

[0111] In an alternative embodiment, the neural network model can also adopt a long short-term memory (LSTM) structure to better handle the long-term dependencies of time series data. The LSTM network contains three control gates: a forget gate, an input gate, and an output gate, which can selectively remember and forget historical information, and has significant advantages in handling the dynamic characteristics of power systems.

[0112] In another alternative embodiment, an ensemble learning method can be used to combine multiple neural network models with different structures to obtain the final prediction result through voting or weighted averaging. Ensemble learning can reduce the overfitting risk of a single model and improve the stability and reliability of the prediction.

[0113] It should be noted that the core advantage of the deep learning adaptive Kalman filter algorithm is the combination of the nonlinear modeling capability of deep learning and the optimal estimation characteristics of Kalman filtering. Deep learning can automatically learn complex nonlinear relationships from data, while Kalman filtering can effectively handle system noise and observation noise. The combination of the two achieves accurate prediction of the operating state of the power transmission line. At the same time, the adaptive mechanism enables the model to automatically adjust as the operating environment changes, maintaining long-term prediction accuracy.

[0114] In the embodiment of the present application, the new Manchester code is generated according to the multi-parameter electric signal data and the operating state prediction value in step S300, and the ciphertext is generated by encryption using quantum key distribution, including the following steps C1:

[0115] C1: The new Manchester code generation process includes:

[0116] The original signal is sampled at a fixed frequency and quantized into discrete digital values;

[0117] According to the level value, the high level is encoded as 10, and the low level is encoded as 01;

[0118] Based on the bit parity, check bits are inserted to generate an encoded signal with error detection capability.

[0119] Specifically, the original signal sampling process uses a high-precision analog-to-digital converter (ADC), and the sampling frequency is set to 2.5 times the highest frequency of the signal, ensuring that the Nyquist sampling theorem is met. For a power line monitoring system, the main signal frequency range of interest is 0-1 kHz, so the sampling frequency is set to 2.5 kHz. The ADC uses 16-bit resolution, which can provide 65536 quantization levels, ensuring the accuracy of signal quantization.

[0120] The signal quantization process converts continuous analog signals into discrete digital values. The quantizer uses uniform quantization, which equally divides the signal amplitude range into 2^16 quantization intervals, and the amplitude value of each sampling point is mapped to the nearest quantization level. To reduce the impact of quantization noise, the system also uses sampling and digital filtering techniques to improve the signal-to-noise ratio by increasing the sampling frequency and subsequent digital filtering.

[0121] The combination rule of digital values is designed according to the requirements of transmission efficiency and error detection capability. The system combines every 8 quantization bits into a symbol, forming 256 possible symbol states. The length of the symbol needs to be balanced between transmission efficiency and error detection capability. An 8-bit symbol length can ensure sufficient data capacity and provide effective error detection capability.

[0122] The level value is determined based on the statistical properties of the digital values within the symbol. The system calculates the weighted average of all bits within the symbol. When the average value is greater than the threshold, it is judged as a high level and encoded as "10"; when the average value is less than the threshold, it is judged as a low level and encoded as "01". The threshold is set using an adaptive method, which dynamically adjusts according to the statistical distribution of historical data to adapt to different signal characteristics and noise environments.

[0123] Parity bits are inserted using a combination of parity and cyclic redundancy checking (CRC). First, a parity check is performed on the data bits within a symbol. The number of "1s" in the data bits is counted. If the number is odd, a parity bit of "1" is inserted; if the number is even, a parity bit of "0" is inserted. A CRC calculation is then performed on the entire symbol (including the data bits and parity bits) to generate a 4-bit CRC code, which is appended to the end of the symbol.

[0124] The CRC check uses the CRC-4 standard, with the generating polynomial x^4+x+1. This check can detect all single-bit errors, all double-bit errors, and all odd-numbered errors, as well as most burst errors. The CRC calculation is implemented in hardware using a linear feedback shift register to ensure real-time checksum calculations.

[0125] In an optional implementation, New Manchester encoding can also employ differential encoding, which improves noise immunity by encoding the differences between adjacent bits rather than their absolute values. Differential encoding offers improved immunity to phase jitter and frequency offset, making it particularly suitable for wireless transmission environments.

[0126] In the embodiment of the present application, step S400 transmits the ciphertext to the client based on the terahertz communication channel, decrypts the data using the quantum key and issues a security warning, including the following steps D1-D2:

[0127] D1: Terahertz communication channel transmission includes:

[0128] Check whether the terahertz communication transmission rate meets the set standard;

[0129] Converting the New Manchester code into analog signal form for terahertz channel transmission;

[0130] High-speed data transmission is achieved through amplitude and phase modulation.

[0131] For the terahertz communication channel between the cloud platform and the client, check whether the transmission rate of the terahertz communication meets the set standard. If it does, use the terahertz communication channel. If it does not, notify the staff to adjust the signal bandwidth and signal-to-noise ratio.

[0132] The specific formula for calculating the transmission rate of terahertz communication is:

[0133] R THz =B THz log2(1+SNR THz )

[0134] Among them, R THz is the transmission rate of terahertz communication, and the signal bandwidth is B THz, signal-to-noise ratio is SNR THz .

[0135] Further, the ciphertext is sent to the client based on the terahertz communication channel, specifically:

[0136] The new Manchester code is converted into an analog signal form transmitted in the terahertz communication channel, and the new Manchester code is mapped to different amplitude and phase combinations, and the modulated signal is s(t):

[0137]

[0138] where p represents the position of the signal in the time sequence, p is an integer, e is the natural constant, π is the circular constant, j is the imaginary unit, , represents the phase of the pth modulated signal, g(…) is the pulse shaping function, t represents the continuous time variable number, T is the interval of adjacent two modulated signals in time, i.e. symbol period;

[0139] The modulated signal is transmitted to the client through the terahertz communication channel.

[0140] Specifically, the terahertz communication system works in the 0.1-10THz frequency band, has abundant spectrum resources and extremely high transmission rate potential. The system uses a 340GHz carrier frequency, which has a relatively low attenuation in the atmospheric window and is suitable for short-distance high-speed communication applications. The generation of terahertz signal adopts photon mixing technology, which generates beat frequency signal through two lasers with different frequencies, and the difference frequency of the beat frequency is exactly in the terahertz frequency band.

[0141] The transmission rate checking mechanism is based on the Shannon channel capacity theorem, which monitors the signal-to-noise ratio and bandwidth of the channel in real time and calculates the theoretical transmission rate upper limit. The system sets the standard transmission rate to 10Gbps, and when the actual transmission rate is lower than 80% of the standard value, the system will trigger the channel optimization mechanism to adjust the transmission power, modulation method or switch to the standby channel. The monitoring of transmission rate uses two indicators of bit error rate and delay time, and the channel quality is evaluated by periodically sending test frames.

[0142] The signal conversion process converts the digital encoded new Manchester code stream into an analog signal suitable for terahertz transmission. The conversion process includes three steps of digital up-conversion, pulse shaping and power amplification. Digital up-conversion moves the baseband signal to an intermediate frequency, pulse shaping uses a root-raised cosine filter to reduce intersymbol interference, and power amplification raises the signal power to a level sufficient to penetrate the atmosphere for propagation.

[0143] The modulation mode adopts quadrature amplitude modulation (16-QAM), and the amplitude and phase of the carrier are modulated, and each symbol can carry 4 bits of information, effectively improving the spectrum utilization. The 16-QAM modulation mode has 16 constellation points on the complex plane, and each constellation point corresponds to a combination of 4 bits of data. The design of the constellation diagram adopts Gray code mapping, and there is only 1 bit difference between adjacent constellation points, which reduces the influence of error rate on system performance.

[0144] The amplitude modulation part transmits information by controlling the envelope amplitude of the carrier signal, and adopts linear modulation to ensure the fidelity of the signal. The phase modulation part transmits information by controlling the phase of the carrier signal, and the phase modulation is not sensitive to amplitude noise and has better noise immunity. The combination of the two modulation modes makes the system have good anti-interference ability while maintaining high transmission rate.

[0145] The transmission of terahertz signals adopts a horn antenna, which has high gain and strong directivity. The design frequency of the antenna is 340GHz, the gain reaches 40dBi, and the half-power beam width is 1.5 degrees. The high-gain antenna can concentrate the transmission power and improve the propagation distance of the signal; the strong directivity can reduce multipath propagation and interference and improve the communication quality.

[0146] In an alternative embodiment, terahertz communication can also use multiple-input multiple-output (MIMO) technology to transmit and receive signals through multiple antennas, and use spatial diversity to improve transmission rate and reliability. MIMO technology can significantly improve system capacity without increasing bandwidth and transmission power.

[0147] In another alternative embodiment, the system can also use adaptive beamforming technology to dynamically adjust the direction and shape of the transmission beam according to the channel conditions and the position of the receiving end, optimize the received power and signal-to-noise ratio of the signal, and improve the communication quality.

[0148] It should be noted that the advantage of terahertz communication technology is its ultra-large bandwidth and ultra-high transmission rate, which can meet the demand of large-capacity data transmission of the power line monitoring system. At the same time, the strong directivity and low power density characteristics of terahertz signals make them have good confidentiality and low interference characteristics, which are suitable for secure communication applications of power systems.

[0149] D2: The security warning includes:

[0150] The client decrypts the ciphertext using the same quantum key;

[0151] Restore the new Manchester code and restore the multi-parameter telecommunication signal data and the operating state prediction value;

[0152] Trigger the alarm mechanism and store the monitoring data when the operating state prediction value exceeds the set threshold.

[0153] Specifically, the quantum key management system of the client maintains strict synchronization with the sending end, ensuring that the decryption process uses the correct key. The key synchronization mechanism uses both time stamps and sequence numbers for double identification, and each data packet is accompanied by time stamp and key sequence number information. The client selects the corresponding decryption key from the key pool based on this information. The storage of the key uses a hardware security module (HSM) to provide tamper-proof key protection.

[0154] The decryption process uses a stream cipher algorithm to recover the original data by performing an XOR operation between the ciphertext data stream and the key stream. The decryption algorithm is completely symmetrical with the encryption algorithm, ensuring the correctness and efficiency of the decryption. The decryption process also includes integrity verification, which verifies whether the data has been tampered with during transmission through a message authentication code (MAC).

[0155] The decoding process of the new Manchester encoding first performs error detection and correction. The decoder detects transmission errors based on the check bit information and automatically corrects correctable errors. For uncorrectable errors, it requests retransmission. The decoding process uses a soft decision decoding algorithm to improve decoding performance using the amplitude information of the received signal.

[0156] The data recovery process reorganizes the decoded digital signal into the original multi-parameter telecommunication signal data format. The recovery process includes three steps: symbol reorganization, data rearrangement, and format conversion. Symbol reorganization reorganizes the received bit stream into the original symbol structure, data rearrangement restores the time sequence relationship of the data based on the timestamp information of the original data, and format conversion converts binary data into corresponding physical quantity values.

[0157] The extraction of the running state prediction value separates the prediction result information from the recovered data. The prediction value includes multiple dimensions of information such as load prediction, temperature prediction, and fault probability prediction. Each prediction value is accompanied by confidence information indicating the reliability of the prediction result. The calculation of the confidence is based on the historical accuracy of the prediction model and the quality of the current input data.

[0158] The alarm mechanism uses a multi-level threshold design to trigger different levels of alarms according to the severity of the running state prediction value. Level one alarm corresponds to a slight anomaly, with a threshold set at 1.2 times the normal value; level two alarm corresponds to a moderate anomaly, with a threshold set at 1.5 times the normal value; and level three alarm corresponds to a serious anomaly, with a threshold set at 2 times the normal value. Different levels of alarms correspond to different response measures and notification ranges.

[0159] After the alarm is triggered, the system will automatically execute a series of predefined response actions. First, the system will perform a secondary confirmation to verify the effectiveness of the alarm through historical data analysis and multi-sensor data fusion to avoid false alarms. After confirming the effectiveness, the system will send alarm notifications to relevant personnel, including SMS, email, and system interface pop-up windows, among other methods.

[0160] The data storage adopts a distributed storage architecture, storing monitoring data and prediction results in multiple geographically dispersed data centers. The storage system adopts RAID technology and data backup strategies to ensure data security and reliability. The data is organized in time series, supporting fast historical data query and analysis.

[0161] The stored data includes raw sensor data, preprocessed data, prediction results, alarm records, and other types. Each type of data has a corresponding retention period and compression strategy, with raw data saved for 1 year, prediction results saved for 5 years, and alarm records saved permanently. Data compression uses lossless compression algorithms to reduce storage space while ensuring data integrity.

[0162] In an alternative embodiment, the safety warning system can also integrate artificial intelligence assisted decision-making function, through machine learning algorithm analysis historical alarm data and processing results, automatic optimization of alarm threshold and response strategy, improve the intelligent level of the warning system.

[0163] In another alternative embodiment, the system can also provide mobile application, operation and maintenance personnel can view monitoring data and alarm information in real time through mobile phone or tablet computer, realize mobile operation and maintenance. The mobile application has data visualization, historical trend analysis, alarm confirmation and other functions.

[0164] It should be noted that the design of the safety warning system fully considers the actual needs of power system operation and maintenance. The power system has very high requirements for safety and reliability, and any failure can cause large-scale power outages and huge economic losses. Therefore, the warning system adopts multiple protection mechanisms, including data redundancy, algorithm redundancy, communication redundancy, etc., to ensure normal operation under various abnormal conditions. At the same time, the system also has self-learning and self-optimization capabilities, which can continuously improve the prediction accuracy and warning effect based on operational experience.

[0165] In summary, the present application combines quantum communication technology, terahertz communication technology, deep learning algorithm and new Manchester coding technology to build a complete online safety monitoring system for power transmission lines. This system not only solves the shortcomings of traditional monitoring systems in data security, transmission efficiency and prediction accuracy, but also provides a new technical path for the intelligent operation and maintenance of power systems. Through the coordinated work of multi-modal sensors, the security protection of quantum encryption, the accurate prediction of intelligent algorithms and the real-time transmission of high-speed communication, the running state of the power transmission line is monitored comprehensively, all-weather and high-precision, providing strong technical support for the safe and stable operation of the power system.

[0166] Example 3

[0167] The above is a schematic scheme of a power transmission line online safety monitoring method based on quantum communication. It should be noted that the technical scheme of the power transmission line online safety monitoring system based on quantum communication belongs to the same concept as the technical scheme of the power transmission line online safety monitoring method based on quantum communication described above. The technical details of the power transmission line online safety monitoring system based on quantum communication in this embodiment are not described in detail, and can be referred to the description of the technical scheme of the power transmission line online safety monitoring method based on quantum communication described above.

[0168] The embodiment also provides a power transmission line online safety monitoring system based on quantum communication, comprising:

[0169] A parameter acquisition module is configured to synchronously acquire multi-parameter electrical signal data of the power transmission line through a multi-modal fusion sensor, and perform quantum encryption instantaneous recording on the multi-parameter electrical signal data.

[0170] A signal cloud processing module is configured to extract the multi-parameter electrical signal data based on the quantum encryption instantaneous recording, and predict the operation state of the power transmission line through a deep learning self-adaptive Kalman filtering algorithm combined with a neural network.

[0171] A data cloud encryption communication module is configured to generate a new Manchester code according to the multi-parameter electrical signal data and the operation state prediction value, and perform encryption to generate ciphertext by using quantum key distribution.

[0172] A secure transmission module is configured to transmit the ciphertext to a client based on a terahertz communication channel, recover the data by quantum key decryption, and perform a safety warning.

[0173] The embodiment also provides an electronic device suitable for the power transmission line online safety monitoring based on quantum communication, comprising a memory and a processor. The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions to implement the power transmission line online safety monitoring method based on quantum communication proposed in the above embodiment.

[0174] The embodiment also provides a storage medium having a computer program stored thereon. The program is executed by a processor to implement the power transmission line online safety monitoring method based on quantum communication proposed in the above embodiment.

[0175] The storage medium proposed in the embodiment belongs to the same inventive concept as the power transmission line online safety monitoring method based on quantum communication proposed in the above embodiment. The technical details not described in detail in the embodiment can be referred to the above embodiment, and the embodiment has the same beneficial effects as the above embodiment.

[0176] Those skilled in the art can clearly understand the present application by the above description of the embodiments, and the present application can be realized by software and necessary general hardware, and of course, can also be realized by hardware. Based on such understanding, the technical solutions of the present application or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a floppy disk, a read-only memory (ROM), a random access memory (RAM), a FLASH, a hard disk, or an optical disc, and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods of various embodiments of the present application.

[0177] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application but not limit the present application, and although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and all should be covered in the scope of the claims of the present application.

Claims

1. A method for online safety monitoring of power transmission lines based on quantum communication, characterized by: The method comprises synchronously collecting multi-parameter electrical signal data of a power transmission line through a multi-modal fusion sensor, and performing quantum encryption instantaneous recording on the multi-parameter electrical signal data; Extract multi-parameter electrical signal data based on quantum encryption instantaneous records, and predict the operating status of transmission lines through deep learning adaptive Kalman filtering algorithm combined with neural network; Generate new Manchester code based on multi-parameter electrical signal data and operating status prediction values, and use quantum key distribution to encrypt and generate ciphertext; The ciphertext is transmitted to the client based on the terahertz communication channel, and the data is recovered through quantum key decryption and a security warning is issued.

2. The method for online security monitoring of power transmission lines based on quantum communication according to claim 1, characterized in that: The multimodal fusion sensor includes: a current sensing unit, a voltage sensing unit, and a temperature sensing unit; The multi-parameter electrical signal data includes real-time monitoring data of current value, voltage value and temperature value.

3. The method for online security monitoring of power transmission lines based on quantum communication according to claim 2, characterized in that: The quantum encryption instantaneous record includes: A quantum random number generator is used to generate a sequence of quantum bits, where the quantum bits are in different quantum states; Send the qubit sequence to the cloud platform and measure it using a random measurement basis; Eavesdropping is detected by measuring basis consistency, and data is encrypted and stored using quantum encryption keys.

4. The method for online security monitoring of power transmission lines based on quantum communication according to claim 3, characterized in that: The deep learning adaptive Kalman filter algorithm includes: Establish a state prediction model based on a neural network and input the multi-parameter electrical signal data at the current moment; State estimation is performed through Kalman filter prediction equation and update equation; The neural network parameters are optimized by minimizing the mean square error to achieve accurate prediction of the operating status.

5. The method for online security monitoring of power transmission lines based on quantum communication according to claim 4, characterized in that: The new Manchester code generation process includes: The original signal is sampled at a fixed frequency and quantized into discrete digital values; According to the level value, the high level is encoded as 10 and the low level is encoded as 01; A check bit is inserted based on bit parity to generate a coded signal with error detection capability.

6. The method for online security monitoring of power transmission lines based on quantum communication according to claim 5, characterized in that: The terahertz communication channel transmission includes: Check whether the terahertz communication transmission rate meets the set standard; Converting the New Manchester code into analog signal form for terahertz channel transmission; High-speed data transmission is achieved through amplitude and phase modulation.

7. The method for online security monitoring of power transmission lines based on quantum communication according to claim 6, characterized in that: The safety warning includes: The client decrypts the ciphertext using the same quantum key; Restore the New Manchester code and restore multi-parameter electrical signal data and operating status prediction values; When the predicted value of the operating status exceeds the set threshold, the alarm mechanism is triggered and the monitoring data is stored.

8. A transmission line online security monitoring system based on quantum communication, based on the transmission line online security monitoring method based on quantum communication according to any one of claims 1 to 7, characterized in that: The system also includes a parameter acquisition module for synchronously acquiring multi-parameter electrical signal data of the power transmission line through a multi-modal fusion sensor, and performing quantum encryption instantaneous recording on the multi-parameter electrical signal data; The signal cloud processing module is used to extract multi-parameter electrical signal data based on quantum encryption instantaneous records and predict the operating status of transmission lines through a deep learning adaptive Kalman filter algorithm combined with a neural network; The data cloud encryption communication module is used to generate the new Manchester code based on the multi-parameter electrical signal data and the operation status prediction value, and use quantum key distribution to encrypt and generate ciphertext; The secure transmission module is used to transmit ciphertext to the client based on the terahertz communication channel, recover data through quantum key decryption and issue security warnings.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for online safety monitoring of transmission lines based on quantum communication according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for online safety monitoring of transmission lines based on quantum communication according to any one of claims 1 to 7 are implemented.

Images