Power equipment state monitoring system based on Internet of Things

Abstract

The invention discloses a power equipment state monitoring system based on the Internet of Things, and relates to the technical field of wireless communication networks. Comprising a spectrum sensing module for detecting and identifying noise characteristics in electromagnetic signals through a quantum spectrum sensing array to obtain corresponding spectrum data and classification results; the dynamic evaluation module is used for screening out an available channel list through dynamic channel survivability and determining a corresponding channel from the available channel list for signal transmission according to a classification result of the SVW classifier; and the frequency hopping optimization module is used for determining a global optimal frequency hopping sequence through the available channel list and the total energy among different channels. Through the superconducting resonant cavity and the quantum compressed sensing algorithm, capture of microsecond transient noise is achieved, meanwhile, anti-interference channels are screened out in real time through dynamic channel survivability, the optimal channel combination is obtained, and channel switching is completed within 10 ms.

Description

Technical Field

[0001] The present invention relates to the technical field of wireless communication networks, and in particular to an Internet of Things-based power equipment status monitoring system. Background Art

[0002] With the growth of global energy demand and the continuous expansion of power grids, the complexity of power systems is increasing. Traditional power equipment monitoring methods can no longer meet the requirements of modern power grids for reliability and efficiency. Due to the lack of real-time monitoring methods, power equipment failures can often only be discovered after they occur, which not only leads to huge economic losses, but may also have serious impacts on society.

[0003] The Internet of Things (IoT) technology has developed rapidly in recent years, bringing revolutionary changes to all walks of life. By connecting physical devices to the Internet and using sensors, communication technologies and data analysis algorithms, real-time monitoring and control of various environmental parameters can be achieved. For the power industry, the application of the Internet of Things has opened up a new era of smart grids, making the status monitoring of power equipment more intelligent and efficient.

[0004] The Chinese invention patent with publication number CN109548032A discloses a distributed collaborative spectrum recognition method for full-band detection in dense networks. The process is as follows: S1: Group all frequency points to be detected, and each node is assigned to a group of frequency points to be detected, and ensure that all frequency points are fully allocated within the one-hop range of each node; S2: Each node performs energy detection on the assigned frequency points; S3: Obtain the interaction order of all nodes in the entire network; S4: According to the interaction order, the detected energy information is interactively shared; S5: The node that receives the shared information iterates it with the result of its last iteration until all nodes complete a sharing and finally reach a consistent convergence result, otherwise it returns to S3; S6: Each node compares the iteration result with the decision threshold to obtain the final frequency decision for the global frequency point. This method can effectively meet the needs of full-band detection in dense network scenarios, effectively reducing the perception delay while ensuring high detection accuracy.

[0005] When monitoring the status of power equipment using the above and similar detection methods, traditional wireless monitoring solutions mostly rely on static frequency band division (such as reserving 8 sub-channels in the 868MHz frequency band). However, in areas with dense power equipment (such as 500kV substations), there is a serious mismatch between the static spectrum allocation mechanism and dynamic electromagnetic interference. At the same time, the transient arc caused by the operation of the isolating switch in the substation can instantly excite 0.5MHz~5GHz wideband electromagnetic noise, and its equivalent isotropic radiated power (EIRP) jumps from -40dBm to +20dBm within 2μs, which will cause the target channel to be submerged in the noise floor. At the same time, due to the lack of dynamic perception of spectrum holes and fast frequency hopping (<10ms switching) capabilities, the channel signal-to-noise ratio (SNR) will deteriorate from 20dB to below 3dB, and the nodes will be forced to maintain communication in the blocked channel, which will cause the bit error rate (BER) to increase from 1e⁻ 6 It soars to 1e⁻², and the number of packet retransmissions exceeds the maximum threshold of the protocol stack (for example, the LoRa ADR mechanism is limited to 3 times), eventually triggering a link interruption. Summary of the invention

[0006] The purpose of the present invention is to provide an Internet of Things-based power equipment status monitoring system to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: a power equipment status monitoring system based on the Internet of Things, comprising:

[0008] The spectrum sensing module detects and identifies the noise characteristics in the electromagnetic signal through the quantum spectrum sensing array, and obtains the corresponding spectrum data and classification results, including:

[0009] S1: Through the constructed superconducting resonant cavity, the power amplification factor of the signal after passing through the resonant cavity is obtained, and the obtained transient arc noise power is amplified, specifically:

[0010]

[0011] in: is the amplified transient arc noise power, is the original transient arc noise power, is the power amplification factor of the signal after passing through the resonant cavity;

[0012] S2: using the amplified transient arc noise power as the input of the parameterized quantum circuit, obtaining a measurement matrix and an observation vector, and constructing an optimization problem, and obtaining a reconstructed signal according to the constraint conditions of the reconstructed signal;

[0013] S3: extracting quantum fingerprint features from the reconstructed signal, and combining the quantum fingerprint features with traditional features to obtain a three-dimensional feature vector, and training and testing the SVW classifier through the three-dimensional feature vector to obtain a classification result;

[0014] A dynamic evaluation module, which filters out a list of available channels through dynamic channel survival, and determines a corresponding channel from the list of available channels for signal transmission according to a classification result of the SVW classifier;

[0015] The frequency hopping optimization module determines a global optimal frequency hopping sequence through the available channel list and the total energy between different channels.

[0016] Furthermore, the reconstructed signal is obtained, including:

[0017] S2.1: Obtaining an observation vector: compressing the original signal through a superconducting resonant cavity and constructing a measurement matrix, and at the same time compressing the amplified transient arc noise power through the measurement matrix to obtain the observation vector;

[0018] S2.2: Obtaining a preliminary reconstructed signal: Based on the measurement matrix and the observation vector, an optimization problem is constructed, and the optimization problem is encoded into a quantum Hamiltonian to obtain a preliminary reconstructed signal, specifically:

[0019]

[0020] in: is the quantum Hamiltonian, is the i-th preliminary reconstructed signal, To initially reconstruct the index of the signal, is the low-dimensional observation signal, is the measurement matrix, is the regularization parameter, is the amplified transient arc noise power, To initially reconstruct the signal;

[0021] S2.3: Obtain the final reconstructed signal: According to the quantum bit resources, the preliminary reconstructed signal is divided into blocks and encoded into quantum states. At the same time, the loss function is minimized through the quantum state parameters in the quantum state to obtain the final reconstructed signal.

[0022] Furthermore, obtaining the observation vector includes:

[0023] S2.1.1: Obtaining the dimension of the compressed signal: compressing the original signal through the superconducting resonant cavity, obtaining the bandwidth compression ratio of the signal, and determining the dimension of the signal after compression by the superconducting resonant cavity according to the bandwidth compression ratio, specifically:

[0024]

[0025] in: is the dimension of the signal after compression by the superconducting resonant cavity, is the dimension of the original signal, is the bandwidth compression ratio;

[0026] Step SA2.1.2: Constructing a measurement matrix: Constructing a measurement matrix according to the dimension of the signal compressed by the superconducting resonant cavity and the dimension of the original signal, specifically:

[0027]

[0028] in: is the measurement matrix, is a complex field, is the dimension of the signal after compression by the superconducting resonant cavity, is the dimension of the original signal;

[0029] S2.1.3: Determine the observation vector: compress the amplified transient arc noise power through the measurement matrix to obtain the observation vector, which is specifically:

[0030]

[0031] in: is the low-dimensional observation signal, is the measurement matrix, is the amplified transient arc noise power, is the observation noise.

[0032] Furthermore, the final reconstructed signal is obtained, including:

[0033] S2.3.1: Obtaining quantum state parameters: The preliminary reconstructed signal is divided into blocks through quantum bit resources, and each sub-signal is mapped into a quantum state probability amplitude through amplitude coding, specifically:

[0034]

[0035] in: is the parameterized quantum state, is the quantum state parameter, is the jth component of the preliminary reconstructed signal, is the index of the component of the preliminary reconstructed signal, is the sum of the absolute values ​​of all signal components;

[0036] S2.3.2: Determine the final reconstructed signal: Update the quantum state parameters through the gradient descent method, and obtain the minimized loss function based on the updated quantum state parameters. The reconstructed signal corresponding to the minimized loss function is the final reconstructed signal.

[0037] Furthermore, the classification results are obtained, including:

[0038] S3.1: Extract quantum fingerprint features: Based on the frequency domain signal and coupling signal in the final reconstructed signal, construct the Hamiltonian and obtain the expected value of the quantum state under the Hamiltonian. At the same time, determine the size of the adjustable parameter based on the ground state energy.

[0039] S3.2: Classification decision: The ground state energy is combined with the traditional features to obtain a three-dimensional feature vector, and the three-dimensional feature vector is divided into a training set and a test set, and the SVW classifier is trained and tested. At the same time, the arc operation status is identified through the trained and tested SVW classifier.

[0040] Furthermore, the size of the adjustable parameters is determined, including:

[0041] S3.1.1: Construct Hamiltonian: Encode the frequency domain signal and coupling signal in the final reconstructed signal into the Hamiltonian of the quantum system, specifically:

[0042]

[0043] in: is the quantum Hamiltonian, is the total number of frequency components in the final reconstructed signal, is the energy of the gth frequency component of the final reconstructed signal, To generate the operator, is the annihilation operator, is the interaction strength between the gth frequency component and the oth frequency component of the final reconstructed signal, , is the index of the frequency component in the final reconstructed signal;

[0044] S3.1.2: Prepare variational quantum state: According to the Hamiltonian, obtain the expected value of the quantum state under the Hamiltonian, specifically:

[0045]

[0046] in: is the expected value of energy, is the parameterized quantum state, is the quantum Hamiltonian, is an adjustable parameter;

[0047] S3.1.3: Parameter optimization: Adjust and update the adjustable parameters by gradient descent method to obtain the ground state energy. The update formula of the adjustable parameters is as follows:

[0048]

[0049] in: is the adjustable parameter at the k+1th iteration, is the adjustable parameter at the kth iteration, is the learning rate, is the expected value of energy at the kth iteration About the adjustable parameters at the kth iteration gradient.

[0050] Furthermore, determining a corresponding channel for signal transmission includes:

[0051] SB1: Obtaining an available channel: The quantum entanglement entropy, electromagnetic field strength and vibration acceleration are integrated to obtain the dynamic channel survival degree, and the dynamic channel survival degree is compared with the preset survival degree, and a dynamic channel survival degree not less than the preset survival degree is determined, and the dynamic channel survival degree not less than the preset survival degree is an available channel. The dynamic channel survival degree is obtained by the formula as follows:

[0052]

[0053] in: is the channel survivability, is the normalization constant, is the quantum entanglement entropy, is the threshold entropy, is the regulating factor;

[0054] SB2: Select channel: According to the available channel and the classification result of the SVW classifier, the channel of the normal arc is set as the regular channel, and the channel of the fault arc is set as the available channel.

[0055] Furthermore, the dynamic channel survivability is optimized, including:

[0056] SB1.1: Obtain electromagnetic-vibration coupling factor: Use the historical interference power density, electromagnetic field intensity time series data and vibration acceleration time series data as the input of the LSTM model, output the interference power density prediction value at the preset time, and obtain the electromagnetic-vibration coupling factor, specifically:

[0057]

[0058] in: is the electromagnetic-vibration coupling factor, is the instantaneous amplitude of the electromagnetic field, is the root mean square of mechanical vibration acceleration, is the integration time window of interference power density;

[0059] SB1.2: Adjust dynamic weight: compare the electromagnetic-vibration coupling factor with the preset coupling factor, and adjust the weight of quantum entanglement entropy according to the comparison result, specifically:

[0060] When the electromagnetic-vibration coupling factor is greater than the preset coupling factor, the weight of the quantum entanglement entropy is increased through the weight constraint formula, otherwise, the weight of the quantum entanglement entropy is kept unchanged;

[0061] SB1.3: Determine the quantum entanglement entropy: Determine the final quantum entanglement entropy size according to the adjusted weight of the quantum entanglement entropy, and determine the optimized dynamic channel survival degree according to the final quantum entanglement entropy size. The formula for obtaining the final quantum entanglement entropy is specifically as follows:

[0062]

[0063] in: is the final quantum entanglement entropy, is the weight of quantum entanglement entropy, is the quantum entanglement entropy.

[0064] Furthermore, the global optimal frequency hopping sequence is determined, including:

[0065] SC1: Get coupling strength: Get the coupling strength between different channels according to the channel survival degree corresponding to each available channel, specifically:

[0066]

[0067] in: is the coupling strength between the hth channel and the uth channel, is the scale factor, is the channel survivability of the h-th channel, is the channel survivability of the u-th channel, , is the index of the channel;

[0068] SC2: Obtaining the optimal channel combination: According to the coupling strength between the different channels, the total energy between the channels is obtained, and the minimum total energy between the channels is determined therefrom. The channel combination corresponding to the minimum total energy between the channels is the optimal channel combination. The formula for obtaining the total energy between the channels is specifically:

[0069]

[0070] in: is the total energy between the hth channel and the uth channel, is the coupling strength between the hth channel and the uth channel, is the Pauli Z matrix acting on the hth channel, is the Pauli Z matrix acting on the u-th channel.

[0071] Compared with the prior art, the present invention has the following beneficial effects:

[0072] First, the present invention uses superconducting resonant cavities and quantum compressed sensing algorithms to capture microsecond transient noise, thereby increasing the sensitivity of spectrum hole detection by 40 dB. At the same time, the dynamic channel survival rate is used to screen out anti-interference channels in real time, and the optimal channel combination is obtained, so that channel switching can be completed within 10 ms.

[0073] Second, the present invention realizes nonlinear power amplification through superconducting resonant cavity, realizes reconstruction of broadband signals through quantum compressed sensing algorithm, and reduces the feature dimension from traditional 256 dimensions to 3 dimensions through quantum fingerprint feature extraction technology, thereby improving the classification accuracy by 12.7%;

[0074] Third: The present invention combines quantum entanglement entropy, electromagnetic field strength and vibration acceleration to obtain the corresponding channel survival degree, and through a dynamic weight adjustment mechanism, the channel assessment misjudgment rate is reduced to less than 0.5%. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 It is a monitoring flow diagram of the power equipment status monitoring system of the present invention.

[0076] Figure 2 It is a comparison diagram of transient noise in the present invention.

[0077] Figure 3 It is a performance diagram of the original signal in the present invention.

[0078] Figure 4 It is a performance diagram of the reconstructed signal in the present invention.

[0079] Figure 5 This is a graph showing the change of quantum entanglement entropy over time in the present invention.

[0080] Figure 6 This is a graph showing how the channel survivability varies with time in the present invention.

[0081] Figure 7 This is the survival threshold baseline diagram in the present invention. DETAILED DESCRIPTION

[0082] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0083] When monitoring the status of power equipment, the existing detection methods mostly rely on static frequency band division (such as reserving 8 sub-channels in the 868MHz band). However, in areas with dense power equipment (such as 500kV substations), there is a serious mismatch between the static spectrum allocation mechanism and dynamic electromagnetic interference. At the same time, the transient arc caused by the operation of the isolating switch in the substation can instantly excite 0.5MHz~5GHz wideband electromagnetic noise, and its equivalent isotropic radiated power (EIRP) jumps from -40dBm to +20dBm within 2μs, which will cause the target channel to be submerged in the noise floor. At the same time, due to the lack of dynamic perception of spectrum holes and fast frequency hopping (<10ms switching) capabilities, the channel signal-to-noise ratio (SNR) will deteriorate from 20dB to below 3dB, and the nodes will be forced to maintain communication in the blocked channel, which will cause the bit error rate (BER) to increase from 1e⁻ 6 It soared to 1e⁻², and the number of packet retransmissions exceeded the maximum threshold of the protocol stack (such as the LoRa ADR mechanism is limited to 3 times), eventually triggering a link interruption. The technical solution of this application amplifies transient arc noise through a superconducting resonant cavity, reconstructs the signal through quantum compressed sensing, and trains the SVW classifier with quantum fingerprint features and traditional features for state classification. At the same time, it dynamically selects normal / faulty arc dedicated channels based on the classification results, and obtains the coupling strength between channels based on the channel survival, from which the global optimal frequency hopping sequence is determined to effectively solve the broadband electromagnetic interference problem caused by transient arcs.

[0084] Example 1

[0085] refer to Figure 1-Figure 7 , this embodiment provides an Internet of Things-based power equipment status monitoring system, which includes a spectrum sensing module, a dynamic evaluation module, a frequency hopping optimization module and an anti-destruction transmission module. The spectrum sensing module detects and identifies the noise characteristics in the electromagnetic signal through a quantum spectrum sensing array to obtain corresponding spectrum data and corresponding classification results. The dynamic evaluation module establishes a calculation formula for dynamic channel survival based on quantum entanglement entropy, electromagnetic field strength and vibration acceleration, and uses the spectrum data and classification results as input data for dynamic channel survival to filter out a list of available channels. The frequency hopping optimization module obtains the channel quantum state based on the available channel list and the channel switching cost parameter, and obtains the global optimal frequency hopping sequence through the channel quantum state.

[0086] In this embodiment, the spectrum sensing module performs corresponding amplification processing on the input signal through the superconducting resonant cavity. At the same time, the amplified signal is mapped to the quantum state amplitude and verified through the reconstruction error. Furthermore, the verified signal is classified and processed accordingly through the SVW classifier to determine whether the input signal is a fault arc. The details are as follows:

[0087] Step SA1: Perform quantum state amplification. That is, obtain the quality factor of the resonant cavity through the constructed superconducting resonant cavity, and determine the power amplification factor of the signal after passing through the resonant cavity through the quality factor of the resonant cavity, specifically:

[0088]

[0089] in: is the power amplification factor of the signal after passing through the resonant cavity, is the quality factor of the resonant cavity, is the free space impedance, is the external coupling impedance, is the natural oscillation frequency of the resonant cavity, is the frequency width of the resonance peak at half the maximum power.

[0090] In this embodiment, a cylindrical cavity (radius 50 mm, height 100 mm) is constructed by niobium superconducting material, and the surface of the cavity is polished to a surface roughness of no more than 0.1 μm. At the same time, the cavity temperature is stabilized at 4K by a liquid helium closed-loop refrigeration system to ensure the stability of the superconducting state, and a magnetic shielding layer is wound by a niobium-titanium alloy superconducting wire to suppress external magnetic field interference.

[0091] Furthermore, the noise characteristics (transient arc noise) in the electromagnetic signal are amplified by the constructed superconducting resonant cavity. In this embodiment, the transient arc noise power obtained is amplified by the power amplification factor of the signal after passing through the resonant cavity, specifically:

[0092]

[0093] in: is the amplified transient arc noise power, is the original transient arc noise power, is the power amplification factor of the signal after passing through the resonant cavity.

[0094] Step SA2: Reconstruct sparse signals. The amplified transient arc noise power obtained in step SA1 is used as the input of the parameterized quantum circuit to obtain the measurement matrix and observation vector, thereby constructing the corresponding optimization problem and combining the constraints of the reconstructed signal to obtain the reconstructed signal. The details are as follows:

[0095] Step SA2.1: Obtain the observation vector. That is, the input original signal is compressed through the superconducting resonant cavity constructed in step SA1, and a measurement matrix is ​​constructed based on the compressed signal. At the same time, the amplified transient arc noise power obtained in step SA1 is compressed through the measurement matrix to obtain the observation vector. The details are as follows:

[0096] Step SA2.1.1: Obtain the dimension of the compressed signal. That is, the input original signal is compressed through the superconducting resonant cavity constructed in step SA1 to obtain the signal bandwidth and bandwidth compression ratio of the compressed signal, specifically:

[0097]

[0098] in: is the bandwidth compression ratio, is the bandwidth of the original signal, is the signal bandwidth after compression by the superconducting resonant cavity.

[0099] Furthermore, according to the dimension of the original signal and the obtained bandwidth compression ratio, the dimension of the signal after compression by the superconducting resonant cavity is determined, specifically:

[0100]

[0101] in: is the dimension of the signal after compression by the superconducting resonant cavity, is the dimension of the original signal, is the bandwidth compression ratio.

[0102] Step SA2.1.2: Construct a measurement matrix. That is, based on the signal dimension after compression by the superconducting resonant cavity determined in step SA2.1.1 and the dimension of the original signal, a measurement matrix is ​​constructed, specifically:

[0103]

[0104] in: is the measurement matrix, is a complex field, is the dimension of the signal after compression by the superconducting resonant cavity, is the dimension of the original signal.

[0105] Step SA2.1.3: Determine the observation vector. That is, through the measurement matrix constructed in step SA2.1.2, the amplified transient arc noise power obtained in step SA1 is compressed, that is, compressed into a low-dimensional measurement value to obtain the observation vector, specifically:

[0106]

[0107] in: is the low-dimensional observation signal, is the measurement matrix, is the amplified transient arc noise power, is the observation noise.

[0108] Step SA2.2: Obtain the preliminary reconstructed signal. That is, based on the measurement matrix constructed in step SA2.1.2 and the observation vector obtained in step SA2.1.3, construct an optimization problem, specifically:

[0109]

[0110] in: To reconstruct the signal initially, is the low-dimensional observation signal, is the measurement matrix.

[0111] Furthermore, through the quantum approximate optimization algorithm, the optimization problem is encoded into a quantum Hamiltonian, specifically:

[0112]

[0113] in: is the quantum Hamiltonian, is the i-th preliminary reconstructed signal, To initially reconstruct the index of the signal, is the low-dimensional observation signal, is the measurement matrix, is the regularization parameter.

[0114] It is worth noting that the preliminary reconstructed signal obtained by the quantum Hamiltonian satisfies the following constraints:

[0115]

[0116] in: is the amplified transient arc noise power, To reconstruct the signal initially.

[0117] Step SA2.3: Obtain the final reconstructed signal. That is, according to the quantum bit resources, the preliminary reconstructed signal obtained in step SA2.2 is divided into blocks and encoded into quantum states. At the same time, the loss function is minimized through the quantum state parameters in the quantum state corresponding to the preliminary reconstructed signal to obtain the final reconstructed signal. The details are as follows:

[0118] Step SA2.3.1: Obtain quantum state parameters. That is, by using the quantum bit resource size (block coded signal), the preliminary reconstructed signal obtained in step SA2.2 is divided into blocks, that is, into multiple sub-signals, and each sub-signal is mapped to a quantum state probability amplitude through amplitude coding, specifically:

[0119]

[0120] in: is the parameterized quantum state, is the quantum state parameter, is the jth component of the preliminary reconstructed signal, is the index of the component of the preliminary reconstructed signal, is the sum of the absolute values ​​of all signal components.

[0121] Step SA2.3.2: Determine the final reconstructed signal. That is, the quantum state parameters obtained in step SA2.3.1 are updated by the gradient descent method, and the minimized loss function is obtained according to the updated quantum state parameters. The reconstructed signal corresponding to the minimized loss function is the final reconstructed signal.

[0122] Furthermore, the loss function in this embodiment is specifically:

[0123]

[0124] in: is the loss function, is the quantum state parameter, is the regularization parameter, is the parameterized preliminary reconstructed signal, is the low-dimensional observation signal, is the measurement matrix, is the data fitting term, is the sum of the absolute values ​​of all signal components.

[0125] Specifically, when the loss function in this embodiment is not greater than 0.1, the reconstructed signal corresponding to the loss function not greater than 0.1 is the final reconstructed signal.

[0126] Step SA3: Perform quantum fingerprint recognition. That is, extract the quantum fingerprint features from the final reconstructed signal, and combine the quantum fingerprint features with the traditional features (pulse width and peak amplitude) to obtain a three-dimensional feature vector to train and test the SVW classifier. In other words, the corresponding classification results (normal arc and fault arc) are obtained through the trained and tested SVW classifier. The details are as follows:

[0127] Step SA3.1: Extract quantum fingerprint features. That is, based on the frequency domain signal and coupling signal in the final reconstructed signal determined in step SA2.3.2, construct the Hamiltonian, and obtain the expected value of the quantum state under the Hamiltonian. At the same time, based on the obtained minimum expected value, determine the corresponding adjustable parameter size. The details are as follows:

[0128] Step SA3.1.1: Construct Hamiltonian. That is, extract the frequency domain energy and coupling strength of the final reconstructed signal from the final reconstructed signal determined in step SA2.3.2, and encode it into the Hamiltonian of the quantum system, specifically:

[0129]

[0130] in: is the quantum Hamiltonian, is the total number of frequency components in the final reconstructed signal, is the energy of the gth frequency component of the final reconstructed signal, To generate the operator, is the annihilation operator, is the interaction strength between the gth frequency component and the oth frequency component of the final reconstructed signal, , is the index of the frequency component in the final reconstructed signal.

[0131] Step SA3.1.2: Prepare the variational quantum state. That is, according to the Hamiltonian of the quantum system obtained in step SA3.1, combine it with the three quantum bits to obtain the expected value of the quantum state under the Hamiltonian, specifically:

[0132]

[0133] in: is the expected value of energy, is the parameterized quantum state, is the quantum Hamiltonian, It is an adjustable parameter.

[0134] Step SA3.1.3: Parameter optimization. That is, the adjustable parameters are continuously adjusted and updated through the gradient descent method to obtain the minimum energy expectation value, that is, the ground state energy. In other words, the update formula of the adjustable parameters is specifically:

[0135]

[0136] in: is the adjustable parameter at the k+1th iteration, is the adjustable parameter at the kth iteration, is the learning rate, is the expected value of energy at the kth iteration About the adjustable parameters at the kth iteration gradient.

[0137] Step SA3.2: Classification decision. The ground state energy obtained in step SA3.1.3 is combined with the traditional features to obtain a three-dimensional feature vector, specifically:

[0138]

[0139] in: is a multidimensional feature vector, is the ground state energy, is the pulse width in the time domain signal of the final reconstructed signal, is the peak amplitude in the time domain signal of the final reconstructed signal.

[0140] Furthermore, the SVW classifier is trained by acquiring multiple three-dimensional feature vectors. Specifically, the multiple three-dimensional feature vectors are divided, with 80% of the data used as a training set and 20% of the data used as a test set, so as to perform relevant training and testing on the SVW classifier. In other words, according to the trained and tested SVW classifier, its corresponding classification result can be obtained, that is, normal arc and fault arc can be effectively distinguished.

[0141] In this embodiment, the dynamic evaluation module determines the dynamic channel survival degree according to quantum entanglement entropy, electromagnetic field strength and vibration acceleration to screen out a list of available channels, and uses the spectrum data and the arc classification result output by the SVW classifier in step SA3.2 as input data of the dynamic channel survival degree, and selects the corresponding channel from the screened available channel list for signal transmission. The details are as follows:

[0142] Step SB1: Obtain available channels. That is, quantum entanglement entropy, electromagnetic field strength and vibration acceleration are integrated to obtain dynamic channel survival, and the dynamic channel survival is compared with the preset survival, and a dynamic channel survival that is not less than the preset survival is determined, and the channel corresponding to the determined dynamic channel survival is the available channel.

[0143] In this embodiment, the formula for obtaining the dynamic channel survival degree is specifically:

[0144]

[0145] in: is the channel survivability, is the normalization constant, is the quantum entanglement entropy, is the threshold entropy, is the adjustment factor.

[0146] In the specific implementation process, the threshold entropy is set to 1.0, the normalization constant is set to 1.0, the adjustment factor is set to 5.0, and the quantum entanglement entropy corresponding to the normal channel is 0.8, that is, the corresponding channel survival is 0.73. It is worth noting that the preset survival set in this embodiment is 0.8, that is, the channel survival (0.73) obtained in this embodiment is less than the preset survival (0.8), that is, the channel corresponding to the channel survival in this embodiment is not retained, that is, it is not an available channel.

[0147] Step SB2: Select a channel. That is, according to the arc classification result output by the SVW classifier in step SA3.2 and the available channel obtained in step SB1, the channel of the normal arc is set to a regular channel, which is a channel corresponding to a channel survival degree not less than the regular survival degree. At the same time, the channel of the fault arc is set to the available channel obtained in step SB1, that is, the channel corresponding to a channel survival degree not less than the preset survival degree.

[0148] In the process of specific implementation, when the arc classification results output by the SVW classifier include both normal arcs and fault arcs. Specifically, during the transmission of the normal arc, it is transmitted through a conventional channel. It is worth noting that in this embodiment, the conventional survival degree is set to 0.6, that is, the channels corresponding to the channel survival degree not less than 0.6 can be used to transmit normal arcs. Further, during the transmission of the fault arc, it is transmitted through the available channels obtained in step SB1. In other words, the channels corresponding to the channel survival degree not less than 0.8 can be used to transmit the fault arc.

[0149] In this embodiment, the frequency hopping optimization module obtains the total energy between different channels according to the available channel list determined in step SB2, and determines the global optimal frequency hopping sequence through the total energy between different channels. The details are as follows:

[0150] Step SC1: Acquire coupling strength. That is, according to the channel survival degree corresponding to each available channel determined in step SB2, acquire the coupling strength between different channels, specifically:

[0151]

[0152] in: is the coupling strength between the hth channel and the uth channel, is the scale factor, is the channel survivability of the h-th channel, is the channel survivability of the u-th channel, , is the index of the channel.

[0153] In a specific implementation process, the channel survivability of the first channel is 0.92, the channel survivability of the second channel is 0.88, and the proportional factor is set to 10, so the coupling strength between the first channel and the second channel is 8.1.

[0154] Step SC2: Obtain the optimal channel combination. That is, the total energy between channels is determined by the coupling strength between different channels obtained in step SC1, specifically:

[0155]

[0156] in: is the total energy between the hth channel and the uth channel, is the coupling strength between the hth channel and the uth channel, is the Pauli Z matrix acting on the hth channel, is the Pauli Z matrix acting on the u-th channel.

[0157] In the specific implementation process, the channel survival of the first channel is 0.92, the channel survival of the third channel is 0.90, and the channel survival of the fifth channel is 0.88, then the coupling strength between the first channel and the third channel is 8.28, the coupling strength between the first channel and the third channel is 8.1, and the coupling strength between the third channel and the fifth channel is 7. Therefore, the total energy corresponding to the three coupling strengths is -24.3.

[0158] Furthermore, according to the determined total energy between channels, the lowest energy state is determined from the total energy between all channels, and the channel combination corresponding to the lowest energy state is the optimal channel combination.

[0159] refer to Figure 2 , Figure 2 is a comparison diagram of transient noise in this embodiment, Figure 2 It can be seen that the peak power of the input signal is +20dBm, and after amplification by the superconducting resonant cavity, its peak power is increased to +60dBm. At the same time, the Gaussian pulse shape of the input signal (centered at 0.5μs, and the pulse width is controlled by a standard deviation of 0.1μs) is completely retained after amplification, so no waveform distortion is introduced during the amplification process. Furthermore, the rise time of the input signal (from -40dBm to +20dBm) is about 0.2μs, and the rise time of the output signal is consistent with it.

[0160] refer to Figure 3 and Figure 4 , Figure 3 is the performance diagram of the original signal in this embodiment, Figure 4 is the performance diagram of the reconstructed signal in this embodiment, Figure 3 and Figure 4 It can be seen that the original signal has the typical sparse characteristics of Laplace distribution: a small number of large-amplitude spikes (sparse components) and a large number of small-amplitude noises close to zero. The reconstructed signal accurately captures all significant spikes, but has a smoothing effect on small components. The maximum local error occurs at the signal mutation point (such as the falling edge of the spike near index 500), with an error amplitude of about 0.3, corresponding to a relative error of 15%.

[0161] refer to Figure 5-Figure 7 , Figure 5 This is a graph showing the change of quantum entanglement entropy over time in this embodiment. Figure 6 is a graph showing the variation of channel survival over time in this embodiment, Figure 7 is the survival threshold baseline diagram in this embodiment, Figure 5-Figure 7 It can be seen that the random uniform distribution of quantum entanglement entropy simulates the dynamic fluctuation characteristics of quantum channels in actual environments, covering the typical operating range (0.6–0.9). The channel survival rate shows a Sigmoid curve characteristic near the threshold of quantum entanglement entropy of 7, which meets the probabilistic evaluation requirements of channel status. At the same time, the normal operating conditions account for 82% and the abnormal operating conditions account for 18%, which is consistent with the statistics of power equipment failure rates. The dotted line threshold is used as an early warning threshold, which can identify potential channel degradation 5-10ms in advance (for example, when the quantum entanglement entropy is close to 0.7 at 30ms, the channel survival rate begins to decline).

[0162] Example 2

[0163] The present embodiment provides an Internet of Things-based power equipment status monitoring system, and its specific implementation method is the same as that of Embodiment 1, except that the dynamic channel survival degree is compared with the preset survival degree, and a dynamic channel survival degree that is not less than the preset survival degree is determined therefrom. The channel corresponding to the determined dynamic channel survival degree is the available channel. The present invention is illustrated below with reference to the specific implementation method of the present embodiment.

[0164] In this embodiment, the interference power density within a preset time is obtained through the LSTM model, and the weight of the quantum entanglement entropy is dynamically adjusted according to the interference power density within the preset time to optimize the initially obtained available channels. The details are as follows:

[0165] Step SB1.1: Obtain the electromagnetic-vibration coupling factor. That is, the historical interference power density (for example, the time window is set to 100ms and the sampling interval is set to 1ms), the time series data of the electromagnetic field intensity, and the time series data of the vibration acceleration are used as the input of the LSTM model, and the output is the interference power density prediction value at the preset time.

[0166] In the specific implementation process, the time series data of the electromagnetic field intensity is set to [48,49,50]V / m, and the time series data of the vibration acceleration is set to [0.18,0.19,0.20,]m / s 2 , which obtains the interference power density of 120μW / Hz within the preset time through the LSTM model.

[0167] Furthermore, the electromagnetic-vibration coupling factor is obtained through the interference power density prediction value at a preset time, specifically:

[0168]

[0169] in: is the electromagnetic-vibration coupling factor, is the instantaneous amplitude of the electromagnetic field, is the root mean square of mechanical vibration acceleration, is the integration time window of the interference power density.

[0170] In the specific implementation process, under normal working conditions, the instantaneous amplitude of the electromagnetic field is 50V / m, and the root mean square of the mechanical vibration acceleration is 0.2m / s 2 , the integration time window of the interference power density is 0.1s, so the electromagnetic-vibration coupling factor is 31.6. Further, when in a strong interference condition, the instantaneous amplitude of the electromagnetic field is 200V / m, and the root mean square of the mechanical vibration acceleration is 0.5m / s 2 The integration time window of the interference power density is 0.1s, so the electromagnetic-vibration coupling factor is 316.

[0171] Step SB1.2: Adjust the dynamic weight. That is, compare the electromagnetic-vibration coupling factor obtained in step SB1.1 with the preset coupling factor, and adjust the weight of the quantum entanglement entropy according to the comparison result, specifically:

[0172] When the obtained electromagnetic-vibration coupling factor is greater than the preset coupling factor, the weight of the quantum entanglement entropy is increased, otherwise, the weight of the quantum entanglement entropy is kept unchanged.

[0173] Furthermore, in the process of adjusting the weight of quantum entanglement entropy, the corresponding weight can be adjusted according to actual needs. It is worth noting that in the process of weight adjustment, the weight satisfies the following constraint formula, which is specifically:

[0174]

[0175] in: is the weight of quantum entanglement entropy, is the weight of the instantaneous amplitude of the electromagnetic field, is the weight of mechanical vibration acceleration.

[0176] Step SB1.3: Determine the quantum entanglement entropy. That is, according to the weight of the quantum entanglement entropy determined in step SB1.2, determine the final quantum entanglement entropy size, specifically:

[0177]

[0178] in: is the final quantum entanglement entropy, is the weight of quantum entanglement entropy, is the quantum entanglement entropy.

[0179] In the specific implementation process, the threshold entropy is set to 1.0, the normalization constant is set to 1.0, the adjustment factor is set to 5.0, and the quantum entanglement entropy corresponding to the normal channel is 0.8, that is, the corresponding channel survival is 0.73. It is worth noting that the preset survival set in this embodiment is 0.8, that is, the channel survival (0.73) obtained in this embodiment is less than the preset survival (0.8), that is, the channel corresponding to the channel survival in this embodiment is not retained, that is, it is not an available channel.

[0180] Furthermore, in this embodiment, the weight of the quantum entanglement entropy is set to 0.75, that is, the final quantum entanglement entropy is 0.6, so the corresponding channel survival is 0.88. In other words, the channel survival (0.88) obtained in this embodiment is not less than the preset survival (0.8), that is, the channel corresponding to the channel survival in this embodiment will be retained, that is, the available channel.

[0181] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is limited by the attached embodiments and their equivalents.

Claims

1. An Internet of Things-based power equipment status monitoring system, characterized in that: Included are: The spectrum sensing module detects and identifies the noise characteristics in the electromagnetic signal through the quantum spectrum sensing array, and obtains the corresponding spectrum data and classification results, including: S1: Through the constructed superconducting resonant cavity, the power amplification factor of the signal after passing through the resonant cavity is obtained, and the obtained transient arc noise power is amplified, specifically: ； in: is the amplified transient arc noise power, is the original transient arc noise power, is the power amplification factor of the signal after passing through the resonant cavity; S2: using the amplified transient arc noise power as the input of the parameterized quantum circuit, obtaining a measurement matrix and an observation vector, and constructing an optimization problem, and obtaining a reconstructed signal according to the constraint conditions of the reconstructed signal; S3: extracting quantum fingerprint features from the reconstructed signal, and combining the quantum fingerprint features with traditional features to obtain a three-dimensional feature vector, and training and testing the SVW classifier through the three-dimensional feature vector to obtain a classification result; A dynamic evaluation module, which filters out a list of available channels through dynamic channel survival, and determines a corresponding channel from the list of available channels for signal transmission according to a classification result of the SVW classifier; The frequency hopping optimization module determines a global optimal frequency hopping sequence through the available channel list and the total energy between different channels.

2. The power equipment status monitoring system based on the Internet of Things according to claim 1 is characterized in that: Get the reconstructed signal, including: S2.1: Obtaining an observation vector: compressing the original signal through a superconducting resonant cavity and constructing a measurement matrix, and at the same time compressing the amplified transient arc noise power through the measurement matrix to obtain the observation vector; S2.2: Obtaining a preliminary reconstructed signal: Based on the measurement matrix and the observation vector, an optimization problem is constructed, and the optimization problem is encoded into a quantum Hamiltonian to obtain a preliminary reconstructed signal, specifically: ； in: is the quantum Hamiltonian, is the i-th preliminary reconstructed signal, To initially reconstruct the index of the signal, is the low-dimensional observation signal, is the measurement matrix, is the regularization parameter, is the amplified transient arc noise power, To initially reconstruct the signal; S2.3: Obtain the final reconstructed signal: According to the quantum bit resources, the preliminary reconstructed signal is divided into blocks and encoded into quantum states. At the same time, the loss function is minimized through the quantum state parameters in the quantum state to obtain the final reconstructed signal.

3. The power equipment status monitoring system based on the Internet of Things according to claim 2 is characterized in that: Obtaining the observation vector includes: S2.1.1: Obtaining the dimension of the compressed signal: compressing the original signal through the superconducting resonant cavity, obtaining the bandwidth compression ratio of the signal, and determining the dimension of the signal after compression by the superconducting resonant cavity according to the bandwidth compression ratio, specifically: ； in: is the dimension of the signal after compression by the superconducting resonant cavity, is the dimension of the original signal, is the bandwidth compression ratio; Step SA2.1.2: Constructing a measurement matrix: Constructing a measurement matrix according to the dimension of the signal compressed by the superconducting resonant cavity and the dimension of the original signal, specifically: ； in: is the measurement matrix, is a complex field, is the dimension of the signal after compression by the superconducting resonant cavity, is the dimension of the original signal; S2.1.3: Determine the observation vector: compress the amplified transient arc noise power through the measurement matrix to obtain the observation vector, which is specifically: ； in: is the low-dimensional observation signal, is the measurement matrix, is the amplified transient arc noise power, is the observation noise.

4. The power equipment status monitoring system based on the Internet of Things according to claim 2 is characterized in that: Get the final reconstructed signal, including: S2.3.1: Obtaining quantum state parameters: The preliminary reconstructed signal is divided into blocks through quantum bit resources, and each sub-signal is mapped into a quantum state probability amplitude through amplitude coding, specifically: ； in: is the parameterized quantum state, is the quantum state parameter, is the jth component of the preliminary reconstructed signal, is the index of the component of the preliminary reconstructed signal, is the sum of the absolute values ​​of all signal components; S2.3.2: Determine the final reconstructed signal: Update the quantum state parameters through the gradient descent method, and obtain the minimized loss function based on the updated quantum state parameters. The reconstructed signal corresponding to the minimized loss function is the final reconstructed signal.

5. The power equipment status monitoring system based on the Internet of Things according to claim 1 is characterized in that: Get classification results, including: S3.1: Extract quantum fingerprint features: Based on the frequency domain signal and coupling signal in the final reconstructed signal, construct the Hamiltonian and obtain the expected value of the quantum state under the Hamiltonian. At the same time, determine the size of the adjustable parameter based on the ground state energy. S3.2: Classification decision: The ground state energy is combined with the traditional features to obtain a three-dimensional feature vector, and the three-dimensional feature vector is divided into a training set and a test set, and the SVW classifier is trained and tested. At the same time, the arc operation status is identified through the trained and tested SVW classifier.

6. The power equipment status monitoring system based on the Internet of Things according to claim 5 is characterized in that: Determine the size of the adjustable parameters, including: S3.1.1: Construct Hamiltonian: Encode the frequency domain signal and coupling signal in the final reconstructed signal into the Hamiltonian of the quantum system, specifically: ； in: is the quantum Hamiltonian, is the total number of frequency components in the final reconstructed signal, is the energy of the gth frequency component of the final reconstructed signal, To generate the operator, is the annihilation operator, is the interaction strength between the gth frequency component and the oth frequency component of the final reconstructed signal, , is the index of the frequency component in the final reconstructed signal; S3.1.2: Prepare variational quantum state: According to the Hamiltonian, obtain the expected value of the quantum state under the Hamiltonian, specifically: ； in: is the expected value of energy, is the parameterized quantum state, is the quantum Hamiltonian, is an adjustable parameter; S3.1.3: Parameter optimization: Adjust and update the adjustable parameters by gradient descent method to obtain the ground state energy. The update formula of the adjustable parameters is as follows: ； in: is the adjustable parameter at the k+1th iteration, is the adjustable parameter at the kth iteration, is the learning rate, is the expected value of energy at the kth iteration About the adjustable parameters at the kth iteration gradient.

7. The power equipment status monitoring system based on the Internet of Things according to claim 1 is characterized in that: Determine the corresponding channel for signal transmission, including: SB1: Obtaining an available channel: The quantum entanglement entropy, electromagnetic field strength and vibration acceleration are integrated to obtain the dynamic channel survival degree, and the dynamic channel survival degree is compared with the preset survival degree, and a dynamic channel survival degree not less than the preset survival degree is determined, and the dynamic channel survival degree not less than the preset survival degree is an available channel. The dynamic channel survival degree is obtained by the formula as follows: ； in: is the channel survivability, is the normalization constant, is the quantum entanglement entropy, is the threshold entropy, is the regulating factor; SB2: Select channel: According to the available channel and the classification result of the SVW classifier, the channel of the normal arc is set as the regular channel, and the channel of the fault arc is set as the available channel.

8. The power equipment status monitoring system based on the Internet of Things according to claim 7 is characterized in that: Optimizing the dynamic channel survivability includes: SB1.1: Obtain electromagnetic-vibration coupling factor: Use the historical interference power density, electromagnetic field intensity time series data and vibration acceleration time series data as the input of the LSTM model, output the interference power density prediction value at the preset time, and obtain the electromagnetic-vibration coupling factor, specifically: ； in: is the electromagnetic-vibration coupling factor, is the instantaneous amplitude of the electromagnetic field, is the root mean square of mechanical vibration acceleration, is the integration time window of interference power density; SB1.2: Adjust dynamic weight: compare the electromagnetic-vibration coupling factor with the preset coupling factor, and adjust the weight of quantum entanglement entropy according to the comparison result, specifically: When the electromagnetic-vibration coupling factor is greater than the preset coupling factor, the weight of the quantum entanglement entropy is increased through the weight constraint formula, otherwise, the weight of the quantum entanglement entropy is kept unchanged; SB1.3: Determine the quantum entanglement entropy: Determine the final quantum entanglement entropy size according to the adjusted weight of the quantum entanglement entropy, and determine the optimized dynamic channel survival degree according to the final quantum entanglement entropy size. The formula for obtaining the final quantum entanglement entropy is specifically as follows: ； in: is the final quantum entanglement entropy, is the weight of quantum entanglement entropy, is the quantum entanglement entropy.

9. The power equipment status monitoring system based on the Internet of Things according to claim 1 is characterized in that: Determine the global optimal frequency hopping sequence, including: SC1: Get coupling strength: Get the coupling strength between different channels according to the channel survival degree corresponding to each available channel, specifically: ； in: is the coupling strength between the hth channel and the uth channel, is the scale factor, is the channel survivability of the h-th channel, is the channel survivability of the u-th channel, , is the index of the channel; SC2: Obtaining the optimal channel combination: According to the coupling strength between the different channels, the total energy between the channels is obtained, and the minimum total energy between the channels is determined therefrom. The channel combination corresponding to the minimum total energy between the channels is the optimal channel combination. The formula for obtaining the total energy between the channels is specifically: ； in: is the total energy between the hth channel and the uth channel, is the coupling strength between the hth channel and the uth channel, is the Pauli Z matrix acting on the hth channel, is the Pauli Z matrix acting on the u-th channel.

Images