A self-detection and early warning system for insulation impedance of charging piles

Abstract

This invention discloses a self-detection and early warning system for the insulation impedance of charging piles, relating to the field of power equipment condition monitoring technology. It includes: a vector construction module, which extracts characteristic frequency displacement and dielectric loss gradient based on frequency domain feature data and constructs a material micro-aging state vector; a strength analysis module, which calculates the characteristic frequency displacement acceleration based on the material micro-aging state vector, combines it with the dielectric loss gradient to obtain a risk coupling strength tensor, and generates a risk level label; a trajectory prediction module, which constructs an insulation state trajectory prediction model and generates an insulation resistance state change trajectory based on the risk level label; and an early warning decision module, which generates graded response instructions and obtains operation and maintenance response strategies based on the insulation resistance state change trajectory using a dynamic early warning decision algorithm. This invention accurately captures molecular-level micro-vibrations through quantum displacement acceleration vectors, achieving feature identification of the electrochemical corrosion latency period.

Description

Technical Field

[0001] This invention relates to the field of power equipment condition monitoring technology, and in particular to a self-detection and early warning system for insulation impedance of charging piles. Background Technology

[0002] With advancements in charging pile insulation condition monitoring technology, the correlation modeling between microscopic aging state vectors and macroscopic insulation performance has matured. The calculation of displacement acceleration at characteristic frequencies, combined with dielectric loss gradients to generate risk coupling strength tensors, drives the development of risk level labels towards dynamic and refined levels. The construction of insulation state trajectory prediction models enables cross-scale extrapolation from risk level labels to insulation resistance state change trajectories. Trajectory-based risk abrupt change moment location technology, combined with quantum state encoding to generate graded response commands, marks the transformation of early warning decision-making mechanisms from rule-driven to intelligence-driven, forming a closed-loop system of detection-early warning-decision.

[0003] Current charging pile insulation condition monitoring technology still faces two major bottlenecks. In terms of identifying sudden risks, traditional threshold alarm methods rely on fixed rules, making it difficult to effectively capture the nonlinear abrupt changes in insulation condition. Especially under complex operating conditions such as sudden changes in temperature and humidity, millisecond-level resistance drops often lead to missed detections due to response delays. In the field of cross-scale condition modeling, the correlation between microscopic aging conditions and macroscopic insulation performance still has theoretical limitations. Classical physical models simplify the influence of quantum tunneling effects on displacement acceleration at characteristic frequencies, leading to deviations in the mapping relationship between dielectric loss gradient and risk coupling strength tensor. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a self-detection and early warning system for the insulation impedance of charging piles to solve the problems of static thresholds failing to capture dynamic change risks and cross-scale modeling distortion.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] This invention provides a self-detection and early warning system for the insulation impedance of charging piles, comprising,

[0008] The frequency domain processing module collects impedance response data and generates frequency domain feature data through preprocessing. The vector construction module extracts the displacement and dielectric loss gradient of characteristic frequency points based on the frequency domain feature data and constructs a material micro-aging state vector. The strength analysis module calculates the displacement acceleration of characteristic frequency points based on the material micro-aging state vector, and obtains the risk coupling strength tensor by combining it with the dielectric loss gradient, generating risk level labels. The trajectory prediction module constructs an insulation state trajectory prediction model and generates an insulation resistance state change trajectory based on the risk level labels. The early warning decision module generates graded response instructions and obtains operation and maintenance response strategies based on the insulation resistance state change trajectory through a dynamic early warning decision algorithm.

[0009] As a preferred embodiment of the charging pile insulation impedance self-detection and early warning system of the present invention, the impedance response data includes insulation resistance value, capacitance value, frequency domain amplitude and phase information;

[0010] The preprocessing includes signal amplification, filtering and noise reduction, and analog-to-digital conversion.

[0011] As a preferred embodiment of the charging pile insulation impedance self-detection and early warning system of the present invention, wherein:

[0012] The specific steps for extracting the characteristic frequency point displacement and dielectric loss gradient based on frequency domain feature data are as follows.

[0013] Based on frequency domain response data, the displacement trajectory of characteristic frequency points is captured in real time, and displacement data of characteristic frequency points is generated.

[0014] Input the displacement at the characteristic frequency point into the displacement loss field coupling equation to calculate the dielectric loss gradient.

[0015] As a preferred embodiment of the charging pile insulation impedance self-detection and early warning system of the present invention, the construction of the material micro-aging state vector refers to the fusion of characteristic frequency point displacement and dielectric loss gradient to generate a multi-dimensional fused feature tensor, and the construction of the material micro-aging state vector through an optical projection algorithm.

[0016] As a preferred embodiment of the charging pile insulation impedance self-detection and early warning system of the present invention, the specific steps for calculating the displacement acceleration at characteristic frequency points based on the material's microscopic aging state vector and obtaining the risk coupling strength tensor by combining the dielectric loss gradient are as follows.

[0017] Based on the material's micro-aging state vector, the displacement acceleration at characteristic frequency points is calculated, and a quantum displacement acceleration vector is generated.

[0018] The quantum displacement acceleration vector and dielectric loss gradient are input into the nonlinear coupling equation to calculate the risk coupling strength tensor.

[0019] As a preferred embodiment of the charging pile insulation impedance self-detection and early warning system of the present invention, the generation of risk level labels refers to generating a risk intensity distribution map by mapping the risk coupling strength tensor through three-dimensional grid coordinates, and generating risk level labels through phase transition characteristic analysis.

[0020] As a preferred embodiment of the charging pile insulation impedance self-detection and early warning system of the present invention, the specific steps for constructing the insulation state trajectory prediction model are as follows:

[0021] Extract the risk type from the risk level label and construct a time-dimensional prediction framework by binding timestamps;

[0022] Based on a time-dimensional prediction framework, a multi-source fusion training tensor is generated by combining frequency domain feature data.

[0023] Based on the multi-source fusion training tensor, a coupling coefficient matrix is ​​generated through the quantum annealing algorithm, and an insulation state trajectory prediction model is constructed in parallel through quantum tunneling.

[0024] As a preferred embodiment of the charging pile insulation impedance self-detection and early warning system of the present invention, wherein: generating the insulation resistance state change trajectory based on the risk level label refers to inputting the risk level label into the insulation state trajectory prediction model, generating the evolution path of the micro aging state vector through the quantum tunneling parallel algorithm, and outputting the insulation resistance state change trajectory through coordinate transformation.

[0025] As a preferred embodiment of the charging pile insulation impedance self-detection and early warning system of the present invention, the step of generating graded response commands based on the insulation resistance state change trajectory through a dynamic early warning decision algorithm is as follows:

[0026] Based on the trajectory of changes in insulation resistance, the moment of risk abrupt change is located, and a risk inflection point dataset is obtained.

[0027] Based on the risk inflection point dataset, a risk intensity distribution field is constructed to obtain a dynamic risk intensity tensor, and hierarchical response instructions are generated by encoding entangled states of qubits.

[0028] As a preferred embodiment of the charging pile insulation impedance self-detection and early warning system of the present invention, the acquisition of the operation and maintenance response strategy refers to combining the graded response command and the insulation resistance state change trajectory, and outputting the operation and maintenance response strategy through a non-equilibrium statistical optimization algorithm.

[0029] The beneficial effects of this invention are as follows: by accurately capturing molecular-level micro-vibrations through quantum displacement acceleration vectors, the characteristic frequency displacement is dynamically correlated with the quantum tunneling effect, thereby realizing the characteristic identification of the electrochemical corrosion latency; at the same time, the quantum entangled state encoding decision maintains instruction consistency through coherence, realizes a low-delay response to the sharp drop in resistance, and suppresses the interference of temperature and humidity fluctuations. Attached Figure Description

[0030] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 This is a schematic diagram of a charging pile insulation impedance self-detection and early warning system.

[0032] Figure 2 A flowchart for constructing the microscopic aging state vector of a material.

[0033] Figure 3 A flowchart for generating the trajectory of insulation resistance state changes.

[0034] Figure 4 The flowchart for executing the dynamic early warning decision algorithm. Detailed Implementation

[0035] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0036] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0037] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0038] Reference Figures 1-4 As one embodiment of the present invention, this embodiment provides a charging pile insulation impedance self-detection and early warning system, including the following steps:

[0039] like Figure 1 The aforementioned charging pile insulation impedance self-detection and early warning system includes: a frequency domain processing module, a vector construction module, an intensity analysis module, a trajectory prediction module, and an early warning decision module.

[0040] The frequency domain processing module acquires impedance response data and generates frequency domain characteristic data through preprocessing.

[0041] Impedance response data includes insulation resistance, capacitance, frequency domain amplitude, and phase information;

[0042] It should be noted that the insulation resistance value is the original resistance measurement value between the DC bus of the charging pile and the grounding terminal directly collected by a high-precision sensor. It represents the ability of the insulation material to prevent current leakage. The higher the insulation resistance value, the better the insulation performance. Its function is to serve as a basic parameter to assess the overall health status of the insulation material and detect potential aging or defect risks.

[0043] The capacitance value is a data point on the capacitance characteristics of insulating materials measured in real time by sensors. It reflects the dielectric properties of the insulating material in terms of stored charge. The capacitance value is related to the polarization response of the material and serves to assist in the analysis of the dynamic behavior of the insulating material under an alternating electric field, providing input for the calculation of dielectric loss.

[0044] Frequency domain amplitude is the impedance amplitude value in the frequency domain feature data generated by the frequency domain signal collected by the frequency domain sensor. It represents the magnitude and intensity of the impedance signal at different frequencies. Frequency domain amplitude reflects the frequency response characteristics and is used to identify the displacement of key characteristic frequency points to support the subsequent extraction of dielectric loss gradient.

[0045] Phase information is also part of the impedance response data. It is obtained by converting the phase signal collected by the phase sensor and represents the phase difference angle between the voltage and current waveforms. The phase signal reveals the phase shift of the signal in the frequency domain and plays a role in quantifying dielectric loss and associating it with the micro-aging state of the material. For example, an abnormal phase angle can indicate the latency of electrochemical corrosion.

[0046] Preprocessing includes signal amplification, filtering and noise reduction, and analog-to-digital conversion;

[0047] It should be noted that an instrumentation amplifier is used to gain the impedance response data, thereby increasing the amplitude of weak signals. The instrumentation amplifier amplifies the current signal to a voltage-level effective signal, ensuring the signal strength for subsequent processing stages.

[0048] Noise separation is achieved by applying filtering and noise reduction to the amplified impedance response data. Filtering benchmarks are set for power frequency interference and high-frequency white noise respectively, achieving a signal-to-noise separation effect where interference attenuation is greater than the filtering benchmark.

[0049] The filtered impedance response data is digitally sampled using an analog-to-digital converter to generate a discrete digital signal sequence.

[0050] Frequency domain characteristic data includes impedance amplitude, phase angle, and characteristic frequency.

[0051] Specifically, the impedance amplitude in the frequency domain feature data comes from the processing result of performing a fast Fourier transform on the preprocessed frequency domain signal. It represents the magnitude and intensity of the impedance signal in the frequency domain. The impedance amplitude reflects the amplitude change characteristics of the impedance at different frequencies. Its function is to provide basic data for the identification of feature frequency points and support the subsequent capture of displacement trajectories.

[0052] The phase angle is also generated from the phase signal through a fast Fourier transform, representing the angle difference between the voltage and current waveforms. The phase signal reveals the degree of phase shift in the frequency domain and is used to quantify dielectric loss behavior and correlate with the aging state of materials. For example, an abnormal phase angle can indicate the risk of electrochemical corrosion.

[0053] The characteristic frequency point is the result of locating the extreme point in the curve composed of phase angles. The characteristic frequency point is the frequency coordinate at a specific frequency. Its function is to serve as the anchor point for displacement trajectory analysis, and to calculate displacement acceleration and construct aging state vector.

[0054] The vector construction module extracts the displacement of characteristic frequency points and dielectric loss gradient based on frequency domain feature data, and constructs a vector of the material's micro-aging state.

[0055] Based on frequency domain response data, the displacement trajectory of characteristic frequency points is captured in real time, and displacement data of characteristic frequency points is generated.

[0056] It should be noted that the phase angles in the frequency domain feature data are filtered; for each phase angle, an amplitude comparison is performed, comparing the phase angle of the current frequency point with the phase angles of the left and right adjacent frequency points. If the phase angle value of the current frequency point is greater than the phase angle values ​​of the left and right adjacent frequency points at the same time, it is marked as a local maximum point; if it is less than the phase angle values ​​of the left and right adjacent frequency points at the same time, it is marked as a local minimum point; noise suppression processing is performed on the marked local maximum and local minimum points, and the frequency coordinate sequence of the feature frequency points is output.

[0057] Each characteristic frequency point's frequency coordinate is bound to a synchronization timestamp from data acquisition, forming a time-frequency coordinate pair sequence. Based on the characteristic frequency coordinates of adjacent timestamps, the difference between the characteristic frequency coordinates of the preceding and following timestamps is used as the timestamp-frequency offset to generate characteristic frequency point displacement data.

[0058] Input the displacement at the characteristic frequency point into the displacement loss field coupling equation to calculate the dielectric loss gradient;

[0059] It should be noted that the frequency offset is extracted from the displacement data of the characteristic frequency points; the displacement loss field coupling equation is called, and the frequency offset is substituted into the displacement loss field coupling equation to perform algebraic operations to calculate the dielectric loss gradient; the timestamp-dielectric loss gradient value sequence is output, and the dielectric loss gradient is generated by identifying the inflection point of the timestamp-dielectric loss gradient value sequence.

[0060] Furthermore, the physical meaning of the displacement loss field coupling equation is to quantify the mapping relationship between the characteristic frequency displacement and the dielectric loss gradient. The characteristic frequency displacement characterizes the characteristic frequency shift caused by the micro-vibration of the molecular chain of the insulating material, and the dielectric loss gradient reflects the spatial attenuation rate of the material's dielectric properties. The structure of the loss field coupling equation reflects the linear positive correlation between the dielectric loss gradient and the characteristic frequency displacement. The role of the loss field coupling equation is to realize the cross-scale conversion from microscopic molecular vibration to dielectric performance indicators, highlight the potential risks of small displacements through the linear amplification effect, and support the early identification of the electrochemical corrosion latency period.

[0061] The expression for calculating the dielectric loss gradient is:

[0062] ;

[0063] in, For dielectric loss gradient, The molecular chain polarizability The relative permittivity, For dielectric relaxation time, The energy threshold for electron transitions. This represents the energy value of the electron transition. The displacement at the characteristic frequency point For time intervals, It is the natural logarithm function.

[0064] The electronic transition energy threshold is based on the core parameters of the quantum effect of insulating materials; for example, the electronic transition energy threshold of epoxy resin ranges from [value missing]. The electronic transition energy threshold value range of silicone rubber is: The range of electronic transition energy threshold values ​​for high-temperature ceramics is as follows: The electronic transition energy threshold of polytetrafluoroethylene ranges from [value missing]. .

[0065] The preferred displacement loss field coupling equation is the core mathematical model connecting the quantum tunneling vibrations of microscopic molecular chains with the macroscopic degradation of dielectric properties. The physical essence of this equation is a nonlinear mapping process from the displacement at a quantized characteristic frequency point to the dielectric loss gradient. Through this coupling mechanism, the equation achieves spatial transfer from molecular-level micro-vibrations to the dielectric properties of insulating materials. Its function is to convert quantum-scale frequency drift signals into detectable dielectric gradient values, solving the distortion problem in cross-scale modeling under fluctuating temperature and humidity conditions using traditional methods. In practice, the equation calculates the dielectric loss gradient in real time based on characteristic frequency displacement data, supporting the construction of the material's microscopic aging state vector, ultimately achieving early warning of electrochemical corrosion latency, forming a closed-loop technology for insulation state trajectory prediction and risk level label generation.

[0066] The characteristic frequency shift and dielectric loss gradient are fused to generate a multi-dimensional fused feature tensor, and a material micro-aging state vector is constructed using an optical projection algorithm, such as... Figure 2 The process involves: capturing displacement trajectories of characteristic frequency points in real time based on frequency domain response data to generate characteristic frequency point displacement data; inputting the characteristic frequency point displacement into the displacement loss field coupling equation to calculate the dielectric loss gradient; fusing the characteristic frequency point displacement and the dielectric loss gradient to generate a multi-dimensional fused characteristic tensor; and using an optical projection algorithm to perform three-dimensional coordinate mapping to output a material micro-aging state vector. The first dimension coordinate value quantifies the intensity of molecular chain micro-vibration, the second dimension coordinate value characterizes the dielectric property decay rate, and the third dimension reveals the aging process in the time dimension (time decay factor).

[0067] It should be noted that, for feature frequency point displacements and dielectric loss gradients with the same timestamp, the frequency offset in the feature frequency point displacement and the dielectric loss gradient value in the dielectric loss gradient are extracted; the matched timestamp, frequency offset, and dielectric loss gradient value are integrated into a single data point (timestamp, frequency offset, and dielectric loss gradient value) in a three-dimensional structure; all single data points are arranged in time series, with the row dimension being the timestamp sequence and the column dimension containing the three data dimensions of timestamp, frequency offset, and dielectric loss gradient value to construct a multi-dimensional fused feature tensor.

[0068] The maximum values ​​of frequency offset, timestamp, and dielectric loss gradient are statistically analyzed in the multi-dimensional fused feature tensor. Coordinate mapping is performed on each data point, and the ratio of frequency offset to the maximum frequency offset is used as the first-dimensional coordinate value (quantifying the intensity of molecular chain micro-vibration), the ratio of dielectric loss gradient to the maximum dielectric loss gradient is used as the second-dimensional coordinate value (characterizing the dielectric property decay rate), and the ratio of the current timestamp to the maximum timestamp is used as the time decay factor to generate the third-dimensional coordinate value (revealing the aging process in the time dimension). The three-dimensional coordinate vector is output to form the material micro-aging state vector.

[0069] A superior optical projection algorithm is a mathematical transformation method that maps high-dimensional feature data to low-dimensional state vectors. The core of the optical projection algorithm lies in achieving the fusion of the physical meaning of multi-source heterogeneous data through coordinate normalization. The optical projection algorithm originates from the need for visualization of microstructures in materials science. By projecting the characteristic frequency point displacement, dielectric loss gradient, and time decay factor into three-dimensional space, it generates a fused vector that simultaneously quantifies the micro-vibration intensity of molecular chains, the dielectric property decay rate, and the aging process.

[0070] The strength analysis module calculates the displacement acceleration at characteristic frequency points based on the material's micro-aging state vector, and obtains the risk coupling strength tensor by combining the dielectric loss gradient, thereby generating risk level labels.

[0071] Based on the material's micro-aging state vector, the displacement acceleration at characteristic frequency points is calculated, and a quantum displacement acceleration vector is generated.

[0072] It should be noted that the first-dimensional coordinate value sequence and the corresponding timestamp sequence are extracted from the material's micro-aging state vector. Adjacent timestamp difference operations are performed on the first-dimensional coordinate value sequence, and the difference between the first-dimensional coordinate value of the preceding timestamp and the first-dimensional coordinate value of the following timestamp is used as the instantaneous velocity sequence (timestamp-velocity value sequence). Adjacent timestamp difference operations are then performed on the instantaneous velocity sequence, and the difference between the instantaneous velocity of the preceding timestamp and the instantaneous velocity of the following timestamp is used as the characteristic frequency displacement acceleration sequence (timestamp-acceleration value sequence). The displacement acceleration sequence is then bound to the timestamps to output the quantum displacement acceleration vector.

[0073] The quantum displacement acceleration vector and dielectric loss gradient are input into the nonlinear coupling equation to calculate the risk coupling strength tensor.

[0074] It should be noted that, for data points with the same timestamp as the quantum displacement acceleration vector and the dielectric loss gradient, the acceleration value in the quantum displacement acceleration vector and the dielectric loss gradient value in the dielectric loss gradient are extracted; the acceleration value and the dielectric loss gradient value are substituted into the nonlinear coupling equation to perform hyperbolic tangent operation, and the risk coupling strength value is output; the timestamp and the risk coupling strength value are bound to generate the risk coupling strength tensor.

[0075] The expression for calculating the risk coupling strength value is:

[0076] ;

[0077] in, This represents the risk coupling strength value. The temperature sensitivity coefficient of the material. This is the phase angle offset. As the reference phase angle, This represents the quantum displacement acceleration value. As the reference acceleration, For dielectric loss gradient, It is the hyperbolic tangent function.

[0078] The range of values ​​for the material's temperature sensitivity coefficient is: This is derived from frequency domain phase angle temperature drift experimental calibration, combined with the temperature response characteristics of molecular chain polarizability. For example, the material temperature sensitivity coefficient of epoxy resin ranges from [value missing]. The temperature sensitivity coefficient of silicone rubber ranges from [value missing]. The temperature sensitivity coefficient of polytetrafluoroethylene (PTFE) ranges from [value missing]. The temperature sensitivity coefficient of high-temperature ceramics ranges from [value missing]. .

[0079] A superior approach is to use the nonlinear coupling equation as the core mathematical model for the early warning system to achieve a dynamic correlation between quantum displacement acceleration and dielectric loss gradient. The physical essence of the nonlinear coupling equation lies in using the saturated nonlinearity of the hyperbolic tangent function to fuse molecular-level micro-vibration signals with macroscopic dielectric decay behavior across scales. The nonlinear coupling equation addresses the dual challenges of "missed detection of sudden risks" and "distortion in cross-scale modeling" by introducing a material temperature-sensitive coefficient to achieve adaptive compensation for environmental disturbances.

[0080] The risk coupling strength tensor is mapped to three-dimensional grid coordinates to generate a risk intensity distribution map, and risk level labels are generated through phase transition feature analysis.

[0081] It should be noted that a three-dimensional coordinate system is constructed, with the timestamp as the horizontal axis, the dielectric loss gradient value as the vertical axis, and the risk coupling strength value as the vertical axis. The timestamp value, dielectric loss gradient value, and risk coupling strength value of each data point in the risk coupling strength tensor are mapped to the three-dimensional coordinate system. The number of all coordinate points and the total risk coupling strength within the grid area of ​​each three-dimensional coordinate system are counted, and the ratio of the total risk coupling strength to the number of all coordinate points within the grid area is taken as the average risk coupling strength.

[0082] Based on the average risk coupling strength, areas with risk coupling strength above the average are marked as high-risk, and those below the average are marked as low-risk. The risk level of the corresponding grid area is assigned to each timestamp, generating a timestamp-risk level sequence and outputting the risk level label.

[0083] The trajectory prediction module constructs an insulation state trajectory prediction model and generates insulation resistance state change trajectories based on risk level labels.

[0084] Extract the risk type from the risk level label and construct a time-dimensional prediction framework by binding timestamps;

[0085] It should be noted that risk level labels are obtained as input data. Each data point in the risk level label includes a timestamp and a risk level. When parsing the risk level, if the risk level value is high, it is marked as high risk type code; if the risk level value is low, it is marked as low risk type code. The risk type code is bound to the corresponding timestamp, keeping the original timestamp of the risk level label unchanged, and the risk type code replaces the original risk level, generating a timestamp-risk type code sequence, which constitutes the time-dimensional prediction framework.

[0086] Based on a time-dimensional prediction framework, a multi-source fusion training tensor is generated by combining frequency domain feature data.

[0087] It should be noted that the time-dimensional prediction framework and frequency domain feature data are obtained; each timestamp in the time-dimensional prediction framework is traversed, and data points with the same timestamp are located in the frequency domain feature data; the risk type code (high or low risk type code) in the corresponding time-dimensional prediction framework and the impedance amplitude, phase angle, and characteristic frequency points in the frequency domain feature data are extracted for the same timestamp; the timestamp value, risk type code, impedance amplitude, phase angle, and characteristic frequency points are integrated into five-dimensional data points; all five-dimensional data points are arranged in ascending order of timestamp, with the row dimension being the timestamp sequence and the column dimension containing the five-dimensional data, to construct a multi-source fusion training tensor.

[0088] An insulation state trajectory prediction model is constructed based on the multi-source fusion training tensor using the quantum annealing algorithm;

[0089] It should be noted that the risk type code, impedance magnitude, phase angle, and characteristic frequency of each data point in the multi-source fusion training tensor are analyzed; the quantum annealing energy function includes a quantum spin variable product term and a linear bias term.

[0090] The quantum annealing energy function is initialized to a high-temperature state. Under the constraint of multi-source fusion training tensor data, the quantum spin variable is encoded with a risk type code (e.g., a high risk type code corresponds to a positive one quantum spin variable, and a low risk type code corresponds to a negative one quantum spin variable). The quantum annealing energy function is then subjected to a temperature decrease, linearly cooling from the high-temperature state to a low-temperature final state. Through the quantum tunneling effect, the energy barrier is penetrated, and the quantum annealing energy function collapses to the low-temperature ground state at the low-temperature final state. The global minimum is reached when the quantum annealing energy function collapses to the low-temperature ground state.

[0091] The quantum annealing energy function reaches its global minimum, outputting the optimal quantum spin variable configuration, linear bias term, and the interaction strength of the associated impedance amplitude, phase angle, characteristic frequency point, and risk type code. The interaction strength of the associated impedance amplitude, phase angle, characteristic frequency point, and risk type code is constructed into a coupling coefficient matrix. The coupling coefficient matrix and the linear bias term are integrated into the insulation state trajectory prediction model parameter set to form the insulation state trajectory prediction model.

[0092] The superior quantum annealing algorithm originates from the need to solve combinatorial optimization problems in the field of quantum computing. It is designed to handle the complex nonlinear correlation between frequency domain characteristics and risk types. By constructing an energy function containing quantum spin variable coupling terms and linear bias terms, it simulates the quantum annealing process from a high-temperature initial state to a low-temperature ground state, and achieves the optimal solution output of the coupling coefficient matrix.

[0093] The risk level label is input into the insulation state trajectory prediction model. The evolution path of the microscopic aging state vector is generated using a quantum tunneling parallel algorithm, and the insulation resistance state change trajectory is output through coordinate transformation. Figure 3The process involves: extracting risk types from risk level labels and binding them with timestamps to construct a time-dimensional prediction framework; generating a multi-source fusion training tensor by combining frequency domain feature data; constructing an insulation state trajectory prediction model based on the multi-source fusion training tensor using a quantum annealing algorithm; inputting risk level labels into the insulation state trajectory prediction model; and outputting the evolution path of all time steps through quantum parallel computing to output the trajectory of insulation resistance state changes.

[0094] It should be noted that the risk level label timestamp risk level sequence is input into the insulation state trajectory prediction model to obtain the coupling coefficient matrix and linear bias term parameter set; the first set of values ​​of the micro aging state vector is initialized through the quantum tunneling parallel algorithm, and the micro aging state vector of the current timestamp is encoded as a quantum bit superposition state, so that a single quantum bit can simultaneously represent multiple evolution states; the coupling coefficient matrix of the insulation state trajectory prediction model is called to construct the evolution Hamiltonian, so that the evolution path of all time steps is synchronously output in the quantum superposition state, and the evolution results of all time steps are extracted. The first dimension coordinate value (molecular chain micro-vibration intensity) of the micro aging state vector corresponding to each timestamp in the evolution path is extracted, and the sequence of timestamp insulation resistance values ​​constitutes the insulation resistance state change trajectory.

[0095] The superior insulation state trajectory prediction model is a core prediction model built on the quantum annealing algorithm. It aims to generate a multi-source fusion training tensor by processing risk level labels, timestamps, and frequency domain feature data, and to use the quantum tunneling parallel algorithm to deduce the evolution path of the microscopic aging state vector, thereby predicting the future change trajectory of the insulation resistance state. The insulation state trajectory prediction model is significant because it links microscopic quantum effects with macroscopic performance degradation across scales, solves the problems of missed detection of sudden risks and modeling distortion, and its functions include early warning of steep resistance drops, driving graded response decisions, and optimizing the overall closed-loop performance.

[0096] The early warning decision module generates graded response instructions based on the insulation resistance state change trajectory and obtains operation and maintenance response strategies through a dynamic early warning decision algorithm.

[0097] Based on the trajectory of changes in insulation resistance, the moment of risk abrupt change is located, and a risk inflection point dataset is obtained.

[0098] It should be noted that the insulation resistance value corresponding to each time point in the trajectory of insulation resistance state change is analyzed; the ratio of the difference between the insulation resistance value of the next time point and the insulation resistance value of the previous time point to the time interval is taken as the differential change rate of the insulation resistance value of adjacent time points.

[0099] Based on the statistical distribution characteristics of the current differential change rate sequence, the absolute values ​​of the current differential change rate are sorted in ascending order. The moment of risk mutation is located as the dynamic boundary value. The current differential change rate is compared with the dynamic boundary value. If the current differential change rate is greater than the dynamic boundary value, the corresponding timestamp is marked as the moment of risk mutation. If the current differential change rate is less than the dynamic boundary value, it is not marked. The timestamp and insulation resistance value of the moment of risk mutation are extracted. The timestamp and insulation resistance value are bound together to form a timestamp-insulation resistance value sequence, which constitutes the risk inflection point dataset.

[0100] Based on the risk inflection point dataset, a risk intensity distribution field is constructed to obtain a dynamic risk intensity tensor, and hierarchical response instructions are generated through entangled state encoding of qubits, such as... Figure 4 The process involves: locating the moment of risk abrupt change based on the trajectory of insulation resistance state change, and obtaining a risk inflection point dataset; constructing a risk intensity distribution field based on the risk inflection point dataset to obtain a dynamic risk intensity tensor; and generating hierarchical response instructions through entangled state encoding of quantum bits: the primary response executes continuous monitoring followed by increasing the monitoring frequency; the intermediate response executes local maintenance to reinforce the material; and the highest-level response executes shutdown maintenance to replace the insulation module.

[0101] It should be noted that the timestamps in the risk inflection point dataset are used as time coordinate axes, and the insulation resistance values ​​are used as risk intensity values. A risk intensity distribution field is constructed using spatial interpolation techniques, and a continuous matrix of timestamp risk intensity values ​​is output.

[0102] Extract the risk intensity value corresponding to each timestamp from the continuous matrix of risk intensity values, and arrange them in time series to generate a dynamic risk intensity tensor. Iterate through each risk intensity value in the dynamic risk intensity tensor and perform qubit entanglement state encoding operation to normalize the risk intensity value. Map the normalized risk intensity value to a quantum state probability amplitude (the ground state probability amplitude is negatively correlated with the normalized risk intensity value, and the excited state probability amplitude is positively correlated with the normalized risk intensity value). Apply quantum superposition to obtain a binary string. Convert the binary string into an instruction code and output hierarchical response instructions (the instruction code corresponds to the primary response of continuous monitoring, the instruction code corresponds to the intermediate response of maintenance within a specific time, and the instruction code corresponds to the highest level response of immediate shutdown and maintenance).

[0103] By combining graded response commands with the insulation resistance state change trajectory, an operation and maintenance response strategy is output through a non-equilibrium statistical optimization algorithm.

[0104] It should be noted that when the insulation resistance state change trajectory shows a steady oscillation, a primary response command is executed, corresponding to increasing the monitoring frequency and activating the auxiliary diagnostic strategy set; when the insulation resistance state change trajectory shows continuous inflection points, an intermediate response command is executed, corresponding to the local component replacement and material reinforcement strategy set; when the insulation resistance state change trajectory shows a precipitous drop, a highest-level response command is executed, corresponding to the whole machine shutdown maintenance and insulation module replacement strategy set; and a candidate strategy set is obtained.

[0105] Randomly select an initial strategy solution from the candidate strategy set, fine-tune the strategy parameters within the initial strategy solution to generate neighboring strategy solutions, and output the operation and maintenance response strategy based on the performance changes of neighboring strategy solutions (such as risk suppression effect or execution efficiency improvement).

[0106] Furthermore, the operation and maintenance response strategy includes a primary response strategy, an intermediate response strategy, and a highest-level response strategy. The primary response strategy performs continuous monitoring and auxiliary diagnosis, generates real-time frequency domain characteristic data by collecting impedance response data at a reference frequency, activates the quantum tunneling parallel algorithm to track the evolution path of the material's micro-aging state vector, dynamically determines the displacement acceleration and dielectric loss gradient at characteristic frequency points, and maintains monitoring or triggers upgrades.

[0107] The intermediate response strategy involves replacing local components and reinforcing materials. Based on the trajectory of changes in insulation resistance, the spatial coordinates of the moment of risk mutation are located. Reinforcing materials are injected into the region of abnormal dielectric loss gradient to verify the characteristic frequency point displacement regression benchmark.

[0108] The highest level response strategy involves shutting down the entire machine for maintenance, cutting off the main power supply to the charging pile, comprehensively scanning the risk coupling strength tensor and comparing it with the output of the insulation state trajectory prediction model. When the quantum displacement acceleration vector remains high, the entire set of insulation materials is replaced. Finally, the displacement acceleration at the characteristic frequency point is ensured to return to zero through full-band impedance scanning.

[0109] The optimal dynamic early warning decision algorithm is the core decision-making mechanism of the charging pile insulation impedance early warning system. It is specifically designed to convert the insulation resistance state change trajectory into graded response commands. The technical significance of the dynamic early warning decision algorithm lies in its ability to dynamically optimize the identification and response strategy at moments of sudden risk changes through a quantum bit entanglement encoding mechanism.

[0110] In summary, this invention achieves the characteristic identification of the electrochemical corrosion latency by accurately capturing molecular-level micro-vibrations using quantum displacement acceleration vectors and dynamically correlating characteristic frequency displacements with quantum tunneling effects. Simultaneously, quantum entangled state encoding decisions maintain instruction consistency through coherence, achieving a low-latency response to a sharp drop in resistance and suppressing interference from temperature and humidity fluctuations.

[0111] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A self-detection and early warning system for insulation impedance of charging piles, characterized in that: include, The frequency domain processing module acquires impedance response data and generates frequency domain characteristic data through preprocessing. The vector construction module extracts the displacement of characteristic frequency points and dielectric loss gradient based on frequency domain feature data, and constructs a vector of the material's micro-aging state. The strength analysis module calculates the displacement acceleration at characteristic frequency points based on the material's micro-aging state vector, and obtains the risk coupling strength tensor by combining the dielectric loss gradient, thereby generating risk level labels. The trajectory prediction module constructs an insulation state trajectory prediction model and generates insulation resistance state change trajectories based on risk level labels. The early warning decision module generates graded response instructions based on the insulation resistance state change trajectory and obtains operation and maintenance response strategies through a dynamic early warning decision algorithm.

2. The charging pile insulation impedance self-detection and early warning system as described in claim 1, characterized in that: The impedance response data includes insulation resistance value, capacitance value, frequency domain amplitude, and phase information; The preprocessing includes signal amplification, filtering and noise reduction, and analog-to-digital conversion.

3. The charging pile insulation impedance self-detection and early warning system as described in claim 2, characterized in that: The specific steps for extracting the characteristic frequency point displacement and dielectric loss gradient based on frequency domain feature data are as follows. Based on frequency domain response data, the displacement trajectory of characteristic frequency points is captured in real time, and displacement data of characteristic frequency points is generated. Input the displacement at the characteristic frequency point into the displacement loss field coupling equation to calculate the dielectric loss gradient.

4. The charging pile insulation impedance self-detection and early warning system as described in claim 3, characterized in that: The construction of the material micro-aging state vector refers to fusing the characteristic frequency point displacement and dielectric loss gradient to generate a multi-dimensional fused feature tensor, and then constructing the material micro-aging state vector through an optical projection algorithm.

5. The charging pile insulation impedance self-detection and early warning system as described in claim 4, characterized in that: The method involves calculating the displacement acceleration at characteristic frequencies based on the material's microscopic aging state vector, and then obtaining the risk coupling strength tensor by combining it with the dielectric loss gradient. The specific steps are as follows: Based on the material's micro-aging state vector, the displacement acceleration at characteristic frequency points is calculated, and a quantum displacement acceleration vector is generated. The quantum displacement acceleration vector and dielectric loss gradient are input into the nonlinear coupling equation to calculate the risk coupling strength tensor.

6. The charging pile insulation impedance self-detection and early warning system as described in claim 5, characterized in that: The generation of risk level labels refers to generating a risk intensity distribution map by mapping the risk coupling strength tensor through three-dimensional grid coordinates, and generating risk level labels through phase transition feature analysis.

7. The charging pile insulation impedance self-detection and early warning system as described in claim 6, characterized in that: The specific steps for constructing the insulation state trajectory prediction model are as follows. Extract the risk type from the risk level label and construct a time-dimensional prediction framework by binding timestamps; Based on a time-dimensional prediction framework, a multi-source fusion training tensor is generated by combining frequency domain feature data. Based on the multi-source fusion training tensor, a coupling coefficient matrix is ​​generated through the quantum annealing algorithm, and an insulation state trajectory prediction model is constructed in parallel through quantum tunneling.

8. The charging pile insulation impedance self-detection and early warning system as described in claim 7, characterized in that: The process of generating an insulation resistance state change trajectory based on a risk level label refers to inputting the risk level label into an insulation state trajectory prediction model, generating the evolution path of the microscopic aging state vector through a quantum tunneling parallel algorithm, and outputting the insulation resistance state change trajectory through coordinate transformation.

9. The charging pile insulation impedance self-detection and early warning system as described in claim 8, characterized in that: The process of generating tiered response commands based on the insulation resistance state change trajectory using a dynamic early warning decision algorithm involves the following steps: Based on the trajectory of changes in insulation resistance, the moment of risk abrupt change is located, and a risk inflection point dataset is obtained. Based on the risk inflection point dataset, a risk intensity distribution field is constructed to obtain a dynamic risk intensity tensor, and hierarchical response instructions are generated by encoding entangled states of qubits.

10. The charging pile insulation impedance self-detection and early warning system as described in claim 9, characterized in that: The aforementioned operation and maintenance response strategy refers to combining graded response commands with the insulation resistance state change trajectory, and outputting the operation and maintenance response strategy through a non-equilibrium statistical optimization algorithm.

Images