LABVIEW-based cable sheath ring current fault positioning in-loop simulation method and LABVIEW-based cable sheath ring current fault positioning in-loop simulation system

Abstract

The invention discloses a cable sheath ring current fault positioning in-loop simulation method and system based on LABVIEW. The method comprises the following steps: collecting ring current data of cable sheath monitoring points in real time under the control of LABVIEW, and carrying out digital display and graphical display; decomposing circulation data to obtain a wavelet coefficient and calculating features, and inputting a classification model to obtain a fault type when the features are abnormal; calculating a compensation coefficient considering the influence of the electromagnetic field, and calculating the position of a fault point in combination with a double-end traveling wave method; the operation model switches a typical working condition simulation mode, prediction of a Bayesian reasoning correction model is carried out, and the full-life-cycle operation state of the cable is simulated; and performing fault early warning through the LSTM model and risk assessment. The method can effectively improve the cable operation and maintenance efficiency and reliability, and is widely applied to cable fault detection and guarantee of safe and stable operation of a power system.

Description

Technical Field

[0001] The present invention belongs to the technical field of cable sheath circulating current fault location, and relates to a cable sheath circulating current fault location in-loop simulation method and system based on LABVIEW. Background Art

[0002] In modern power systems, cable lines are widely used in various fields, including urban power grids and industrial power supply, due to their numerous advantages in power transmission, such as small footprint, aesthetic appeal, and relatively low environmental impact. They have become critical infrastructure for power transmission. The circulating current condition of the cable sheath directly impacts the safety and stability of cable operation. Any circulating current failure can have serious consequences, such as localized overheating leading to accelerated insulation aging, cable short circuits, and even fires, leading to widespread power outages and significant economic losses and inconvenience to social production and life.

[0003] Traditional cable sheath circulating current fault location technology has exposed numerous problems in practical applications. Regarding data acquisition, the sensors used in most existing equipment lack sensitivity, making it difficult to accurately capture subtle changes in cable sheath circulating current. Furthermore, effective anti-interference measures are generally lacking. In complex electromagnetic environments, such as those near substations or in areas where high-voltage lines run parallel, power frequency interference and electromagnetic radiation interference frequently occur, causing significant noise to be present in the collected signals. This severely impacts the accuracy and reliability of the data, creating potential problems for subsequent fault diagnosis and location.

[0004] Traditional fault diagnosis technologies rely primarily on simple threshold judgments or empirical rules. This single diagnostic approach is inadequate for the increasingly complex and diverse types of cable faults. Complex faults or weak signal changes at the initial stages of a fault often cannot be accurately identified, leading to missed or misdiagnosed faults and delaying the optimal repair opportunity.

[0005] Existing fault location algorithms are mostly based on idealized models and fail to fully consider the many complex factors in actual cable operation. Dynamic changes in the electromagnetic field surrounding the cable, variations in cable parameters across different sections, and complex installation environments can significantly impact circulating current data, leading to significant deviations in location results. Furthermore, over long-term operation, the cable's electrical parameters change over time and due to factors such as ambient temperature and humidity. Traditional algorithms struggle to adapt to these dynamic changes and cannot consistently guarantee location accuracy.

[0006] Furthermore, traditional technologies typically focus solely on detecting and locating faults after they occur, lacking the ability to systematically simulate and analyze the cable's operating status throughout its entire lifecycle, making it impossible to predict potential failure risks in advance. During operation and maintenance, personnel struggle to fully understand the cable's operating characteristics under different operating conditions, making it difficult to formulate scientific and rational preventive maintenance strategies. This results in a reactive approach to cable operation and maintenance, hindering the safe and stable operation of the power system. Summary of the Invention

[0007] To address the deficiencies in the prior art, the present invention provides a cable sheath circulating current fault location in-loop simulation method and system based on LABVIEW, which can accurately collect data in real time and operate with low power consumption. It can accurately locate and identify cable sheath circulating current faults, simulate multi-operating condition operation for auxiliary diagnosis, and predict potential fault risks in advance through systematic simulation and analysis of the cable's operating status throughout its life cycle. It also realizes multi-language interaction and 3D display, optimizes the operating experience, and effectively improves the efficiency and reliability of cable operation and maintenance. It is widely applicable to cable fault detection and ensuring the safe and stable operation of power systems.

[0008] The present invention adopts the following technical solutions.

[0009] The first aspect of the present invention provides a cable sheath circulating current fault location in-loop simulation method based on LABVIEW, comprising: Step 1: Under the control of LABVIEW, the current sensor collects the circulating current data of the cable sheath monitoring point in real time based on micro-energy, and displays it digitally and graphically on LABVIEW; Step 2: Decompose the circulation data using wavelet transform to obtain corresponding wavelet coefficients, and calculate the wavelet coefficient features. When the wavelet coefficient features are abnormal, input the pre-trained classification model to obtain the fault type. Step 3: Calculate the compensation coefficient considering the influence of the electromagnetic field based on the real-time monitored electromagnetic field data, and calculate the fault point location using the double-terminal traveling wave method; Step 4: The operation model uses real-time data on fault type, fault location, and cable operating parameters, and automatically switches to the corresponding typical operating condition simulation mode based on preset operating condition discrimination logic and threshold judgment conditions. The model then continuously adjusts its predictions of the cable operating status under different simulated conditions through Bayesian reasoning, simulating the cable's full lifecycle operating status to provide a reference for risk assessment. Step 5: Input the real-time data of the cable's operating parameters into the trained LSTM model for real-time prediction. The risk value is evaluated based on the predicted data. When the risk value exceeds the safety threshold, the fault warning mechanism is triggered.

[0010] Preferably, the digital display and graphical presentation on LABVIEW in step 1 includes: In the data display area of ​​LABVIEW, the circulating current value, temperature and voltage of the cable sheath monitoring point are updated in real time in digital form; in the graphical display area of ​​LABVIEW, intuitive charts and 3D dynamic models are used to present the changing trend of the circulating current data and the internal structure of the cable and the direction of the circulating current.

[0011] Preferably, in step 2, the cable sheath circulating current data is decomposed using wavelet transform, and the formula is as follows:

[0012] in, and Decomposition layers Next k-th scaling coefficient and wavelet coefficient; is the nth circulation data; and Decomposition Time Decomposition Layer Next k-th father wavelet and mother wavelet; is the number of decomposition levels of wavelet transform.

[0013] Preferably, in step 3, the formula for calculating the compensation coefficient considering the influence of the electromagnetic field based on the real-time monitored electromagnetic field data is as follows:

[0014] in is the compensation coefficient; is the deviation of the real-time monitored electromagnetic field intensity from the historical mean; is the historical mean value of electromagnetic field intensity; Indicates the spatial attenuation characteristics of electromagnetic interference; is the distance between the historical fault point and the electromagnetic interference source; 、 is the calibration factor.

[0015] Preferably, in step 3, the compensation coefficient is combined with the double-terminal traveling wave method to calculate the fault point location, and the formula is as follows: =

[0016] in, is the fault point location; 、 is the circulating current at the monitoring point at time t when the cable sheath ends A and B fail; 、 is the circulating current at the cable sheath end A and end B at the monitoring point t during normal operation; 、 The start and end time of the selected time interval; is the compensation coefficient; is the cable sheath length; is the traveling wave propagation speed.

[0017] Preferably, in step 5, the formula for evaluating the risk value based on the predicted data is as follows:

[0018]

[0019] in, is the risk value; is the feature weight; The basic weights are determined by analyzing historical fault data and the principal component analysis-linear discriminant analysis PCA-LDA joint algorithm; is the matching degree between the feature and the current fault type; is the adjustment factor; is the feature mapping function; is the i-th input feature obtained based on the predicted data; n is the total number of features.

[0020] Preferably, the feature mapping function for:

[0021]

[0022] in, is the normal reference value of the input feature; is the sensitivity adjustment coefficient; is the baseline sensitivity, is the magnification factor.

[0023] Preferably, the LSTM model is a fusion structure that introduces an attention mechanism and a residual connection. The attention mechanism assigns dynamic weights to parameter sequences at different operation stages of the cable, and the residual connection adds a jump connection between hidden layers of the LSTM.

[0024] Preferably, the LSTM model adopts a dynamic phased training strategy. The first phase uses historical normal operating data for pre-training. The second phase introduces fault simulation data containing fault samples under different working conditions for fine-tuning. The third phase absorbs newly collected operation and maintenance data in real time through the online learning module and updates the model parameters through a sliding window.

[0025] Preferably, the loss function of the LSTM model is a weighted hybrid loss function:

[0026] in is the mean square error, is the cross entropy, is the mean absolute error, 、 、 is the dynamic adjustment coefficient.

[0027] In a second aspect, the present invention provides a LABVIEW-based cable sheath circulating current fault location in-loop simulation system. The system includes a hardware part and a software part. The hardware part includes a current sensor and its built-in micro energy harvesting device and a matching adaptive anti-interference circuit, which is used to accurately collect circulating current data at the cable sheath monitoring point in real time based on micro energy. The software part includes: The operation and display module is built on the LABVIEW development platform. The human-computer interaction interface of the operation and display module includes a system control button area, a real-time data display area, and a graphical result display area. It is used to control the current sensor to collect the circulating current data of the cable sheath monitoring point in real time based on micro-energy, and to display it digitally and graphically. A fault type identification module is used to decompose the circulation data using wavelet transform to obtain corresponding wavelet coefficients and calculate wavelet coefficient features. When the wavelet coefficient features are abnormal, they are input into a pre-trained classification model to obtain the fault type. The fault point location module is used to calculate the compensation coefficient considering the influence of the electromagnetic field based on the real-time monitored electromagnetic field data, and calculate the fault point location by combining the double-terminal traveling wave method; The operation model module is used to run the model using real-time data on cable operating parameters. It automatically switches to the corresponding typical operating condition simulation mode through preset operating condition discrimination logic and threshold judgment conditions. It also continuously corrects the operation model's prediction of the cable operating status under different simulated conditions through Bayesian reasoning, simulating the cable's operating status throughout its life cycle to provide a reference for risk assessment. The intelligent early warning module is used to input the real-time data of the cable's operating parameters into the trained LSTM model for real-time prediction, evaluate the risk value based on the predicted data, and trigger the fault early warning mechanism when the risk value exceeds the safety threshold.

[0028] A third aspect of the present invention provides a terminal, comprising a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the method.

[0029] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method when executed by a processor.

[0030] Compared with the prior art, the beneficial effects of the present invention include at least: 1. The present invention uses wavelet transform to decompose the cable sheath circulating current data, obtains corresponding wavelet coefficients, and calculates wavelet coefficient characteristics. When the wavelet coefficient characteristics are abnormal, they are input into a pre-trained classification model to obtain the fault type. Based on the real-time monitored electromagnetic field data, a compensation coefficient that takes into account the electromagnetic field influence is calculated. Combined with the double-ended traveling wave method to calculate the fault point location, the method can accurately identify the fault type and precisely determine the fault location, effectively shortening the fault investigation time, improving the efficiency of power cable operation and maintenance, and reducing power outage losses. The double-ended traveling wave method can more accurately extract the current change characteristics caused by the fault by comparing the circulating current during fault and normal operation, eliminating the interference of current fluctuations during normal operation on fault judgment, and further improving the accuracy of fault location. By incorporating the spatial attenuation characteristics of electromagnetic interference into compensation, the interference effects at different locations are dynamically corrected, reducing positioning errors. This method is particularly suitable for areas with strong electromagnetic interference, such as those near substations.

[0031] 2. When evaluating risk values ​​based on predicted data, the present invention breaks through the limitations of fixed weights by dynamically adapting weights according to fault types, effectively improving the accuracy of risk assessment and preventing key features from being masked by secondary features. Feature mapping is achieved based on the sensitivity adjustment coefficient. The greater the deviation, the exponential increase in sensitivity, which strengthens the response to serious deviations from normal conditions, avoids excessive early warning of minor fluctuations, and ensures rapid identification of major anomalies.

[0032] 3. The LSTM model of the present invention is a fusion structure that introduces the attention mechanism and the residual connection, and adopts a dynamic staged training strategy and uses a weighted hybrid loss function for training. It combines the attention mechanism to focus on key features, and dynamically trains to adapt to the entire life cycle. The hybrid loss function balances prediction accuracy and robustness, and has the ability to improve the sensitivity of early weak fault signals and enhance the generalization ability of the model under complex working conditions.

[0033] 4. The current sensor of the present invention collects the circulating current data of the cable sheath monitoring point in real time based on micro-energy. The current sensor has a built-in micro-energy collection device, which can use the electromagnetic field energy around the cable to convert and power it, thereby achieving low-power continuous monitoring, reducing dependence on external power supply, reducing maintenance costs, and enhancing the system's long-term stable monitoring capabilities in complex environments.

[0034] 5. Based on LABVIEW, the present invention realizes a multi-language human-computer interaction interface and 3D dynamic graph display function, which is convenient for personnel in different regions to operate, makes cable circulation and fault information intuitive and visible, and helps operation and maintenance personnel to quickly grasp the cable operation status, thereby improving operation convenience and information acquisition efficiency.

[0035] 6. The present invention can adapt to changes in cable working conditions, correct models in real time, provide accurate warnings, reduce interference from environmental factors, and significantly improve the accuracy and reliability of system fault diagnosis and positioning by switching the typical working condition simulation mode of the operating model, updating the model through Bayesian reasoning, and predicting and assessing the risk of the LSTM model. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flow chart of the cable sheath circulating current fault location in-loop simulation method based on LABVIEW of the present invention. DETAILED DESCRIPTION

[0037] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. The embodiments described in this application are only part of the embodiments of the present invention, not all of them. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without making creative efforts are all within the scope of protection of the present invention.

[0038] Embodiment 1 of the present invention provides a cable sheath circulating current fault location in-loop simulation method based on LABVIEW, such as Figure 1 Shown, including: Step 1: Under the control of LABVIEW, the current sensor collects the circulating current data of the cable sheath monitoring point in real time based on micro-energy, and displays it digitally and graphically on LABVIEW; Further preferably, the digital display and graphical presentation on LABVIEW includes: In the data display area of ​​LABVIEW, the circulating current values, temperature, and voltage of the cable sheath monitoring points are updated in real time in digital form; in the graphical display area of ​​LABVIEW, intuitive charts and 3D dynamic models are used to present the changing trends of the circulating current data and the internal structure of the cable and the direction of the circulating current.

[0039] Step 2: Decompose the cable sheath circulating current data using wavelet transform to obtain corresponding wavelet coefficients, and calculate the wavelet coefficient features. When the wavelet coefficient features are abnormal, input the pre-trained classification model to obtain the fault type. Further preferably, the cable sheath circulating current data is decomposed using wavelet transform, and the formula is as follows:

[0040] in, and Decomposition layers The kth scale coefficient and wavelet coefficient; j represents the decomposition layer index of the wavelet transform, which plays a role in level identification in the decomposition process, and its value range is from 1 to the selected decomposition layer. Different The values ​​correspond to the decomposition results at different scales. As the signal increases, it is decomposed into a finer scale, and the characteristic information of different frequency bands can be obtained. For example, when analyzing the cable sheath circulation data, the larger The value helps to capture more subtle fault feature changes in the data; k is an index variable related to the scale coefficient and wavelet coefficient, and is used in each decomposition layer. Next, it is used to traverse and determine the corresponding scale coefficient and wavelet coefficients In different layer, The value range of will be determined according to the actual data processing requirements. Its function is to accurately characterize the coefficient values ​​of the corresponding scale and wavelet function at different positions or times. These coefficients contain the characteristic information of the cable sheath circulating current data at different scales and positions. The nth cable sheath circulation data; n is the index of time or data point. middle, Used to represent data at different times or sampling points. The corresponding circulation data is subjected to wavelet transformation, which can analyze the characteristics of data changes over time or position, and then identify the fault type; and Decomposition Time Decomposition Layer Next k-th father wavelet and mother wavelet; is the number of decomposition levels of wavelet transform.

[0041] Step 3: Calculate the compensation coefficient considering the influence of the electromagnetic field based on the real-time monitored electromagnetic field data, and calculate the fault point location using the double-terminal traveling wave method; Further preferably, the fault point location is calculated by combining the double-terminal traveling wave method, and the formula is as follows: =

[0042] in, The fault point location, that is, the location information of the fault point on the cable line relative to the starting point; 、 = is the circulating current at the monitoring point at time t when a fault occurs at either end of the cable sheath, A or B. These two current values ​​are key monitoring data when a fault occurs, and their changes contain information about the fault. In the two-terminal traveling wave method, the traveling wave generated by the fault propagates to both ends of the cable, causing changes in the circulating current at the monitoring points at both ends. By analyzing the characteristics of these two currents (such as amplitude and phase), we can obtain information related to the fault and use it to calculate the fault location. 、 The circulating current at ends A and B of the cable sheath at time t during normal operation serves as reference data for comparison with the circulating current during a fault. By comparing the circulating current during fault and normal operation, the two-terminal traveling wave method can more accurately extract the current variation characteristics caused by the fault, eliminate interference from current fluctuations during normal operation on fault diagnosis, and improve fault location accuracy. 、 The start and end time of the selected time interval is a period of time selected during the fault process. Through the analysis of a large amount of historical fault data and simulated fault experiments, it is determined that the circulating current signal contains rich fault traveling wave information within this specific time interval. For example, for most cable short-circuit faults, the time interval of 10μs to 50μs after the fault occurs is often selected as to The selection of this time interval is crucial for fault location calculation. If it is not selected properly, the fault traveling wave information may not be accurately captured, resulting in fault location deviation. This is a compensation coefficient used to account for the impact of changes in the electromagnetic field around the cable on the circulating current data. Since the dynamic changes in the electromagnetic field around the cable can interfere with the circulating current data and thus affect the accuracy of fault location, a compensation coefficient is introduced for correction. This coefficient is calculated in real time using a built-in function based on the real-time monitored electromagnetic intensity parameters. In actual applications, high-precision electromagnetic field sensors installed around the cable monitor the electromagnetic intensity parameters in real time. Based on a mathematical model established using electromagnetic field theory and a large amount of experimental data, this is converted into a calculation function for the compensation coefficient, thereby obtaining an accurate compensation coefficient value and minimizing positioning errors caused by environmental factors. And preferably, , To monitor the deviation of electromagnetic field intensity from historical mean in real time, is the historical mean electromagnetic field intensity, is the distance between the historical fault point and the electromagnetic interference source, 、 is the calibration coefficient, , , by taking the spatial attenuation characteristics of electromagnetic interference into account Incorporate compensation to dynamically correct interference effects at different locations, thereby reducing positioning errors. This is especially applicable to areas with strong electromagnetic interference, such as those near substations. The line length is a fixed, known parameter. When calculating the fault location, it is used as a reference length and combined with other parameters to determine the relative position of the fault point in the line. The traveling wave propagation velocity (Vt) is the speed at which a traveling wave propagates through a cable. It is determined by the cable's material and structural characteristics. Different cable types have different Vts. In actual calculations, this value can be determined using empirical formulas or actual measurement data. It influences the proportional relationship in the fault location calculation formula. The greater the Vt, the farther the fault point is likely to be from the monitoring point under the same time and other conditions.

[0043] Step 4: The operation model uses real-time data on fault type, fault location, and cable operating parameters, and automatically switches to the corresponding typical operating condition simulation mode based on preset operating condition discrimination logic and threshold judgment conditions. The model continuously corrects the prediction of the cable operating status under different simulated operating conditions through Bayesian reasoning, simulating the cable's full life cycle operating status to provide a reference for risk assessment. The model also regularly generates data comparison reports between simulated and actual operating conditions. In step 2 above, the fault type is obtained by analyzing the cable sheath circulating current data through wavelet transform. In step 3, the fault point location is calculated by combining the double-end traveling wave method and the compensation coefficient. These two steps provide key basic data for step 4. The fault type and fault point location information can be used to optimize the operation model's simulation of the fault condition.

[0044] In step 4, the running model uses real-time data on cable operating parameters to switch to a typical operating condition simulation mode. The fault type and fault location information help more accurately simulate the cable's operating status under fault conditions. For example, if the fault type is a short circuit and the fault location is known, the running model can more accurately simulate the changes in current, voltage, and other parameters near the fault point and throughout the cable line after the short circuit occurs. It can also simulate the recovery process of the cable's operating status under different repair measures, providing a more reliable basis for predicting the operating status after the fault is repaired. At the same time, when using Bayesian reasoning to correct the running model's prediction of the cable's operating status under different simulated conditions, the fault type and fault location, as important factors affecting the cable's operating status, are incorporated into the model's prediction correction process, allowing the model to better fit the actual operating conditions and improving the accuracy of the simulation.

[0045] In specific implementation, step 4 simulates the cable's full lifecycle operating status, providing data support and risk assessment reference for step 5, improving early warning accuracy. The two are closely linked and work together to ensure the safe and stable operation of the cable system. For example, the simulation results obtained in step 4 help to more accurately calculate the risk value in step 5. By comparing simulated and actual operating conditions, potential trends in cable operating conditions can be identified. When this information is incorporated into the risk assessment function, the risk assessment can be more accurately reflected. If the simulation results show a gradual increase in cable circulating current under a certain operating condition, and similar changes begin to occur under actual operating conditions, this trend will be taken into account when calculating the risk value in step 5, and the risk assessment weight will be increased accordingly, making the risk value more reflective of the actual failure risk.

[0046] Step 5: Input the real-time data of the cable's operating parameters into the trained LSTM model for real-time prediction. The risk value is evaluated based on the predicted data. When the risk value exceeds the safety threshold, the fault warning mechanism is triggered.

[0047] Further preferably, the LSTM model is a fusion structure that introduces an attention mechanism and a residual connection. The attention mechanism assigns dynamic weights to the parameter sequences of the cable at different operation stages, and the residual connection adds a jump connection between the hidden layers of the LSTM. The LSTM model adopts a dynamic phased training strategy. In the first phase, historical normal operation data is used for pre-training. In the second phase, fault simulation data containing fault samples of different working conditions is introduced for fine-tuning. In the third phase, newly collected operation and maintenance data is absorbed in real time through an online learning module and the model parameters are updated through a sliding window. The loss function of the LSTM model is a weighted hybrid loss function:

[0048] in is the mean square error, is the cross entropy, is the mean absolute error, 、 、 is the dynamic adjustment coefficient.

[0049] By combining the attention mechanism to focus on key features, dynamic training adapts to the entire life cycle, and the hybrid loss function balances prediction accuracy and robustness; it has the ability to improve the sensitivity of early weak fault signals and enhance the generalization ability of the model under complex working conditions.

[0050] Further preferably, the risk value is calculated by comparing the predicted value with a preset threshold value through a risk assessment function, and the formula is as follows:

[0051] in, is the risk value, which combines the various input characteristics Feature mapping function The processed results are then classified according to the feature weights Weighted sum, when the calculated risk value When the preset safety threshold is exceeded, the fault warning mechanism will be triggered. The preset threshold is a limit value set based on cable operation safety standards, historical fault data, and actual operation and maintenance experience. It is used to determine whether the current cable operation status is within the safe range, thereby deciding whether to issue an early warning signal. is the feature weight; the fault type and fault location are important references for risk assessment. When the intelligent early warning module performs real-time predictions and calculates risk values ​​based on the LSTM model, if the prediction results show an abnormal change trend in the parameters associated with the known fault type and fault location, the assessment weight of the risk will be increased. For example, if a short circuit fault is known to have occurred at a certain location, when the circulating current near that location fluctuates abnormally again, the intelligent early warning module will more accurately judge the possibility of fault recurrence based on historical fault type and location information, improve the accuracy and timeliness of the early warning, and thus more effectively ensure the safe and stable operation of the cable system; And preferably, , The basic weights are determined by analyzing historical fault data and the principal component analysis-linear discriminant analysis PCA-LDA joint algorithm. is the matching degree between the feature and the current fault type, In order to adjust the coefficient, the weight is dynamically adapted according to the fault type, breaking through the limitations of fixed weights, thereby improving the accuracy of risk assessment and avoiding the key features being masked by secondary features.

[0052] The prediction result of the LSTM model trained by the real-time data input of the cable operation parameters is converted into the input feature i Participate in risk assessment calculations. For example, predict the cable's circulating current amplitude, temperature and other parameters. These predicted values ​​will be processed into corresponding input features based on the cable's operating characteristics and fault mechanism. They may be used directly as input features, or they may be calculated and converted into input features and substituted into the feature mapping function. to process; n is the total number of features; It is a feature mapping function, which is designed according to the cable operation characteristics and fault mechanism, and the input feature (including predicted values ​​and features after predicted values ​​are converted) and converted into indicators that are more relevant to failure risks, so as to reflect the impact of predicted values ​​on risk assessment. Taking the cable circulating current amplitude as an example, the details are as follows: Mapping Function The model is constructed based on operating characteristics. First, the relationship between fault risk and circulating current amplitude is considered: Generally, the further the cable circulating current amplitude deviates from the normal range, the higher the fault risk. During normal operation, the cable circulating current amplitude is within a certain range. When the circulating current amplitude exceeds this range, the fault risk increases rapidly. A modified form of the Gaussian function is selected, taking advantage of its good symmetry and attenuation characteristics on both sides of the center value, which can simulate the trend of fault risk changing with circulating current amplitude. The specific formula is:

[0053] in, Indicates the cable circulating current amplitude input characteristics; and It is a parameter determined based on the cable operation characteristics and historical fault data. The normal reference value representing the cable circulation amplitude can be obtained by statistical analysis of a large amount of historical normal operation data, such as calculating the mean or median of the historical normal circulation amplitude as value. It is used to adjust the sensitivity of the function and control the speed at which the fault risk increases when the circulating current amplitude deviates from the normal reference value. The larger the value, the steeper the function curve, that is, the slight deviation of the circulating current amplitude will increase the faster the fault risk; The smaller the value, the flatter the curve. By fitting historical fault data, combining different The accuracy of the failure risk assessment function under the value is determined.

[0054] The function characteristics and fault risk assessment match as follows: when , that is, when the cable circulating current amplitude is at the normal reference value, , indicating that the risk of failure is low at this time.

[0055] along with Deviation , whether increasing or decreasing, The value of will increase. The value of will decrease, The value of will increase, which means the risk of failure increases.

[0056] Moreover, due to the characteristics of the exponential function, when the circulation amplitude deviates greatly from the normal range, It will quickly approach 1, which well reflects the high fault risk under high circulating current amplitude; in, , is the baseline sensitivity, ranging from 0.8 to 1.2. is the amplification factor, the value range is 1.5-2.0, the greater the deviation, the greater the sensitivity Exponentially improve, strengthening the response to major deviations from normal conditions, thereby avoiding excessive warnings for small fluctuations while ensuring rapid identification of major anomalies.

[0057] Embodiment 2 of the present invention provides a LABVIEW-based cable sheath circulating current fault location in-loop simulation system for implementing the method described in Embodiment 1. The system includes a hardware component and a software component. The hardware component includes a cable sheath circulating current fault information acquisition device for accurately and real-timely collecting cable sheath circulating current data. The cable sheath circulating current fault information acquisition device also includes a built-in micro energy harvesting device for utilizing the weak electromagnetic field energy around the cable to convert power, thereby achieving low-power continuous operation. The software component includes: The operation display module has an intuitive and convenient human-computer interaction interface, which enables comprehensive control of the entire simulation system and clear display of various information. Users can easily issue commands and view real-time status through this interface; The fault type identification module based on wavelet analysis uses Daubechies wavelet to perform wavelet transform operation on the acquired cable sheath circulating current data. Its decomposition formula is:

[0058] Where, is the scale coefficient, is the wavelet coefficient, is the scaling function, is the wavelet function, For the selected decomposition level, the fault type can be accurately identified by means of detailed analysis of the wavelet coefficients; The fault location algorithm module builds a fault location algorithm based on the improved two-terminal traveling wave method. It builds an equivalent circuit model based on the precise electrical parameters of the cable and uses the collected circulating current data according to the formula: =

[0059] in represents the wave speed, 、 They are the circulating currents at the monitoring points when faults occur at both ends of the line, 、 They are the circulating currents at the monitoring points at both ends of the line during normal operation, 、 For the selected time interval, is the total length of the cable, so as to accurately determine the location of the fault point; The operation model module is used to simulate the operating conditions of cables under multiple working conditions, including daily operation, peak operation, and after fault repair, providing a key reference for in-depth diagnosis and precise positioning of faults.

[0060] The details are as follows: 1. System hardware construction and debugging Installation and calibration of cable sheath circulating current fault information collection device The cable sheath circulating current fault information acquisition device uses a high-sensitivity, low-noise current sensor, and the sensor is equipped with an adaptive anti-interference circuit that can automatically adjust the filtering parameters according to the intensity of external interference to ensure the purity of the collected signal.

[0061] Sensor Selection and Installation: Carefully select highly sensitive, low-noise current sensors whose technical specifications meet the requirements for accurately sensing minute changes in the current circulating in the cable sheath. During installation, strictly follow electrical equipment installation specifications to ensure a tight and secure connection between the sensor and the cable sheath to prevent measurement errors caused by improper installation. For example, use a specialized fixture to secure the sensor to the designated monitoring point on the cable sheath to ensure good contact between the sensor electrode and the cable sheath, ensuring efficient signal transmission.

[0062] Adaptive Anti-Interference Circuit Debugging: The sensor's adaptive anti-interference circuit is meticulously debugged. In a laboratory environment, external interference sources of varying strengths and types, such as power frequency interference and electromagnetic radiation interference, are simulated to observe the circuit's effectiveness in suppressing interference signals. By adjusting circuit parameters such as filter cutoff frequency and gain, the circuit automatically optimizes filtering performance based on interference intensity, ensuring the collected cable sheath circulating current signal is pure and stable, providing a reliable data foundation for subsequent analysis.

[0063] 2. System Software Configuration and Operation Process (1) Construction and function implementation of the operation display module The operation display module supports multi-language switching to meet the needs of users in different regions, and can also present the internal circulation direction of the cable and the location of the fault in the form of a 3D dynamic graphic.

[0064] Human-computer interaction interface design: Leveraging the LABVIEW development platform, a rich set of graphical programming tools was used to construct the human-computer interaction interface for the operation and display module. The interface layout should be concise and clear, with distinct functional areas, including the system control button area, the real-time data display area, and the graphical results display area. For example, buttons such as "Start Acquisition," "Stop Acquisition," and "Parameter Settings" should be placed in the control button area to facilitate user operation. The data display area should update key parameters such as cable sheath circulating current values, temperature, and voltage in real time in digital form. The graphical display area should utilize intuitive charts (such as line charts and bar graphs) and 3D dynamic models to present circulating current data trends, the cable's internal structure, and the direction of the circulating current.

[0065] Multi-language switching and 3D dynamic graphics: For the multi-language switching feature, we first collected and organized interface text resources in multiple common languages ​​(such as Chinese, English, and Japanese) and stored them as language pack files. Within the program, a language switch event is triggered through the language selection drop-down menu. Based on the user's selection, the text in the corresponding language pack is called up to update the interface display. For 3D dynamic graphics, we utilize LABVIEW's 3D drawing library, combined with the cable's geometric parameters and real-time circulation data, to construct a three-dimensional cable model. By dynamically updating the direction and size of the vector arrows representing the circulation in the model and using color gradients to represent the distribution of circulation intensity, we present a smooth animation effect showcasing the dynamic changes in the cable's internal circulation and the location of faults. To ensure a stable frame rate, we optimized the drawing algorithm, reducing unnecessary graphics rendering calculations and implementing an efficient data caching mechanism to ensure a good user experience.

[0066] (2) Operation steps of the fault type identification module based on wavelet analysis The wavelet analysis-based fault type identification module additionally has a built-in machine learning auxiliary discrimination unit, which uses a large amount of early fault sample data to train the model. When the wavelet analysis result is questionable, the unit is activated for secondary screening to improve the fault identification accuracy.

[0067] Wavelet transform parameter setting and data processing: The cable sheath circulation data obtained by the acquisition device is input into the fault type identification module based on Daubechies wavelet. First, according to the characteristics of the cable and the experience of previous fault data analysis, the number of decomposition layers of the wavelet transform is reasonably determined. Generally speaking, for complex cable systems and variable fault types, it may be necessary to select a larger number of decomposition layers to extract richer fault feature information, but at the same time, the limitations of computing resources and processing time must also be considered. For example, after many tests and comparisons, for the common medium-voltage cable sheath circulation fault analysis, the initial selection can be , then, according to the formula

[0068] Perform wavelet transform operation to obtain the scale coefficient and wavelet coefficients ,During the calculation process, we make full use of the numerical calculation ,function and efficient array processing mechanism of LABVIEW to ensure the accuracy and ,speed of the calculation.

[0069] Fault Feature Extraction and Intelligent Identification: In-depth fault feature extraction and analysis are performed on the wavelet coefficients obtained through wavelet transform. Various statistical features of the wavelet coefficients, such as energy distribution, amplitude mean, variance, and kurtosis, are calculated. These features can reflect fault-related information, such as the energy concentration and fluctuation characteristics of the circulating current signal in different frequency bands. Simultaneously, a machine learning-assisted identification unit uses a large amount of previously collected and labeled fault sample data for model training. A classification model is constructed using machine learning algorithms such as support vector machines (SVMs) and neural networks, using the extracted wavelet coefficient features as model input. During model training, cross-validation and other techniques are used to optimize model parameters and improve model generalization. The machine learning-assisted identification unit is activated when wavelet analysis results are abnormal or outside the preset confidence interval. For example, when the energy distribution of the wavelet coefficients changes suddenly in a specific frequency band and exceeds the normal fluctuation range, the current wavelet coefficient feature vector is input into the trained model. The model then performs a secondary classification based on the learned fault pattern and outputs a final fault type determination, such as short circuit, open circuit, or insulation aging, effectively improving the accuracy of fault type identification.

[0070] (III) Detailed operation process of the fault location algorithm module During the calculation process of the fault point location algorithm module, the compensation coefficient is introduced to consider the influence of the electromagnetic field change around the cable on the circulating current data. , minimizing positioning errors caused by environmental factors.

[0071] Equivalent circuit model construction and parameter initialization: In the fault location algorithm module, first accurately measure the cable resistance based on the cable's detailed electrical parameter manual and actual measurement data. ,inductance ,capacitance Parameters such as the power supply voltage and current are used to build an equivalent circuit model of the cable in the software. Circuit simulation algorithms are then used to simulate the cable's electrical characteristics under normal and fault conditions. For example, for long-distance cable lines, a distributed parameter circuit model is used for more accurate simulation, taking into account the influence of distributed line parameters. During the model building process, parameters are initialized and verified for plausibility to ensure that the model accurately reflects the cable's electrical behavior.

[0072] Fault location calculation based on the two-terminal traveling wave method: the circulating current at the monitoring point at both ends of the line is collected 、 and the circulating current during normal operation 、 Import the fault location algorithm. According to the formula = Calculation is performed. The time interval needs to be 、 Make a selection; Specifically, through the analysis of a large amount of historical fault data and simulated fault experiments, it is determined that within a specific time window before and after the fault occurs, the circulating current signal within this time period contains rich fault traveling wave information. For most cable short circuit faults, the time window after the fault occurs can be selected. to The time interval as to , wave speed Determine the integral term using empirical formulas or actual measurement data based on the cable's material and structural characteristics. When calculating the integral term, use a numerical integration algorithm (such as the trapezoidal method or Simpson's method) to ensure the accuracy of the result.

[0073] Compensation calculation considering the influence of electromagnetic field: To reduce the impact of electromagnetic field changes around the cable on the circulating current data, high-precision electromagnetic field sensors installed around the cable monitor the electromagnetic intensity parameters in real time. Based on electromagnetic field theory and a large amount of experimental data, a mathematical model between electromagnetic field intensity and circulating current error is established and converted into a compensation coefficient. The calculation function of In the software, the compensation coefficient is calculated through the built-in function based on the real-time monitoring electromagnetic field data , and substitute it into the revised formula = , to achieve accurate calculation of the fault point location and effectively improve the accuracy of fault location. The electromagnetic intensity parameters monitored in real time are calculated in real time through built-in functions to minimize positioning errors caused by environmental factors.

[0074] (IV) Function execution process of running model module The operation model module has an intelligent scene switching function, which can automatically switch to the corresponding typical working condition simulation based on the cable operation parameters collected in real time, and can generate a comparison report between the simulated working condition and the actual working condition to assist operation and maintenance personnel in analysis and judgment.

[0075] The operation model module builds a high-fidelity digital twin, combines machine learning algorithms to update model parameters in real time, and continuously corrects model predictions based on real-time monitoring data according to the Bayesian inference formula to simulate the operation status of the cable throughout its life cycle, which is used to improve the fit with actual operation data.

[0076] Model Initialization and Parameter Setting: Upon startup, the operating model module builds a basic operating model based on the cable's basic design parameters (such as cable length, conductor cross-sectional area, and insulation material properties) and historical operating data (such as circulating current data, temperature curves, and load conditions under different operating conditions). Statistical methods and machine learning algorithms are used to analyze and process this historical data, extracting key features and patterns that serve as the initial model parameter settings. Specifically, a cluster analysis algorithm is used to classify historical operating data, determining the typical value ranges and changing trends of cable operating parameters under different operating conditions, providing an initial state estimate for the model.

[0077] Real-time data-driven operating condition simulation and model updates: During system operation, data acquisition devices acquire real-time cable operating parameters such as temperature, voltage, current, and circulating current. Leveraging this real-time data, the system automatically switches to the corresponding typical operating condition simulation based on preset operating condition judgment logic and threshold conditions.

[0078] Specifically, when the cable current is detected to exceed 80% of the rated value and the duration exceeds 10 minutes, it is determined that the cable has entered the peak load operating condition and the model switches to the corresponding simulation mode. At the same time, combined with machine learning algorithms, such as online learning neural networks or incremental support vector machines, the model parameters are continuously updated according to the newly collected data. Use real-time monitoring data as evidence when updating models , constantly revise the model's prediction of cable operating status under different working conditions Through continuous iterative updates, the model can closely track the changes in the actual operating status of the cable and simulate the operation of the cable throughout its life cycle. is the posterior probability, is the likelihood function, is the prior probability, As evidence.

[0079] Comparison report generation and auxiliary analysis: During the simulation process, the operating model module regularly generates comparison reports between simulated and actual operating conditions. The report includes comparison curves of key operating parameters (such as circulating current amplitude, phase, and temperature changes), deviation statistical analysis, trend forecast comparisons, and other information. Using data visualization technology and statistical analysis methods, complex data information is presented to operation and maintenance personnel in an intuitive and easy-to-understand manner. Specifically, a line chart is used to compare the changes in simulated and actual circulating current amplitudes over time. The degree of deviation between the two is quantified by calculating indicators such as the root mean square error (RMSE) and correlation coefficient, and trend line fitting is used to analyze future changes in the two. Based on the comparison report, operation and maintenance personnel can gain an in-depth understanding of the cable's operating status, promptly identify potential problems, and provide a comprehensive and powerful reference for fault diagnosis and location.

[0080] (V) Working mechanism and implementation of the intelligent early warning module The intelligent early warning module learns and predicts the cable operation data sequence based on the long short-term memory network, and evaluates it through a risk assessment function based on the comparison between the predicted value and the threshold.

[0081] Data Preprocessing and Model Training: The intelligent early warning module first performs comprehensive data preprocessing on a large amount of historical cable operation data. This includes data cleaning to remove outliers and noise, and data normalization to bring operating parameters of different dimensions into the same numerical range to facilitate model training and calculation. For example, Z-score normalization is used to convert data such as temperature and current into standard normal distributions with a mean of and a standard deviation of . The processed historical data is then divided into training and validation sets according to a specific time series. These are then fed into a prediction model based on a long short-term memory (LSTM) network for training. During training, the LSTM network's weights and bias parameters are adjusted based on the error between the predicted and actual values. The Adam optimizer is used to minimize the loss function, improving the model's prediction accuracy and generalization capabilities.

[0082] Real-time prediction and risk assessment: In actual operation, the intelligent early warning module continuously receives new cable operation data sequences and inputs them into the trained LSTM model for real-time prediction.

[0083] Conduct an assessment, where is the risk value, is the feature weight, is the input feature, is the feature mapping function. Feature weight The contribution of different input features to the failure risk is determined by analyzing historical failure data and using the principal component analysis-linear discriminant analysis PCA-LDA joint algorithm. Feature mapping function According to the cable operation characteristics and fault mechanism design, a nonlinear mapping function is used to convert the circulating current amplitude characteristics into an indicator that is more relevant to the fault risk. During the process, calculations are performed strictly according to the formula to ensure the accuracy of the evaluation results.

[0084] Warning trigger and information output: When the calculated risk value When the set safety threshold is exceeded, the intelligent early warning module immediately triggers the early warning mechanism and sends early warning information to the operation and maintenance personnel in various ways, such as pop-up window prompts on the operation display interface and sound alarms of a specific frequency. The early warning information displays the relevant data of the current risk assessment in detail, including the input characteristic values, predicted values, risk values, etc. The system provides the calculation process and results, as well as possible fault cause analysis and recommended measures based on historical failure cases and expert experience. Specifically, if the risk assessment results indicate a short circuit risk in the cable, the warning information may indicate the possible fault location and range, and recommend checking the cable connectors for looseness or insulation damage. This provides strong support for operation and maintenance personnel to take effective maintenance measures in a timely manner, ensuring the safe and stable operation of the cable system.

[0085] Embodiment 3 of the present invention provides a terminal, including a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the method.

[0086] Embodiment 4 of the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method when executed by a processor.

[0087] Compared with the prior art, the beneficial effects of the present invention include at least: 1. The present invention's fault location module utilizes a modified two-terminal traveling wave method and precise electrical parameter modeling, combined with an advanced wavelet analysis fault type identification module. This module can accurately determine the fault location and accurately identify the fault type, effectively shortening troubleshooting time, improving power cable operation and maintenance efficiency, and reducing power outage losses. By incorporating the spatial attenuation characteristics of electromagnetic interference into compensation, the interference effects at different locations are dynamically corrected, reducing positioning errors. This makes it particularly suitable for areas with strong electromagnetic interference, such as those near substations.

[0088] 2. When evaluating risk values ​​based on predicted data, the present invention breaks through the limitations of fixed weights by dynamically adapting weights according to fault types, effectively improving the accuracy of risk assessment and preventing key features from being masked by secondary features. Feature mapping is achieved based on the sensitivity adjustment coefficient. The greater the deviation, the exponential increase in sensitivity, which strengthens the response to serious deviations from normal conditions, avoids excessive early warning of minor fluctuations, and ensures rapid identification of major anomalies.

[0089] 3. The LSTM model of the present invention is a fusion structure that introduces the attention mechanism and the residual connection, and adopts a dynamic staged training strategy and uses a weighted hybrid loss function for training. It combines the attention mechanism to focus on key features, and dynamically trains to adapt to the entire life cycle. The hybrid loss function balances prediction accuracy and robustness, and has the ability to improve the sensitivity of early weak fault signals and enhance the generalization ability of the model under complex working conditions.

[0090] 4. Through low-power continuous monitoring and protection: the cable sheath circulating current fault information collection device has a built-in micro energy collection device, which uses the electromagnetic field energy around the cable to convert power, achieve low-power continuous operation, reduce dependence on external power supply, reduce maintenance costs, and enhance the system's long-term stable monitoring capabilities in complex environments.

[0091] 5. The multi-language human-computer interaction interface and 3D dynamic graphic display function of the operation display module facilitate operation by personnel in different regions, making cable circulation and fault information intuitively visible, allowing operation and maintenance personnel to quickly grasp the cable operation status, improving operation convenience and information acquisition efficiency.

[0092] 6. By running the intelligent scene switching of the model module, updating the Bayesian reasoning, and the long-short-term memory network prediction and risk assessment of the intelligent early warning module, it can adapt to changes in cable working conditions, correct the model in real time, accurately warn, reduce interference from environmental factors, and significantly improve the accuracy and reliability of system fault diagnosis and positioning.

[0093] The present disclosure may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0094] A computer-readable storage medium can be a tangible device that can hold and store instructions for use by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punched card or raised structure in a groove on which instructions are stored, and any suitable combination thereof. As used herein, a computer-readable storage medium is not to be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse passing through a fiber optic cable), or an electrical signal transmitted through an electrical wire.

[0095] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0096] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, the state information of the computer-readable program instructions is used to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), so that the electronic circuit can execute the computer-readable program instructions, thereby implementing various aspects of the present disclosure.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A cable sheath circulating current fault location in-loop simulation method based on LABVIEW, characterized in that: include: Step 1: Under the control of LABVIEW, the current sensor collects the circulating current data of the cable sheath monitoring point in real time based on micro-energy, and displays it digitally and graphically on LABVIEW; Step 2: Decompose the circulation data using wavelet transform to obtain corresponding wavelet coefficients, and calculate the wavelet coefficient features. When the wavelet coefficient features are abnormal, input the pre-trained classification model to obtain the fault type. Step 3: Calculate the compensation coefficient considering the influence of the electromagnetic field based on the real-time monitored electromagnetic field data, and calculate the fault point location using the double-terminal traveling wave method; Step 4: The operation model uses real-time data on fault type, fault location, and cable operating parameters, and automatically switches to the corresponding typical operating condition simulation mode based on preset operating condition discrimination logic and threshold judgment conditions. The model then continuously adjusts its predictions of the cable operating status under different simulated conditions through Bayesian reasoning, simulating the cable's full lifecycle operating status to provide a reference for risk assessment. Step 5: Input the real-time data of the cable's operating parameters into the trained LSTM model for real-time prediction. The risk value is evaluated based on the predicted data. When the risk value exceeds the safety threshold, the fault warning mechanism is triggered.

2. The cable sheath circulating current fault location in-loop simulation method based on LABVIEW according to claim 1 is characterized by: Step 1: Digital display and graphical presentation on LABVIEW, including: In the data display area of ​​LABVIEW, the circulating current value, temperature and voltage of the cable sheath monitoring point are updated in real time in digital form; in the graphical display area of ​​LABVIEW, intuitive charts and 3D dynamic models are used to present the changing trend of the circulating current data and the internal structure of the cable and the direction of the circulating current.

3. The cable sheath circulating current fault location in-loop simulation method based on LABVIEW according to claim 1 is characterized by: In step 2, the cable sheath circulating current data is decomposed using wavelet transform, and the formula is as follows: in, and Decomposition layers Next k-th scaling coefficient and wavelet coefficient; is the nth circulation data; and Decomposition Time Decomposition Layer Next k-th father wavelet and mother wavelet; is the number of decomposition levels of wavelet transform.

4. The cable sheath circulating current fault location in-loop simulation method based on LABVIEW according to claim 1 is characterized by: In step 3, the formula for calculating the compensation coefficient considering the influence of the electromagnetic field based on the real-time monitored electromagnetic field data is as follows: in is the compensation coefficient; is the deviation of the real-time monitored electromagnetic field intensity from the historical mean; is the historical mean value of electromagnetic field intensity; Indicates the spatial attenuation characteristics of electromagnetic interference; is the distance between the historical fault point and the electromagnetic interference source; 、 is the calibration factor.

5. The cable sheath circulating current fault location in-loop simulation method based on LABVIEW according to claim 1 is characterized by: In step 3, the compensation coefficient is combined with the double-terminal traveling wave method to calculate the fault point location. The formula is as follows: = in, is the fault point location; 、 is the circulating current at the monitoring point at time t when the cable sheath ends A and B fail; 、 is the circulating current at the cable sheath end A and end B at the monitoring point t during normal operation; 、 The start and end time of the selected time interval; is the compensation coefficient; is the cable sheath length; is the traveling wave propagation speed.

6. The cable sheath circulating current fault location in-loop simulation method based on LABVIEW according to claim 1, characterized in that: In step 5, the formula for evaluating risk value based on the predicted data is as follows: in, is the risk value; is the feature weight; The basic weights are determined by analyzing historical fault data and the principal component analysis-linear discriminant analysis PCA-LDA joint algorithm; is the matching degree between the feature and the current fault type; is the adjustment factor; is the feature mapping function; is the i-th input feature obtained based on the predicted data; n is the total number of features.

7. The cable sheath circulating current fault location in-loop simulation method based on LABVIEW according to claim 6, characterized in that: Feature Mapping Function for: in, is the normal reference value of the input feature; is the sensitivity adjustment coefficient, is the baseline sensitivity, is the magnification factor.

8. The cable sheath circulating current fault location in-loop simulation method based on LABVIEW according to claim 1, characterized in that: The LSTM model is a fusion structure that introduces an attention mechanism and a residual connection. The attention mechanism assigns dynamic weights to parameter sequences at different operation stages of the cable, and the residual connection adds skip connections between hidden layers of the LSTM.

9. The cable sheath circulating current fault location in-loop simulation method based on LABVIEW according to claim 1, characterized in that: The LSTM model adopts a dynamic phased training strategy. In the first phase, historical normal operation data is used for pre-training. In the second phase, fault simulation data containing fault samples under different working conditions are introduced for fine-tuning. In the third phase, the online learning module absorbs the newly collected operation and maintenance data in real time and updates the model parameters through a sliding window.

10. The cable sheath circulating current fault location in-loop simulation method based on LABVIEW according to claim 1, characterized in that: The loss function of the LSTM model is a weighted hybrid loss function: in is the mean square error, is the cross entropy, is the mean absolute error, 、 、 is the dynamic adjustment coefficient.

11. A cable sheath circulating current fault location in-loop simulation system based on LABVIEW, used to implement the method according to any one of claims 1 to 10, characterized in that: The system includes hardware and software. The hardware includes a current sensor and its built-in micro energy harvesting device and a matching adaptive anti-interference circuit, which is used to accurately collect circulating current data at the cable sheath monitoring point in real time based on micro energy. The software includes: The operation and display module is built on the LABVIEW development platform. The human-computer interaction interface of the operation and display module includes a system control button area, a real-time data display area, and a graphical result display area. It is used to control the current sensor to collect the circulating current data of the cable sheath monitoring point in real time based on micro-energy, and to display it digitally and graphically. A fault type identification module is used to decompose the circulation data using wavelet transform to obtain corresponding wavelet coefficients and calculate wavelet coefficient features. When the wavelet coefficient features are abnormal, they are input into a pre-trained classification model to obtain the fault type. The fault point location module is used to calculate the compensation coefficient considering the influence of the electromagnetic field based on the real-time monitored electromagnetic field data, and calculate the fault point location by combining the double-terminal traveling wave method; The operation model module is used to run the model using real-time data on cable operating parameters. It automatically switches to the corresponding typical operating condition simulation mode through preset operating condition discrimination logic and threshold judgment conditions. It also continuously corrects the operation model's prediction of the cable operating status under different simulated conditions through Bayesian reasoning, simulating the cable's operating status throughout its life cycle to provide a reference for risk assessment. The intelligent early warning module is used to input the real-time data of the cable's operating parameters into the trained LSTM model for real-time prediction, evaluate the risk value based on the predicted data, and trigger the fault early warning mechanism when the risk value exceeds the safety threshold.

12. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images