Direct current transmission fault diagnosis method and system based on multi-modal data analysis

Abstract

The invention discloses a DC power transmission fault diagnosis method and system based on multi-modal data analysis, and relates to the field of DC power transmission line fault diagnosis, and the method comprises the steps: starting temporary line protection measures when a DC power transmission line has abnormal fluctuation, and importing parameters into a data processing center for feature extraction; obtaining fault types corresponding to the effective features; and performing statistics on each associated feature of each fault type to obtain a fault diagnosis result. According to the invention, the multi-modal parameters of the DC transmission line are monitored in real time, and electromagnetic interference is eliminated, so that the accuracy of fault diagnosis is improved, the reliability of data quality is ensured, and the precision of fault diagnosis is improved. And monitoring and protection strategies are adjusted, so that the optimal operation guarantee is achieved. And through dynamic monitoring and tracking analysis of potential faults, the stability and reliability of the system are improved.

Description

Technical Field

[0001] The present invention relates to the field of DC transmission line fault diagnosis, and in particular to a DC transmission fault diagnosis method and system based on multimodal data analysis. Background Art

[0002] In modern power systems, high-voltage direct current (HVDC) transmission technology is widely used in grid construction due to its advantages, including long-distance, low-loss transmission, ability to interconnect asynchronous grids, and flexible power flow control. However, HVDC systems are subject to various faults during operation, such as converter station failures, DC line faults, ground faults, control system anomalies, and electromagnetic interference. To address these issues, fault diagnosis technology has become crucial to ensuring the safe and stable operation of power grids.

[0003] Due to the complexity, nonlinearity, and strong electromagnetic interference characteristics of DC transmission systems, traditional fault diagnosis approaches based on a single data source and a single analysis method have significant limitations in terms of accuracy, interference immunity, real-time performance, and adaptability. Currently, mainstream HVDC fault diagnosis methods, primarily based on single data sources (such as voltage, current, and power) and single analysis methods (such as threshold methods, rule matching, and traditional signal processing), still have many limitations. Therefore, fault diagnosis based on multimodal data analysis is an important direction for future DC transmission fault diagnosis.

[0004] Existing technologies, such as the invention patent with announcement number CN104820158B, are a method for determining a DC line break fault in a flexible DC transmission system. The method detects and calculates the positive and negative DC bus currents, the positive and negative DC bus current change rates, and the AC and DC power difference. When the above parameters simultaneously meet the following conditions, it is determined that a DC line break fault has occurred in the system: ① The absolute value of either the positive or negative DC bus current is less than the current limit; ② The absolute values of the positive and negative DC bus current change rates are both greater than the current change rate limit; ③ The absolute value of the difference between the AC power and the DC power is greater than the power difference limit.

[0005] The prior art, such as the invention patent with announcement number CN118604530B, is a DC fault location method and system, which includes obtaining a first voltage and current signal of a DC line in real time; obtaining a positive current signal and a negative current signal of the DC line respectively, and calculating the current between the positive and negative poles of the DC line based on the positive current signal and the negative current signal using a component formula, obtaining a second voltage and current signal of the DC line within a preset time period, connecting all the second voltage and current signals within the preset time in sequence, and performing curve fitting on the formed line to form a fitting line; selecting a third voltage and current signal corresponding to two random time points of the fitting line, and selecting a corresponding matrix formula based on the type of the fault signal, and using a distance calculation formula to calculate the location of the DC line fault based on the value of the current between the positive and negative poles of the DC line, the voltage matrix, and the current matrix.

[0006] Based on the above scheme, it can be seen that the existing technology in the field of DC transmission fault diagnosis often relies on fixed parameter limits. However, under different operating conditions (such as load changes, ambient temperature changes, and grid disturbances), fixed parameter limits may lead to misjudgment or missed judgment. In addition, the existing technology often only investigates a single fault, but the DC transmission system has multiple fault types such as DC short circuit, ground fault, and converter fault. The judgment method of a single parameter combination cannot cover all fault modes. In actual applications, the DC transmission system is easily affected by factors such as electromagnetic interference, and ignoring the influence of these interferences may misjudge certain transient fluctuations as faults. Therefore, when diagnosing DC transmission faults, it is necessary to comprehensively consider multi-modal parameters after removing the influence of other factors to conduct comprehensive fault diagnosis. Summary of the Invention

[0007] In response to the shortcomings of the prior art, the present invention provides a DC transmission fault diagnosis method and system based on multimodal data analysis. To achieve the above objectives, the present invention is implemented through the following technical solutions: The DC transmission fault diagnosis method based on multimodal data analysis includes:

[0008] The DC transmission lines are monitored in real time. When abnormal fluctuations occur in the DC transmission lines, temporary line protection measures are activated. At the same time, the DC transmission line parameters at the abnormal moment are fed into the data processing center for feature extraction.

[0009] When the extracted feature value of a key feature is greater than its corresponding feature threshold, the key feature is recorded as a valid feature and the fault types corresponding to the valid feature are matched.

[0010] The associated features of each fault type are counted, and the fault diagnosis confidence score value of each fault type is obtained by analysis and processing. The score is then compared with the fault diagnosis confidence threshold to obtain the fault diagnosis result.

[0011] As a preferred technical solution, real-time monitoring of DC transmission lines is carried out. When abnormal fluctuations occur in the DC transmission lines, temporary line protection measures are activated. The specific process is as follows:

[0012] Real-time collection of DC transmission line parameters, including electrical parameters, converter station control parameters, and equipment parameters.

[0013] Electrical parameters include DC voltage, DC current, active power and harmonic content.

[0014] The control parameters of the converter station include the trigger angle and the arc extinguishing angle.

[0015] Equipment parameters include converter valve temperature, line insulation test score and ground current.

[0016] The DC transmission line parameters are transmitted to the data processing center for processing and analysis to obtain an abnormal fluctuation risk value. When the abnormal fluctuation risk value is greater than the abnormal fluctuation risk threshold, it is determined that abnormal fluctuation has occurred in the DC transmission line. The time when the DC transmission line parameters are obtained is recorded as the abnormal time. Based on the abnormal fluctuation risk value, a mapping is performed with the temporary line protection measures corresponding to each abnormal fluctuation risk value interval pre-stored in the built-in database of the data processing center to obtain the temporary line protection measures for the abnormal fluctuation risk value, and the temporary line protection is activated. The specific process includes:

[0017] When the abnormal fluctuation risk value is greater than or equal to the highest risk threshold, it is determined that the abnormal fluctuation risk value is in the first interval, and the temporary line protection measure set in the first interval is matched and the temporary line protection is turned on.

[0018] When the abnormal fluctuation risk value is less than the highest risk threshold and greater than or equal to the medium risk threshold, the abnormal fluctuation risk value is determined to be in the second interval, and the temporary line protection measures set in the second interval are matched and the temporary line protection is turned on.

[0019] When the abnormal fluctuation risk value is less than the medium risk threshold and greater than or equal to the abnormal fluctuation risk threshold, the abnormal fluctuation risk value is determined to be in the third interval, and the temporary line protection measures set in the third interval are matched and the temporary line protection is turned on.

[0020] As a preferred technical solution, the DC transmission line parameters at the abnormal moment are fed into the data processing center for feature extraction. The specific process is as follows:

[0021] The parameters of the DC transmission line at the abnormal moment are fed into the data processing center for standardization;

[0022] The time domain features and frequency domain features are extracted respectively, and the principal component analysis is performed on the time domain features and the frequency domain features to obtain the key features of the DC transmission line parameters. The key features are imported into the fault diagnosis processor built into the data processing center for fault diagnosis analysis.

[0023] As a preferred technical solution, when the extracted feature value of a key feature is greater than its corresponding feature threshold, the key feature is recorded as a valid feature and matched to obtain the corresponding fault types of the valid feature, specifically including:

[0024] After receiving each key feature, the fault diagnosis processor built into the data processing center calculates the characteristic value of each key feature, and extracts the characteristic threshold of each key feature from the built-in database of the data processing center, and compares the characteristic value of each key feature with its corresponding characteristic threshold. When the characteristic value of a key feature is greater than its corresponding characteristic threshold, the key feature is determined to be a valid feature, and the fault types corresponding to the valid feature are counted.

[0025] When the characteristic value of a key feature is less than or equal to its corresponding characteristic threshold, the key feature is determined to be an invalid feature, and fault diagnosis is performed based on the determination results of each key feature.

[0026] As a preferred technical solution, fault diagnosis is performed based on the judgment results of each key feature, specifically including:

[0027] When all key features are invalid, the abnormal moment is recorded, and the DC transmission line is switched to a pending state, and a short-term monitoring cycle is set for trial operation.

[0028] Conduct trial operation monitoring on the DC transmission line to obtain the trial operation electrical test parameters within a short monitoring period, input them into the data processing center for feature extraction, obtain each key feature and determine whether each key feature is a valid feature, and obtain the trial operation monitoring results of the DC transmission line.

[0029] If the test operation monitoring results of the DC transmission line show that all the features are invalid, it is determined that the DC transmission line has no fault and is switched to a normal operation state.

[0030] If the trial operation monitoring result of the DC transmission line shows that there are valid features, it is determined that there is a fault in the DC transmission line, and various fault types corresponding to various valid features are counted.

[0031] As a preferred technical solution, statistics of the associated features of each fault type are collected and analyzed to obtain the fault diagnosis confidence score value of each fault type, specifically including:

[0032] The effective features corresponding to each fault type are counted as the associated features of each fault type to obtain the fault index of each associated feature. Based on the fault index of each associated feature and the number of associated features of each fault type, the coupling processing is corrected to obtain the fault diagnosis confidence score value of each fault type.

[0033] Obtain the fault index of each associated feature, including:

[0034] The feature value of each associated feature is subtracted from its corresponding feature threshold to obtain the feature difference value of each associated feature. Based on the feature difference value of each associated feature, it is mapped and matched with the fault index corresponding to each feature difference value preset in the built-in database of the data processing center to obtain the fault index of each valid feature.

[0035] As a preferred technical solution, the fault diagnosis result is obtained by comparing it with the fault diagnosis confidence threshold, which specifically includes:

[0036] The fault diagnosis confidence score value of each fault type is compared with the fault diagnosis confidence threshold. If the fault diagnosis confidence score value of a fault type is greater than or equal to the fault diagnosis confidence threshold, the fault type is determined to be a significant fault.

[0037] If the fault diagnosis confidence score value of a certain fault type is less than the fault diagnosis confidence threshold, the fault type is determined to be a potential fault.

[0038] As the preferred technical solution, the fault diagnosis results are obtained, and the specific processing conditions are:

[0039] The fault types of which the fault diagnosis results are significant faults are statistically analyzed and recorded as significant fault types. The significant fault types are sorted based on the fault diagnosis confidence scores of the significant fault types and sent to the data management terminal for early warning.

[0040] If the fault diagnosis results of each fault type are all potential faults, then based on the total number of fault types, the system matches the dynamic monitoring period corresponding to the total number of each fault type preset in the database built into the data processing center to obtain the dynamic monitoring period. Based on the dynamic monitoring period, the system dynamically monitors the DC transmission line, specifically including:

[0041] Based on the dynamic monitoring cycle, real-time monitoring data of the DC transmission line within the dynamic monitoring cycle is obtained, and trend analysis is performed on the data to obtain tracking analysis results of the DC transmission line.

[0042] If the associated characteristic value of a potential fault continues to rise and exceeds its corresponding characteristic threshold during the dynamic monitoring cycle, the tracking analysis result of the DC transmission line will be determined as a tracking fault, and the fault type will be determined as a significant fault and sent to the data management terminal for early warning.

[0043] If the associated characteristic values of each potential fault remain stable and do not exceed their corresponding characteristic thresholds during the dynamic monitoring cycle, the tracking analysis results of the DC transmission line are determined to be short-term fluctuations, the dynamic monitoring cycle is terminated, and the normal monitoring cycle is switched.

[0044] As a preferred technical solution, real-time acquisition of DC transmission line parameters also includes sensor detection to remove the influence of internal electromagnetic interference in the sensor. The specific processing conditions are:

[0045] Monitor sensor power data at abnormal times, including voltage change rate, current change rate, and electromagnetic interference spectrum.

[0046] The voltage change rate is used to determine whether it is a high-frequency interference source, the current change rate is used to determine whether the electromagnetic interference has radiation interference characteristics, and the electromagnetic interference spectrum is used to determine the location of the interference source.

[0047] Based on the power data of the sensor at the abnormal moment, it is imported into the data processing center for feature extraction. After confirming the characteristics of the electromagnetic interference, it is mapped and matched with the filtering algorithms corresponding to each feature preset in the built-in database of the data processing center to obtain the filtering algorithms corresponding to the electromagnetic interference characteristics for electromagnetic interference elimination processing.

[0048] Record the quality data of DC transmission line parameters before and after filtering, including harmonic content, signal-to-noise ratio and mean square error.

[0049] The filtered DC transmission line parameters are re-imported into the data processing center, and the quality data of the DC transmission line parameters before and after filtering are compared to verify whether the electromagnetic interference is effectively eliminated.

[0050] If the electromagnetic interference is effectively eliminated, the filtered DC transmission line parameters are subsequently analyzed and processed.

[0051] If the electromagnetic interference is not effectively eliminated, an early warning will be sent to the data management terminal.

[0052] The DC transmission fault diagnosis system based on multimodal data analysis includes:

[0053] The real-time monitoring module is used to monitor the DC transmission line in real time. When the DC transmission line experiences abnormal fluctuations, temporary line protection measures are activated. At the same time, the DC transmission line parameters at the abnormal moment are fed into the data processing center for feature extraction.

[0054] The fault type matching module is used to record a key feature as a valid feature and match the fault types corresponding to the valid feature when the feature value of the extracted key feature is greater than its corresponding feature threshold.

[0055] The fault type judgment module is used to count the associated features of each fault type, analyze and process to obtain the fault diagnosis confidence score value of each fault type, and compare it with the fault diagnosis confidence threshold to obtain the fault diagnosis result.

[0056] Compared with the prior art, the embodiments of the present invention have at least the following beneficial effects:

[0057] (1) The present invention provides a DC transmission fault diagnosis method based on multimodal data analysis. By real-time monitoring of the multimodal parameters of the DC transmission line, the method can significantly improve the response speed to faults and ensure the stability and safety of the system. The method provides a comprehensive understanding of the operating status of the DC transmission line from multiple perspectives. By extracting and analyzing features from this multimodal data, the data center facilitates accurate diagnosis of the type and cause of the fault.

[0058] (2) The present invention monitors the voltage change rate, current change rate and electromagnetic interference spectrum, and combines the filtering algorithm of the data processing center to eliminate interference, ensure data quality, and prevent electromagnetic interference from misleading fault diagnosis results, thereby improving the accuracy of fault diagnosis. By using intelligent filtering algorithms, electromagnetic interference, noise and other factors in the sensor are effectively eliminated, ensuring the reliability of data quality. This improves the accuracy of fault diagnosis.

[0059] (3) The present invention adjusts the monitoring and protection strategies according to different fault types and diagnostic confidence scores, so that the system has strong adaptability. The matching of different risk intervals and temporary protection measures can dynamically adjust the protection level to achieve the best operation guarantee. Through dynamic monitoring and tracking analysis of potential faults, the system can identify and respond to impending faults in advance, thereby improving the stability and reliability of the system. A dynamic monitoring cycle is introduced to continuously track and analyze potential faults. When the associated characteristic values of certain potential faults continue to rise and exceed the characteristic threshold, the system will adjust the diagnostic strategy in real time, determine the fault type as a significant fault and issue an early warning. Through this dynamic adjustment mechanism, the system can continuously optimize the accuracy of fault diagnosis and take corresponding protection measures in a timely manner, avoiding omissions and misjudgments caused by static judgments.

[0060] Of course, any product implementing the present invention does not necessarily need to achieve all of the above advantages at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 Schematic diagram of the method of the present invention.

[0062] Figure 2 Schematic diagram of the system module of the present invention. DETAILED DESCRIPTION

[0063] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0064] In the description of the present invention, it should be understood that the terms "opening", "upper", "lower", "thickness", "top", "middle", "length", "inside", "around" and the like indicating orientation or positional relationship are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0065] See also Figure 1 As shown, an embodiment of the present invention provides a DC transmission fault diagnosis method based on multimodal data analysis, which specifically includes:

[0066] The DC transmission lines are monitored in real time. When abnormal fluctuations occur in the DC transmission lines, temporary line protection measures are activated. At the same time, the DC transmission line parameters at the abnormal moment are fed into the data processing center for feature extraction.

[0067] Real-time monitoring of DC transmission lines is carried out. When abnormal fluctuations occur on the DC transmission lines, temporary line protection measures are activated. The specific process is as follows:

[0068] Real-time collection of DC transmission line parameters, including electrical parameters, converter station control parameters, and equipment parameters.

[0069] Electrical parameters include DC voltage, DC current, active power and harmonic content.

[0070] DC voltage, the voltage difference between the two ends of a DC power transmission line, is a fundamental parameter in power transmission. The magnitude of DC voltage directly determines the flow of current and the transmission capacity. Higher voltages improve transmission efficiency, but excessively high voltages can damage equipment.

[0071] DC current refers to the amount of electricity flowing along a DC transmission line. It represents the current actually flowing through the circuit at a given voltage. The magnitude of this current directly affects the load and power transmission capacity of the DC transmission line. Excessive current can cause line overloads and even damage equipment.

[0072] Active power refers to the actual electrical energy transmitted, representing the energy conversion between current and voltage and representing the actual usable power. It reflects the workload of the DC transmission line and the efficiency of electrical energy use. Low active power indicates inefficient system performance, while excessive power may lead to system overload and compromise equipment safety.

[0073] Harmonic content refers to the distortion of current or voltage waveforms in DC transmission lines, particularly when using power electronics (such as converter stations). The ideal voltage and current waveforms in DC transmission lines are sinusoidal. However, due to nonlinear loads or the use of converter equipment, deviations from these waveforms can occur, creating harmonics. High harmonic content can cause heating in electrical equipment, reduced efficiency, and decreased system stability.

[0074] The control parameters of the converter station include the trigger angle and the arc extinguishing angle.

[0075] In a direct current transmission system, a converter station is a key device that converts alternating current (AC) into direct current (DC) or converts DC into AC.

[0076] The trigger angle is the angle within the AC power cycle when the trigger signal for a thyristor (SCR) in a converter station occurs. Converter stations use thyristors to control the conduction and cutoff of current, and the trigger angle controls the moment the thyristor turns on.

[0077] By adjusting the trigger angle, the current conduction time can be controlled, thereby affecting the current magnitude and direction and regulating the flow of transmitted power. The trigger angle directly affects the inverter's output voltage. Changing the trigger angle can adjust the magnitude and fluctuation range of the DC voltage. By adjusting the trigger angle, the amount of active power transmitted can be varied. A larger trigger angle (i.e., delaying the trigger moment) reduces the current conduction time, thereby reducing output power. Conversely, a smaller trigger angle increases power output.

[0078] The arc extinction angle is the angle relative to the AC cycle when the thyristor in the converter station is turned off. It determines the moment when the thyristor switches from the on state to the off state.

[0079] The purpose of the arc-extinguishing angle is to ensure that the thyristor can be completely turned off at the correct moment in the AC cycle, avoiding "reverse breakdown" or the inability to switch state due to current reversal.

[0080] Appropriate arc extinguishing angle ensures that the converter station can effectively "extinguish the arc", preventing the current from being shut down too early or too late, thereby avoiding unstable operation of the converter.

[0081] If the arc extinguishing angle is not set properly, the thyristor may not be able to be effectively closed, resulting in overcurrent or overvoltage, thus affecting the safe operation of the system.

[0082] During the AC / DC conversion process, the arc extinguishing angle affects the switching timing of the current flow direction, ensuring that the converter station can smoothly perform power direction conversion or current zero crossing.

[0083] Equipment parameters include converter valve temperature, line insulation test score and ground current.

[0084] Converter valve temperature refers to the operating temperature of the converter valves in converter stations. The current flowing through these valves generates heat during operation, and temperature fluctuations can affect their performance and safety. Excessively high temperatures can damage valve components or shorten their lifespan. Excessively high valve temperatures can also affect their electrical conductivity, potentially leading to equipment overload or failure.

[0085] The Line Insulation Test Score (TIS) evaluates the insulation performance of transmission lines, determining their health by measuring the insulation resistance of the transmission line. This score, derived by measuring the insulation resistance and other relevant parameters, reflects the presence of aging, cracks, or other defects that could affect insulation performance. Insulation performance is a key factor in ensuring the safe operation of DC transmission lines. Low insulation resistance indicates poor insulation performance, potentially posing a risk of leakage current, short circuits, or equipment damage.

[0086] In an embodiment of the present invention, the insulation performance of a transmission line is detected by transmitting a DC high voltage to the transmission line, specifically including:

[0087] Connect the high-voltage end of the high-voltage generator to the circuit under test, ground the other end, and connect the leakage current meter in series in the loop. Increase the voltage gradually according to the standard (e.g., 1.5-2 times the rated voltage) to avoid insulation damage caused by shock. Record the leakage current as it changes with voltage. If there is an abnormal increase, that is, its single increase does not exceed the preset increase threshold but the total increase in current exceeds the preset increase threshold, there may be an insulation defect. Continue to apply the test voltage according to the duration standard and observe whether the leakage current is stable. If the leakage current is small and stable, that is, the increase in the leakage current changes with the voltage and remains within the preset increase threshold, it indicates good insulation performance. If the leakage current gradually increases, that is, the leakage current slowly increases with the increase in voltage until the leakage current exceeds the preset increase threshold at a certain voltage, it may indicate moisture or aging problems. If the leakage current suddenly increases, that is, the single increase in the leakage current exceeds the preset increase threshold, it may indicate insulation damage or partial discharge. Gradually reduce the voltage to avoid breakdown caused by sudden changes in the electric field.

[0088] Ground current refers to the current flowing to the ground through the grounding device. Grounding in DC transmission lines is a method of protecting systems and equipment from electric shock and other electrical faults. When a system fault occurs (such as insulation breakdown or current leakage), ground current flows to the ground, protecting personnel and equipment from electrical hazards. The magnitude of the ground current can indicate the presence of a ground fault or current leakage in the DC transmission line. Excessive ground current usually indicates a fault in a part of the system that requires immediate inspection and repair.

[0089] The DC transmission line parameters are transmitted to the data processing center, and the DC transmission verification parameters of the DC transmission line are extracted from the built-in database of the data processing center. The abnormal fluctuation risk value is obtained through processing and analysis, specifically including:

[0090]

[0091] Among them, R is the abnormal fluctuation risk value, U is the DC voltage, I is the DC current, P is the active power, THD is the harmonic content, FA is the trigger angle, CA is the arc extinguishing angle, T is the converter valve temperature, I gc is the ground current, LIT is the line insulation test score, U0 is the calibration DC voltage, I0 is the calibration DC current, P0 is the calibration active power, THD0 is the calibration harmonic content, FA0 is the calibration trigger angle, CA0 is the calibration arc extinguishing angle, T0 is the calibration converter valve temperature, I gc0 To verify the ground current, LIT0 is the line insulation test score threshold, ω1 is the electrical parameter weight factor, ω2 is the converter station control parameter weight factor, ω3 is the equipment parameter weight factor, ε U is the voltage parameter unification factor, ε I is the current parameter unification factor, ε P is the active power parameter unification factor, ε THD is the harmonic content parameter unification factor, ε T is the temperature parameter unification factor, ε LIT Unify factors for line insulation test scoring parameters.

[0092] It should be noted that the electrical parameter weight factor, the converter station control parameter weight factor, and the equipment parameter weight factor all have a value range between 0 and 1 and satisfy ω1+ω2+ω3=1. The electrical parameter weight factor is an influencing factor of the electrical parameter pre-stored in the built-in database of the data processing center, indicating the degree of influence of the electrical parameter on the abnormal fluctuation risk value; the converter station control parameter weight factor is an influencing factor of the converter station control parameter pre-stored in the built-in database of the data processing center, indicating the degree of influence of the converter station control parameter on the abnormal fluctuation risk value; the equipment parameter weight factor is an influencing factor of the equipment parameter pre-stored in the built-in database of the data processing center, indicating the degree of influence of the equipment parameter on the abnormal fluctuation risk value. When used, they are directly extracted from the built-in database of the data processing center. For example, the electrical parameters of the DC transmission parameters of the power system, the converter station control parameters, and the equipment parameters are input into a preset mapping set in the built-in database of the data processing center to obtain the electrical parameter weight factor, the converter station control parameter weight factor, and the equipment parameter weight factor of the DC transmission parameters of the power system, and the corresponding mapping relationship is one-to-one.

[0093] It should also be noted that electrical parameters, converter station control parameters, and equipment parameters are closely correlated. DC voltage, DC current, and active power are core operating parameters of a DC transmission system, and their changes are directly affected by converter station control parameters. Increasing the firing angle reduces DC voltage, potentially decreasing DC current, and reducing active power. Reducing the firing angle increases DC voltage, potentially increasing DC current, and increasing active power. The arc extinction angle affects the shutoff state of the converter valve, which in turn affects DC voltage stability. If the arc extinction angle is too small, the converter valve may not fully shut off, resulting in abnormal current fluctuations and, in turn, affecting power quality. Higher DC currents increase the converter valve conduction time and higher temperatures, potentially leading to valve overheating. Excessively high valve temperatures can reduce valve reliability and even damage it, causing abnormal voltage and current fluctuations. High harmonic content may be caused by abnormal converter valve operation (such as improper firing or arc extinction angle control), which can lead to additional current fluctuations and compromise equipment safety. Degraded insulation performance (lower line insulation test scores) can cause voltage waveform distortion and exacerbate harmonic effects, leading to abnormal equipment heating or electromagnetic interference. Excessive ground current may indicate insulation damage, causing current leakage, which in turn affects the stability of DC current and voltage. If DC current is excessively high for a long period of time, the converter valve temperature will continue to rise, potentially causing insulation aging and, in turn, affecting line insulation performance (lower line insulation test scores). Degraded insulation performance can cause leakage, leading to increased ground leakage current. If ground current continues to increase, it may threaten the safe operation of equipment and even affect the operational stability of the converter station.

[0094] It should also be noted that the voltage parameter unified factor, current parameter unified factor, active power parameter unified factor, harmonic content parameter unified factor, temperature parameter unified factor and line insulation test score parameter unified factor are adjustment coefficients used in the embodiment of the present invention to eliminate the mismatch between different parameters and enable multiple parameters with different physical units or types to be linearly operated.

[0095] When the abnormal fluctuation risk value is greater than the abnormal fluctuation risk threshold, it is determined that abnormal fluctuation occurs in the DC transmission line. The time when the DC transmission line parameters are obtained is recorded as the abnormal time. Based on the abnormal fluctuation risk value, a mapping and matching is performed with the temporary line protection measures corresponding to each abnormal fluctuation risk value interval pre-stored in the built-in database of the data processing center to obtain the temporary line protection measures for the abnormal fluctuation risk value, and activate the temporary line protection. In an embodiment of the present invention, the temporary line protection measures include switching to an alternative route, reclosing control, and dynamic load adjustment, and specifically include:

[0096] When the abnormal fluctuation risk value is greater than or equal to the highest risk threshold, it is determined that the abnormal fluctuation risk value is in the first interval, and the temporary line protection measure set in the first interval is matched and the temporary line protection is turned on. In the embodiment of the present invention, the temporary line protection measure is to switch to a backup route.

[0097] When the abnormal fluctuation risk value is less than the highest risk threshold and greater than or equal to the medium risk threshold, it is determined that the abnormal fluctuation risk value is in the second interval, and the temporary line protection measures set in the second interval are matched and the temporary line protection is turned on. In the embodiment of the present invention, the temporary line protection measures are controlled by reclosing.

[0098] When the abnormal fluctuation risk value is less than the medium risk threshold and greater than the abnormal fluctuation risk threshold, it is determined that the abnormal fluctuation risk value is in the third interval, and the temporary line protection measures set in the third interval are matched and the temporary line protection is turned on. In the embodiment of the present invention, the temporary line protection measures adopt dynamic load adjustment.

[0099] It's important to note that in DC transmission lines, temporary line protection measures are implemented quickly in the event of abnormal fluctuations to ensure stable system operation and prevent wider-scale failures. Switching to an alternate route involves the system automatically or by notifying a designated operator to manually switch to a pre-determined backup power transmission line. This prevents a fault from spreading to other parts of the system by redirecting power flow.

[0100] Reclosing control refers to the process of automatically reclosing the circuit breaker after a short-term power line fault. Specifically, after a line fault occurs, the system disconnects the line, waits for a few seconds (usually a few hundred milliseconds to a few seconds), and then automatically recloses the circuit breaker to restore power if the fault has resolved. Some faults may be temporary, such as contact issues in power lines caused by external factors like lightning or windblown branches. Reclosing can effectively resolve these temporary faults without requiring a prolonged power outage. Reclosing control can quickly restore power supply, reducing the duration of outages and the impact on users.

[0101] Dynamic load regulation is the process of controlling system load to alleviate system pressure when abnormal fluctuations occur on DC transmission lines. This is typically accomplished by adjusting the DC transmission lines based on their load reduction values to reduce partial load supply and maintain system stability. When a DC transmission line faces the risk of overload, dynamic load regulation can alleviate pressure by temporarily reducing partial load, preventing the DC transmission line from collapsing.

[0102] It should be noted that, in an embodiment of the present invention, the abnormal fluctuation risk value is subtracted from the abnormal fluctuation risk threshold to obtain the abnormal fluctuation difference, which is mapped and matched with each load reduction value corresponding to the abnormal fluctuation difference pre-stored in the built-in database of the data processing center to obtain the load reduction value of the DC transmission line.

[0103] Real-time acquisition of DC transmission line parameters also includes sensor detection and removal of internal electromagnetic interference in the sensors. The specific processing conditions are:

[0104] Monitor sensor power data at abnormal moments, including voltage change rate, current change rate, and electromagnetic interference spectrum.

[0105] The voltage change rate is used to determine whether it is a high-frequency interference source, the current change rate is used to determine whether the electromagnetic interference has radiation interference characteristics, and the electromagnetic interference spectrum is used to determine the location of the interference source.

[0106] Based on the power data of the sensor at the abnormal moment, it is imported into the data processing center for feature extraction. After the characteristics of the electromagnetic interference are confirmed, it is mapped and matched with the filtering and denoising methods corresponding to each feature preset in the built-in database of the data processing center. The filtering algorithm corresponding to the electromagnetic interference feature is obtained to eliminate the electromagnetic interference. The specific process is as follows:

[0107] Monitor the sensor's voltage and current rate of change at the moment of an abnormality. The voltage rate of change reflects the speed of voltage fluctuations. Rapid voltage rate of change can be used to determine the presence of high-frequency electromagnetic interference sources. Generally speaking, high-frequency interference sources cause rapid voltage changes, manifesting as rapid voltage fluctuations.

[0108] The current rate of change reflects the speed at which the current changes. By monitoring the current rate of change, it is possible to identify whether current fluctuations exhibit radiated interference characteristics. For example, electromagnetic interference can cause sudden current changes, manifesting as sudden current fluctuations. Radiated interference typically manifests as strong, instantaneous current fluctuations.

[0109] Abnormal high-frequency components in the spectrum can be used to identify the characteristics and location of electromagnetic interference sources. By comparing the spectrum characteristics, the frequency range, intensity, and location of the interference source can be determined.

[0110] Based on the voltage and current rates of change, and the electromagnetic interference spectrum, the signals are fed into the data processing center for analysis. This analysis involves determining if the voltage rate of change is large and a significant high-frequency signal appears in the spectrum, indicating the presence of an external or internal source of high-frequency electromagnetic interference, such as electrical equipment switching or lightning. If the current rate of change exhibits a significant abrupt change and the spectrum shows a strong interference signal, this is due to a radiated interference source (such as a transformer or converter). Spectrum analysis can determine the frequency range of the electromagnetic interference source and further analyze its origin. For example, interference in a specific frequency band may be associated with specific equipment (such as high-frequency equipment or switching devices), helping to locate the interference source.

[0111] The data is imported into the data processing center to extract time-domain and frequency-domain features. The electromagnetic interference features are clustered through pattern recognition (e.g., K-means clustering). In this embodiment, these include power frequency interference, high-frequency switching noise, harmonic interference, arc interference, etc. The extracted electromagnetic interference features are matched with the denoising filters in the built-in database of the data processing center to obtain the corresponding filtering algorithm for the electromagnetic interference features. The filtering algorithm is then applied to denoise the sensor data.

[0112] Record the quality data of DC transmission line parameters before and after filtering, including harmonic content, signal-to-noise ratio and mean square error.

[0113] The filtered DC transmission line parameters are re-imported into the data processing center. The quality data of the DC transmission line parameters before and after filtering are compared to verify whether the electromagnetic interference has been effectively eliminated. Specifically, the following are performed:

[0114] The quality data of the DC transmission line parameters after filtering, including harmonic content, signal-to-noise ratio, and mean square error, are compared with the quality data of the DC transmission line parameters before filtering to obtain the electromagnetic interference elimination evaluation value of the DC transmission line parameters. The specific processing conditions are:

[0115]

[0116] Where D is the electromagnetic interference elimination evaluation value of the DC transmission line parameters, THD after is the harmonic content after filtering, SNRafter is the signal-to-noise ratio after filtering, MSE after is the mean square error after filtering, THD before is the harmonic content before filtering, SNR before is the signal-to-noise ratio before filtering, MSE before is the mean square error before filtering.

[0117] The electromagnetic interference elimination evaluation value based on the DC transmission line parameters is compared with the preset electromagnetic interference elimination evaluation threshold. If the electromagnetic interference elimination evaluation value of the DC transmission line parameters is greater than or equal to the electromagnetic interference elimination evaluation threshold, it is determined that the electromagnetic interference is not effectively eliminated; if the electromagnetic interference elimination evaluation value of the DC transmission line parameters is less than the electromagnetic interference elimination evaluation threshold, it is determined that the electromagnetic interference is effectively eliminated.

[0118] If the electromagnetic interference is effectively eliminated, the filtered DC transmission line parameters are subsequently analyzed and processed.

[0119] If the electromagnetic interference is not effectively eliminated, an early warning will be sent to the data management terminal.

[0120] The filtering algorithms include bandpass filtering, wavelet transform denoising, adaptive filtering and morphological filtering. The DC transmission line parameters at the abnormal moment are fed into the data processing center for feature extraction. The specific process is as follows:

[0121] The parameters of the DC transmission line at the abnormal moment are fed into the data processing center for standardization;

[0122] The time domain features and frequency domain features are extracted respectively, and the principal component analysis is performed on the time domain features and the frequency domain features to obtain the key features of the DC transmission line parameters. The key features are imported into the fault diagnosis processor built into the data processing center for fault diagnosis analysis.

[0123] It should be noted that the purpose of standardization is to convert data of different dimensions and ranges into a unified scale for subsequent analysis. A common standardization method is to subtract the mean of each feature value and divide it by the standard deviation, so that the data has zero mean and unit variance.

[0124] Time domain features refer to features extracted from the time series data of the original signal, including mean, variance, peak, skewness, kurtosis, etc. These features can be used to obtain information such as the volatility, trend, and periodicity of the signal.

[0125] Frequency domain features are obtained by performing frequency domain analysis on the signal (such as fast Fourier transform FFT), including the signal's spectrum, the intensity of the frequency components, the harmonic components, the frequency bandwidth, etc. These features help to identify periodic patterns and interference in the signal.

[0126] Principal component analysis (PCA) is a commonly used dimensionality reduction technique that projects the original features into a new space through a linear transformation, generating new "principal components" that are linear combinations of the data with the largest variance. The goal of PCA is to reduce the dimensionality of the data while preserving the main information in the data.

[0127] After principal component analysis, the main components obtained are the key features of the DC transmission line parameters. These key features can effectively reflect the overall behavior of the DC transmission line and help detect potential faults or anomalies.

[0128] When the extracted feature value of a key feature is greater than its corresponding feature threshold, the key feature is recorded as a valid feature and the fault types corresponding to the valid feature are matched.

[0129] When the extracted feature value of a key feature is greater than its corresponding feature threshold, the key feature is recorded as a valid feature and matched to obtain the corresponding fault types of the valid feature, including:

[0130] After receiving each key feature, the fault diagnosis processor built into the data processing center calculates the characteristic value of each key feature, including:

[0131] In the embodiments of the present invention, the key features include but are not limited to voltage swell, voltage sag, DC current surge, DC current sag, DC bus potential drift, IGBT temperature rise, enhanced partial discharge and IGBT temperature rise.

[0132] The mean, root mean square value, peak-to-peak value, kurtosis and skewness of each feature data under each key feature are extracted to calculate the time domain features and obtain the time domain feature value of each key feature.

[0133] By performing Fourier transform on the signal, calculating the intensity of each frequency component in the signal, and performing frequency domain feature calculation, the frequency domain eigenvalue of each key feature is obtained.

[0134] The time domain eigenvalues and frequency domain eigenvalues of each key feature are integrated and input into the built-in fault diagnosis processor of the data processing center to calculate and obtain the eigenvalues of each key feature.

[0135] It should be noted that the methods for synthesizing the time domain eigenvalues and frequency domain eigenvalues of each key feature include feature normalization, feature fusion, and weighted fusion. In the embodiment of the present invention, weighted fusion is selected to comprehensively process the time domain eigenvalues and frequency domain eigenvalues of each key feature. Deep learning is performed through the neural network of the data processing center to automatically obtain the weights of the time domain eigenvalues and frequency domain eigenvalues of each key feature. The eigenvalue of a key feature is calculated, and the specific process includes:

[0136] F time=[μ,RMS,PtP,Kurtosis,Skewness];

[0137] F freq =[MF,SE,HR,PSD,SN];

[0138] Among them, F time is the initial matrix of the time domain features of the key features, F freq is the initial frequency domain feature matrix of the key feature, μ is the mean of the key feature, and the mean is used to measure the average level of the signal. RMS is the root mean square value of the key feature, and the root mean square value is a representative indicator of signal energy. PtP is the peak-to-peak value of the key feature, and PtP is used to describe the maximum amplitude range. Kurtosis is the kurtosis of the key feature, and Kurtosis is used to measure the degree of mutation of the signal and detect impact characteristics. Skewness is the skewness of the key feature, and Skewness is used to describe the symmetry of the signal. MF is the main frequency of the key feature, which is used to characterize the frequency component with the largest energy in the signal. SE is the spectral energy of the key feature, which is used to characterize the total energy of the signal in the frequency domain. HR is the harmonic content of the key feature, which is used to analyze the amplitude ratio of the fault feature frequency. PSD is the power spectral density of the key feature, which is used to describe the power distribution of the signal at different frequencies. SN is the spectral entropy of the key feature, which is used to measure whether the energy distribution of the spectrum is uniform.

[0139] After normalization, the normalized matrix is obtained, which specifically includes:

[0140]

[0141] Among them, F time，norm is the time domain feature normalization matrix of the key feature, F freq，norm is the frequency domain feature normalization matrix of the key feature, is the normalized mean of the key feature. is the normalized RMS value of the key feature. is the normalized peak-to-peak value of the key feature. is the normalized kurtosis of the key feature. is the normalized skewness of the key feature. is the normalized main frequency of the key feature. is the normalized spectral energy of the key feature. is the normalized harmonic content of the key feature. is the normalized power spectral density of the key feature. is the normalized spectral entropy of the key feature.

[0142] Use neural networks for deep learning training to automatically calculate the optimal weights of time domain and frequency domain features:

[0143] ω=NN(F time，norm ,F freq，norm )=(ω time ,ω freq );

[0144] The neural network is trained using a multi-layer perceptron (MLP), and the weights are determined by optimizing the objective function. NN is the neural network model, ω time is the time domain feature weight, ω freq is the frequency domain feature weight.

[0145] F final =F time，norm *ω time +F freq，norm *ω freq ;

[0146] Among them, F final is the fusion feature matrix of the key feature, F time，norm is the time domain feature normalization matrix of the key feature, F freq，norm is the frequency domain feature normalization matrix of the key feature, ω time is the time domain feature weight, ω freq is the frequency domain feature weight.

[0147] Based on the fusion feature matrix of the key feature, the eigenvalue of the key feature is calculated, specifically including:

[0148] det(F final -λI)=0;

[0149] Among them, F final is the fusion feature matrix of the key feature, λ is the eigenvalue of the key feature, I is the unit matrix, and det is the determinant.

[0150] Solve the above equation to obtain the eigenvalue of the key feature.

[0151] The feature threshold of each key feature is extracted from the built-in database of the data processing center, and the feature value of each key feature is compared with its corresponding feature threshold. When the feature value of a key feature is greater than its corresponding feature threshold, the key feature is determined to be a valid feature, and the fault types corresponding to the valid feature are extracted and counted from the built-in database of the data processing center.

[0152] In the embodiment of the present invention, the corresponding relationship between the fault type and the valid features is shown in Table 1 below.

[0153] Table 1 Fault type-valid feature correspondence table

[0154]

[0155]

[0156] As can be seen from Table 1, each fault type usually corresponds to one or more valid features.

[0157] When the characteristic value of a key feature is less than or equal to its corresponding characteristic threshold, the key feature is determined to be an invalid feature, and fault diagnosis is performed based on the determination results of each key feature.

[0158] Fault diagnosis is performed based on the judgment results of each key feature, including:

[0159] When the characteristic values of each key feature are less than their corresponding characteristic thresholds, that is, they are all invalid features, the abnormal moment is recorded, and the DC transmission line is switched to a pending state, and a short-term monitoring cycle is set for trial operation.

[0160] Conduct trial operation monitoring on the DC transmission line to obtain the trial operation electrical test parameters within a short monitoring period, input them into the data processing center for feature extraction, obtain each key feature and determine whether each key feature is a valid feature, and obtain the trial operation monitoring results of the DC transmission line.

[0161] The trial operation electrical test parameters within the short-time monitoring period specifically include the trial operation DC voltage, trial operation DC current, trial operation active power and trial operation harmonic content within the short-time monitoring period.

[0162] If the test operation monitoring results of the DC transmission line show that all the features are invalid, it is determined that the DC transmission line has no fault and is switched to a normal operation state.

[0163] If the trial operation monitoring result of the DC transmission line shows that there are valid features, it is determined that there is a fault in the DC transmission line, and various fault types corresponding to the valid features are counted.

[0164] The associated features of each fault type are counted, and the fault diagnosis confidence score value of each fault type is obtained by analysis and processing. The score is then compared with the fault diagnosis confidence threshold to obtain the fault diagnosis result.

[0165] The effective features corresponding to each fault type are counted as the associated features of each fault type, and the fault index of each associated feature is obtained. Based on the fault index of each associated feature and the number of associated features of each fault type, the fault diagnosis confidence score value of each fault type is obtained by correcting the coupling process, which specifically includes:

[0166] Obtain the fault index of each associated feature, including:

[0167] The characteristic value of each associated feature is subtracted from its corresponding characteristic threshold to obtain the characteristic difference value of each associated feature. Based on the characteristic difference value of each associated feature, it is mapped and matched with the fault index corresponding to each characteristic difference value preset in the built-in database of the data processing center to obtain the fault index of each associated feature. The fault index is used to evaluate the severity of the deviation of each associated feature, that is, the possibility of causing a fault. The larger the characteristic difference value of a certain associated feature, the greater the possibility of the associated feature causing a fault.

[0168] The number of associated features of each fault type is counted, and mapped and matched with the associated feature quantity factors corresponding to the intervals of the number of associated features pre-stored in the database built into the data processing center to obtain the associated feature quantity factors of each fault type. The associated feature quantity factors are proportional to the number of associated features. The more associated features a fault type has, the greater the fault diagnosis confidence of that fault type.

[0169] The fault diagnosis confidence score values of each fault type are obtained by correcting the coupling process, including:

[0170]

[0171] Among them, B i is the fault diagnosis confidence score value of the i-th fault type, δ i,u is the fault index of the u-th associated feature of the i-th fault type, is the number factor of the associated features, u is the associated feature number, u=1,2,3,...,N i , N i is the number of associated features matched to the i-th fault type, i is the fault type number, i=1,2,3,...,n, and n is the total number of fault types.

[0172] Compare with the fault diagnosis confidence threshold to obtain the fault diagnosis results, including:

[0173] The fault diagnosis confidence score value of each fault type is compared with the fault diagnosis confidence threshold. If the fault diagnosis confidence score value of a fault type is greater than or equal to the fault diagnosis confidence threshold, the fault type is determined to be a significant fault.

[0174] If the fault diagnosis confidence score value of a certain fault type is less than the fault diagnosis confidence threshold, the fault type is determined to be a potential fault.

[0175] Get the fault diagnosis results, the specific processing conditions are:

[0176] The fault types whose fault diagnosis results are significant faults are recorded as significant fault types. The significant fault types are sorted based on the size of the fault diagnosis confidence score of each significant fault type. The sorting rule is from large to small, and the data is sent to the data management terminal for early warning.

[0177] If the fault diagnosis results of each fault type are all potential faults, then based on the total number of fault types, the system matches the dynamic monitoring period corresponding to the total number of each fault type preset in the database built into the data processing center to obtain the dynamic monitoring period. Based on the dynamic monitoring period, the system dynamically monitors the DC transmission line, specifically including:

[0178] Based on the dynamic monitoring cycle, real-time monitoring data of the DC transmission line within the dynamic monitoring cycle is obtained, and tracking analysis results of the DC transmission line are obtained.

[0179] If, during the dynamic monitoring cycle, the associated characteristic value of a potential fault exceeds its corresponding characteristic threshold, the tracking analysis result of the DC transmission line will be determined as a tracking fault, and the fault type will be determined as a significant fault, and sent to the data management terminal for early warning.

[0180] If the associated characteristic values of each potential fault do not exceed their corresponding characteristic thresholds during the dynamic monitoring period, the tracking analysis results of the DC transmission line will be determined as short-term fluctuations, the dynamic monitoring period will be terminated, and the normal monitoring period will be switched.

[0181] like Figure 2 As shown, in this embodiment, the present invention provides a DC transmission fault diagnosis system based on multimodal data analysis, comprising:

[0182] The real-time monitoring module is used to monitor the DC transmission line in real time. When the DC transmission line experiences abnormal fluctuations, temporary line protection measures are activated. At the same time, the DC transmission line parameters at the abnormal moment are fed into the data processing center for feature extraction.

[0183] The fault type matching module is used to record a key feature as a valid feature and match the fault types corresponding to the valid feature when the feature value of the extracted key feature is greater than its corresponding feature threshold.

[0184] The fault type judgment module is used to count the associated features of each fault type, analyze and process to obtain the fault diagnosis confidence score value of each fault type, and compare it with the fault diagnosis confidence threshold to obtain the fault diagnosis result.

[0185] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0186] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all details in detail, nor do they limit the invention to specific implementation methods. Obviously, many modifications and changes can be made based on the contents of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can better understand and utilize the present invention. As long as they do not deviate from the structure of the present invention or exceed the scope defined by the present invention, they should fall within the scope of protection of the present invention.

Claims

1. A DC transmission fault diagnosis method based on multimodal data analysis, characterized in that: include: Real-time monitoring of DC transmission lines. When abnormal fluctuations occur in the DC transmission lines, temporary line protection measures are activated. At the same time, the DC transmission line parameters at the time of abnormality are fed into the data processing center for feature extraction. When the extracted feature value of a key feature is greater than its corresponding feature threshold, the key feature is recorded as a valid feature and the fault types corresponding to the valid feature are matched; The associated features of each fault type are counted, and the fault diagnosis confidence score value of each fault type is obtained by analysis and processing. The score is then compared with the fault diagnosis confidence threshold to obtain the fault diagnosis result.

2. The DC transmission fault diagnosis method based on multimodal data analysis according to claim 1, characterized in that: The DC transmission line is monitored in real time. When abnormal fluctuations occur in the DC transmission line, temporary line protection measures are activated. The specific process is as follows: Real-time collection of DC transmission line parameters, including electrical parameters, converter station control parameters, and equipment parameters; The electrical parameters include DC voltage, DC current, active power and harmonic content; The converter station control parameters include trigger angle and arc extinguishing angle; The equipment parameters include converter valve temperature, line insulation test score and ground current; The DC transmission line parameters are transmitted to the data processing center for processing and analysis to obtain an abnormal fluctuation risk value. When the abnormal fluctuation risk value is greater than the abnormal fluctuation risk threshold, it is determined that abnormal fluctuation has occurred in the DC transmission line. The time when the DC transmission line parameters are obtained is recorded as the abnormal time. Based on the abnormal fluctuation risk value, a mapping is performed with the temporary line protection measures corresponding to each abnormal fluctuation risk value interval pre-stored in the built-in database of the data processing center to obtain the temporary line protection measures for the abnormal fluctuation risk value, and the temporary line protection is activated. The specific process includes: When the abnormal fluctuation risk value is greater than or equal to the highest risk threshold, it is determined that the abnormal fluctuation risk value is in the first interval, and the temporary line protection measure set in the first interval is matched and the temporary line protection is turned on; When the abnormal fluctuation risk value is less than the highest risk threshold and greater than or equal to the medium risk threshold, it is determined that the abnormal fluctuation risk value is in the second interval, and the temporary line protection measure set in the second interval is matched and the temporary line protection is turned on; When the abnormal fluctuation risk value is less than the medium risk threshold and greater than or equal to the abnormal fluctuation risk threshold, the abnormal fluctuation risk value is determined to be in the third interval, and the temporary line protection measures set in the third interval are matched and the temporary line protection is turned on.

3. The DC transmission fault diagnosis method based on multimodal data analysis according to claim 1, characterized in that: The DC transmission line parameters at the abnormal moment are fed into the data processing center for feature extraction. The specific process is as follows: The parameters of the DC transmission line at the abnormal moment are fed into the data processing center for standardization; The time domain features and frequency domain features are extracted respectively, and the principal component analysis is performed on the time domain features and the frequency domain features to obtain the key features of the DC transmission line parameters. The key features are imported into the fault diagnosis processor built into the data processing center for fault diagnosis analysis.

4. The DC transmission fault diagnosis method based on multimodal data analysis according to claim 3 is characterized by: When the extracted feature value of a key feature is greater than its corresponding feature threshold, the key feature is recorded as a valid feature and matched to obtain the fault types corresponding to the valid feature, specifically including: After receiving each key feature, the fault diagnosis processor built into the data processing center calculates the characteristic value of each key feature and extracts the characteristic threshold of each key feature from the built-in database of the data processing center. The characteristic value of each key feature is compared with its corresponding characteristic threshold. When the characteristic value of a key feature is greater than its corresponding characteristic threshold, the key feature is determined to be a valid feature, and the fault types corresponding to the valid feature are counted. When the characteristic value of a key feature is less than or equal to its corresponding characteristic threshold, the key feature is determined to be an invalid feature, and fault diagnosis is performed based on the determination results of each key feature.

5. The DC transmission fault diagnosis method based on multimodal data analysis according to claim 4 is characterized in that: The fault diagnosis based on the determination results of each key feature specifically includes: When all key features are invalid, the abnormal moment is recorded, and the DC transmission line is switched to a pending state, and a short monitoring period is set for trial operation; Conduct trial operation monitoring on the DC transmission line to obtain the trial operation electrical test parameters within a short monitoring period. These parameters are input into the data processing center for feature extraction, key features are obtained, and whether each key feature is a valid feature is determined to obtain the trial operation monitoring results of the DC transmission line. If the test operation monitoring results of the DC transmission line show that all features are invalid, it is determined that the DC transmission line has no fault and switches to normal operation; If the trial operation monitoring result of the DC transmission line shows that there are valid features, it is determined that there is a fault in the DC transmission line, and various fault types corresponding to the valid features are counted.

6. The DC transmission fault diagnosis method based on multimodal data analysis according to claim 1, characterized in that: The statistical analysis of the associated features of each fault type to obtain the fault diagnosis confidence score of each fault type specifically includes: The effective features corresponding to each fault type are counted as the associated features of each fault type, and the fault index of each associated feature is obtained. Based on the fault index of each associated feature and the number of associated features of each fault type, the coupling process is corrected to obtain the fault diagnosis confidence score value of each fault type; Obtaining the fault index of each associated feature specifically includes: The feature value of each associated feature is subtracted from its corresponding feature threshold to obtain the feature difference value of each associated feature. Based on the feature difference value of each associated feature, it is mapped and matched with the fault index corresponding to each feature difference value preset in the built-in database of the data processing center to obtain the fault index of each valid feature.

7. The method for diagnosing DC power transmission faults based on multimodal data analysis according to claim 3, characterized in that: The fault diagnosis result is obtained by comparing the result with the fault diagnosis confidence threshold, which specifically includes: Compare the fault diagnosis confidence score value of each fault type with the fault diagnosis confidence threshold. If the fault diagnosis confidence score value of a fault type is greater than or equal to the fault diagnosis confidence threshold, then the fault type is determined to be a significant fault. If the fault diagnosis confidence score value of a certain fault type is less than the fault diagnosis confidence threshold, the fault type is determined to be a potential fault.

8. The DC transmission fault diagnosis method based on multimodal data analysis according to claim 7, characterized in that: The fault diagnosis result is obtained, and the specific processing conditions are as follows: The fault types of which the fault diagnosis results are significant faults are counted and recorded as significant fault types. The significant fault types are sorted based on the fault diagnosis confidence scores of the significant fault types and sent to the data management terminal for early warning. If the fault diagnosis results of each fault type are all potential faults, then based on the total number of fault types, the system matches the dynamic monitoring period corresponding to the total number of each fault type preset in the database built into the data processing center to obtain the dynamic monitoring period. Based on the dynamic monitoring period, the system dynamically monitors the DC transmission line, specifically including: Based on the dynamic monitoring cycle, real-time monitoring data of the DC transmission line within the dynamic monitoring cycle is obtained, trend analysis is performed on the data, and tracking analysis results of the DC transmission line are obtained; If the associated characteristic value of a potential fault continues to rise and exceeds its corresponding characteristic threshold during the dynamic monitoring cycle, the tracking analysis result of the DC transmission line will be determined as a tracking fault, and the fault type will be determined as a significant fault, and sent to the data management terminal for early warning; If the associated characteristic values of each potential fault remain stable and do not exceed their corresponding characteristic thresholds during the dynamic monitoring cycle, the tracking analysis results of the DC transmission line are determined to be short-term fluctuations, the dynamic monitoring cycle is terminated, and the normal monitoring cycle is switched.

9. The method for diagnosing DC power transmission faults based on multimodal data analysis according to claim 2, characterized in that: The real-time acquisition of DC transmission line parameters also includes detecting sensors to remove the influence of internal electromagnetic interference in the sensors. The specific processing conditions are: Monitor sensor power data at abnormal times, including voltage change rate, current change rate, and electromagnetic interference spectrum; The voltage change rate is used to determine whether it is a high-frequency interference source, the current change rate is used to determine whether the electromagnetic interference has radiation interference characteristics, and the electromagnetic interference spectrum is used to determine the location of the interference source; Based on the power data of the sensor at the time of abnormality, it is imported into the data processing center for feature extraction. After the characteristics of the electromagnetic interference are confirmed, it is mapped and matched with the filtering algorithms corresponding to each feature preset in the built-in database of the data processing center. The filtering algorithm corresponding to the electromagnetic interference feature is obtained to eliminate the electromagnetic interference; Record the quality data of DC transmission line parameters before and after filtering, including harmonic content, signal-to-noise ratio, and mean square error; The filtered DC transmission line parameters are re-imported into the data processing center, and the quality data of the DC transmission line parameters before and after filtering are compared to verify whether the electromagnetic interference has been effectively eliminated; If the electromagnetic interference is effectively eliminated, the filtered DC transmission line parameters are subsequently analyzed and processed; If the electromagnetic interference is not effectively eliminated, an early warning will be sent to the data management terminal.

10. A DC power transmission fault diagnosis system based on multimodal data analysis, applying the DC power transmission fault diagnosis method based on multimodal data analysis according to any one of claims 1 to 9, characterized in that: The real-time monitoring module is used to monitor the DC transmission line in real time. When the DC transmission line experiences abnormal fluctuations, temporary line protection measures are activated. At the same time, the DC transmission line parameters at the time of abnormality are fed into the data processing center for feature extraction. The fault type matching module is used to record the key feature as a valid feature and match the fault types corresponding to the valid feature when the feature value of the extracted key feature is greater than its corresponding feature threshold; The fault type judgment module is used to count the associated features of each fault type, analyze and process to obtain the fault diagnosis confidence score value of each fault type, and compare it with the fault diagnosis confidence threshold to obtain the fault diagnosis result.

Images