A direct current ice melting monitoring and early warning method and system

Abstract

The application discloses a direct current ice melting monitoring and early warning method and system, the method comprising: collecting line parameters of direct current ice melting operation, device reference parameters on the line, real-time environmental parameters around the line, determining line ice melting targets of direct current ice melting operation, calculating line electrical reference parameters and obtaining ice melting demand reference parameters and correcting; collecting line electrical actual parameters, line ice melting thickness actual parameters and device actual parameters in real time; comparing line electrical reference parameters with line electrical actual parameters, ice melting demand reference parameters with line ice melting thickness actual parameters, and device reference parameters with device actual parameters in real time, judging whether various faults exist and fault levels; generating early warning information according to the judgment result and matching corresponding preset remote control strategy, and completing remote control according to the corresponding preset remote control strategy. The application can realize online monitoring of the ice melting process, improve fault response speed, and enhance the accuracy and safety of ice melting operation.

Description

Technical Field

[0001] This application relates to the technical field of monitoring and early warning of DC de-icing operations in power systems, specifically to a DC de-icing monitoring and early warning method and system. Background Technology

[0002] DC de-icing technology plays a crucial role in ensuring the safe and stable operation of the power grid. With the development of power systems, especially under severe winter conditions, icing on power grid lines occurs frequently, seriously affecting the normal operation of transmission lines. To address this challenge, the industry is continuously exploring relevant technologies to improve the efficiency and safety of de-icing operations and reduce the impact of faults such as line breaks and grounding caused by icing on power grid operation.

[0003] Currently, when addressing similar issues, the industry typically employs a combination of regular inspections and simple monitoring tools. Specifically, traditional methods include manual on-site inspections, using portable measuring instruments to check line status, and relying on periodic checks at fixed time intervals to assess de-icing effectiveness. Additionally, in some scenarios, basic equipment such as thermometers and ammeters are used for simple monitoring of local parameters, but these methods lack real-time capability and systematic approach.

[0004] Given that existing conventional methods generally cannot achieve real-time online monitoring, resulting in slow fault response and difficulty in accurately grasping the dynamic changes during the ice-melting process, this lag makes it difficult to detect and handle potential faults in a timely manner, thus affecting ice-melting efficiency and the overall safety of the power grid. Therefore, there is a need for a DC ice-melting monitoring and early warning method and system that supports full-process online monitoring of the ice-melting process, improves fault response speed, and enhances the accuracy and safety of ice-melting operations. Summary of the Invention

[0005] To achieve full online monitoring of the ice melting process, improve fault response speed, and enhance the accuracy and safety of ice melting operations, this application provides a DC ice melting monitoring and early warning method and system.

[0006] Firstly, this application provides a DC ice-melting monitoring and early warning method, including:

[0007] Collect line parameters for DC ice melting operations, determine the ice melting target of the DC ice melting operations, calculate the line electrical reference parameters and obtain the ice melting demand reference parameters; collect the equipment reference parameters deployed on the DC ice melting operations line; collect the real-time environmental parameters around the DC ice melting operations line, and correct the line electrical reference parameters and DC ice melting equipment reference parameters based on the real-time environmental parameters.

[0008] By utilizing sensors deployed at key nodes and equipment sides of the DC de-icing operation lines, the actual electrical parameters of the lines, the actual de-icing thickness parameters of the lines, and the actual equipment parameters are collected in real time. The reference parameters of the line electrical parameters are compared with the actual electrical parameters of the lines, the reference parameters of de-icing demand parameters are compared with the actual de-icing thickness parameters of the lines, and the reference parameters of the equipment parameters are compared with the actual equipment parameters to determine whether there is an electrical fault, equipment fault, or de-icing fault, as well as the level of each type of fault.

[0009] Based on the acquired electrical faults, equipment faults, or de-icing faults, as well as various fault levels, early warning information is generated and matched with corresponding preset remote control strategies. Remote control is then completed according to the corresponding preset remote control strategies. The corresponding preset remote control strategies are obtained by training a remote control strategy acquisition model based on historical remote control strategies with fault elimination rates greater than preset fault elimination rates, according to the corresponding type and level of faults.

[0010] By adopting the above scheme, dynamic correction reference parameters are obtained from multiple perspectives, such as line electrical parameters, ice melting thickness parameters, and equipment parameters, and compared with real-time acquired parameters. This enables accurate determination of the existence of various fault types, improving the timeliness, accuracy, and comprehensiveness of fault detection. Based on the fault type and level, early warning information is generated and matched with optimized remote control strategies, effectively improving the pertinence and efficiency of fault handling, ensuring the safe and reliable conduct of ice melting operations, and realizing comprehensive real-time monitoring and intelligent early warning of line status during DC ice melting operations.

[0011] Preferred options also include:

[0012] By combining deep learning algorithms, it is determined whether there are conflicts between the acquired electrical faults, equipment faults, or de-icing faults and the corresponding remote control strategies for each fault level. If there are conflicts, the corresponding remote control strategies are executed sequentially according to the control strategy priority. The control strategy priority setting rules include: the remote control strategy that ensures line safety has the highest priority, the remote control strategy that ensures equipment safety has the second priority, and the remote control strategy that optimizes line and equipment operating parameters has the lowest priority.

[0013] By adopting the above scheme, conflict detection is performed on remote control strategies that match electrical faults, equipment faults, or de-icing faults and various fault levels. The priority of conflicting control strategies is determined and executed level by level, ensuring that various faults can be eliminated in an orderly and efficient manner in complex fault scenarios, thereby guaranteeing the safety and smooth progress of DC de-icing operations.

[0014] Preferred options also include:

[0015] Obtain the short-circuit capacity of the power grid connection point where the DC ice melting operation line is located;

[0016] The system determines whether the ice-melting current in the actual electrical parameters of the DC ice-melting line exceeds the preset multiple of the short-circuit capacity of the grid connection point where the DC ice-melting line is located, and collects the equipment status of the circuit breakers at both ends of the DC ice-melting line. Based on the equipment status of the circuit breakers at both ends of the line and the parameters of the DC ice-melting line, it determines whether the DC ice-melting line forms a closed loop.

[0017] If the judgment result is that the short-circuit capacity of the power grid access point where the DC de-icing operation is located is exceeded by a preset multiple or a closed loop is not formed, a power grid fault warning message will be generated and a corresponding preset remote control strategy will be matched.

[0018] By adopting the above scheme and determining whether the de-icing current in the DC de-icing line exceeds the short-circuit capacity of the grid connection point, the stability of the grid can be judged and abnormal grid parameters can be detected in a timely manner. Combined with the monitoring of the grid parameters where the DC de-icing operation line is located, the stability and safety of the DC de-icing operation can be more comprehensively guaranteed.

[0019] Preferred, including:

[0020] Calculate the transmission rate of the line parameters and equipment parameters on the DC ice melting operation line;

[0021] Statistical analysis was conducted on the parameter data and equipment specifications of historical DC ice melting operations to obtain the communication transmission reference data for the parameters of each line and the parameters of the equipment on it. The transmission rate of the line parameter data of the DC ice melting operation was compared with the communication transmission reference data of the line parameters, and the transmission rate of the equipment parameter data of the DC ice melting operation was compared with the communication transmission reference data of the equipment parameters on the line. If any comparison result was lower than the corresponding reference data, a communication fault was identified.

[0022] Using a hierarchical diagnostic process, the system sequentially performs equipment self-tests, network link self-tests, and multi-device status comparison self-tests. Based on the self-test results, it identifies the source of communication faults and generates early warning prompts. Based on the generated early warning prompts, it matches corresponding communication fault recovery strategies to complete the communication fault recovery of the DC de-icing operation line. The communication fault recovery strategies include: if the communication fault originates from the equipment, restarting the equipment or switching to a backup device; if the communication fault originates from the network link, switching to a backup communication link.

[0023] By adopting the above scheme, the transmission rate of line parameter data and equipment parameter data in DC ice melting operation is monitored in real time and compared with the communication transmission reference data to accurately determine whether there is a communication fault. Once a communication fault is detected, the fault source can be located through a hierarchical diagnostic process to ensure the comprehensiveness of fault investigation and match the corresponding communication fault recovery strategy, which effectively improves the communication reliability of the system and ensures the continuity and stability of DC ice melting operation.

[0024] Preferred options also include:

[0025] Constructing a digital twin model for DC ice melting includes: building a three-dimensional geometric and electrical equivalent physical layer model based on the line parameters, equipment parameters on the line, and power grid parameters of the line; building an environmental layer model based on the real-time environmental parameters and icing characteristic parameters of the line's surroundings; and building a control layer model by integrating the line equipment control logic and mapping the response characteristics of remote control commands. Importing a benchmark parameter set based on historical ice melting data, which includes line electrical benchmark parameters, ice melting demand benchmark parameters, and equipment benchmark parameters.

[0026] The DC ice-melting digital twin model is driven by the real-time collected actual electrical parameters of the line, the actual ice-melting thickness of the line, and the actual equipment parameters to complete the data mapping and calibration of the DC ice-melting digital twin model.

[0027] The system uses a digital twin model of DC ice melting to simulate and predict the operation data of the line for DC ice melting operations at a predetermined time in the future, including the line's electrical parameters, ice melting thickness parameters, and equipment parameters; and uses a fault identification model built based on deep learning algorithms to obtain the fault type and fault level of the line for DC ice melting operations at the predetermined time in the future.

[0028] Match the corresponding preset remote control strategy and perform simulation control in the DC ice melting digital twin model according to the corresponding preset remote control strategy; by obtaining the fault elimination status of the DC ice melting operation line in the DC ice melting digital twin model after simulation control, verify the accuracy of matching the corresponding preset remote control strategy. If the verification is successful, execute the matching corresponding preset remote control strategy; otherwise, optimize the matching corresponding preset remote control strategy.

[0029] By adopting the above scheme, a digital twin model of DC ice melting is constructed and simulated for prediction and control verification. This allows for the prediction of the types and levels of faults that may occur in the DC ice melting operation line at a predetermined time in the future, thus achieving accurate early warning of potential problems.

[0030] Preferred options also include:

[0031] Each sensor deployed on the critical nodes of the DC ice melting operation line and equipment side has an embedded GPS module. Whenever an electrical fault, equipment fault, or ice melting fault is detected, the corresponding critical node of the DC ice melting operation line and equipment side is locked. A drone device is assigned to collect fault images of the critical node of the DC ice melting operation line and equipment side. The preset fault conditions of the critical node of the DC ice melting operation line and equipment side are continuously obtained through image analysis technology to verify the preset fault judgment results and judge the effect of subsequent remote control.

[0032] By adopting the above scheme, when an electrical fault, equipment fault, or de-icing fault is detected, the GPS module embedded in the sensor is used to accurately locate the location of the fault, and the fault image is collected by a drone. Combined with image analysis technology, the fault details are continuously obtained, which improves the accuracy of fault location and provides an intuitive means of verifying the effect of subsequent remote control, thereby improving the efficiency of fault handling and the reliability of system operation.

[0033] Preferred options also include:

[0034] Collect icing characteristic parameters of the DC de-icing operation line, and correct the line electrical reference parameters and DC de-icing equipment reference parameters based on the icing characteristic parameters; the icing characteristic parameters include: icing type.

[0035] By adopting the above scheme, we can analyze and identify icing characteristic parameters, further dynamically correct the line electrical reference parameters and DC de-icing equipment reference parameters, more accurately adapt to the de-icing operation requirements under different environmental conditions, improve the accuracy of early warning monitoring, and enhance the safety and efficiency of the de-icing process.

[0036] Secondly, this application provides a DC ice-melting monitoring and early warning system, comprising:

[0037] The DC ice melting reference parameter acquisition module is used to collect line parameters for DC ice melting operations, determine the ice melting target of the DC ice melting operation, calculate the electrical reference parameters of the line and obtain the ice melting requirement reference parameters; and collect the reference parameters of the equipment deployed on the DC ice melting operation line.

[0038] The DC ice-melting reference parameter correction module is used to collect real-time environmental parameters around the DC ice-melting operation line and correct the line electrical reference parameters and DC ice-melting equipment reference parameters based on the real-time environmental parameters.

[0039] The DC ice melting actual parameter acquisition module is used to collect the actual electrical parameters of the line, the actual ice melting thickness of the line, and the actual equipment parameters in real time by using sensors deployed at key nodes of the line and equipment side of the DC ice melting operation.

[0040] The DC de-icing fault judgment module is used to compare the line electrical reference parameters with the actual line electrical parameters, the de-icing demand reference parameters with the actual line de-icing thickness parameters, and the equipment reference parameters with the actual equipment parameters in real time, so as to determine whether there is an electrical fault, equipment fault, or de-icing fault, as well as the various fault levels.

[0041] The DC de-icing fault control module is used to generate early warning information based on the acquired electrical faults, equipment faults, or de-icing faults and various fault levels, and match them with corresponding preset remote control strategies. The module then performs remote control according to the preset remote control strategies. The preset remote control strategies are obtained by training a remote control strategy acquisition model based on historical remote control strategies with fault elimination rates greater than preset fault elimination rates for the corresponding types and levels of faults.

[0042] By adopting the above scheme, comprehensive monitoring and intelligent control of the status of lines and equipment in DC ice melting operations can be achieved.

[0043] Thirdly, this application provides a computer-readable storage medium including a stored computer program, wherein the computer program, when running, controls the device where the computer-readable storage medium is located to perform the method described above.

[0044] Fourthly, this application provides a computer device, the computer device including a memory, a processor and a program stored in the memory and executable thereon, the program being executed by the processor to implement the steps of the method described above.

[0045] In summary, this application has the following beneficial effects:

[0046] 1. By using sensors to collect line electrical parameters, ice melting thickness parameters, and equipment parameters in real time, and comparing them with dynamically corrected benchmark parameters in real time, the fault type and level can be determined comprehensively and quickly, realizing full-process visual monitoring of the ice melting process and significantly improving fault response speed; and based on the fault type and level, early warning information is generated and matched with optimized remote control strategies, eliminating electrical faults, equipment faults, and ice melting faults through remote control, thereby improving the accuracy and safety of ice melting operations;

[0047] 2. By obtaining the reference values ​​of the power grid parameters where the DC ice melting operation line is located, and determining whether the electrical reference parameters of the line associated with the power grid parameters exceed the reference values ​​of the power grid parameters, abnormal power grid parameters can be detected in a timely manner, realizing comprehensive monitoring of the power grid parameters where the DC ice melting operation line is located, and further improving the accuracy and safety of the ice melting operation.

[0048] 3. Monitor the transmission rate of line parameter data and equipment parameter data in real time during DC ice melting operations, and compare it with the communication transmission reference data to accurately determine whether there is a communication fault; introduce a communication fault self-check and recovery mechanism to reduce overall monitoring failure caused by communication interruption and improve the accuracy and safety of ice melting operations. Attached Figure Description

[0049] Figure 1 This is a flowchart of the DC de-icing monitoring and early warning method described in a specific embodiment;

[0050] Figure 2 This is a schematic diagram of the DC ice melting monitoring and early warning system described in a specific embodiment. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0052] like Figure 1 As shown in the figure, this application discloses a DC ice melting monitoring and early warning method, and the specific steps are as follows.

[0053] S1. Determination of baseline values ​​for DC de-icing operations.

[0054] Specifically, in order to achieve online monitoring of the entire DC ice melting operation, it is necessary to predetermine the baseline values ​​for the DC ice melting operation so that abnormal situations can be identified based on these baseline values. Furthermore, for more comprehensive and accurate monitoring, baseline values ​​for operation data should be determined from multiple aspects, including key nodes of the DC ice melting operation line and equipment on the DC ice melting operation line (such as DC ice melting operation equipment), to assist in the real-time monitoring of various operation data.

[0055] Considering that different lines and different de-icing requirements are all factors affecting the baseline values ​​of DC de-icing operations, the line parameters for DC de-icing operations are collected, including: the material of the DC de-icing operation line (aluminum / steel-cored aluminum stranded wire, etc.), cross-sectional area, length, allowable current carrying capacity, DC resistance, etc.; and the de-icing targets of the DC de-icing operation line are determined, such as: the target de-icing time for melting the preset ice thickness, the de-icing rate, etc.

[0056] Based on the collected line parameters for DC ice melting operations, the electrical reference parameters for the DC ice melting operation line are calculated. Specific calculation formulas include: calculating the base current value based on the heat balance formula required for conductor ice melting, the formula is as follows:

[0057]

[0058] In the formula, P冰 R is the latent heat of melting of ice, L is the length of the conductor, δ is the thickness of the ice layer, and R is the molten heat of ice. dc Let t be the DC resistance of the line conductor, and t be the target melting time for the preset ice thickness, set not exceeding the smaller of 90% of the rated current of the ice-melting device and the maximum allowable temperature rise current of the line. According to Ohm's law, the voltage reference value is the product of the current and the total resistance of the line, expressed by the formula: V = I × R total , where R total The contact resistance of the connector is typically taken as 5%-10% of the DC resistance of the line conductor, and should not exceed 95% of the rated current of the de-icing device; the formula for the capacity reference value is: P = I 2 ×R total Furthermore, the rated capacity of the de-icing device should not exceed 95%; the impedance reference parameter can be calculated based on the conductor material (the line impedance under DC conditions is mainly the conductor resistance, ignoring inductive reactance), and the formula is:

[0059]

[0060] In the formula, ρ is the resistivity of the conductor material, and A is the cross-sectional area of ​​the conductor.

[0061] Based on the line de-icing target of DC de-icing operation, obtain the de-icing demand benchmark parameters, such as: the target de-icing time for melting the preset ice thickness, the de-icing rate, etc.

[0062] Collect and obtain the reference parameters of the equipment deployed on the DC ice-melting line, including but not limited to the rated capacity of the ice-melting device, maximum output current, voltage regulation range, rectification / inverter method (such as LCC or MMC), and rated parameters of the cooling system (oil temperature / water temperature thresholds). Among these, the above data can be determined by directly reading the values ​​marked on the nameplate of the ice-melting equipment.

[0063] In addition, the baseline value of line conductor deformation can be determined based on the line conductor deformation data during normal operation of the DC ice melting line.

[0064] S2, Dynamic correction of the baseline values ​​for DC de-icing operations.

[0065] Considering that environmental factors are an important factor affecting the parameters of DC ice melting operation, real-time environmental parameters around the DC ice melting operation line are collected, and the line electrical reference parameters and equipment reference parameters are corrected based on the real-time environmental parameters.

[0066] Specifically, the line electrical reference parameters are corrected based on real-time environmental parameters, including meteorological data (temperature, humidity, wind speed, wind direction, and ice thickness) and geographical environmental data (altitude, tower structure), etc. A deep neural network algorithm is used to obtain the correction values ​​for the corresponding line electrical reference parameters and equipment reference parameters under different environmental parameters. For example, for low temperature correction, the current reference value increases by 3%-5% for every 5 degrees Celsius decrease in ambient temperature; for wind speed correction, the current increases by 8%-10% for every 2 m / s increase in wind speed.

[0067] In addition, the equipment's operating years can be selected, and the equipment's baseline values ​​can be adjusted based on the equipment's operating years. Deep learning algorithms can be used to train a neural network to learn the equipment's operating years and the baseline values ​​of the equipment based on expert experience. For example, if the equipment's operating years exceed 5 years, the output capacity will decrease by 1%-2% per year.

[0068] Furthermore, considering that different icing characteristic parameters affect the de-icing progress, icing characteristic parameters of the DC de-icing operation line are collected, and the line electrical reference parameters and DC de-icing equipment reference parameters are corrected based on these icing characteristic parameters. These icing characteristic parameters include: icing type. Specifically, for example, rime ice has high conductivity, which effectively increases the surface conductivity of the line, leading to a decrease in impedance; dry snow icing, on the other hand, has high insulation, resulting in an increase in impedance. Therefore, a mapping relationship between icing type and impedance correction coefficient is established through experimental data to correct the impedance reference value.

[0069] S3. Collect actual parameters of DC ice melting operation.

[0070] Specifically, a sensor assembly can be formed by sensors deployed at key nodes of the DC de-icing line and on the equipment side to collect real-time actual electrical parameters of the line, such as current, voltage, and capacity, as well as actual parameters of the line de-icing thickness, such as the de-icing thickness at a preset time, and actual parameters of the equipment, such as the oil temperature and water temperature in the cooling system.

[0071] In addition, sensors can be used to collect actual data on line deformation, including line jitter amplitude and line bending value.

[0072] S4. Compare the baseline values ​​of the dynamically corrected DC ice melting operation with the actual parameters of the collected DC ice melting operation, and determine whether there is a fault, as well as the fault type and level, based on the comparison results.

[0073] The system compares the line electrical reference parameters with the actual line electrical parameters, the ice melting demand reference parameters with the actual ice melting thickness parameters, and the equipment reference parameters with the actual equipment parameters in real time to determine whether there is an electrical fault, equipment fault, or ice melting fault, as well as the level of each fault.

[0074] Specifically, when the error between the actual electrical parameters of the line and the reference electrical parameters of the line is greater than the preset first error, an electrical fault is identified. The preset first error can have multiple levels, each corresponding to a different fault level. For different actual electrical parameters, if a fault is found when compared with the corresponding type of line reference parameters, an electrical fault of that type is generated, and a preset first error within a corresponding range is set. For example, using a DC current ±5% reference value, if the comparison result has a deviation of 5%-10%, a current fault level 1 is generated; if it has a deviation of 10%-15%, a current fault level 2 is generated; and if it has a deviation greater than 15%, a current fault level 3 is generated.

[0075] Similarly, when the error between the baseline parameter for de-icing demand and the actual parameter for the de-icing thickness of the line is greater than the preset second error, a de-icing fault is identified. The preset second error can have multiple levels, each corresponding to a different fault level. For example, the baseline value is a preset time de-icing thickness error of ±5mm. When the preset time de-icing thickness is between 5-10mm, a level 1 de-icing fault is generated. When the preset time de-icing thickness is between 10-15mm, a level 2 de-icing fault is generated. When the preset time de-icing thickness exceeds 15mm, a level 3 de-icing fault is generated.

[0076] Similarly, when the error between the equipment's reference parameters and actual parameters exceeds a preset third error, a equipment fault is identified. The preset third error can have multiple levels, each corresponding to a different fault level. For different equipment actual parameters, if a fault is found when compared with the corresponding type of equipment reference parameters, a fault of that type is generated, and a preset third error within a corresponding range is set. For example, using ±1 degree Celsius as the reference value for the converter oil temperature in a DC de-icing device, a level 1 fault is generated if the comparison result has a deviation of ±3 degrees Celsius; a level 3 fault is generated if the deviation is ±5 degrees Celsius; and a level 3 fault is generated if the deviation is greater than ±5 degrees Celsius.

[0077] Furthermore, to further ensure the accuracy of fault diagnosis, GPS modules are embedded in each sensor deployed at key nodes of the DC ice-melting line and on the equipment side. Whenever an electrical fault, equipment fault, or ice-melting fault is detected, the corresponding key node of the DC ice-melting line and the equipment side are located, and UAV devices are assigned to collect fault images, including infrared images, of the key nodes of the DC ice-melting line and the equipment side. Image analysis technology is used to continuously acquire preset fault conditions of the key nodes of the DC ice-melting line and the equipment side to verify whether the preset fault diagnosis results are correct, such as verifying the overheating fault of the DC ice-melting equipment, and judging the effect of subsequent remote control, such as the disappearance of the overheating fault of the DC ice-melting equipment after remote control.

[0078] In addition, by comparing the baseline value of line conductor deformation with the actual value of line conductor deformation, and based on whether the error between the two exceeds the preset deformation error, it is determined whether there is a line conductor jitter fault or a line conductor deformation fault, and the corresponding fault level.

[0079] S5. Match the corresponding preset remote control strategy according to the determined fault type and level, and complete the remote control to eliminate the fault.

[0080] Early warning information is generated based on the acquired electrical faults, equipment faults, or de-icing faults, as well as various fault levels. This includes early warning information that contains both the fault type and the fault level.

[0081] The system generates early warning information and matches it with corresponding preset remote control strategies. For example, it matches early warning information for the first level of line current fault with a remote control strategy that is compatible with the early warning information for the first level of current fault. The corresponding preset remote control strategy is obtained by training a remote control strategy acquisition model based on historical remote control strategies with fault elimination rates greater than a preset fault elimination rate for the corresponding type and level of fault.

[0082] For example, electrical faults such as voltage fault level 3, current fault level 3, and impedance fault level 3 may be serious faults caused by short circuits, grounding, or poor contact. In such cases, the preset remote control strategies include: immediately cutting off the de-icing power supply, remotely closing the fast grounding switches on both sides of the line, disconnecting the faulty line from the power grid, and sending a power outage maintenance request to the dispatch system.

[0083] Complete remote control according to the corresponding preset remote control strategy.

[0084] In a specific embodiment, considering the existence of numerous different types of faults in the line, and the conflicts between different types of faults on the remote control strategies applied to fault elimination, to ensure the normal operation of DC de-icing operations, the method further includes: after matching the corresponding preset remote control strategy according to the determined fault type and level, and before completing remote control to eliminate the fault, the method further includes:

[0085] By combining deep learning algorithms, this method determines whether there are conflicts between acquired electrical faults, equipment faults, or de-icing faults, and the corresponding remote control strategies for each fault level. Specifically, a conflict judgment neural network is set up using deep learning algorithms. This network is trained with historically acquired electrical faults, equipment faults, or de-icing faults, and the corresponding remote control strategies for each fault level, along with labeled data indicating whether there is a conflict and the conflicting strategies based on expert judgments of actual operation results. The currently acquired fault type and level, along with the corresponding preset remote control strategies, are then input into the conflict judgment neural network to determine whether a conflict exists and, if so, the specific remote control strategy for the conflict.

[0086] If a conflict exists, the corresponding remote control strategies will be executed sequentially according to the control strategy priority. The control strategy priority setting rules include: the remote control strategy that ensures line safety has the highest priority, the remote control strategy that ensures equipment safety has the second highest priority, and the remote control strategy that optimizes line and equipment operating parameters has the lowest priority.

[0087] For example, when a line short circuit / grounding fault is triggered, the protection shutdown → fault isolation → status verification (a remote control strategy to ensure line safety) should be executed first, and other control strategies (such as power boost) should be temporarily suspended; if the device needs to be derated due to a fault, the de-icing current of non-critical lines should be reduced (to ensure equipment safety), and other control strategies (such as power boost) should be temporarily suspended.

[0088] In a specific embodiment, to further improve the comprehensiveness, accuracy, and safety of DC ice melting operation monitoring and early warning, the method further includes:

[0089] Obtain the short-circuit capacity of the power grid connection point where the DC ice melting operation line is located;

[0090] The system determines whether the melting current in the actual electrical parameters of the DC ice-melting line exceeds a preset multiple of the short-circuit capacity of the grid connection point where the DC ice-melting line is located; for example, the melting current should be less than 30% of the short-circuit capacity of the connection point. It also collects the equipment status of the circuit breakers at both ends of the DC ice-melting line and determines whether the DC ice-melting line forms a closed loop based on the equipment status of the circuit breakers at both ends of the line and the line parameters (line topology); for example, a 500kV line needs to form a melting loop through the substation grounding switch. The short-circuit capacity of the grid connection point where the DC ice-melting line is located can be updated and calculated based on the original short-circuit capacity (the product of the grid-side voltage and the effective value of the three-phase short-circuit current) and the newly added impedance (the impedance of the newly added DC ice-melting device).

[0091] If the judgment result exceeds the preset multiple of the short-circuit capacity of the grid connection point where the DC de-icing operation is located, or if a closed loop is not formed, a corresponding grid fault warning message will be generated, and a corresponding preset remote control strategy will be matched. For example, for grid voltage / frequency abnormal faults, the input parameters of the de-icing device will be dynamically adjusted, or for grid short-circuit faults, the device will be remotely triggered to shut down in an emergency; or for grid harmonic exceedance or resonance faults, the AC filter matched with the de-icing device will be remotely activated.

[0092] In a specific embodiment, to further improve the timeliness and accuracy of monitoring and early warning for DC ice melting operations, the method further includes:

[0093] Calculate the transmission rate of the line parameters and equipment parameters of the DC ice melting operation, that is, the amount of data of the line parameters and equipment parameters of the DC ice melting operation per unit time.

[0094] Statistical analysis was conducted on the parameter data and equipment specifications of historical DC ice melting operations to obtain the communication transmission baseline data for the parameters of each line and the equipment parameters on it. The transmission rate of the line parameter data of the DC ice melting operation was compared with the communication transmission baseline data of the line parameters, and the transmission rate of the equipment parameter data of the DC ice melting operation was compared with the communication transmission baseline data of the equipment parameters on the line. If any comparison result was lower than the corresponding baseline data, a communication fault was identified.

[0095] Using a layered diagnostic process, device self-tests, network link self-tests, and multi-device status comparison self-tests are performed sequentially. Based on the self-test results, the source of communication faults is identified and early warning prompts are generated. Specifically, terminal self-tests include remotely triggering self-test programs for devices such as de-icing devices and monitoring terminals to determine if communication faults exist. Network link self-tests include checking VPN channels and data platform interfaces for authentication failures, insufficient bandwidth, and other issues to verify the presence of network link faults. Multi-device status comparison self-tests compare the communication status of multiple devices; if only a single device is faulty, it is identified as a device problem; however, if multiple devices in the area experience a collective disconnection, it is identified as a base station / aggregation node fault.

[0096] Based on the generated early warning prompts, a corresponding communication fault recovery strategy is matched to complete the communication fault recovery of the DC de-icing operation line; the communication fault recovery strategy includes: determining that the communication fault originates from the equipment, restarting the equipment or switching to a backup equipment; determining that the communication fault originates from the network link, switching to a backup communication link; determining that the base station / aggregation node is faulty, switching to a backup base station / aggregation node.

[0097] In one specific embodiment, to further improve the timeliness and accuracy of monitoring and early warning for DC ice melting operations, the method further includes:

[0098] Construct a digital twin model for DC ice melting; including: constructing a three-dimensional geometric and electrical equivalent physical layer model based on the line parameters, equipment parameters on the line, and power grid parameters of the line; constructing an environmental layer model based on the real-time environmental parameters and icing characteristic parameters of the line's surroundings; and constructing a control layer model by integrating the line equipment control logic and mapping the response characteristics of remote control commands; and importing a set of reference parameters based on historical ice melting data, which includes line electrical reference parameters, ice melting demand reference parameters, and equipment reference parameters.

[0099] The DC ice-melting digital twin model is driven by the real-time collected actual electrical parameters of the line, the actual ice-melting thickness of the line, and the actual equipment parameters to complete the data mapping and calibration of the DC ice-melting digital twin model; in addition, the twin model parameters can be dynamically corrected by using the Kalman filter algorithm.

[0100] The system uses a digital twin model of DC ice melting to simulate and predict the operation data of the line for DC ice melting operations at a predetermined time in the future, including the line's electrical parameters, ice melting thickness parameters, and equipment parameters. A fault identification model based on a deep learning algorithm is used to obtain the predicted fault types and fault levels of the line for DC ice melting operations at the predetermined time in the future. The fault identification model is generated by training using historical operation data of DC ice melting operations and labeled fault types and fault levels.

[0101] Match the corresponding preset remote control strategy and perform simulated control in the DC ice melting digital twin model according to the corresponding preset remote control strategy; by obtaining the fault elimination status (fault efficiency success or failure) of the DC ice melting operation line in the DC ice melting digital twin model after simulated control, verify the accuracy of matching the corresponding preset remote control strategy. If the verification is successful, execute the matching corresponding preset remote control strategy; otherwise, optimize the matching corresponding preset remote control strategy. The optimization of matching the corresponding preset remote control strategy is achieved through incremental learning.

[0102] like Figure 2 As shown in the figure, this application discloses a DC ice melting monitoring and early warning system, which specifically includes:

[0103] The DC ice melting reference parameter acquisition module 101 is used to collect line parameters for DC ice melting operations, determine the ice melting target of the DC ice melting operation, calculate the electrical reference parameters of the line and obtain the ice melting requirement reference parameters; and collect the reference parameters of the equipment deployed on the DC ice melting operation line.

[0104] The DC ice melting reference parameter correction module 102 is used to collect real-time environmental parameters around the DC ice melting operation line and correct the line electrical reference parameters and DC ice melting equipment reference parameters according to the real-time environmental parameters.

[0105] The DC ice melting actual parameter acquisition module 103 is used to collect the actual electrical parameters of the line, the actual ice melting thickness of the line and the actual equipment parameters in real time by using sensors deployed on the key nodes of the line and the equipment side of the DC ice melting operation.

[0106] The DC de-icing fault judgment module 104 is used to compare the line electrical reference parameters with the actual line electrical parameters, the de-icing demand reference parameters with the actual line de-icing thickness parameters, and the equipment reference parameters with the actual equipment parameters in real time, so as to complete the judgment of whether there is an electrical fault, equipment fault or de-icing fault and the various fault levels.

[0107] The DC de-icing fault control module 105 is used to generate early warning information based on the acquired electrical faults, equipment faults, or de-icing faults and various fault levels, and match the corresponding preset remote control strategies to complete remote control according to the corresponding preset remote control strategies. The corresponding preset remote control strategies are obtained by training a remote control strategy acquisition model based on the corresponding type and level of faults and selecting historical remote control strategies with a fault elimination rate greater than the preset fault elimination rate.

[0108] In a specific embodiment, the DC de-icing fault control module 105 in the system is further used to combine deep learning algorithms to determine whether there is a conflict between the acquired electrical faults, equipment faults, or de-icing faults and the corresponding remote control strategies for each fault level; if a conflict exists, the corresponding remote control strategies are executed sequentially according to the control strategy priority for remote control; the control strategy priority setting rules include: the remote control strategy that ensures line safety has the highest priority, the remote control strategy that ensures equipment safety has the second priority, and the remote control strategy that optimizes the line and equipment operating parameters has the lowest priority.

[0109] In one specific embodiment, the DC ice melting reference parameter acquisition module 101 in the system is also used to acquire the reference values ​​of the power grid parameters where the DC ice melting operation line is located.

[0110] The DC de-icing fault judgment module 104 is also used to judge and compare whether the actual electrical parameters of the line associated with the power grid where the DC de-icing operation is located meet the preset multiple of the power grid parameter reference value, and to collect the equipment status of the circuit breakers at both ends of the DC de-icing operation line, and to judge whether the DC de-icing operation line has formed a closed loop based on the equipment status of the circuit breakers at both ends of the line and the DC de-icing operation line parameters; if the judgment result is that the power grid parameter reference data is exceeded or a closed loop is not formed, a corresponding power grid fault warning message is generated and a corresponding preset remote control strategy is matched.

[0111] In one specific embodiment, the DC ice melting actual parameter acquisition module 103 in the system is also used to calculate the transmission rate of the line parameters of the DC ice melting operation and the equipment parameters on the line of the DC ice melting operation.

[0112] The DC ice melting reference parameter acquisition module 101 is also used to statistically analyze the parameter data and equipment specifications of the lines in historical DC ice melting operations, and to acquire the communication transmission reference data of the parameters of each line and the parameters of the equipment on it.

[0113] The DC ice melting fault judgment module 104 is also used to compare the transmission rate of the line parameter data of the DC ice melting operation with the communication transmission reference data of the line parameters, and the transmission rate of the equipment parameter data on the line of the DC ice melting operation with the communication transmission reference data of the equipment parameters on the line. If any comparison result is lower than the corresponding reference data, then a communication fault is identified.

[0114] The DC de-icing fault control module 105 is also used to utilize a hierarchical diagnostic process to sequentially control equipment self-test, network link self-test, and multi-device status comparison self-test. Based on the self-test results, it determines the communication fault source and generates an early warning prompt. Based on the generated early warning prompt, it matches the corresponding communication fault recovery strategy to complete the communication fault recovery of the DC de-icing line. The communication fault recovery strategy includes: if the communication fault originates from the equipment, restarting the equipment or switching to a backup equipment; if the communication fault originates from the network link, switching to a backup communication link.

[0115] In a specific embodiment, the system further includes: a DC ice-melting fault prediction and control module 106, used to construct a DC ice-melting digital twin model; drive the DC ice-melting digital twin model to run based on the collected real-time actual electrical parameters of the line, the actual ice-melting thickness parameters of the line, and the actual equipment parameters, and complete the data mapping and calibration of the DC ice-melting digital twin model; use the DC ice-melting digital twin model to simulate and predict the operation data of the line for DC ice-melting operations at a future preset time, including the line electrical parameters, the line ice-melting thickness parameters, and the equipment parameters; use a fault identification model built based on a deep learning algorithm to obtain the predicted fault type and fault level of the line for DC ice-melting operations at the future preset time; match a corresponding preset remote control strategy and perform simulated control in the DC ice-melting digital twin model according to the corresponding preset remote control strategy; verify the accuracy of matching the corresponding preset remote control strategy by obtaining the fault elimination status of the DC ice-melting operation line in the DC ice-melting digital twin model after simulated control, and execute the matching corresponding preset remote control strategy after verification, otherwise optimize the matching corresponding preset remote control strategy.

[0116] In one specific embodiment, the DC ice-melting fault verification module 107 is used to embed a GPS module in each sensor deployed on the key nodes of the DC ice-melting line and the equipment side. Whenever an electrical fault, equipment fault, or ice-melting fault is detected, the corresponding key node of the DC ice-melting line and the equipment side are locked, and a UAV device is assigned to collect fault images of the key node of the DC ice-melting line and the equipment side. The preset fault conditions of the key node of the DC ice-melting line and the equipment side are continuously obtained through image analysis technology to verify the preset fault judgment results and judge the effect of subsequent remote control.

[0117] In one specific embodiment, the DC de-icing reference parameter correction module 102 is also used to collect the icing characteristic parameters of the DC de-icing operation line and correct the line electrical reference parameters and DC de-icing equipment reference parameters based on the icing characteristic parameters.

[0118] This application also discloses a computer-readable storage medium.

[0119] Specifically, the computer-readable storage medium stores a computer program that can be loaded by a processor and executed, such as the DC ice melting monitoring and early warning method described above. The computer-readable storage medium includes, for example, various media that can store program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0120] This application also discloses a computer device.

[0121] Specifically, the computer device includes a memory and a processor, and the memory stores a computer program that can be loaded by the processor and executed to perform the aforementioned DC ice melting monitoring and early warning method.

[0122] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A DC de-icing monitoring and early warning method, characterized in that, include: Collect line parameters for DC de-icing operations, determine the line de-icing targets for DC de-icing operations, calculate the line electrical reference parameters, and obtain the de-icing demand reference parameters; Collect and obtain the reference parameters of the equipment deployed on the DC ice melting operation line; Collect real-time environmental parameters around the DC de-icing operation line, and correct the line electrical reference parameters and DC de-icing equipment reference parameters based on the real-time environmental parameters; By utilizing sensors deployed at key nodes of the DC ice melting operation line and on the equipment side, the actual electrical parameters of the line, the actual ice melting thickness of the line, and the actual equipment parameters are collected in real time. Real-time comparison of line electrical reference parameters with actual line electrical parameters, de-icing demand reference parameters with actual line de-icing thickness parameters, and equipment reference parameters with actual equipment parameters, to determine whether there are electrical faults, equipment faults, or de-icing faults, as well as the level of each type of fault; Based on the acquired electrical faults, equipment faults, or de-icing faults, as well as various fault levels, early warning information is generated and matched with corresponding preset remote control strategies. Remote control is then completed according to the corresponding preset remote control strategies. The corresponding preset remote control strategies are obtained by training a remote control strategy acquisition model based on historical remote control strategies with fault elimination rates greater than preset fault elimination rates, according to the corresponding type and level of faults.

2. The DC de-icing monitoring and early warning method according to claim 1, characterized in that, Also includes: By combining deep learning algorithms, it is determined whether there are conflicts between the acquired electrical faults, equipment faults, or de-icing faults and the corresponding remote control strategies for matching various fault levels; If a conflict exists, the corresponding remote control strategy will be executed sequentially according to the priority of the control strategy to perform remote control. The control strategy priority setting rules include: the remote control strategy that ensures line safety has the highest priority, the remote control strategy that ensures equipment safety has the second-highest priority, and the remote control strategy that optimizes line and equipment operating parameters has the lowest priority.

3. The DC de-icing monitoring and early warning method according to claim 1, characterized in that, Also includes: Obtain the short-circuit capacity of the power grid connection point where the DC ice melting operation line is located; The system determines whether the ice-melting current in the actual electrical parameters of the DC ice-melting line exceeds the preset multiple of the short-circuit capacity of the grid connection point where the DC ice-melting line is located, and collects the equipment status of the circuit breakers at both ends of the DC ice-melting line. Based on the equipment status of the circuit breakers at both ends of the line and the parameters of the DC ice-melting line, it determines whether the DC ice-melting line forms a closed loop. If the judgment result is that the short-circuit capacity of the power grid access point where the DC de-icing operation is located is exceeded by a preset multiple or a closed loop is not formed, a power grid fault warning message will be generated and a corresponding preset remote control strategy will be matched.

4. The DC de-icing monitoring and early warning method according to claim 1, characterized in that, Also includes: Calculate the transmission rate of the line parameters and equipment parameters on the DC ice melting operation line; Statistical analysis was conducted on the parameter data and equipment specifications of historical DC ice melting operations to obtain the communication transmission reference data for the parameters of each line and the parameters of the equipment on it. The transmission rate of the line parameter data of the DC ice melting operation was compared with the communication transmission reference data of the line parameters, and the transmission rate of the equipment parameter data of the DC ice melting operation was compared with the communication transmission reference data of the equipment parameters on the line. If any comparison result was lower than the corresponding reference data, a communication fault was identified. Using a hierarchical diagnostic process, the system sequentially controls device self-testing, network link self-testing, and multi-device status comparison self-testing. Based on the self-test results, it identifies the source of communication faults and generates early warning prompts. Based on the generated early warning prompts, match the corresponding communication fault recovery strategy to complete the communication fault recovery of the DC de-icing operation line; The communication failure recovery strategy includes: determining that the communication failure originates from the device, restarting the device, or switching to a backup device; Once the communication failure is determined to originate from the network link, switch to a backup communication link.

5. The DC de-icing monitoring and early warning method according to claim 1, characterized in that, Also includes: Constructing a digital twin model for DC ice melting includes: building a three-dimensional geometric and electrical equivalent physical layer model based on the line parameters, equipment parameters on the line, and power grid parameters of the line; building an environmental layer model based on the real-time environmental parameters and icing characteristic parameters of the line's surroundings; and building a control layer model by integrating the line equipment control logic and mapping the response characteristics of remote control commands. Importing a benchmark parameter set based on historical ice melting data, which includes line electrical benchmark parameters, ice melting demand benchmark parameters, and equipment benchmark parameters. The DC ice-melting digital twin model is driven by the real-time collected actual electrical parameters of the line, the actual ice-melting thickness of the line, and the actual equipment parameters to complete the data mapping and calibration of the DC ice-melting digital twin model. The system uses a digital twin model of DC ice melting to simulate and predict the operation data of the line for DC ice melting operations at a predetermined time in the future, including the line's electrical parameters, ice melting thickness parameters, and equipment parameters; and uses a fault identification model built based on deep learning algorithms to obtain the fault type and fault level of the line for DC ice melting operations at the predetermined time in the future. Match the corresponding preset remote control strategy and perform simulation control in the DC ice melting digital twin model according to the corresponding preset remote control strategy; by obtaining the fault elimination status of the DC ice melting operation line in the DC ice melting digital twin model after simulation control, verify the accuracy of matching the corresponding preset remote control strategy. If the verification is successful, execute the matching corresponding preset remote control strategy; otherwise, optimize the matching corresponding preset remote control strategy.

6. The DC de-icing monitoring and early warning method according to claim 1, characterized in that, Also includes: Each sensor deployed at key nodes of the DC ice-melting line and on the equipment side has an embedded GPS module. Whenever an electrical fault, equipment fault, or ice-melting fault is detected, the corresponding key node of the DC ice-melting line and the equipment side are located. A drone is then deployed to collect fault images of the key node of the DC ice-melting line and the equipment side. Image analysis technology is used to continuously obtain preset fault conditions of the key node of the DC ice-melting line and the equipment side to verify the preset fault judgment results and assist in judging the effectiveness of subsequent remote control.

7. The DC de-icing monitoring and early warning method according to claim 1, characterized in that, Also includes: Collect icing characteristic parameters of DC de-icing operation lines, and correct the line electrical reference parameters and DC de-icing equipment reference parameters based on the icing characteristic parameters; The icing characteristic parameters include: icing type.

8. A DC de-icing monitoring and early warning system, characterized in that, include: The DC ice melting reference parameter acquisition module is used to collect line parameters for DC ice melting operations, determine the ice melting target of the DC ice melting operation, calculate the line electrical reference parameters, and obtain the ice melting requirement reference parameters. Collect and obtain the reference parameters of the equipment deployed on the DC ice melting operation line; The DC ice-melting reference parameter correction module is used to collect real-time environmental parameters around the DC ice-melting operation line and correct the line electrical reference parameters and DC ice-melting equipment reference parameters based on the real-time environmental parameters. The DC ice melting actual parameter acquisition module is used to collect the actual electrical parameters of the line, the actual ice melting thickness of the line, and the actual equipment parameters in real time by using sensors deployed at key nodes of the line and equipment side of the DC ice melting operation. The DC de-icing fault judgment module is used to compare the line electrical reference parameters with the actual line electrical parameters, the de-icing demand reference parameters with the actual line de-icing thickness parameters, and the equipment reference parameters with the actual equipment parameters in real time, so as to determine whether there is an electrical fault, equipment fault, or de-icing fault, as well as the various fault levels. The DC de-icing fault control module is used to generate early warning information based on the acquired electrical faults, equipment faults, or de-icing faults and various fault levels, and match them with corresponding preset remote control strategies. The module then performs remote control according to the preset remote control strategies. The preset remote control strategies are obtained by training a remote control strategy acquisition model based on historical remote control strategies with fault elimination rates greater than preset fault elimination rates for the corresponding types and levels of faults.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the method as described in any one of claims 1 to 7.

10. A computer device, characterized in that, The computer device includes a memory, a processor, and a program stored in and executable on the memory, the program being executed by the processor to implement the steps of the method as described in any one of claims 1 to 7.

Images