Parallel fault-tolerant type converter cross-mode collaborative control method and system

Abstract

This invention discloses a cross-modal cooperative control method and system for parallel fault-tolerant converters, belonging to the field of power electronics technology. It includes a converter control module, a model analysis module, a monitoring and judgment module, and a cooperative control module. The converter control module is used to convert electrical energy generated by wind power generation into electrical energy that meets grid requirements and is then fed into the grid through a parallel fault-tolerant converter. The model analysis module is used to establish a loss analysis model to analyze the probability of equipment failure in power units under different loss risk values. The monitoring and judgment module is used to analyze the collected real-time power data, predict the probability of equipment failure in power units, and determine whether to increase the number of connected power units. The cooperative control module is used to dynamically adjust the output power of the output terminals in different power units, thereby achieving derating fault-tolerant operation.

Description

Technical Field

[0001] This invention relates to the field of power electronics technology, specifically to a method and system for cross-modal coordinated control of parallel fault-tolerant converters. Background Technology

[0002] Cross-modal cooperative control of converters refers to the use of intelligent control algorithms and system architecture to enable converters to switch between different operating modes, thereby achieving coordinated optimization of multiple control objectives. With the rapid development of distributed energy and microgrids in offshore wind power, traditional single-mode converters are no longer able to cope with dynamic coupling problems under multiple operating conditions. Through cross-modal cooperative control, which integrates real-time data and intelligent decision-making, not only can the system's resource management efficiency be improved, but also the stability of new energy grid connection and the autonomy of microgrids can be effectively improved when facing emergencies by identifying and adjusting faulty power devices.

[0003] Parallel fault-tolerant converters are typically composed of multiple converter units connected in parallel. In offshore wind power systems, due to the complexity of the offshore environment, factors such as wind speed fluctuations and grid faults require adjustments to the converter modes. However, existing technologies for converter analysis and control are relatively simple, making it difficult for the system to meet the coordinated control requirements under various variable scenarios. Furthermore, uneven current distribution and long-term operation can increase converter aging, which not only shortens equipment lifespan but also, in severe cases, further exacerbates the risk of safety failures. Summary of the Invention

[0004] The purpose of this invention is to provide a cross-modal cooperative control method and system for parallel fault-tolerant converters to solve the problems mentioned in the background art.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a cross-modal cooperative control method for parallel fault-tolerant converters, the method comprising the following steps:

[0006] Step S10: The electrical energy generated by wind power generation is converted into electrical energy that meets the grid requirements through a parallel fault-tolerant converter and then connected to the grid. Power data during the power conversion process is collected. The power data includes the number of connected power units, the package volume of different power units, and the current and voltage changes at the input and output terminals of different power units.

[0007] Step S20: Establish a storage unit to store historical power data in different power conversion processes; based on the historical power data containing equipment failures in the storage unit, establish a loss analysis model to analyze the probability of equipment failure in the power unit under different loss risk values;

[0008] Step S30: Analyze the real-time power data collected in step S10, and predict the probability of equipment failure in the power unit based on the loss analysis model established in step S20; compare the predicted probability of equipment failure in the power unit with the safety threshold to determine whether it is necessary to increase the number of connected power units; if it is not necessary to increase the number of power units, repeat step S30; if it is necessary to increase the number of power units, execute step S40.

[0009] Step S40: Connect a new power unit and dynamically adjust the output power of the output terminals in different power units.

[0010] Furthermore, the parallel fault-tolerant converter includes several parallel independent power units; each power unit can operate independently, converting electrical energy into electrical energy that meets the grid requirements before connecting it to the grid; when a power unit fails, the faulty power unit is isolated, and the power at the output of other power units is redistributed.

[0011] Furthermore, the method steps of step S20 are as follows:

[0012] Step S21: Retrieve historical power data showing equipment failure from the storage unit for analysis, identify the power units that experienced equipment failure in different historical power data, and obtain the package volume V1, V2, ..., V of each power unit. n Based on the input and output current and voltage of different power units experiencing equipment failures at different times t, the input power of different power units at different times t is determined. and output power Where n represents the number of historical power data points with existing equipment failures being analyzed;

[0013] Step S22, according to and Calculate the loss risk values ​​S1, S2, ..., S when different power units experience equipment failure. n According to the calculation formula:

[0014]

[0015] Among them, S i This represents the loss risk value when the i-th type of power unit experiences a device failure. This represents the input power of the i-th power unit that experienced a device failure at different times t. V represents the output power of the i-th power unit that has experienced a equipment failure at different times t; i This represents the package volume of the i-th power unit; The lower limit of integration is the timestamp of the power unit's first operation, and the upper limit of integration is the timestamp of the power unit's equipment failure.

[0016] Step S23: Establish a loss analysis model. Based on the loss risk value of each power unit when equipment failure occurs, use the Weibull distribution to analyze the probability of equipment failure of the power unit under different loss risk values:

[0017]

[0018] in,

[0019] Where S represents the loss risk value when a device failure occurs in the power unit being analyzed; This represents the average loss risk value when equipment failure occurs from the n historical power data points analyzed. M represents the shape parameter; Q represents the scale parameter; and Q represents the probability of equipment failure occurring in the power unit.

[0020] Furthermore, the method in step S30 is as follows: analyze the real-time power data to determine the number m of currently connected power units, determine the package volume of different currently connected power units, and calculate the loss risk value of each power unit in the event of a device failure based on the current and voltage changes at the input and output terminals of each power unit. Determine the safety threshold K for equipment failure, and... Substitute these values ​​into the established loss analysis model to predict the probability of equipment failure in different power units. And compare it with K; when the probability of equipment failure in each power unit is less than the safety threshold, no power unit needs to be added; when the probability of equipment failure in any power unit is greater than the safety threshold, power units need to be added.

[0021] Furthermore, the method for dynamically adjusting the output power of different power units is as follows: determine the output power of different power units at the next time step. make Formula that satisfies the condition: in, This represents the loss risk value when a device failure occurs in each of the j-th power units currently connected; This represents the package volume of the j-th type of power unit currently connected; This represents the output power of the currently connected j-th power unit at the next time t0; This represents the input power of the j-th power unit currently connected at the next time t0; Δt represents the time step; W represents the performance index reflecting the safety level of the parallel fault-tolerant converter. The smaller W is, the safer the parallel fault-tolerant converter is. According to Adjust the output power of the output terminals of different power units at the next time step.

[0022] A parallel fault-tolerant converter cross-modal cooperative control system, which includes a converter control module, a data acquisition module, a model analysis module, a monitoring and judgment module, and a cooperative control module;

[0023] The converter control module is used to convert the electrical energy generated by wind power generation into electrical energy that meets the grid requirements and then connect it to the grid through a parallel fault-tolerant converter; the parallel fault-tolerant converter contains several parallel independent power units.

[0024] The data acquisition module is used to collect power data during the power conversion process in the converter control module; the power data includes the number of connected power units, the package volume of different power units, and the current and voltage changes at the input and output terminals of different power units; the collected power data is sent to the model analysis module and the monitoring and judgment module;

[0025] The model analysis module is used to establish a storage unit to store historical power data in different power conversion processes; based on the historical power data containing equipment failures in the storage unit, a loss analysis model is established to analyze the probability of equipment failure in the power unit under different loss risk values;

[0026] The monitoring and judgment module is used to analyze the collected real-time power data, predict the probability of equipment failure in the power unit based on the loss analysis model established in the model analysis module, compare the predicted probability of equipment failure in the power unit with the safety threshold, and determine whether it is necessary to increase the number of connected power units. If it is not necessary to increase the number of power units, the judgment continues. If it is necessary to increase the number of power units, the signal for connecting the new power units is sent to the collaborative control module.

[0027] The collaborative control module is used to connect new power units and dynamically adjust the output power of the output terminals in different power units.

[0028] Furthermore, the model analysis module includes a storage unit, a historical data analysis unit, a loss risk value calculation unit, and a model training unit;

[0029] The storage unit is used to establish a storage unit and store historical power data in different power conversion processes;

[0030] The historical data analysis unit is used to retrieve historical power data with equipment failures from the storage unit for analysis, determine the power units with equipment failures in different historical power data, obtain the package volume of each power unit, and determine the input power and output power of different power units at different times based on the current and voltage at the input and output terminals of different power units with equipment failures at different times.

[0031] The loss risk value calculation unit is used to calculate the loss risk value when different power units experience equipment failure.

[0032] The model training unit is used to establish a loss analysis model. Based on the loss risk value of each power unit when equipment failure occurs, the Weibull distribution is used to analyze the probability of equipment failure of the power unit under different loss risk values.

[0033] Furthermore, the monitoring and judgment module includes a real-time data analysis unit and an intelligent judgment unit;

[0034] The real-time data analysis unit is used to analyze real-time power data, determine the number of currently connected power units, determine the package volume of different currently connected power units, and calculate the loss risk value when equipment failure occurs in different currently connected power units based on the changes in current and voltage at the input and output terminals of each power unit.

[0035] The intelligent judgment unit is used to determine the safety threshold for equipment failure. It substitutes the loss risk value of each power unit in the currently connected power units when equipment failure occurs into the established loss analysis model to predict the probability of equipment failure in the current power units and compares it with the safety threshold. When the probability of equipment failure in each power unit is less than the safety threshold, no power unit needs to be added. When the probability of equipment failure in any power unit is greater than the safety threshold, a power unit needs to be added.

[0036] Furthermore, the collaborative control module includes an intelligent computing unit and an intelligent control unit;

[0037] The intelligent computing unit is used to determine the output power of different power unit output terminals at the next time step.

[0038] The intelligent control unit is used to adjust the output power of the output terminals of different power units in the next time step according to the output power of the output terminals of different power units in the next time step.

[0039] Furthermore, a human-machine interaction platform is provided, through which managers can view historical power data in the storage unit, calculate the loss risk value when different power units experience equipment failure, and the probability of equipment failure of power units under different loss risk values.

[0040] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: It assesses the risk of equipment failure based on the Weibull distribution, predicts the probability of equipment failure under different energy losses, thereby helping managers assess the health status of different power units and reducing the complexity of maintaining parallel fault-tolerant converters; through the established loss analysis model, it monitors the loss risk value of each power unit in real time when equipment failure occurs, and intervenes in advance when the probability is too high, by connecting a new power unit in advance, reducing the safety risk caused by excessive output power during power allocation of other power units, making the system more stable; and by dynamically adjusting the output power at the output end of different power units, it effectively reduces the probability of system equipment failure. Attached Figure Description

[0041] Figure 1 This is a schematic diagram illustrating the steps of the parallel fault-tolerant converter cross-modal cooperative control method of the present invention;

[0042] Figure 2 This is a schematic diagram of the cross-modal cooperative control system for parallel fault-tolerant converters of the present invention. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0044] Please see Figure 1-2 The present invention provides the following technical solution:

[0045] Please see Figure 1 In this embodiment, a cross-modal cooperative control method for parallel fault-tolerant converters is provided, which includes the following steps:

[0046] Step S10: The electrical energy generated by wind power generation is converted into electrical energy that meets the grid requirements through a parallel fault-tolerant converter and then connected to the grid. Power data during the power conversion process is collected. The power data includes the number of connected power units, the package volume of different power units, and the current and voltage changes at the input and output terminals of different power units.

[0047] Furthermore, the parallel fault-tolerant converter includes several parallel independent power units; each power unit can operate independently, converting electrical energy into electrical energy that meets the grid requirements before connecting it to the grid; when a power unit fails, the faulty power unit is isolated, and the power at the output of other power units is redistributed.

[0048] In this embodiment, the parallel fault-tolerant converter adopts a modular redundancy design. When any power unit fails, the fault current of the power unit is cut off by the fuse, the thyristor bypass switch is turned on, the faulty unit is short-circuited and isolated, and the main control system adjusts the output power of other power units through PWM modulation, thereby ensuring that the grid-connected output power is not derated.

[0049] Step S20: Establish a storage unit to store historical power data in different power conversion processes; based on the historical power data containing equipment failures in the storage unit, establish a loss analysis model to analyze the probability of equipment failure in the power unit under different loss risk values.

[0050] Specifically, the steps are as follows:

[0051] Step S21: Retrieve historical power data showing equipment failure from the storage unit for analysis, identify the power units that experienced equipment failure in different historical power data, and obtain the package volume V1, V2, ..., V of each power unit. n Based on the input and output current and voltage of different power units experiencing equipment failures at different times t, the input power of different power units at different times t is determined. and output power Where n represents the number of historical power data points with existing equipment failures being analyzed;

[0052] Step S22, according to and Calculate the loss risk values ​​S1, S2, ..., S when different power units experience equipment failure. n According to the calculation formula:

[0053]

[0054] Among them, S i This represents the loss risk value when the i-th type of power unit experiences a device failure. This represents the input power of the i-th power unit that experienced a device failure at different times t. V represents the output power of the i-th power unit that has experienced a equipment failure at different times t; i This represents the package volume of the i-th power unit; The lower limit of integration is the timestamp of the power unit's first operation, and the upper limit of integration is the timestamp of the power unit's equipment failure.

[0055] Step S23: Establish a loss analysis model. Based on the loss risk value of each power unit when equipment failure occurs, use the Weibull distribution to analyze the probability of equipment failure of the power unit under different loss risk values:

[0056]

[0057] in,

[0058] Where S represents the loss risk value when a device failure occurs in the power unit being analyzed; This represents the average loss risk value when equipment failure occurs from the n historical power data points analyzed. M represents the shape parameter; Q represents the scale parameter; and Q represents the probability of equipment failure occurring in the power unit.

[0059] It should be noted that the equipment failure refers to a fault in the equipment components of the power unit that prevents the conversion of electrical energy generated by wind power generation, such as a short circuit in the converter.

[0060] It should be noted that by analyzing historical power data generated by power units that have experienced equipment failures, the risk of equipment failure can be assessed based on the Weibull distribution, and the probability of equipment failure under different energy losses can be predicted. This helps managers assess the health status of different power units and reduces the complexity of maintaining parallel fault-tolerant converters; among them, shape parameters The shape of the Weibull distribution is determined, reflecting the changing trend of equipment failure in the power unit with the magnitude of loss risk value; the scale parameter M determines the scaling range of the Weibull distribution, representing the average loss risk value before equipment failure occurs; through the Weibull distribution, the failure probability of equipment devices in the power unit can be predicted more directly.

[0061] It should be noted that Q(S) is a functional relationship between the independent variable S and the dependent variable Q. By analyzing historical power data, a loss analysis model is established, and S1, S2, ..., S... n As training parameters of S, they are substituted into the functional relationship of Q(S) to determine the probability of equipment failure in the power unit, thereby facilitating the evaluation of the failure probability of equipment devices in the power unit and providing data support for cross-modal collaborative control of parallel fault-tolerant converters.

[0062] It should be noted that, since different power units are packaged, the coupling effect between different power units is not considered in this implementation.

[0063] Step S30: Analyze the real-time power data collected in step S10, and predict the probability of equipment failure in the power unit based on the loss analysis model established in step S20; compare the predicted probability of equipment failure in the power unit with the safety threshold to determine whether it is necessary to increase the number of connected power units; if it is not necessary to increase the number of power units, repeat step S30; if it is necessary to increase the number of power units, execute step S40.

[0064] Specifically, the method is as follows: Analyze real-time power data to determine the number m of currently connected power units, determine the package volume of different currently connected power units, and calculate the loss risk value of each power unit in the event of equipment failure based on the current and voltage changes at the input and output terminals of each power unit. Determine the safety threshold K for equipment failure, and... Substitute these values ​​into the established loss analysis model to predict the probability of equipment failure in different power units. And compare it with K; when the probability of equipment failure in each power unit is less than the safety threshold, no power unit needs to be added; when the probability of equipment failure in any power unit is greater than the safety threshold, power units need to be added.

[0065] Step S40: Connect a new power unit and dynamically adjust the output power of the output terminals in different power units.

[0066] It should be noted that by establishing a loss analysis model, the loss risk value of each power unit in different power units is monitored in real time when equipment failure occurs, and the probability of equipment failure is judged. When the probability is too high, a new power unit is connected in advance for early intervention, rather than simply judging by the failure threshold. If equipment failure occurs at this time, the safety risk caused by excessive output power during the power distribution process of other power units is reduced due to the connection of a new power unit, making the system more stable.

[0067] In one embodiment, it is necessary to add power units. The method for dynamically adjusting the output power of the output terminals of different power units is as follows: determine the output power of the output terminals of different power units at the next time step. make Formula that satisfies the condition: in, This represents the loss risk value when a device failure occurs in each of the j-th power units currently connected; This represents the package volume of the j-th type of power unit currently connected; This represents the output power of the currently connected j-th power unit at the next time t0; This represents the input power of the j-th power unit currently connected at the next time t0; Δt represents the time step; W represents the performance index reflecting the safety level of the parallel fault-tolerant converter. The smaller W is, the safer the parallel fault-tolerant converter is. According to The output power of the output terminals of different power units is adjusted at the next time step; the output power, current and voltage of the power unit output terminals are all within a safe range. By dynamically adjusting the output power of the output terminals of different power units, the probability of system equipment failure is effectively reduced.

[0068] In another embodiment, it is not necessary to add power units at this time. Step S30 is repeated, and the output power of the output terminal in different power units is dynamically adjusted to meet the condition of minimum W.

[0069] Please see Figure 2 In this embodiment, a parallel fault-tolerant converter cross-modal cooperative control system is provided. The system includes a converter control module, a data acquisition module, a model analysis module, a monitoring and judgment module, and a cooperative control module.

[0070] The converter control module is used to convert the electrical energy generated by wind power generation into electrical energy that meets the grid requirements and then connect it to the grid through a parallel fault-tolerant converter; the parallel fault-tolerant converter contains several parallel independent power units.

[0071] The data acquisition module is used to collect power data during the power conversion process in the converter control module; the power data includes the number of connected power units, the package volume of different power units, and the current and voltage changes at the input and output terminals of different power units; the collected power data is sent to the model analysis module and the monitoring and judgment module;

[0072] The model analysis module is used to establish a storage unit to store historical power data in different power conversion processes; based on the historical power data containing equipment failures in the storage unit, a loss analysis model is established to analyze the probability of equipment failure in the power unit under different loss risk values;

[0073] The monitoring and judgment module is used to analyze the collected real-time power data, predict the probability of equipment failure in the power unit based on the loss analysis model established in the model analysis module, compare the predicted probability of equipment failure in the power unit with the safety threshold, and determine whether it is necessary to increase the number of connected power units. If it is not necessary to increase the number of power units, the judgment continues. If it is necessary to increase the number of power units, the signal for connecting the new power units is sent to the collaborative control module.

[0074] The collaborative control module is used to connect new power units and dynamically adjust the output power of the output terminals in different power units.

[0075] Furthermore, the model analysis module includes a storage unit, a historical data analysis unit, a loss risk value calculation unit, and a model training unit;

[0076] The storage unit is used to establish a storage unit and store historical power data in different power conversion processes;

[0077] The historical data analysis unit is used to retrieve historical power data with equipment failures from the storage unit for analysis, determine the power units with equipment failures in different historical power data, obtain the package volume of each power unit, and determine the input power and output power of different power units at different times based on the current and voltage at the input and output terminals of different power units with equipment failures at different times.

[0078] The loss risk value calculation unit is used to calculate the loss risk value when different power units experience equipment failure.

[0079] The model training unit is used to establish a loss analysis model. Based on the loss risk value of each power unit when equipment failure occurs, the Weibull distribution is used to analyze the probability of equipment failure of the power unit under different loss risk values.

[0080] Furthermore, the monitoring and judgment module includes a real-time data analysis unit and an intelligent judgment unit;

[0081] The real-time data analysis unit is used to analyze real-time power data, determine the number of currently connected power units, determine the package volume of different currently connected power units, and calculate the loss risk value when equipment failure occurs in different currently connected power units based on the changes in current and voltage at the input and output terminals of each power unit.

[0082] The intelligent judgment unit is used to determine the safety threshold for equipment failure. It substitutes the loss risk value of each power unit in the currently connected power units when equipment failure occurs into the established loss analysis model to predict the probability of equipment failure in the current power units and compares it with the safety threshold. When the probability of equipment failure in each power unit is less than the safety threshold, no power unit needs to be added. When the probability of equipment failure in any power unit is greater than the safety threshold, a power unit needs to be added.

[0083] Furthermore, the collaborative control module includes an intelligent computing unit and an intelligent control unit;

[0084] The intelligent computing unit is used to determine the output power of different power unit output terminals at the next time step.

[0085] The intelligent control unit is used to adjust the output power of the output terminals of different power units in the next time step according to the output power of the output terminals of different power units in the next time step.

[0086] Furthermore, a human-machine interaction platform is provided, through which managers can view historical power data in the storage unit, calculate the loss risk value when different power units experience equipment failure, and the probability of equipment failure of power units under different loss risk values.

[0087] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for cross-modal cooperative control of parallel fault-tolerant converters, characterized in that: The method includes the following steps: Step S10: The electrical energy generated by wind power generation is converted into electrical energy that meets the grid requirements through a parallel fault-tolerant converter and then connected to the grid. Power data during the power conversion process is collected. The power data includes the number of connected power units, the package volume of different power units, and the current and voltage changes at the input and output terminals of different power units. Step S20: Establish a storage unit to store historical power data in different power conversion processes; based on the historical power data containing equipment failures in the storage unit, establish a loss analysis model to analyze the probability of equipment failure in the power unit under different loss risk values; The method steps of step S20 are as follows: Step S21: Retrieve historical power data containing equipment failures from the storage unit for analysis, identify the power units that experienced equipment failures in different historical power data sets, and obtain the package volume of each power unit. Depending on the power unit that experienced the equipment failure at different times The input and output currents and voltages are used to determine the different power units at different times. Input power and output power ;in, This indicates the amount of historical power data containing existing equipment failures in the analysis. Step S22, according to , and Calculate the loss risk value when different power units experience equipment failure. According to the calculation formula: ； in, Indicates the first The loss risk value when a power unit experiences equipment failure; This indicates the first equipment failure. Power units at different times The input power is as follows; This indicates the first equipment failure. Power units at different times Output power at the following levels; Indicates the first The package size of the power unit; The lower limit of integration is the timestamp of the power unit's first operation, and the upper limit of integration is the timestamp of the power unit's equipment failure. Step S23: Establish a loss analysis model. Based on the loss risk value of each power unit when equipment failure occurs, use the Weibull distribution to analyze the probability of equipment failure of the power unit under different loss risk values: ； in, ; ; in, This represents the loss risk value when a device failure occurs in the power unit being analyzed; This represents the average loss risk value when equipment failure occurs from the n historical power data points analyzed. Indicates shape parameters; Indicates the scale parameter; This indicates the probability of a device failure occurring in the power unit; Step S30: Analyze the real-time power data collected in step S10, and predict the probability of equipment failure in the power unit based on the loss analysis model established in step S20; compare the predicted probability of equipment failure in the power unit with the safety threshold to determine whether it is necessary to increase the number of connected power units; if it is not necessary to increase the number of power units, repeat step S30; if it is necessary to increase the number of power units, execute step S40. Step S40: Connect a new power unit and dynamically adjust the output power of the output terminals in different power units.

2. The method for cross-modal cooperative control of parallel fault-tolerant converters according to claim 1, characterized in that: The parallel fault-tolerant converter comprises several parallel independent power units; each power unit can operate independently, converting electrical energy into electrical energy that meets the grid requirements before connecting it to the grid; when a power unit fails, the faulty power unit is isolated, and the power at the output of other power units is redistributed.

3. The method for cross-modal cooperative control of parallel fault-tolerant converters according to claim 1, characterized in that: The method in step S30 is as follows: analyze the real-time power data to determine the number of power units currently connected. Determine the package volume of the different power units currently connected, and calculate the loss risk value of each power unit in the event of a device failure based on the changes in current and voltage at the input and output terminals of each power unit. Determine the safe threshold for equipment failure. ,Will Substitute these values ​​into the established loss analysis model to predict the probability of equipment failure in different power units. and with The comparison is performed; when the probability of equipment failure in any power unit is less than the safety threshold, no additional power unit is needed; when the probability of equipment failure in any power unit is greater than the safety threshold, an additional power unit is needed.

4. The method for cross-modal cooperative control of parallel fault-tolerant converters according to claim 3, characterized in that: The method for dynamically adjusting the output power of different power units is as follows: determine the output power of different power units at the next time step. ,make Formula that satisfies the condition: ;in, Indicates the number of currently connected devices. The loss risk value when each power unit in a power unit experiences a device failure; Indicates the number of currently connected devices. The package size of the power unit; Indicates the number of currently connected devices. The power unit in the next time Output power at the following levels; Indicates the number of currently connected devices. The power unit in the next time The input power is as follows; Indicates the time step. This indicates a performance index reflecting the safety level of a parallel fault-tolerant converter. The smaller the value, the safer the parallel fault-tolerant converter; according to The output power of the output terminals of different power units is adjusted at the next time step.

5. A parallel fault-tolerant converter cross-modal cooperative control system, characterized in that: The system includes a converter control module, a data acquisition module, a model analysis module, a monitoring and judgment module, and a collaborative control module; The converter control module is used to convert the electrical energy generated by wind power generation into electrical energy that meets the grid requirements and then connect it to the grid through a parallel fault-tolerant converter; the parallel fault-tolerant converter contains several parallel independent power units. The data acquisition module is used to collect power data during the power conversion process in the converter control module; the power data includes the number of connected power units, the package volume of different power units, and the current and voltage changes at the input and output terminals of different power units; the collected power data is sent to the model analysis module and the monitoring and judgment module; The model analysis module is used to establish a storage unit to store historical power data in different power conversion processes; based on the historical power data containing equipment failures in the storage unit, a loss analysis model is established to analyze the probability of equipment failure in the power unit under different loss risk values; The model analysis module includes a storage unit, a historical data analysis unit, a loss risk value calculation unit, and a model training unit. The storage unit is used to establish a storage unit and store historical power data in different power conversion processes; The historical data analysis unit is used to retrieve historical power data with equipment failures from the storage unit for analysis, determine the power units with equipment failures in different historical power data, obtain the package volume of each power unit, and determine the input power and output power of different power units at different times based on the current and voltage at the input and output terminals of different power units with equipment failures at different times. The loss risk value calculation unit is used to calculate the loss risk value when different power units experience equipment failure. The model training unit is used to establish a loss analysis model. Based on the loss risk value of each power unit when equipment failure occurs, the Weibull distribution is used to analyze the probability of equipment failure of the power unit under different loss risk values. The monitoring and judgment module is used to analyze the collected real-time power data, predict the probability of equipment failure in the power unit based on the loss analysis model established in the model analysis module, compare the predicted probability of equipment failure in the power unit with the safety threshold, and determine whether it is necessary to increase the number of connected power units. If it is not necessary to increase the number of power units, the judgment continues. If it is necessary to increase the number of power units, the signal for connecting the new power units is sent to the collaborative control module. The collaborative control module is used to connect new power units and dynamically adjust the output power of the output terminals in different power units.

6. The parallel fault-tolerant converter cross-modal cooperative control system according to claim 5, characterized in that: The monitoring and judgment module includes a real-time data analysis unit and an intelligent judgment unit; The real-time data analysis unit is used to analyze real-time power data, determine the number of currently connected power units, determine the package volume of different currently connected power units, and calculate the loss risk value when equipment failure occurs in different currently connected power units based on the changes in current and voltage at the input and output terminals of each power unit. The intelligent judgment unit is used to determine the safety threshold for equipment failure. It substitutes the loss risk value of each power unit in the currently connected power units when equipment failure occurs into the established loss analysis model to predict the probability of equipment failure in the current power units and compares it with the safety threshold. When the probability of equipment failure in each power unit is less than the safety threshold, no power unit needs to be added. When the probability of equipment failure in any power unit is greater than the safety threshold, a power unit needs to be added.

7. The parallel fault-tolerant converter cross-modal cooperative control system according to claim 6, characterized in that: The collaborative control module includes an intelligent computing unit and an intelligent control unit; The intelligent computing unit is used to determine the output power of different power unit output terminals at the next time step. The intelligent control unit is used to adjust the output power of the output terminals of different power units in the next time step according to the output power of the output terminals of different power units in the next time step.

8. The parallel fault-tolerant converter cross-modal cooperative control system according to claim 7, characterized in that: A human-machine interaction platform is provided, which allows managers to view historical power data in the storage unit, calculate the loss risk value when different power units experience equipment failure, and the probability of equipment failure of power units under different loss risk values.

Images