Frequency converter hot redundancy control method and system, computer equipment and storage medium

Abstract

The invention relates to a frequency converter hot redundancy control method and system, computer equipment and a storage medium, and the method comprises the steps: monitoring the real-time operation states of all frequency converters in a frequency converter system in real time, and carrying out the fault prediction according to an artificial intelligence algorithm and the real-time operation states; dynamically adjusting the load conditions of all the frequency converters according to the corresponding fault prediction results; under the condition that any frequency converter breaks down, the fault frequency converter is automatically isolated, and load redistribution is carried out on the frequency converter which does not break down through a load balancing algorithm; obtaining the fault type of the fault frequency converter, and executing a local repair mechanism to recover the function of the fault frequency converter when the fault type is self-repairable; and after the fault frequency converter is successfully repaired, executing a self-adaptive stable switching-in algorithm, and gradually switching the repaired frequency converter into the system again. The method has the effect of improving the recovery efficiency of the frequency converter system after the fault occurs.

Description

Technical Field

[0001] The present application relates to the technical field of inverter thermal redundancy processing, and in particular to an inverter thermal redundancy control method, system, computer equipment and storage medium. Background Art

[0002] At present, frequency converters are widely used in industrial automation systems. Their main function is to adjust the speed and load of the motor to improve the operating efficiency of the system. However, with the expansion of the scale and complexity of industrial automation systems, the reliability and fault tolerance of the frequency converter system have gradually become key factors affecting the stability of the entire system.

[0003] Existing inverter control systems usually rely on manual monitoring and maintenance. When an inverter in the system fails, it is often impossible to detect and handle it in time, resulting in a decrease in the operating efficiency of the entire system and may even cause the system to shut down. In addition, the existing inverter control system has a low degree of automation in load distribution and fault isolation, and the fault recovery speed is slow, which makes it difficult to meet the needs of modern industry for efficient and stable operation.

[0004] The above-mentioned prior art solutions have the following defects: when a fault occurs in the existing inverter system, the recovery efficiency is low, so there is room for improvement. Summary of the invention

[0005] In order to improve the recovery efficiency of a frequency converter system after a fault occurs, the present application provides a frequency converter thermal redundancy control method, system, computer equipment and storage medium.

[0006] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A frequency converter thermal redundancy control system, the frequency converter thermal redundancy control system comprising: Monitor the real-time operating status of all inverters in the inverter system in real time, perform fault prediction based on the artificial intelligence algorithm and the real-time operating status, and dynamically adjust the load conditions of all the inverters according to the corresponding fault prediction results; In the event of a fault in any of the frequency converters, the faulty frequency converter is automatically isolated, and the load is redistributed to the frequency converters that are not faulty by means of a load balancing algorithm; Obtaining the fault type of the faulty frequency converter, and executing a local repair mechanism to restore the function of the faulty frequency converter if the fault type is self-repairable; After the faulty frequency converter is repaired successfully, an adaptive smooth switching algorithm is executed to gradually switch the repaired frequency converter back into the system.

[0007] By adopting the above technical solution, by real-time monitoring of the real-time operating status of all inverters in the inverter system and performing fault prediction based on the artificial intelligence algorithm and the real-time operating status, potential faults can be discovered at an early stage, and corresponding maintenance measures can be taken in advance to avoid the risk of sudden downtime caused by inverter failure, thereby improving the stability and safety of the system; by dynamically adjusting the load conditions of all inverters according to the corresponding fault prediction results, it is possible to effectively avoid individual inverters being in a high-load state for a long time, optimize system resource allocation, reduce damage to the inverter due to overload, extend the service life of the equipment, and improve the overall operating efficiency of the system; by In the event of a frequency converter failure, the faulty frequency converter is automatically isolated, and the load is redistributed to the frequency converter that has not failed through a load balancing algorithm. The system's operating status can be quickly adjusted to ensure that the local impact of the failure does not spread to the entire system, ensuring the continuous operation of the system, thereby improving the system's fault tolerance and operational reliability; by obtaining the fault type of the faulty frequency converter, when the fault type is self-repairable, a local repair mechanism is executed to restore the function of the faulty frequency converter, which can reduce dependence on maintenance personnel, shorten the system's recovery time, improve the system's self-repair capability and maintenance efficiency, and further ensure the system's high availability and stability.

[0008] In a preferred example, the present application may be further configured as follows: the fault prediction according to the artificial intelligence algorithm and the real-time operating status specifically includes: Acquire historical operation data of each inverter, and compare and analyze the historical operation data with the real-time operation status according to a machine learning algorithm; When the degree of conformity between the real-time operating status and the historical abnormal data in the historical operating data exceeds a preset threshold, it is determined that an abnormality occurs in the frequency converter corresponding to the real-time operating status.

[0009] By adopting the above technical solution, by obtaining the historical operation data of each inverter and comparing and analyzing the historical operation data with the real-time operation status according to the machine learning algorithm, it is possible to analyze the historical trend and real-time status based on big data and improve the accuracy of fault prediction; by comparing the historical abnormal data with the real-time data, when the compliance exceeds the preset threshold, the inverter is judged to be abnormal, and effective warning can be given before the fault occurs, and maintenance operations can be arranged in advance, thereby reducing the unplanned downtime of the system and further improving the reliability and maintainability of the system.

[0010] In a preferred example, the present application may be further configured as follows: dynamically adjusting the load conditions of all the inverters according to the corresponding fault prediction results specifically includes: According to the fault prediction result, determining the load bearing capacity of the abnormal frequency converter corresponding to the fault prediction result, and reducing the load proportion of the abnormal frequency converter according to the load bearing capacity; The remaining load-bearing capacity of other frequency converters except the abnormal frequency converter is obtained, and the load is adjusted according to the remaining load-bearing capacity.

[0011] By adopting the above technical solution, by determining the load bearing capacity of the abnormal inverter according to the fault prediction result, and reducing the load proportion of the inverter according to the load bearing capacity, it is possible to effectively avoid the abnormal inverter from being in an overloaded working state, prevent it from further damage, and extend its service life; by obtaining the remaining load-bearing capacity of other inverters and adjusting the load distribution based on the load-bearing capacity, it is possible to ensure that other inverters in the system bear the load reasonably, optimize the load distribution of the system, thereby improving the operating efficiency and load balance of the entire system, and avoiding system crashes caused by single point failures.

[0012] In a preferred example, the present application may be further configured as follows: obtaining the fault type of the faulty inverter, and executing a local repair mechanism to restore the function of the faulty inverter when the fault type is self-repairable, specifically including: Obtaining an operation log of the faulty frequency converter, and determining the fault type of the faulty frequency converter according to the operation log; Query and compare the fault type with a preset fault library to determine whether the fault type is a self-repairable fault; In the case where the fault type is self-repairable, a corresponding local repair mechanism is selected according to the fault type to perform self-repair.

[0013] By adopting the above technical solution, by obtaining the operation log of the faulty inverter and determining the fault type based on the operation log, the cause of the fault can be analyzed quickly and accurately, reducing the troubleshooting time; by querying and comparing the fault type with the preset fault library, efficient automatic diagnosis can be achieved, so as to quickly determine whether the fault type is self-repairable; when it is determined that the fault can be self-repaired, it can be self-repaired through an automated local repair mechanism, thereby reducing manual intervention, improving the system's self-repair capability, shortening the fault repair time, and improving the maintainability and reliability of the system.

[0014] In a preferred example, the present application may be further configured as follows: the querying and comparing the fault type with a preset fault library to determine whether the fault type is a self-repairable fault further includes: In the case where the fault type is a software fault, determining that the fault type corresponding to the software fault is a self-repairable fault; In the case where the fault type is a hardware fault, it is determined that the fault type corresponding to the hardware fault is a fault that cannot be repaired by itself, and a hardware fault message is generated.

[0015] By adopting the above technical solution, by querying and comparing the fault type with the preset fault library, the fault type can be quickly identified and it can be determined whether it can be repaired by itself; when the fault type is a software fault, it is automatically determined to be a self-repairable fault, and self-repair at the software level can be quickly performed to ensure that the system can resume normal operation in a short time; and when the fault type is a hardware fault, a hardware fault message is automatically generated, and the operation and maintenance personnel can be notified in time for manual intervention, thereby avoiding the continued impact of the hardware fault on the system and improving the operating efficiency and safety of the system.

[0016] In a preferred example, the present application can be further configured as follows: the execution of the adaptive smooth cut-in algorithm to gradually cut the repaired inverter back into the system specifically includes: Acquiring inverter configuration information in the inverter system, and synchronizing the repaired inverter with the inverter configuration information; The repaired inverter is switched into the inverter system, and the load carrying ratio of the repaired inverter is gradually increased through a phased load recovery mechanism until the load distribution of the repaired inverter is balanced with that of other inverters.

[0017] By adopting the above technical solution and executing an adaptive smooth cut-in algorithm, the repaired inverter is gradually cut back into the system, which can ensure that the repaired inverter resumes participating in load distribution in a smooth manner and avoid the impact of sudden changes in system load on the system; by obtaining the configuration information of the inverter system and synchronizing the repaired inverter with the system information, the consistency of the system state can be ensured and operational problems caused by configuration mismatch can be avoided; through a phased load recovery mechanism, the load proportion of the repaired inverter is gradually increased, which can ensure a smooth transition of the system load until its load distribution is balanced with that of other inverters, thereby further improving the stability and reliability of the system.

[0018] The second object of the invention is achieved by the following technical solutions: A frequency converter thermal redundancy control system, the frequency converter thermal redundancy control system comprising: A status monitoring module is used to monitor the real-time operating status of all inverters in the inverter system in real time, and to perform fault prediction based on the artificial intelligence algorithm and the real-time operating status, and to dynamically adjust the load conditions of all the inverters according to the corresponding fault prediction results; A fault isolation module is used to automatically isolate the faulty frequency converter when any of the frequency converters fails, and to redistribute the load to the frequency converters that are not faulty by means of a load balancing algorithm; A local repair module, used for obtaining the fault type of the faulty frequency converter, and executing a local repair mechanism to restore the function of the faulty frequency converter when the fault type is self-repairable; The smooth switching module is used to execute an adaptive smooth switching algorithm after the faulty frequency converter is successfully repaired, and gradually switch the repaired frequency converter back into the system.

[0019] By adopting the above technical solution, by real-time monitoring of the real-time operating status of all inverters in the inverter system and performing fault prediction based on the artificial intelligence algorithm and the real-time operating status, potential faults can be discovered at an early stage, and corresponding maintenance measures can be taken in advance to avoid the risk of sudden downtime caused by inverter failure, thereby improving the stability and safety of the system; by dynamically adjusting the load conditions of all inverters according to the corresponding fault prediction results, it is possible to effectively avoid individual inverters being in a high-load state for a long time, optimize system resource allocation, reduce damage to the inverter due to overload, extend the service life of the equipment, and improve the overall operating efficiency of the system; by In the event of a frequency converter failure, the faulty frequency converter is automatically isolated, and the load is redistributed to the frequency converter that has not failed through a load balancing algorithm. The system's operating status can be quickly adjusted to ensure that the local impact of the failure does not spread to the entire system, ensuring the continuous operation of the system, thereby improving the system's fault tolerance and operational reliability; by obtaining the fault type of the faulty frequency converter, when the fault type is self-repairable, a local repair mechanism is executed to restore the function of the faulty frequency converter, which can reduce dependence on maintenance personnel, shorten the system's recovery time, improve the system's self-repair capability and maintenance efficiency, and further ensure the system's high availability and stability.

[0020] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned inverter thermal redundancy control method when executing the computer program.

[0021] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned inverter thermal redundancy control method are implemented.

[0022] In summary, this application includes the following beneficial technical effects: 1. By real-time monitoring of the real-time operating status of all inverters in the inverter system and predicting faults based on the artificial intelligence algorithm and the real-time operating status, potential faults can be discovered at an early stage, and corresponding maintenance measures can be taken in advance to avoid the risk of sudden downtime caused by inverter faults, thereby improving the stability and safety of the system; by dynamically adjusting the load conditions of all inverters according to the corresponding fault prediction results, it is possible to effectively avoid individual inverters being in a high-load state for a long time, optimize system resource allocation, reduce damage caused by overload of the inverter, extend the service life of the equipment, and improve the overall operating efficiency of the system; by automatically isolating the faulty inverter when any inverter fails, and redistributing the load of the inverter that has not failed through the load balancing algorithm, the operating status of the system can be quickly adjusted to ensure that the local impact of the fault will not spread to the entire system, and the continuous operation of the system is guaranteed, thereby improving the fault tolerance and operating reliability of the system; by obtaining the fault type of the faulty inverter, and executing a local repair mechanism to restore the function of the faulty inverter when the fault type is self-repairable, it can reduce the dependence on maintenance personnel, shorten the recovery time of the system, improve the self-repair ability and maintenance efficiency of the system, and further ensure the high availability and stability of the system; 2. By acquiring the historical operation data of each inverter and comparing and analyzing the historical operation data with the real-time operation status according to the machine learning algorithm, it is possible to analyze the historical trend and real-time status based on big data to improve the accuracy of fault prediction; by comparing the historical abnormal data with the real-time data, when the compliance exceeds the preset threshold, the inverter is judged to be abnormal, and effective early warning can be carried out before the fault occurs, and maintenance operations can be arranged in advance, thereby reducing the unplanned downtime of the system and further improving the reliability and maintainability of the system; 3. By determining the load bearing capacity of the abnormal inverter based on the fault prediction results and reducing the load ratio of the inverter according to the load bearing capacity, the abnormal inverter can be effectively avoided from being in an overloaded working state, prevented from further damage, and extended its service life; by obtaining the remaining load capacity of other inverters and adjusting the load distribution based on the load capacity, it can ensure that other inverters in the system bear the load reasonably, optimize the load distribution of the system, thereby improving the operating efficiency and load balance of the entire system, and avoiding system crashes caused by single point failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of a method for controlling thermal redundancy of a frequency converter in one embodiment of the present application; Figure 2 is a flowchart for implementing step S10 in the inverter thermal redundancy control method in one embodiment of the present application; Figure 3is another implementation flow chart of step S10 in the inverter thermal redundancy control method in one embodiment of the present application; Figure 4 is a flowchart for implementing step S30 in the inverter thermal redundancy control method in one embodiment of the present application; Figure 5 is a flowchart for implementing step S32 in the inverter thermal redundancy control method in one embodiment of the present application; Figure 6 is a flowchart for implementing step S40 in the inverter thermal redundancy control method in one embodiment of the present application; Figure 7 This is a principle block diagram of a frequency converter thermal redundancy control system in one embodiment of the present application; Figure 8 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application is further described in detail below in conjunction with the accompanying drawings.

[0025] In one embodiment, if Figure 1 As shown, the present application discloses a method for controlling thermal redundancy of a frequency converter, which specifically includes the following steps: S10: Monitor the real-time operating status of all inverters in the inverter system, and perform fault prediction based on the artificial intelligence algorithm and the real-time operating status, and dynamically adjust the load conditions of all inverters according to the corresponding fault prediction results.

[0026] Specifically, the real-time operating status of each inverter in the inverter system is collected through sensors and internal monitoring modules, including parameters such as voltage, current, temperature and operating time. Then, the artificial intelligence algorithm is based on these real-time data and combined with the multi-layer neural network model built inside the system to dynamically calculate the operating load distribution and potential failure risks in the current system. For example, by comparing the operating status of each inverter with the normal status in the historical operating data, deviation analysis can be performed to infer possible abnormal situations.

[0027] S20: In the event of a fault in any inverter, the faulty inverter is automatically isolated, and the load is redistributed to the inverters that are not faulty through a load balancing algorithm.

[0028] Specifically, when a frequency converter fails, the connection between the failed frequency converter and other frequency converters is automatically disconnected to prevent it from causing further impact on the entire system. At the same time, the load balancing algorithm is used to redistribute and adjust the load of all frequency converters in the frequency converter system according to the load distribution status in the current system, the remaining carrying capacity of each non-faulty frequency converter and the overall load demand of the system, ensuring that other non-faulty frequency converters can smoothly take over the load of the failed frequency converter.

[0029] S30: Obtain the fault type of the faulty inverter, and if the fault type is self-repairable, execute a local repair mechanism to restore the function of the faulty inverter.

[0030] Specifically, by reading the internal operation log of the faulty inverter and the stored real-time data, the changes in the key data parameters of the inverter before and after the fault, such as current surge, temperature abnormality, etc., are analyzed and matched with the operation log to determine whether the fault is a hardware or software fault. For self-repairable fault types, the system will automatically call the local repair mechanism, including software restart, reset of the faulty module, and debugging of system configuration, to maximize the restoration of the function of the faulty inverter and enable it to regain its operating capability.

[0031] S40: After the faulty inverter is repaired successfully, an adaptive smooth cut-in algorithm is executed to gradually reintegrate the repaired inverter into the system.

[0032] Specifically, the repaired inverter is first synchronized with the system through the system's adaptive smooth cut-in algorithm to obtain the configuration parameters in the current inverter system, including voltage, frequency, phase and other information, and compare and correct them one by one with the parameters of the repaired inverter to ensure that all parameters are consistent when cutting in to avoid system instability. Subsequently, through the staged load recovery mechanism, the repaired inverter is put back into system operation in a manner of gradually increasing small loads. In each stage, the system will monitor the inverter according to its carrying capacity and gradually increase its load proportion until its load distribution is consistent with other inverters in the system to ensure a smooth and disturbance-free cutting process.

[0033] In one embodiment, if Figure 2 As shown, in step S10, fault prediction is performed based on the artificial intelligence algorithm and the real-time operating status, specifically including: S11: Obtain historical operation data of each inverter, and compare and analyze the historical operation data with the real-time operation status according to a machine learning algorithm.

[0034] Specifically, the historical operating data of each inverter in the system is continuously collected and recorded, including load conditions, temperature fluctuations, current and voltage changes, fault records and other information. Through machine learning algorithms such as neural network models or decision tree models, typical fault modes and their association with the operating status of the inverter can be mined from these data, and then the real-time operating status data can be compared with these fault modes in the historical data item by item.

[0035] S12: When the degree of conformity between the real-time operating state and the historical abnormal data in the historical operating data exceeds a preset threshold, it is determined that an abnormality occurs in the frequency converter corresponding to the real-time operating state.

[0036] Specifically, by establishing a compliance calculation model, which performs analysis based on the similarity between real-time operating status and historical operating data, when the compliance between real-time data and historical abnormal data exceeds the preset fault prediction threshold, such as 80%, the system will issue an abnormal warning. The compliance calculation is based on the weighted combination of multi-dimensional data, such as the fluctuation amplitude of voltage changes, the rapid rise in temperature, and the load change trend during operation. All dimensions are calculated with set weights to ensure that the detected anomalies are highly matched with historical patterns, thereby improving the accuracy of fault prediction.

[0037] In one embodiment, if Figure 3 As shown, in step S10, the load conditions of all inverters are dynamically adjusted according to the corresponding fault prediction results, specifically including: S13: According to the fault prediction result, determine the load bearing capacity of the abnormal inverter corresponding to the fault prediction result, and reduce the load proportion of the abnormal inverter according to the load bearing capacity.

[0038] Specifically, according to the results generated by the fault prediction algorithm, the load bearing capacity of the abnormal inverter is dynamically adjusted. First, the current bearing capacity of the abnormal inverter is calculated, that is, the stability of its operating state and the remaining bearing capacity. According to this calculation result, the system will set a load reduction ratio to ensure that the load of the abnormal inverter does not exceed its bearing range and reduce the risk of overload. The load reduction operation is automatically performed by the central control unit, which gradually reduces the load by adjusting the operating parameters of the abnormal inverter until it meets its bearing capacity.

[0039] S14: Obtain the remaining load capacity of other inverters except the abnormal inverter, and adjust the load according to the remaining load capacity.

[0040] Specifically, by real-time monitoring the status of each normally operating inverter and evaluating the remaining load capacity of each inverter, the system determines the load-bearing capacity of each inverter by analyzing multiple operating parameters such as current, voltage, temperature, etc. and combining the current load conditions. Based on the calculation results of the remaining load capacity, the load reduced by the abnormal inverter is redistributed to other inverters to ensure that the load distribution of the entire system remains balanced and to avoid excessive load on a certain inverter affecting the overall operating stability of the system.

[0041] In one embodiment, if Figure 4 As shown, in step S30, the fault type of the faulty inverter is obtained. If the fault type is self-repairable, a local repair mechanism is executed to restore the function of the faulty inverter, specifically including: S31: Obtain an operation log of the faulty inverter, and determine a fault type of the faulty inverter according to the operation log.

[0042] Specifically, the operation log of the faulty inverter is extracted, including voltage fluctuations, load pressure, temperature changes during operation, and specific operating time points before and after the failure occurs. By analyzing these log data, the factors that may cause the failure are identified, such as overload caused by excessive voltage or protective shutdown caused by excessive internal temperature. After the analysis is completed, the type of fault, such as hardware problem or software problem, will be further determined based on the key data in the log so that corresponding repair measures can be taken.

[0043] S32: Query and compare the fault type with a preset fault library to determine whether the fault type is a self-repairable fault.

[0044] Specifically, the type of faulty inverter is compared with the fault mode in the fault library through a search algorithm, and similar fault records are matched from the fault library to analyze whether the fault can be solved by itself through a local repair mechanism. The preset fault library includes the modes, causes and repair strategies of various known faults.

[0045] S33: When the fault type is self-repairable, select a corresponding local repair mechanism according to the fault type to perform self-repair.

[0046] Specifically, if it is determined that the fault type can be repaired by itself, the local repair mechanism will be automatically executed. For example, in the case of a program execution failure, the system will restart the software module or perform a configuration repair operation. If there is a voltage or load problem, the system will automatically adjust the control parameters or reset the protection mechanism to reduce the inverter load and resume normal operation.

[0047] In one embodiment, if Figure 5 As shown, in step S32, the fault type is queried and compared with a preset fault library to determine whether the fault type is a self-repairable fault, and further includes: S321: When the fault type is a software fault, determine that the fault type corresponding to the software fault is a self-repairable fault.

[0048] Specifically, the type of software failure is determined based on the data in the fault log, such as system response delay, data overflow, module abnormality, etc. These problems can usually be fixed by restarting the system, clearing the cache, or reloading the configuration file. Such failures are determined to be self-repairable failures.

[0049] S322: When the fault type is a hardware fault, determine that the fault type corresponding to the hardware fault is a fault that cannot be repaired by itself, and generate a hardware fault message.

[0050] Specifically, when the fault log contains indication data of hardware abnormalities, such as current overload, component temperature being too high, or poor contact, the system will identify it as a hardware failure. Since hardware problems usually require physical repair or replacement, the system will not be able to resolve them through local repair mechanisms. Therefore, a hardware failure message will be generated and sent to the operation and maintenance system to alert maintenance personnel to conduct further inspection and repair.

[0051] In one embodiment, if Figure 6 As shown, in step S40, the adaptive smooth switching algorithm is executed to gradually switch the repaired inverter back into the system, which specifically includes: S41: Acquire the inverter configuration information in the inverter system, and synchronize the repaired inverter with the inverter configuration information.

[0052] Specifically, the repaired inverter needs to maintain consistent configuration parameters with all inverters in the system. The system will automatically obtain the inverter configuration information of the current system, including the inverter's voltage, power, frequency, phase and other parameters, and synchronize the parameters corresponding to the repaired inverter with these configuration information to ensure that the inverter is consistent with the system before switching on, avoiding operational risks caused by parameter mismatch.

[0053] S42: Cut the repaired inverter into the inverter system, and gradually increase the load carrying ratio of the repaired inverter through a phased load recovery mechanism until the load distribution of the repaired inverter is balanced with that of other inverters.

[0054] Specifically, after the repaired inverter is synchronized, the system will restore its load in stages according to the current load conditions. First, a small amount of load will be allocated to the repaired inverter, and its operating status will be monitored to ensure that no abnormalities occur under low load conditions. The load will then be gradually increased. A comprehensive inspection will be carried out after each load increase to ensure that the repaired inverter can stably carry the new load. When the inverter reaches the same load ratio as other inverters, the system load distribution returns to normal and the cut-in process ends.

[0055] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0056] In one embodiment, a frequency converter thermal redundancy control system is provided, and the frequency converter thermal redundancy control system corresponds one-to-one to the frequency converter thermal redundancy control method in the above embodiment. Figure 7 As shown, the inverter hot redundancy control system includes a status monitoring module, a fault isolation module, a local repair module, and a smooth cut-in module. The detailed description of each functional module is as follows: The status monitoring module is used to monitor the real-time operating status of all inverters in the inverter system, and to predict faults based on the artificial intelligence algorithm and the real-time operating status, and to dynamically adjust the load conditions of all inverters based on the corresponding fault prediction results; Fault isolation module, used to automatically isolate the faulty inverter when any inverter fails, and redistribute the load to the inverters that are not faulty through load balancing algorithm; A local repair module is used to obtain the fault type of the faulty inverter, and if the fault type is self-repairable, execute a local repair mechanism to restore the function of the faulty inverter; The smooth cut-in module is used to execute an adaptive smooth cut-in algorithm after the faulty inverter is successfully repaired, and gradually cut the repaired inverter back into the system.

[0057] Optionally, the status monitoring module specifically includes: The historical data acquisition submodule is used to obtain the historical operation data of each inverter and compare and analyze the historical operation data with the real-time operation status according to the machine learning algorithm; The abnormality determination submodule is used to determine that the frequency converter corresponding to the real-time operating state is abnormal when the conformity between the real-time operating state and the historical abnormal data in the historical operating data exceeds a preset threshold.

[0058] The load adjustment submodule is used to determine the load bearing capacity of the abnormal inverter corresponding to the fault prediction result according to the fault prediction result, and reduce the load proportion of the abnormal inverter according to the load bearing capacity; The remaining capacity adjustment submodule is used to obtain the remaining carrying capacity of other inverters except the abnormal inverter, and perform load adjustment according to the remaining carrying capacity.

[0059] Optionally, the local repair module specifically includes: The log analysis submodule is used to obtain the operation log of the faulty inverter and determine the fault type of the faulty inverter according to the operation log; The fault comparison submodule is used to query and compare the fault type with the preset fault library to determine whether the fault type is a self-repairable fault; The repair mechanism submodule is used to select a corresponding local repair mechanism according to the fault type to perform self-repair when the fault type is self-repairable.

[0060] Optionally, the fault comparison submodule further includes: A software fault determination unit, used for determining, when the fault type is a software fault, that the fault type corresponding to the software fault is a self-repairable fault; The hardware fault determination unit is used to determine, when the fault type is a hardware fault, that the fault type corresponding to the hardware fault is a fault that cannot be repaired by itself, and to generate a hardware fault message.

[0061] Optional, smooth cut-in module specifically includes: A configuration information synchronization submodule is used to obtain the inverter configuration information in the inverter system and synchronize the repaired inverter with the inverter configuration information; The load recovery submodule is used to cut the repaired inverter into the inverter system and gradually increase the load carrying ratio of the repaired inverter through a phased load recovery mechanism until its load distribution is balanced with that of other inverters.

[0062] For the specific definition of the inverter thermal redundancy control system, please refer to the definition of the inverter thermal redundancy control method above, which will not be repeated here. Each module in the above inverter thermal redundancy control system can be implemented in whole or in part through a combination of software and hardware machines. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0063] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for hot redundancy control of a frequency converter is implemented.

[0064] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Monitor the real-time operating status of all inverters in the inverter system in real time, predict faults based on artificial intelligence algorithms and real-time operating status, and dynamically adjust the load conditions of all inverters based on the corresponding fault prediction results; In the event of a fault in any inverter, the faulty inverter is automatically isolated, and the load is redistributed to the inverters that are not faulty through a load balancing algorithm; Obtaining the fault type of the faulty inverter, and executing a local repair mechanism to restore the function of the faulty inverter if the fault type is self-repairable; After the faulty inverter is repaired successfully, an adaptive smooth cut-in algorithm is executed to gradually reintegrate the repaired inverter into the system.

[0065] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Monitor the real-time operating status of all inverters in the inverter system in real time, predict faults based on artificial intelligence algorithms and real-time operating status, and dynamically adjust the load conditions of all inverters based on the corresponding fault prediction results; In the event of a fault in any inverter, the faulty inverter is automatically isolated, and the load is redistributed to the inverters that are not faulty through a load balancing algorithm; Obtaining the fault type of the faulty inverter, and executing a local repair mechanism to restore the function of the faulty inverter if the fault type is self-repairable; After the faulty inverter is repaired successfully, an adaptive smooth cut-in algorithm is executed to gradually reintegrate the repaired inverter into the system.

[0066] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0067] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0068] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for controlling thermal redundancy of a frequency converter, characterized in that: The inverter thermal redundancy control method comprises: Monitor the real-time operating status of all inverters in the inverter system in real time, perform fault prediction based on the artificial intelligence algorithm and the real-time operating status, and dynamically adjust the load conditions of all the inverters according to the corresponding fault prediction results; In the event of a fault in any of the frequency converters, the faulty frequency converter is automatically isolated, and the load is redistributed to the frequency converters that are not faulty by means of a load balancing algorithm; Obtaining the fault type of the faulty frequency converter, and executing a local repair mechanism to restore the function of the faulty frequency converter if the fault type is self-repairable; After the faulty frequency converter is repaired successfully, an adaptive smooth switching algorithm is executed to gradually switch the repaired frequency converter back into the system.

2. The inverter thermal redundancy control method according to claim 1, characterized in that: The fault prediction according to the artificial intelligence algorithm and the real-time operating status specifically includes: Acquire historical operation data of each inverter, and compare and analyze the historical operation data with the real-time operation status according to a machine learning algorithm; When the degree of conformity between the real-time operating status and the historical abnormal data in the historical operating data exceeds a preset threshold, it is determined that an abnormality occurs in the frequency converter corresponding to the real-time operating status.

3. The inverter thermal redundancy control method according to claim 1, characterized in that: The dynamically adjusting the load conditions of all the inverters according to the corresponding fault prediction results specifically includes: According to the fault prediction result, determining the load bearing capacity of the abnormal frequency converter corresponding to the fault prediction result, and reducing the load proportion of the abnormal frequency converter according to the load bearing capacity; The remaining load-bearing capacity of other frequency converters except the abnormal frequency converter is obtained, and the load is adjusted according to the remaining load-bearing capacity.

4. The inverter thermal redundancy control method according to claim 1, characterized in that: The obtaining of the fault type of the faulty frequency converter and, if the fault type is self-repairable, executing a local repair mechanism to restore the function of the faulty frequency converter specifically includes: Obtaining an operation log of the faulty frequency converter, and determining the fault type of the faulty frequency converter according to the operation log; Query and compare the fault type with a preset fault library to determine whether the fault type is a self-repairable fault; In the case where the fault type is self-repairable, a corresponding local repair mechanism is selected according to the fault type to perform self-repair.

5. The inverter thermal redundancy control method according to claim 1, characterized in that: The querying and comparing the fault type with a preset fault library to determine whether the fault type is a self-repairable fault further includes: In the case where the fault type is a software fault, determining that the fault type corresponding to the software fault is a self-repairable fault; In the case where the fault type is a hardware fault, it is determined that the fault type corresponding to the hardware fault is a fault that cannot be repaired by itself, and a hardware fault message is generated.

6. The inverter thermal redundancy control method according to claim 1, characterized in that: The method of executing the adaptive smooth switching algorithm to gradually switch the repaired inverter back into the system specifically includes: Acquiring inverter configuration information in the inverter system, and synchronizing the repaired inverter with the inverter configuration information; The repaired inverter is switched into the inverter system, and the load carrying ratio of the repaired inverter is gradually increased through a phased load recovery mechanism until the load distribution of the repaired inverter is balanced with that of other inverters.

7. A frequency converter thermal redundancy control system, characterized in that: The inverter thermal redundancy control system comprises: A status monitoring module is used to monitor the real-time operating status of all inverters in the inverter system in real time, and to perform fault prediction based on the artificial intelligence algorithm and the real-time operating status, and to dynamically adjust the load conditions of all the inverters according to the corresponding fault prediction results; A fault isolation module is used to automatically isolate the faulty frequency converter when any of the frequency converters fails, and to redistribute the load to the frequency converters that are not faulty by means of a load balancing algorithm; A local repair module, used for obtaining the fault type of the faulty frequency converter, and executing a local repair mechanism to restore the function of the faulty frequency converter when the fault type is self-repairable; The smooth switching module is used to execute an adaptive smooth switching algorithm after the faulty frequency converter is successfully repaired, and gradually switch the repaired frequency converter back into the system.

8. The inverter thermal redundancy control system according to claim 7, characterized in that: The state monitoring module specifically includes: A historical data acquisition submodule is used to acquire historical operation data of each inverter, and compare and analyze the historical operation data with the real-time operation status according to a machine learning algorithm; The abnormality determination submodule is used to determine that an abnormality occurs in the frequency converter corresponding to the real-time operating state when the degree of conformity between the real-time operating state and the historical abnormal data in the historical operating data exceeds a preset threshold.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the inverter hot redundancy control method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the inverter thermal redundancy control method according to any one of claims 1 to 6 are implemented.

Images