A protection system for improving the fault tolerance of a rectifier

Abstract

The present invention discloses a protection system for improving the fault tolerance rate of a rectifier, which relates to the field of electrical engineering. The system includes: a basic configuration information reading module for reading the basic configuration information of a target rectifier; an incremental learning module for performing incremental learning on a PID self-regulation model; a fault-tolerant redundant topology configuration module for configuring a fault-tolerant redundant topology; a standby trigger mechanism generation module for generating a standby trigger mechanism; a scenario working condition data receiving module for monitoring and receiving the scenario working condition data of the target rectifier; and a fault-tolerant protection module for identifying the scenario working condition data, performing deviation fault tolerance protection on the target rectifier in combination with the PID self-regulation model, and performing fault fault tolerance protection on the target rectifier in combination with the standby trigger mechanism. It solves the technical problem of low fault tolerance rate existing in the existing rectifier fault tolerance protection, and achieves the technical effect of improving the fault tolerance rate of the rectifier, thereby ensuring the stable operation of the power system.

Description

Technical Field

[0001] This application relates to the field of electrical engineering, and particularly to a protection system for improving the fault tolerance rate of a rectifier. Background Art

[0002] In a power system, a rectifier is a key component, and its stability and fault tolerance ability are crucial for ensuring the normal operation of the entire system. When the fault tolerance rate of the rectifier is low, in case of a fault or abnormal situation, it may lead to a decline in system performance, a reduction in efficiency, or even more serious faults. Existing methods usually handle the fault problems of the rectifier through simple fault detection and isolation mechanisms. When a fault is detected, some basic fault tolerance measures are taken, such as switching backup components or adjusting control parameters. However, these methods often only focus on a single type of fault, lacking in-depth understanding and prediction ability of the rectifier operating state, resulting in the inability to quickly take effective fault tolerance measures when a fault occurs.

[0003] In the current related technologies, due to the lack of a comprehensive and intelligent fault tolerance protection strategy, there is a technical problem of low fault tolerance rate of the rectifier. Summary of the Invention

[0004] This application provides a protection system for improving the fault tolerance rate of a rectifier. By using technical means such as reading basic configuration information, mining abnormal fault records, training a PID self-regulation model, configuring a fault tolerance redundant topology, and generating a backup trigger mechanism, the overall optimization and improvement of the rectifier performance are achieved, and the technical effect of improving the fault tolerance rate of the rectifier and thus ensuring the stable operation of the power system is achieved.

[0005] This application provides a protection system for improving the fault tolerance rate of a rectifier, including:

[0006] A basic configuration information reading module, which is used to read the basic configuration information of the target rectifier, and the basic configuration information includes circuit configuration, component configuration, and control system configuration;

[0007] An incremental learning module, which is used to mine the abnormal fault records of the rectifier, train a PID self-regulation model, and perform incremental learning on the PID self-regulation model based on the basic configuration information. The PID self-regulation model includes a distortion repair branch and a deviation correction branch;

[0008] A fault tolerance redundant topology configuration module, which is used to traverse the basic configuration information and configure a fault tolerance redundant topology, and the fault tolerance redundant topology includes a circuit fault tolerance topology and a system redundant topology;

[0009] Standby trigger mechanism generation module, which is used to generate a standby trigger mechanism based on the fault-tolerant redundant topology and configure the target rectifier;

[0010] Scenario working condition data receiving module, which is used to monitor and receive the scenario working condition data of the target rectifier. The scenario working condition data includes electrical data, operating data and environmental data, and the electrical data includes AC-DC conversion data;

[0011] Fault-tolerant protection module, which is used to identify the scenario working condition data, perform deviation fault-tolerant protection on the target rectifier in combination with the PID self-regulation model, and perform fault fault-tolerant protection on the target rectifier in combination with the standby trigger mechanism.

[0012] In a possible implementation manner, the incremental learning module includes:

[0013] Self-fault-tolerant characteristic acquisition unit, which is used to interact with the self-fault-tolerant characteristics of the target rectifier. The self-fault-tolerant characteristics are determined based on the factory configuration;

[0014] Differential analysis unit, which is used to traverse the rectifier abnormal fault records, perform differential analysis in combination with the self-fault-tolerant characteristics, and measure the pre-management fault-tolerant characteristics. The pre-management fault-tolerant characteristics include the mapped fault types and fault tolerance degrees. Among them, the pre-management fault-tolerant characteristics are used for the training constraint of the PID self-regulation model and the structural configuration constraint of the fault-tolerant redundant topology.

[0015] In a possible implementation manner, the basic configuration information reading module includes:

[0016] Front-end control configuration unit, which is used to perform front-end control configuration of the control system on the PID self-regulation model and the standby trigger mechanism.

[0017] In a possible implementation manner, the fault-tolerant protection module includes:

[0018] Error-causing feature determination unit, which is used to identify the scenario working condition data and determine the error-causing features. The error-causing features include error-causing factors and factor feature values;

[0019] Pre-adjustment type determination unit, which is used to traverse the error-causing features, perform abnormal type positioning and clustering, and determine the pre-adjustment type. The pre-adjustment type is at least one of the deviation type and the fault type, and the deviation type includes at least one of the distortion type and the deviation type;

[0020] Fault-tolerant protection unit, which is used to perform fault-tolerant protection on the target rectifier based on the pre-adjustment type.

[0021] In a possible implementation manner, the pre-adjustment type determination unit includes:

[0022] Pre-adjustment branch activation subunit, which is used to activate the pre-adjustment branch in the PID self-regulation model based on the pre-adjustment type, where the pre-adjustment type is mapped to the pre-adjustment branch;

[0023] Calibration control data determination subunit, which is used to adjust the pre-control data of the target rectifier based on the pre-adjustment branch and determine the calibration control data.

[0024] In a possible implementation manner, the pre-adjustment type determination unit includes:

[0025] Operation stability acquisition subunit, which is used to interact with the operation stability of the target rectifier, and the operation stability includes power supply stability and self-stability;

[0026] Control fluctuation range determination subunit, which is used to determine the control fluctuation range based on the operation stability;

[0027] External expansion adjustment subunit, which is used to perform external expansion adjustment on the calibration control data based on the control fluctuation range.

[0028] In a possible implementation manner, the pre-adjustment type determination unit includes:

[0029] Identification traversal subunit, which is used to identify the pre-adjustment type, identify the pre-adjustment range of the target rectifier, and traverse the fault-tolerant redundant topology to locate the access topology partition, where the access topology partition includes at least one;

[0030] Cross-connection and disconnection subunit, which is used to perform cross-connection and disconnection operations on the pre-adjustment range and the access topology partition based on the standby trigger mechanism, where the cross-connection and disconnection standard is the disconnection operation of the pre-adjustment range of the target rectifier and the connection operation of the access topology partition;

[0031] Operation management subunit, which is used to perform operation management based on the pre-control data of the target rectifier after performing the cross-connection and disconnection operations.

[0032] In a possible implementation manner, the fault-tolerant protection module includes:

[0033] A cycle fault tolerance rate determination unit, which is used to read the fault tolerance protection records within a predetermined cycle of the target rectifier and determine the cycle fault tolerance rate;

[0034] An effective fault tolerance sample mining unit, which is used to determine whether the cycle fault tolerance rate meets the fault tolerance threshold. If it does not meet, traverse the fault tolerance protection records to mine effective fault tolerance samples;

[0035] An incremental learning unit, which is used to perform incremental learning on the PID self-regulation model and the standby trigger mechanism based on the effective fault tolerance samples;

[0036] Among them, the effective fault tolerance sample mining unit includes:

[0037] A mining criterion determination subunit, which is used to use the fault occurrence frequency as the first mining criterion and the fault spread range and fault level as the second mining criterion;

[0038] An effective fault tolerance sample determination subunit, which is used to combine the first mining criterion and the second mining criterion, perform integration and preset ratio interception of the fault tolerance protection records in the positive sequence, and determine the effective fault tolerance samples.

[0039] A protection system for improving the fault tolerance rate of a rectifier proposed by this application reads the basic configuration information of the target rectifier through a basic configuration information reading module. The basic configuration information includes circuit configuration, component configuration, and control system configuration. The rectifier abnormal fault records are mined through an incremental learning module, and the PID self-regulation model is trained. Incremental learning is performed on the PID self-regulation model based on the basic configuration information. The PID self-regulation model includes a distortion repair branch and a deviation correction branch. The basic configuration information is traversed through a fault tolerance redundant topology configuration module to configure a fault tolerance redundant topology. The fault tolerance redundant topology includes a circuit fault tolerance topology and a system redundant topology. A standby trigger mechanism based on the fault tolerance redundant topology is generated through a standby trigger mechanism generation module to configure the target rectifier. The scenario working condition data of the target rectifier is monitored and received through a scenario working condition data receiving module. The scenario working condition data includes electrical data, operation data, and environmental data. The electrical data includes AC-DC conversion data. The scenario working condition data is identified through a fault tolerance protection module, and deviation fault tolerance protection of the target rectifier is performed in combination with the PID self-regulation model, and fault tolerance protection of the target rectifier is performed in combination with the standby trigger mechanism, achieving the technical effect of improving the fault tolerance rate of the rectifier and thus ensuring the stable operation of the power system. Description of the Drawings

[0040] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of this application. It should be understood that the operations described above or below do not necessarily need to be performed precisely in sequence. On the contrary, as needed, various steps can be performed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or more steps can be removed from these processes.

[0041] Figure 1 FIG. is a schematic structural diagram of a protection system for improving the fault tolerance rate of a rectifier provided by an embodiment of the present application;

[0042] Figure 2 FIG. is a schematic structural diagram of a fault tolerance protection module of a protection system for improving the fault tolerance rate of a rectifier provided by an embodiment of the present application.

[0043] Explanation of reference numerals: basic configuration information reading module 10, incremental learning module 20, fault tolerance redundant topology configuration module 30, standby trigger mechanism generation module 40, scenario working condition data receiving module 50, fault tolerance protection module 60. Detailed implementation manners

[0044] The above description is only an overview of the technical solutions of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically gives the detailed implementation manners of this application.

[0045] In order to make the purpose, technical solutions and advantages of this application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

[0046] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0047] An embodiment of this application provides a protection system for improving the fault tolerance rate of a rectifier, as Figure 1 shown, the system includes:

[0048] A basic configuration information reading module 10, which is used to read the basic configuration information of the target rectifier. The basic configuration information includes circuit configuration, component configuration, and control system configuration. Specifically, the basic configuration information reading module 10 communicates with the target rectifier to obtain its basic configuration information, including circuit configuration, component configuration, and control system configuration. Among them, the circuit configuration refers to the circuit topology, connection method, and key circuit parameters of the target rectifier, etc.; the component configuration covers the models, specifications, and performance parameters of various components used inside the target rectifier; the control system configuration includes the control strategy, algorithm, and parameter settings of the target rectifier, etc. After reading the basic configuration information, the basic configuration information reading module 10 performs parsing and processing, converts the original basic configuration information into a format recognizable by the system, extracts key features and parameters, and uses this parsed information as input and passes it to the subsequent incremental learning module 20 and fault-tolerant redundant topology configuration module 30.

[0049] In a possible implementation, the basic configuration information reading module 10 includes: a front-end control configuration unit, which is used to perform front-end control configuration of the PID self-regulation model and the backup trigger mechanism for the control system. Specifically, the front-end control configuration unit reads the basic configuration information from the target rectifier, including circuit configuration, component configuration, and control system configuration. Then, it analyzes the read control system configuration to determine the structure, function, and parameter settings of the control system. Based on the analyzed control system configuration, it configures the PID self-regulation model, including setting the parameters of the PID model, defining the input and output interfaces, and configuring the control strategy, to ensure that the PID self-regulation model can perform precise regulation according to the requirements of the actual control system. In addition to the PID self-regulation model, the front-end control configuration unit also configures the backup trigger mechanism, including setting the trigger conditions of the backup trigger mechanism (such as main control system failure, performance degradation, etc.), and defining the startup sequence and logic of the backup control system, to ensure that when the main control system fails, the backup trigger mechanism can take over the work quickly and accurately. After completing the configuration of the PID self-regulation model and the backup trigger mechanism, the front-end control configuration unit generates corresponding control configuration parameters, which are used to guide the subsequent operation and fault handling of the control system. This implementation method can, by setting the front-end control configuration unit, perform targeted configuration of the PID self-regulation model and the backup trigger mechanism according to the basic configuration information, making the PID self-regulation model and the backup trigger mechanism more adaptable to the characteristics and operating environment of the target rectifier, thereby achieving the technical effects of improving the reliability, stability, and performance of the control system of the target rectifier.

[0050] Incremental learning module 20, the incremental learning module 20 is used to mine abnormal fault records of rectifiers, train PID self-regulation model, and incrementally learn the PID self-regulation model based on the basic configuration information. The PID self-regulation model includes a distortion repair branch and a deviation correction branch. Specifically, the incremental learning module 20 extracts abnormal fault records of rectifiers from historical data. The abnormal fault records of rectifiers include various fault conditions that occur during the operation of the rectifier, such as voltage fluctuations, current anomalies, etc. By analyzing the abnormal fault records of rectifiers, the characteristics, causes and effects of the faults are extracted. The PID self-regulation model is trained using the abnormal fault records of rectifiers, wherein the PID self-regulation model is an algorithm model for controlling the operation of the rectifier. By performing proportional, integral and differential processing on the error signal, a control signal is output to adjust the operating state of the rectifier. During the training process, the parameters and structure of the PID self-regulation model are continuously optimized so that it can more accurately identify faults and take corresponding control measures. The incremental learning module 20 also performs incremental learning on the PID self-regulating model according to the basic configuration information of the target rectifier, wherein the basic configuration information includes the circuit design, component parameters, control system settings and other information of the target rectifier. By analyzing these information, the characteristics and behaviors of the target rectifier are determined, and then the PID self-regulating model is optimized in a targeted manner. The incremental learning process is a process of continuous iteration and optimization, which can make the PID self-regulating model gradually adapt to the characteristics of the target rectifier and improve the accuracy and stability of control. The PID self-regulating model includes a distortion repair branch and a deviation correction branch, wherein the distortion repair branch is used to repair the distortion phenomenon in the system, such as waveform distortion, phase shift, etc. When these distortions are detected, the distortion repair branch quickly takes corresponding measures to repair them to ensure the normal operation of the system; the deviation correction branch is used to correct the deviation in the system, such as voltage deviation, current deviation, etc. By continuously adjusting the control signal, the deviation correction branch can make the output of the system gradually approach the expected value to achieve precise control.

[0051] In a possible implementation, the incremental learning module 20 includes: a self-fault tolerance characteristic acquisition unit configured to interact with the self-fault tolerance characteristics of the target rectifier, where the self-fault tolerance characteristics are determined based on the factory configuration. Specifically, the self-fault tolerance characteristic acquisition unit analyzes and extracts the self-fault tolerance characteristics of the target rectifier from the factory configuration (configuration information set at the time of factory production, including hardware parameters, software settings, etc.). The self-fault tolerance characteristics are some characteristics that the target rectifier itself has and can automatically handle faults or errors to a certain extent during the design and manufacturing process. A differential analysis unit configured to traverse the rectifier abnormal fault records and perform differential analysis in combination with the self-fault tolerance characteristics to measure pre-management fault tolerance characteristics, where the pre-management fault tolerance characteristics include the mapped fault tolerance types and degrees of fault tolerance. Among them, the pre-management fault tolerance characteristics are used for training constraints of the PID self-regulation model and structural configuration constraints of the fault tolerance redundant topology. Specifically, the differential analysis unit traverses all stored rectifier abnormal fault records. For each rectifier abnormal fault record, it performs differential analysis in combination with the information obtained from the self-fault tolerance characteristic acquisition unit. By comparing and analyzing the differences between the rectifier abnormal fault records and the self-fault tolerance characteristic data, it finds out the fault situations that exceed the range of self-fault tolerance capabilities. Based on the results of the differential analysis, it measures the pre-management fault tolerance characteristics. The pre-management fault tolerance characteristics are some potential fault tolerance characteristics that need to be pre-managed obtained through differential analysis, including the mapped fault tolerance types (such as hardware redundancy, software fault tolerance, etc.) and degrees of fault tolerance (i.e., the degree of faults that this fault tolerance measure can tolerate). The measured pre-management fault tolerance characteristics are used as training constraints to guide the training process of the PID self-regulation model to ensure that the model can make appropriate responses when facing actual faults; according to the pre-management fault tolerance characteristics, it provides guidance for the configuration of the fault tolerance redundant topology to ensure that the topology structure can meet the required fault tolerance capabilities. This implementation method realizes a more refined management and optimization of the training process of the PID self-regulation model by setting the self-fault tolerance characteristic acquisition unit and the differential analysis unit, achieving the technical effects of improving the adaptability and accuracy of the PID self-regulation model, enabling it to better handle various complex fault situations, and improving the overall fault tolerance ability of the target rectifier.

[0052] Fault-tolerant redundant topology configuration module 30 is used to traverse the basic configuration information and configure a fault-tolerant redundant topology, which includes a circuit fault-tolerant topology and a system redundant topology. Among them, the fault-tolerant redundant topology is a topology structure that improves the fault tolerance of the system by configuring redundant components or systems. When the main component or system fails, the redundant part can quickly take over the work to ensure the continuity and stability of the system; the circuit fault-tolerant topology is a redundant configuration designed at the circuit level, focusing on the redundancy of key components in the circuit and the fault isolation mechanism; the system redundant topology is a redundant configuration designed at the system level, including a backup control system, a backup rectifier, etc., focusing on the redundancy and fault recovery ability of the entire system. Specifically, the fault-tolerant redundant topology configuration module 30 traverses the basic configuration information and analyzes information such as the circuit configuration, component configuration, and control system configuration of the target rectifier. According to the analyzed circuit configuration, identify the key circuit parts in the target rectifier, such as the power input circuit, power conversion circuit, output filter circuit, etc. For vulnerable components in the key circuit, such as power switching transistors, capacitors, inductors, etc., configure redundant components to ensure that when a component fails, it can automatically switch to the standby component to keep the circuit working normally. Design a fault detection mechanism to monitor the working state of the key circuit in real time. Once a fault is detected, quickly isolate the faulty circuit and activate the redundant circuit. At the system level, design a backup control system or a backup rectifier to ensure that when the main system fails, the backup system can quickly take over the work. Establish a communication and synchronization mechanism between the main and backup systems to ensure data consistency and seamless switching of the system. Develop a detailed fault recovery strategy, including steps such as fault identification, isolation, and recovery, to ensure that the normal operation of the system can be quickly restored after a fault occurs. Store the configured fault-tolerant redundant topology information in the internal database and output it to the standby trigger mechanism generation module 40 and other relevant modules for subsequent use.

[0053] Standby trigger mechanism generation module 40, the standby trigger mechanism generation module 40 is used to generate a standby trigger mechanism based on the fault-tolerant redundant topology and configure the target rectifier. Among them, the standby trigger mechanism refers to a mechanism that automatically starts the standby system or takes corresponding measures when a failure occurs in the main system or key parts. By based on preset trigger conditions and strategies, it ensures that it can quickly and accurately take over the work when needed. Specifically, the standby trigger mechanism generation module 40 receives the fault-tolerant redundant topology information of the fault-tolerant redundant topology configuration module 30, analyzes the fault-tolerant redundant topology information, identifies the switching points, trigger conditions, control logic, etc. between the main system and the standby system. Through the analysis, it determines the connection relationship between the structure and components and the working principle of the redundant mechanism. Based on the analyzed topology structure and system requirements, it determines the specific trigger conditions of the standby trigger mechanism, such as the performance degradation of the main system, the failure of key components, and specific parameters exceeding the range. Further generate a standby trigger strategy based on the specific trigger conditions, including defining the startup sequence of the standby system, the control logic during the switching process, and the working mode after the standby system takes over. After generating the standby trigger strategy, it outputs the configuration information to the target rectifier for configuration, including modifying the control software of the target rectifier, adjusting the circuit connection, setting parameters, etc., to ensure that the standby trigger mechanism can take effect in actual operation.

[0054] Scenario working condition data receiving module 50, the scenario working condition data receiving module 50 is used to monitor and receive the scenario working condition data of the target rectifier. The scenario working condition data includes electrical data, operation data, and environmental data, and the electrical data includes AC-DC conversion data. Specifically, the scenario working condition data receiving module 50 performs an initialization operation, establishes a communication connection with the target rectifier, and monitors the scenario working condition data of the target rectifier in real time. The scenario working condition data refers to the real-time data of the target rectifier under different working scenarios and conditions, including electrical data, operation data, and environmental data, which reflect the operation status and performance of the target rectifier. Among them, the electrical data is data related to electricity, such as voltage, current, power, etc. The electrical data includes AC-DC conversion data, and the AC-DC conversion data is the data involved in the process of the target rectifier converting AC power to DC power, including conversion efficiency, input and output voltage and current, etc., which are used to evaluate the performance of the target rectifier and optimize the power conversion process; the operation data is data describing the operation status of the target rectifier, such as switch status, temperature, fan speed, etc., which reflect the real-time operation of the target rectifier; the environmental data is data reflecting the environmental conditions where the target rectifier is located, such as temperature, humidity, air pressure, etc.

[0055] Fault tolerance protection module 60, which is used to identify the scenario working condition data, perform deviation fault tolerance protection on the target rectifier in combination with the PID self-regulation model, and perform fault fault tolerance protection on the target rectifier in combination with the standby trigger mechanism. Among them, the deviation fault tolerance protection is a protection measure that when the performance of the target rectifier deviates, adjusts the control parameters or takes other measures to correct the deviation to ensure the normal operation of the rectifier; the fault fault tolerance protection is a protection measure that when the target rectifier fails, switches to the standby system or takes other fault recovery measures to ensure the continuity and stability of the system. Specifically, the fault tolerance protection module 60 receives the scenario working condition data from the scenario working condition data receiving module 50, identifies and analyzes the scenario working condition data through specific algorithms or models, and extracts the key information related to the performance of the target rectifier. In combination with the PID self-regulation model, the performance of the target rectifier is evaluated in real time. If it is detected that the performance of the target rectifier deviates (such as unstable output current or voltage), the deviation fault tolerance protection mechanism is started, including adjusting the parameters of the PID controller (such as proportional, integral, and derivative terms), etc., to optimize the performance of the target rectifier and make the output of the target rectifier closer to the expected value. When it is identified that the target rectifier fails (such as component damage, circuit short circuit, etc.), the fault fault tolerance protection mechanism is triggered, the severity and scope of the fault are evaluated, and it is determined whether it is necessary to switch to the standby system. If switching is required, the standby trigger mechanism is activated, and according to the preset trigger conditions and strategies, the standby system is started and takes over the work of the target rectifier. The embodiments of the present application adopt technical means such as reading basic configuration information, mining abnormal fault records, training the PID self-regulation model, configuring fault tolerance redundant topology, and generating a standby trigger mechanism, etc., to achieve a comprehensive optimization and improvement of the rectifier performance, and achieve the technical effect of improving the fault tolerance rate of the rectifier and thus ensuring the stable operation of the power system.

[0056] In a possible implementation manner, the fault tolerance protection module 60 includes: an error-causing feature determination unit, which is configured to identify the scenario condition data and determine the error-causing features, where the error-causing features include error-causing factors and factor feature values. Among them, the error-causing features refer to the factors that cause deviations or failures in the target rectifier and their corresponding feature values; the error-causing factors are the specific reasons that may cause abnormal performance of the target rectifier; the factor feature values are the numerical values or indicators that describe the specific manifestations or degrees of the error-causing factors. Specifically, the error-causing feature determination unit receives the scenario condition data sent by the scenario condition data receiving module 50, performs preprocessing operations such as cleaning and format conversion on the scenario condition data to ensure the accuracy and consistency of the data, and analyzes the preprocessed data through a specific algorithm or model to identify the factors that cause deviations or failures in the target rectifier, such as abnormal temperature, voltage fluctuations, etc. For each identified error-causing factor, its corresponding feature value is extracted, such as the value of the abnormal temperature, the amplitude of the voltage fluctuation, etc. A pre-adjustment type determination unit, which is configured to traverse the error-causing features, perform abnormal type positioning and clustering, and determine the pre-adjustment type, where the pre-adjustment type is at least one of a deviation type and a fault type, and the deviation type includes at least one of a distortion type and a deviation type. Specifically, traverse the error-causing features extracted by the error-causing feature determination unit, use a classification algorithm or model to perform abnormal type positioning on each error-causing factor, determine which deviation type or fault type it belongs to, cluster the located abnormal types, and classify similar abnormal types into one category. According to the clustering result, determine the pre-adjustment type currently required by the target rectifier, whether it is a deviation type (distortion type, deviation type) or a fault type, or both a deviation type and a fault type. A fault tolerance protection unit, which is configured to perform fault tolerance protection on the target rectifier based on the pre-adjustment type. Specifically, according to the pre-adjustment type determined by the pre-adjustment type determination unit, select the corresponding pre-adjustment strategy or measure, execute the pre-adjustment strategy, and perform deviation correction or fault recovery on the target rectifier, including adjusting the parameters of the PID self-regulation model, starting a standby trigger mechanism, etc. This implementation manner realizes precise and efficient fault tolerance protection for the target rectifier by setting an error-causing feature determination unit, a pre-adjustment type determination unit, and a fault tolerance protection unit, achieving the technical effect of improving the reliability and stability of the target rectifier control system.

[0057] In a possible implementation, the pre-adjustment type determination unit includes: a pre-adjustment branch activation subunit, and the pre-adjustment branch activation unit is configured to activate the pre-adjustment branch in the PID self-regulation model based on the pre-adjustment type, where the pre-adjustment type is mapped to the pre-adjustment branch. Here, the pre-adjustment branch is a control branch in the PID self-regulation model for handling specific types of deviations or faults, and each pre-adjustment branch has different control logics and parameter settings. Specifically, the pre-adjustment branch activation subunit receives the pre-adjustment type output by the pre-adjustment type determination unit, and consults the pre-stored mapping relation table. The mapping relation table is a table or data structure that stores the corresponding relationship between the pre-adjustment type and the pre-adjustment branch, and is used to quickly match and activate the corresponding pre-adjustment branch. By consulting the mapping relation table, the corresponding pre-adjustment branch in the PID self-regulation model is activated. A calibration control data determination subunit, and the calibration control data determination unit is configured to adjust the pre-control data of the target rectifier based on the pre-adjustment branch to determine the calibration control data. Here, the pre-control data is the data or parameters based on which the target rectifier is initially controlled during the fault tolerance protection process. Specifically, the calibration control data determination subunit obtains the relevant parameters and control logic of the activated pre-adjustment branch, and adjusts the pre-control data of the target rectifier according to the parameters and control logic of the pre-adjustment branch, including modifying set values such as voltage and current, or adjusting the parameters of the control algorithm, and outputs the adjusted pre-control data as the calibration control data to guide the actual operation of the target rectifier. This implementation enables the pre-adjustment type determination unit to more precisely execute the fault tolerance protection strategy according to the pre-adjustment type by setting the pre-adjustment branch activation subunit and the calibration control data determination subunit, achieving precise control of the performance of the target rectifier and reaching the technical effect of improving the accuracy of fault tolerance protection.

[0058] In a possible implementation, the pre-adjustment type determination unit includes: a running stability acquisition subunit, which is configured to interact with the running stability of the target rectifier, and the running stability includes power supply stability and self-stability. Specifically, the running stability acquisition subunit interacts with the target rectifier through a communication interface or a data bus, obtains the current running stability data, and analyzes the obtained running stability data, including two aspects: power supply stability and self-stability. Among them, the power supply stability reflects the stability and reliability of the power supply system; the self-stability describes the running state and performance stability of the target rectifier itself. After the analysis is completed, the running stability acquisition subunit outputs the result of the running stability to the control fluctuation range determination subunit. A control fluctuation range determination subunit, which is configured to determine a control fluctuation range based on the running stability. Specifically, the control fluctuation range determination subunit receives the running stability data output by the running stability acquisition subunit, calculates the control fluctuation range according to the specific value of the running stability and a preset fluctuation range calculation rule, and the control fluctuation range reflects the maximum allowable fluctuation range of the control parameters of the target rectifier under the current running stability. After the calculation is completed, the result of the control fluctuation range is output to the external expansion adjustment subunit. An external expansion adjustment subunit, which is configured to perform external expansion adjustment on the calibration control data based on the control fluctuation range. Specifically, the external expansion adjustment subunit receives the control fluctuation range data output by the control fluctuation range determination subunit, and performs external expansion adjustment on the calibration control data based on the range of the control fluctuation range, that is, expands or shrinks the value range of the control parameters to adapt to the running stability state of the current target rectifier. After the adjustment is completed, the adjusted calibration control data is output to the fault tolerance protection unit to guide the actual operation of the target rectifier. This implementation method finely adjusts the calibration control data by setting the running stability acquisition subunit, the control fluctuation range determination subunit, and the external expansion adjustment subunit, enabling the pre-adjustment type determination unit to more accurately determine and adjust the calibration control data, ensuring that the control parameters neither exceed the allowable range nor can adapt to the running state of the current target rectifier, achieving the technical effects of improving the accuracy and effectiveness of fault tolerance protection.

[0059] In a possible implementation, the pre-adjustment type determination unit includes: an identification traversal subunit, which is used to identify the pre-adjustment type, identify the pre-adjustment range of the target rectifier, and traverse the fault-tolerant redundant topology to locate the access topology partition, where the access topology partition includes at least one. Specifically, the identification traversal subunit identifies the pre-adjustment type of the target rectifier according to a preset algorithm or rule, and further determines the pre-adjustment range of the target rectifier based on the identified pre-adjustment type, that is, the specific range that needs to be adjusted or optimized, such as specific parameters, control logic, or functional modules, etc., traverses the fault-tolerant redundant topology, and locates the access topology partition. The access topology partition refers to the area in the fault-tolerant redundant topology for accessing and switching different functional modules or paths, constituting one or more alternative operating paths or strategies. A cross-connection and disconnection subunit, which is used to perform a cross-connection and disconnection operation on the pre-adjustment range and the access topology partition based on the standby trigger mechanism, where the cross-connection and disconnection criterion is the disconnection operation of the pre-adjustment range of the target rectifier and the connection operation of the access topology partition. Specifically, the cross-connection and disconnection subunit detects whether the standby trigger mechanism is triggered. The standby trigger mechanism is triggered by fault detection, performance degradation, or other abnormal conditions. When the standby trigger mechanism is activated, according to the preset rules, a cross-connection and disconnection operation is performed on the pre-adjustment range and the access topology partition. The cross-connection and disconnection operation refers to the operation of disconnecting the current connection and connecting to an alternative path or strategy to achieve the fault-tolerant or adjustment function, including disconnecting the current connection within the pre-adjustment range of the target rectifier and connecting to the corresponding access topology partition. An operation management subunit, which is used to perform operation management based on the pre-control data of the target rectifier after performing the cross-connection and disconnection operation. Specifically, the operation management subunit obtains the operation data of the target rectifier after the cross-connection and disconnection operation, including parameters, status information, etc., and adjusts the operation strategy of the target rectifier based on the obtained operation data, including parameter optimization, control logic modification, or functional module switching, etc., continuously monitors the operation state of the target rectifier, and adjusts the operation strategy as needed. This implementation method ensures that the target rectifier can switch to an alternative path or strategy in case of a fault or when adjustment is needed by setting an identification traversal subunit, a cross-connection and disconnection subunit, and an operation management subunit, and ensures that the target rectifier can maintain a stable operation state and performance during the fault-tolerant or adjustment process, achieving the technical effect of improving the fault-tolerant ability and stability of the system.

[0060] Such as Figure 2As shown, in a possible implementation, the fault tolerance protection module 60 includes: a periodic fault tolerance rate determination unit, which is used to read the fault tolerance protection records within a predetermined period of the target rectifier and determine the periodic fault tolerance rate. Specifically, the periodic fault tolerance rate determination unit reads the fault tolerance protection records of the target rectifier within a predetermined period. The fault tolerance protection records contain all fault tolerance events and their related information that occurred within the predetermined period. Based on the read fault tolerance protection records, the periodic fault tolerance rate is calculated. The periodic fault tolerance rate refers to the ratio of the number of fault tolerance events that occurred within a predetermined period to the total number of events, reflecting the fault tolerance performance of the target rectifier within a predetermined period. An effective fault tolerance sample mining unit, which is used to determine whether the periodic fault tolerance rate meets the fault tolerance threshold. If not, it traverses the fault tolerance protection records to mine effective fault tolerance samples. Specifically, the effective fault tolerance sample mining unit determines whether the periodic fault tolerance rate meets a preset fault tolerance threshold. Among them, the fault tolerance threshold is a standard value set according to system performance and stability requirements. If the periodic fault tolerance rate does not meet the fault tolerance threshold, it traverses the fault tolerance protection records to mine effective fault tolerance samples. Among them, the effective fault tolerance samples refer to the fault tolerance event records that are valuable for improving the system's fault tolerance ability. Among them, the effective fault tolerance sample mining unit includes: a mining standard determination subunit, which is used to use the fault occurrence frequency as the first mining standard and the fault impact range and fault level as the second mining standard. Specifically, the mining standard determination subunit is used to determine a series of rules and criteria for mining effective fault tolerance samples. Among them, the fault occurrence frequency is used as the first mining standard, and the fault occurrence frequency refers to the frequency of fault tolerance events. Frequently occurring fault tolerance events have higher research value. At the same time, the fault impact range and fault level are used as the second mining standard. The fault impact range and fault level refer to the degree and severity of the impact of the fault tolerance event on the system, and are used to evaluate the importance and priority of the fault tolerance event. An effective fault tolerance sample determination subunit, which is used to combine the first mining standard and the second mining standard, and perform integration and preset ratio truncation of the fault tolerance protection records in a positive sequence to determine the effective fault tolerance samples. Specifically, the effective fault tolerance sample determination subunit evaluates each record in the fault tolerance protection records according to the mining standards, including comprehensive evaluation using the first mining standard and the second mining standard. For each record, a corresponding evaluation value is given, and this evaluation value reflects the importance and value of the record in improving the system's fault tolerance ability. After all the fault tolerance protection records are given evaluation values, the fault tolerance protection records are sorted according to these evaluation values to form a positive sequence arrangement. The higher the evaluation value of the fault tolerance protection record, the higher its ranking. On the basis of the positive sequence arrangement, the fault tolerance protection records are truncated according to a preset ratio. The preset ratio is determined according to system requirements, the goal of improving fault tolerance ability, and the balance of sample quantity.By intercepting, the most representative part is selected from the sorted fault-tolerant protection records as valid fault-tolerant samples. These valid fault-tolerant samples not only have a moderate quantity, but also have high representativeness and research value. An incremental learning unit, which is used to perform incremental learning on the PID self-regulation model and the standby trigger mechanism based on the valid fault-tolerant samples. Specifically, based on the valid fault-tolerant samples, the incremental learning unit performs incremental learning on the PID self-regulation model and the standby trigger mechanism, updates and optimizes the model, and improves the adaptability and accuracy of the model. This implementation method forms a complete fault-tolerant protection mechanism by setting a periodic fault-tolerant rate determination unit, a valid fault-tolerant sample mining unit, and an incremental learning unit, achieving the technical effect of continuously improving the fault-tolerant ability and stability of the system, ensuring the normal operation and performance optimization of the target rectifier.

[0061] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The included individual units and modules are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0062] The above specific implementation manners do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be executed in a different order from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In certain embodiments, multi-task processing and parallel processing are also possible or may be advantageous.

Claims

1. A protection system for improving the fault tolerance of a rectifier, characterized in that, The system includes: A basic configuration information reading module, which is used to read the basic configuration information of the target rectifier. The basic configuration information includes circuit configuration, component configuration, and control system configuration; An incremental learning module, which is used to mine the abnormal fault records of the rectifier, train a PID self-regulation model, and perform incremental learning on the PID self-regulation model based on the basic configuration information. The PID self-regulation model includes a distortion repair branch and a deviation correction branch; A fault-tolerant redundant topology configuration module, which is used to traverse the basic configuration information and configure a fault-tolerant redundant topology. The fault-tolerant redundant topology includes a circuit fault-tolerant topology and a system redundant topology; A standby trigger mechanism generation module, which is used to generate a standby trigger mechanism based on the fault-tolerant redundant topology and configure the target rectifier; A scenario working condition data receiving module, which is used to monitor and receive the scenario working condition data of the target rectifier. The scenario working condition data includes electrical data, operation data, and environmental data. The electrical data includes AC-DC conversion data, and the operation data is data describing the operation state of the target rectifier, including switch state, temperature, and fan speed; A fault-tolerant protection module, which is used to identify the scenario working condition data, perform deviation fault-tolerant protection on the target rectifier in combination with the PID self-regulation model, and perform fault fault-tolerant protection on the target rectifier in combination with the standby trigger mechanism; The fault-tolerant protection module includes: A periodic fault-tolerant rate determination unit, which is used to read the fault-tolerant protection records within a predetermined period of the target rectifier and determine the periodic fault-tolerant rate; An effective fault-tolerant sample mining unit, which is used to determine whether the periodic fault-tolerant rate meets the fault-tolerant threshold. If not, traverse the fault-tolerant protection records to mine effective fault-tolerant samples; An incremental learning unit, which is used to perform incremental learning on the PID self-regulation model and the standby trigger mechanism based on the effective fault-tolerant samples; Among them, the effective fault-tolerant sample mining unit includes: A mining standard determination subunit, which is used to use the fault frequency as the first mining standard and the fault-affected range and fault level as the second mining standard; An effective fault-tolerant sample determination subunit, which is used to combine the first mining standard and the second mining standard, perform integration and preset ratio interception on the fault-tolerant protection records in the positive sequence, and determine the effective fault-tolerant samples. The positive sequence is a positive sequence arrangement formed by sorting the fault-tolerant protection records according to the evaluation value. The fault-tolerant protection records with higher evaluation values are sorted more forward.

2. The protection system for improving the fault tolerance of a rectifier according to claim 1, characterized in that The incremental learning module includes: An autologous fault-tolerant characteristic acquisition unit, which is used to acquire the autologous fault-tolerant characteristics of the target rectifier. The autologous fault-tolerant characteristics are determined based on the factory configuration; A differential analysis unit, which is used to traverse the abnormal fault records of the rectifier, perform differential analysis in combination with the self-fault tolerance characteristics, and measure the pre-management fault tolerance characteristics, where the pre-management fault tolerance characteristics include the mapped fault tolerance types and degrees of fault tolerance. Among them, the pre-management fault tolerance characteristics are used for the training constraint of the PID self-regulation model and the structural configuration constraint of the fault tolerance redundancy topology.

3. The protection system for improving the fault tolerance rate of a rectifier according to claim 1, characterized in that The basic configuration information reading module includes: A front-end control configuration unit, which is used to perform front-end control configuration of the control system for the PID self-regulation model and the standby trigger mechanism.

4. A protection system for improving the fault tolerance rate of a rectifier, characterized in that, The fault tolerance protection module includes: An error-causing feature determination unit, which is used to identify the scenario working condition data and determine the error-causing features, where the error-causing features include error-causing factors and factor feature values; A pre-adjustment type determination unit, which is used to traverse the error-causing features, perform abnormal type positioning and clustering, and determine the pre-adjustment type, where the pre-adjustment type is at least one of the deviation type and the fault type, and the deviation type includes at least one of the distortion category and the deviation category; A fault tolerance protection unit, which is used to perform fault tolerance protection of the target rectifier based on the pre-adjustment type.

5. The protection system for improving the fault tolerance of a rectifier according to claim 4, characterized in that, The pre-adjustment type determination unit includes: A pre-adjustment branch activation sub-unit, which is used to activate the pre-adjustment branch in the PID self-regulation model based on the pre-adjustment type, where the pre-adjustment type is mapped and corresponding to the pre-adjustment branch; A calibration control data determination sub-unit, which is used to adjust the pre-control data of the target rectifier based on the pre-adjustment branch and determine the calibration control data.

6. The protection system for improving the fault tolerance of a rectifier according to claim 5, characterized in that, The pre-adjustment type determination unit includes: An operation stability acquisition sub-unit, which is used to acquire the operation stability of the target rectifier, where the operation stability includes power supply stability and self-stability; A control fluctuation range determination sub-unit, which is used to determine the control fluctuation range based on the operation stability; An external expansion adjustment sub-unit, which is used to perform external expansion adjustment on the calibration control data based on the control fluctuation range.

7. The protection system for improving the fault tolerance rate of a rectifier according to claim 4, characterized in that, The pre-adjustment type determination unit includes: An identification traversal sub-unit, which is used to identify the pre-adjustment type, identify the pre-adjustment range of the target rectifier, and traverse the fault tolerance redundancy topology to locate the access topology partition, where the access topology partition includes at least one; A cross-connection and disconnection sub-unit, which is used to perform cross-connection and disconnection operations on the pre-adjustment range and the access topology partition based on the standby trigger mechanism, where the cross-connection and disconnection standard is the disconnection operation of the pre-adjustment range of the target rectifier and the connection operation of the access topology partition; An operation management sub-unit, which is used to perform operation management based on the pre-control data of the target rectifier after performing the cross-connection and disconnection operation.

Images