A self-diagnosis processing method and device for a direct current controller

Abstract

The application discloses a self-diagnosis processing method and device for a direct current controller, and belongs to the technical field of computers. In the case that a target direct current controller meets a target self-diagnosis condition, a corresponding target self-diagnosis parameter acquisition mode, a target self-diagnosis parameter processing mode and a target self-diagnosis parameter type set are determined. Based on the target self-diagnosis parameter acquisition mode, a plurality of first target self-diagnosis parameters of which the parameter type belongs to the target self-diagnosis parameter type set are acquired, so that the acquisition of basic self-diagnosis parameters is realized. The plurality of first target self-diagnosis parameters are processed by using the target self-diagnosis parameter processing mode, and a plurality of second target self-diagnosis parameters and a plurality of third target self-diagnosis parameters of different self-diagnosis dimensions are obtained. The target self-diagnosis result of the target direct current controller is determined based on the plurality of second target self-diagnosis parameters and the plurality of third target self-diagnosis parameters.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a self-diagnostic processing method and apparatus for a DC controller. Background Technology

[0002] As a core unit for new energy grid connection, electric vehicles, and intelligent manufacturing, the reliability of the controller of the DC power system directly affects the system safety.

[0003] Currently, self-diagnostic technologies for DC controllers mainly rely on single parameter threshold judgments, such as identifying faults by exceeding voltage or current limits. However, such methods are significantly less applicable to complex operating conditions, and their self-diagnostic accuracy is low.

[0004] Therefore, improving the accuracy of self-diagnosis of DC controllers is a hot research topic. Summary of the Invention

[0005] This application provides a self-diagnostic processing method and apparatus for DC controllers, which can improve the accuracy of self-diagnosis of DC controllers. The technical solution is as follows:

[0006] On the one hand, a self-diagnostic processing method for a DC controller is provided, the method comprising:

[0007] When the target DC controller of the target DC component meets the target self-diagnostic condition among multiple candidate self-diagnostic conditions, the target self-diagnostic parameter acquisition method and target self-diagnostic parameter processing method corresponding to the target self-diagnostic condition are determined, and the target self-diagnostic parameter type set corresponding to the target DC controller and the target self-diagnostic condition is determined. The target self-diagnostic condition includes target operating environment conditions, target controller conditions and target DC component conditions.

[0008] Based on the target self-diagnostic parameter acquisition method, multiple first target self-diagnostic parameters whose parameter types belong to the target self-diagnostic parameter type set are acquired. The multiple first target self-diagnostic parameters include multiple first self-diagnostic parameters and multiple second self-diagnostic parameters. The multiple first self-diagnostic parameters are self-diagnostic parameters related to the target DC component, and the multiple second self-diagnostic parameters are self-diagnostic parameters related to the target DC controller.

[0009] The target self-diagnostic parameter processing method is used to process the plurality of first target self-diagnostic parameters to obtain a plurality of second target self-diagnostic parameters and a plurality of third target self-diagnostic parameters of the target DC controller. The plurality of second target self-diagnostic parameters and the plurality of third target self-diagnostic parameters correspond to different self-diagnostic dimensions.

[0010] Based on the plurality of second target self-diagnostic parameters and the plurality of third target self-diagnostic parameters, the target self-diagnostic result of the target DC controller is determined, and the target self-diagnostic result is used to indicate whether the target DC controller has a fault.

[0011] On one hand, a self-diagnostic processing device for a DC controller is provided, the device comprising:

[0012] The determination module is used to determine the target self-diagnostic parameter acquisition method and target self-diagnostic parameter processing method corresponding to the target self-diagnostic condition when the target DC controller of the target DC component meets the target self-diagnostic condition among multiple candidate self-diagnostic conditions, and to determine the target self-diagnostic parameter type set corresponding to the target DC controller and the target self-diagnostic condition. The target self-diagnostic condition includes target operating environment conditions, target controller conditions and target DC component conditions.

[0013] The acquisition module is used to acquire multiple first target self-diagnostic parameters whose parameter types belong to the target self-diagnostic parameter type set based on the target self-diagnostic parameter acquisition method. The multiple first target self-diagnostic parameters include multiple first self-diagnostic parameters and multiple second self-diagnostic parameters. The multiple first self-diagnostic parameters are self-diagnostic parameters related to the target DC component, and the multiple second self-diagnostic parameters are self-diagnostic parameters related to the target DC controller.

[0014] The processing module is used to process the plurality of first target self-diagnostic parameters using the target self-diagnostic parameter processing method to obtain a plurality of second target self-diagnostic parameters and a plurality of third target self-diagnostic parameters of the target DC controller, wherein the plurality of second target self-diagnostic parameters and the plurality of third target self-diagnostic parameters correspond to different self-diagnostic dimensions;

[0015] The diagnostic module is used to determine the target self-diagnostic result of the target DC controller based on the plurality of second target self-diagnostic parameters and the plurality of third target self-diagnostic parameters. The target self-diagnostic result is used to indicate whether the target DC controller has a fault.

[0016] On one hand, a computer device is provided, the computer device including one or more processors and one or more memories, the one or more memories storing at least one computer program, the computer program being loaded and executed by the one or more processors to implement the self-diagnostic processing method for a DC controller.

[0017] On one hand, a computer-readable storage medium is provided, wherein at least one computer program is stored in the computer-readable storage medium, the computer program being loaded and executed by a processor to implement the self-diagnostic processing method for a DC controller.

[0018] On one hand, a computer program product or computer program is provided, which includes program code stored in a computer-readable storage medium. A processor of a computer device reads the program code from the computer-readable storage medium and executes the program code, causing the computer device to perform the self-diagnostic processing method for a DC controller described above.

[0019] The technical solution provided in this application determines the target self-diagnostic parameter acquisition method, target self-diagnostic parameter processing method, and target self-diagnostic parameter type set when the target DC controller meets the target self-diagnostic conditions. Based on the target self-diagnostic parameter acquisition method, multiple first target self-diagnostic parameters whose parameter types belong to the target self-diagnostic parameter type set are acquired, thereby realizing the acquisition of basic self-diagnostic parameters. The target self-diagnostic parameter processing method is used to process the multiple first target self-diagnostic parameters to obtain multiple second target self-diagnostic parameters and multiple third target self-diagnostic parameters with different self-diagnostic dimensions. Based on the multiple second target self-diagnostic parameters and multiple third target self-diagnostic parameters, the target self-diagnostic result of the target DC controller is determined. Compared with the self-diagnostic results obtained by the self-diagnostic methods in related technologies, the accuracy of the target self-diagnostic result is higher due to the combination of richer data and the adoption of appropriate data processing methods. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of the implementation environment of a self-diagnostic processing method for a DC controller provided in an embodiment of this application;

[0022] Figure 2 This is a flowchart of a self-diagnostic processing method for a DC controller provided in an embodiment of this application;

[0023] Figure 3 This is a flowchart of another self-diagnostic processing method for a DC controller provided in an embodiment of this application;

[0024] Figure 4 This is a schematic diagram of the structure of a self-diagnostic processing device for a DC controller provided in an embodiment of this application;

[0025] Figure 5This is a schematic diagram of the structure of a diagnostic device provided in an embodiment of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0027] In this application, the terms "first," "second," etc., are used to distinguish identical or similar items with essentially the same function. It should be understood that there is no logical or temporal dependency between "first," "second," and "nth," nor are there any restrictions on quantity or execution order.

[0028] DC controller: A DC controller is a device used to regulate, manage, and protect the transmission and conversion of DC power. Its core functions include stable voltage / current control, system status monitoring, and fault protection. It is widely used in power systems, industrial equipment, electric vehicles, and aerospace.

[0029] Self-diagnosis: Self-diagnosis is an intelligent function of equipment or system that uses built-in algorithms to monitor its own operating status in real time, identify abnormalities, and provide feedback results. It is mainly used to improve reliability and security.

[0030] Artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain better results.

[0031] Machine learning (ML) is a multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills, and reorganize existing knowledge sub-models to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to endow computers with intelligence; its applications span all areas of artificial intelligence.

[0032] Normalization: Mapping sequences of values ​​with different ranges to the interval (0, 1) to facilitate data processing. In some cases, normalized values ​​can be directly expressed as probabilities.

[0033] Embedded coding, mathematically speaking, represents a correspondence, that is, mapping data in space X to space Y using a function F. This function F is injective, and the mapping result preserves the structure. An injective function means that the mapped data uniquely corresponds to the original data, and preserving the structure means that the size relationship between the original and mapped data is the same. For example, if there are data X1 and X2 before mapping, after mapping we get Y1 corresponding to X1 and Y2 corresponding to X2. If the original data X1 > X2, then correspondingly, the mapped data Y1 > Y2. For words, this means mapping words to another space to facilitate subsequent machine learning and processing.

[0034] Attention weights represent the importance of a piece of data during training or prediction. Importance indicates the magnitude of the influence of input data on output data. Data with high importance corresponds to higher attention weights, while data with low importance corresponds to lower attention weights. The importance of data varies in different scenarios, and training the model to assign attention weights is essentially the process of determining data importance.

[0035] Figure 1 This is a schematic diagram illustrating the implementation environment of a self-diagnostic processing method for a DC controller provided in an embodiment of this application. See also... Figure 1 The implementation environment may include diagnostic device 110, target DC component 120 and target DC controller 140.

[0036] The diagnostic device 110 is connected to the target DC component 120 and the target DC controller 140 via a wired connection. Optionally, the diagnostic device 110 may be a smartphone, tablet, laptop, desktop computer, or dedicated handheld device, but is not limited to these. The diagnostic device 110 has an application installed and running that supports self-diagnostic processing for the DC controller.

[0037] The target DC component 120 is a DC working component, such as a DC motor, a battery, or a generator, etc., and this application embodiment does not limit it.

[0038] The target DC controller 140 is used to control the target DC component 120, and the target DC controller 140 is wired to the target DC component.

[0039] In related technologies, the self-diagnosis of the target DC controller can only be achieved through the self-diagnosis program built into the target DC controller. Due to computing power limitations, the self-diagnosis program is usually quite simple and cannot meet the needs of special scenarios.

[0040] By employing the technical solution provided in the embodiments of this application, and by using an external high-computing-power diagnostic device combined with a unique self-diagnosis method, accurate self-diagnosis of the target DC controller can be completed without replacing the target DC controller.

[0041] The self-diagnostic processing method for DC controllers provided in the embodiments of this application will be described below. Figure 2 This is a flowchart of a self-diagnostic processing method for a DC controller provided in an embodiment of this application. See also... Figure 2 Taking the diagnostic device as the executing entity as an example, the method includes the following steps.

[0042] 201. When the target DC controller of the target DC component meets the target self-diagnostic condition among multiple candidate self-diagnostic conditions, the diagnostic equipment determines the target self-diagnostic parameter acquisition method and target self-diagnostic parameter processing method corresponding to the target self-diagnostic condition, and determines the target DC controller and the target self-diagnostic parameter type set corresponding to the target self-diagnostic condition. The target self-diagnostic condition includes the target working environment condition, the target controller condition and the target DC component condition.

[0043] The target self-diagnostic condition is one of several candidate self-diagnostic conditions. The target DC controller meeting the target self-diagnostic condition indicates that the target DC controller needs to perform self-diagnosis. The target operating environment condition is related to the operating environment of the target DC controller. The target controller condition refers to the condition related to the target DC controller itself. The target DC component condition refers to the condition related to the target DC component. The reason for introducing the target DC component condition is that the target DC controller directly controls the target DC component, so the condition of the target DC component can, to some extent, reflect whether the target DC controller is abnormal. The target DC component is a DC device, such as a DC motor, battery, or generator. Under normal circumstances, the target DC controller can perform stable voltage / current control, system status monitoring, and fault protection for the target DC component. The target self-diagnostic parameter acquisition method is the same as the self-diagnostic parameter acquisition method used in this embodiment for self-diagnosing the target DC controller. The target self-diagnostic parameter processing method refers to the method of processing the acquired self-diagnostic parameters. In this embodiment, the target self-diagnostic parameter acquisition method and the target self-diagnostic parameter processing method are associated with the target self-diagnostic conditions. Since there are multiple candidate self-diagnostic conditions, the target self-diagnostic parameter acquisition method and the target self-diagnostic parameter processing method are different when different candidate self-diagnostic conditions are the target self-diagnostic conditions. The target self-diagnostic parameter type set is the set of parameter types of the self-diagnostic parameters to be acquired. The target self-diagnostic parameter type set is associated with the target DC controller and the target self-diagnostic conditions. When faced with different DC controllers and self-diagnostic conditions, the corresponding target self-diagnostic parameter type set can be found, thereby achieving more accurate self-diagnosis.

[0044] 202. The diagnostic device acquires multiple first target self-diagnostic parameters whose parameter types belong to the target self-diagnostic parameter type set based on the target self-diagnostic parameter acquisition method. The multiple first target self-diagnostic parameters include multiple first self-diagnostic parameters and multiple second self-diagnostic parameters. The multiple first self-diagnostic parameters are self-diagnostic parameters related to the target DC component, and the multiple second self-diagnostic parameters are self-diagnostic parameters related to the target DC controller.

[0045] Among them, the parameter type of the first target self-diagnostic parameter belongs to the target self-diagnostic parameter type set. The first self-diagnostic parameter is related to the target DC component, in other words, it is the component parameter of the target DC component. The second self-diagnostic parameter is related to the target DC controller, in other words, it is the controller parameter of the target DC controller. The idea of ​​obtaining multiple first self-diagnostic parameters is because the target DC controller directly controls the target DC component, so the condition of the target DC component can actually reflect whether the target DC controller is abnormal to a certain extent.

[0046] 203. The diagnostic equipment uses the target self-diagnostic parameter processing method to process the multiple first target self-diagnostic parameters to obtain multiple second target self-diagnostic parameters and multiple third target self-diagnostic parameters of the target DC controller. The multiple second target self-diagnostic parameters and the multiple third target self-diagnostic parameters correspond to different self-diagnostic dimensions.

[0047] The second and third target self-diagnostic methods are obtained by processing the multiple first target self-diagnostic parameters using a target self-diagnostic parameter processing method, and can be used in subsequent self-diagnostic processes. Different self-diagnostic dimensions refer to different data dimensions.

[0048] 204. The diagnostic device determines the target self-diagnostic result of the target DC controller based on the plurality of second target self-diagnostic parameters and the plurality of third target self-diagnostic parameters. The target self-diagnostic result is used to indicate whether the target DC controller has a fault.

[0049] Among them, the target self-diagnosis result is the final self-diagnosis result obtained by performing self-diagnosis on the target DC controller. Compared with the self-diagnosis result obtained by using the self-diagnosis program built into the target DC controller, the target self-diagnosis result is more accurate.

[0050] The technical solution provided in this application determines the target self-diagnostic parameter acquisition method, target self-diagnostic parameter processing method, and target self-diagnostic parameter type set when the target DC controller meets the target self-diagnostic conditions. Based on the target self-diagnostic parameter acquisition method, multiple first target self-diagnostic parameters whose parameter types belong to the target self-diagnostic parameter type set are acquired, thereby realizing the acquisition of basic self-diagnostic parameters. The target self-diagnostic parameter processing method is used to process the multiple first target self-diagnostic parameters to obtain multiple second target self-diagnostic parameters and multiple third target self-diagnostic parameters with different self-diagnostic dimensions. Based on the multiple second target self-diagnostic parameters and multiple third target self-diagnostic parameters, the target self-diagnostic result of the target DC controller is determined. Compared with the self-diagnostic results obtained by the self-diagnostic methods in related technologies, the accuracy of the target self-diagnostic result is higher due to the combination of richer data and the adoption of appropriate data processing methods.

[0051] Steps 201-204 above are a brief introduction to the self-diagnostic processing method for a DC controller provided in the embodiments of this application. The following will provide a clearer explanation of the self-diagnostic processing method for a DC controller provided in the embodiments of this application, using some examples. See [link to relevant documentation]. Figure 3 Taking the diagnostic device as the executing entity as an example, the method includes the following steps.

[0052] 301. The diagnostic equipment determines whether the target DC controller of the target DC component meets any of the multiple candidate self-diagnostic conditions.

[0053] The target DC component refers to DC devices such as DC motors, batteries, and generators. Under normal circumstances, the target DC controller can perform stable voltage / current control, system status monitoring, and fault protection for the target DC component. Determining whether the target DC controller meets multiple candidate self-diagnostic conditions serves two purposes: firstly, to determine whether self-diagnosis of the target DC controller is necessary, and secondly, to find a matching self-diagnostic method. Candidate self-diagnostic conditions include candidate operating environment conditions, candidate controller conditions, and candidate DC component conditions.

[0054] In one possible implementation, the diagnostic device acquires the operating environment parameters of the target DC controller, the controller parameters of the target DC controller, and the DC component parameters of the target DC component. The diagnostic device performs condition matching between the operating environment parameters, the controller parameters, and the third operating parameter and candidate operating environment conditions, candidate controller conditions, and candidate DC component conditions of a plurality of candidate self-diagnostic conditions, respectively, to determine whether the target DC controller meets any of the candidate self-diagnostic conditions.

[0055] The operating environment parameters include ambient temperature and humidity; controller parameters include the controller temperature, controller current, and continuous operating time of the target DC controller; and DC component parameters include the component current and component voltage of the target DC component. Candidate operating environment conditions are whether the ambient temperature and humidity are greater than or equal to a candidate ambient temperature threshold and a candidate ambient humidity threshold, respectively. The candidate ambient temperature and humidity thresholds differ for different candidate operating environment conditions. Candidate controller conditions are whether the controller temperature, controller current, and continuous operating time are greater than or equal to a candidate controller temperature threshold, a candidate controller current threshold, and a candidate controller continuous operating time threshold, respectively. The candidate controller temperature, current, and continuous operating time thresholds differ for different candidate controller conditions. Candidate DC component conditions include whether the component current fluctuation is greater than or equal to a candidate current fluctuation threshold and whether the component voltage fluctuation is greater than or equal to a candidate voltage fluctuation threshold, respectively. The candidate current and voltage fluctuation thresholds differ for different candidate DC component conditions. In some embodiments, the current fluctuation and voltage fluctuation can be represented by current variance and voltage variance, respectively.

[0056] In some embodiments, for any one of a plurality of candidate self-diagnostic conditions, if the working environment parameter satisfies the candidate working environment condition in the candidate self-diagnostic conditions, the controller parameter satisfies the candidate controller condition in the candidate self-diagnostic conditions, and the DC component parameter satisfies the candidate DC component condition in the candidate self-diagnostic conditions, the diagnostic device determines that the target DC controller satisfies the candidate self-diagnostic condition, and the candidate self-diagnostic condition is the target self-diagnostic condition.

[0057] Accordingly, if the operating environment parameter does not meet the candidate operating environment condition in the candidate self-diagnosis condition, the controller parameter does not meet the candidate controller condition in the candidate self-diagnosis condition, or the DC component parameter does not meet the candidate DC component condition in the candidate self-diagnosis condition, the diagnostic device determines that the target DC controller does not meet the candidate self-diagnosis condition.

[0058] 302. When the target DC controller of the target DC component meets the target self-diagnostic condition among multiple candidate self-diagnostic conditions, the diagnostic equipment determines the target self-diagnostic parameter acquisition method and target self-diagnostic parameter processing method corresponding to the target self-diagnostic condition, and determines the target DC controller and the target self-diagnostic parameter type set corresponding to the target self-diagnostic condition. The target self-diagnostic condition includes the target working environment condition, the target controller condition and the target DC component condition.

[0059] The target self-diagnostic condition is one of several candidate self-diagnostic conditions. The target DC controller meeting the target self-diagnostic condition indicates that the target DC controller needs to perform self-diagnosis, and the self-diagnosis will use a method matching the target diagnostic condition. The target operating environment condition is related to the operating environment of the target DC controller. The target controller condition refers to the condition related to the target DC controller itself. The target DC component condition refers to the condition related to the target DC component. The reason for introducing the target DC component condition is that the target DC controller directly controls the target DC component, so the condition of the target DC component can, to some extent, reflect whether the target DC controller is abnormal. The target self-diagnostic parameter acquisition method refers to the method of acquiring self-diagnostic parameters. The self-diagnostic parameters are the relevant parameters used for self-diagnosing the target DC controller in this embodiment. The target self-diagnostic parameter processing method refers to the method of processing the acquired self-diagnostic parameters. In this embodiment, the target self-diagnostic parameter acquisition method and the target self-diagnostic parameter processing method are associated with the target self-diagnostic condition. Since there are multiple candidate self-diagnostic conditions, the target self-diagnostic parameter acquisition method and the target self-diagnostic parameter processing method are different when different candidate self-diagnostic conditions are the target self-diagnostic conditions. The target self-diagnostic parameter type set is a set of parameter types of the self-diagnostic parameters that need to be acquired. The target self-diagnostic parameter type set is associated with the target DC controller and the target self-diagnostic conditions. Under different DC controllers and self-diagnostic conditions, the corresponding target self-diagnostic parameter type set can be found, thereby achieving more accurate self-diagnosis.

[0060] In one possible implementation, when the target DC controller of the target DC component satisfies the target self-diagnostic condition among multiple candidate self-diagnostic conditions, the diagnostic device determines the degree to which the target DC controller meets the condition. This degree of satisfaction indicates the extent to which the target DC controller exceeds the target self-diagnostic condition. Based on the target self-diagnostic condition and the degree of satisfaction, the diagnostic device determines the target self-diagnostic parameter acquisition method and the target self-diagnostic parameter processing method. Based on the degree of satisfaction, the controller type of the target DC controller, and the target self-diagnostic condition, the diagnostic device determines the target self-diagnostic parameter type set.

[0061] The degree to which the target diagnostic conditions are exceeded refers to the extent to which the target DC controller, while meeting the target self-diagnostic conditions, exceeds the parameter thresholds corresponding to those conditions. For example, the target self-diagnostic parameters include target operating environment conditions, target controller conditions, and target DC component conditions. The parameter thresholds corresponding to the target self-diagnostic conditions include environmental condition parameter thresholds corresponding to the target operating environment conditions, controller condition parameter thresholds corresponding to the target controller conditions, and component condition parameter thresholds corresponding to the target DC component conditions. In this embodiment, determining the degree to which the conditions are met is one of the core steps in self-diagnosis, and it plays a crucial role in improving the accuracy of self-diagnosis during ablation experiments.

[0062] To provide a clearer explanation of the above embodiments, the following description is divided into several parts.

[0063] Part 1: When the target DC controller of the target DC component meets the target self-diagnostic condition among multiple candidate self-diagnostic conditions, the diagnostic equipment determines the degree to which the condition of the target DC controller is met.

[0064] In one possible implementation, when the target DC controller of the target DC component satisfies the target self-diagnostic condition among multiple candidate self-diagnostic conditions, the diagnostic device determines the degree of satisfaction of the condition based on the operating environment parameters of the target DC controller and the environmental condition parameter threshold corresponding to the target operating environment condition, the controller parameters of the target DC controller and the controller condition parameter threshold corresponding to the target controller condition, and the DC component parameters of the target DC component and the component condition parameter threshold corresponding to the target DC component condition.

[0065] Specifically, the operating environment parameters are used to match the target operating environment conditions, the controller parameters are used to match the target controller conditions, and the DC component parameters are used to match the target DC component conditions. The matching method is described in step 301 above and will not be repeated here.

[0066] For example, if the target DC controller of a target DC component meets the target self-diagnostic condition among multiple candidate self-diagnostic conditions, the diagnostic device determines the degree of environmental parameter exceedance based on the operating environment parameters of the target DC controller and the corresponding environmental condition parameter thresholds. The diagnostic device then determines the degree of controller parameter exceedance based on the controller parameters of the target DC controller and the corresponding controller condition parameter thresholds. Finally, the diagnostic device determines the degree to which the condition is met based on the degree of environmental parameter exceedance, the degree of controller parameter exceedance, and the degree of DC component parameter exceedance.

[0067] Specifically, the degree of environmental parameter exceedance is obtained by subtracting the operating environment parameter from the environmental condition parameter threshold, and then dividing by the environmental condition parameter threshold. The degree of controller parameter exceedance is obtained by subtracting the controller parameter from the controller condition parameter threshold, and then dividing by the controller condition parameter threshold. The degree of DC component parameter exceedance is obtained by subtracting the component parameter from the component condition parameter threshold, and then dividing by the component condition parameter threshold.

[0068] The above examples will be explained in several parts below.

[0069] A. The diagnostic equipment determines the extent to which the environmental parameters exceed the threshold values ​​corresponding to the operating environment parameters of the target DC controller and the target operating environment conditions.

[0070] In one possible implementation, the working environment parameters include ambient temperature and ambient humidity, and the environmental condition parameter thresholds include an ambient temperature threshold and an ambient humidity threshold. The diagnostic device subtracts the ambient temperature from the ambient temperature threshold and then divides the result by the ambient temperature threshold to obtain the degree of ambient temperature exceedance. The diagnostic device subtracts the ambient humidity from the ambient humidity threshold and then divides the result by the ambient humidity threshold to obtain the degree of ambient humidity exceedance. The diagnostic device then performs a weighted fusion of the ambient temperature exceedance and the ambient humidity exceedance to obtain the degree of environmental parameter exceedance.

[0071] The weights in the aforementioned weighted fusion are related to the target's self-diagnosis conditions, and different weights correspond to different target self-diagnosis conditions.

[0072] B. The diagnostic equipment determines the extent to which the controller parameters exceed the threshold values ​​corresponding to the controller condition of the target DC controller.

[0073] In one possible implementation, the controller parameters include the controller temperature, controller current, and controller continuous operating time of the target DC controller. The controller condition parameter thresholds include a controller temperature threshold, a controller current threshold, and a controller continuous operating time threshold. The diagnostic device subtracts the controller temperature threshold from the controller temperature and divides the result by the controller temperature threshold to obtain the degree of controller temperature exceedance. The diagnostic device subtracts the controller current threshold from the controller current threshold and divides the result by the controller current threshold to obtain the degree of controller current exceedance. The diagnostic device subtracts the controller continuous operating time threshold from the controller continuous operating time threshold and divides the result by the controller continuous operating time threshold to obtain the degree of controller continuous operating time exceedance. The diagnostic device performs a weighted fusion of the degrees of controller temperature exceedance, controller current exceedance, and controller continuous operating time exceedance to obtain the degree of controller parameter exceedance.

[0074] The weights in the aforementioned weighted fusion are related to the target's self-diagnosis conditions, and different weights correspond to different target self-diagnosis conditions.

[0075] C. The diagnostic equipment determines the extent to which the DC component parameters exceed the threshold values ​​corresponding to the DC component conditions and the DC component parameters of the target DC component.

[0076] In one possible implementation, the DC component parameters include the component current and component voltage of the target DC component, and the component condition parameter thresholds include a current fluctuation threshold and a voltage fluctuation threshold. The diagnostic device determines the current fluctuation level of the component current based on the component current of the target DC component. The diagnostic device determines the voltage fluctuation level of the component voltage based on the component voltage of the target DC component. The diagnostic device subtracts the current fluctuation level from the current fluctuation threshold and divides the result by the current fluctuation threshold to obtain the current fluctuation exceedance level. The diagnostic device subtracts the voltage fluctuation level from the voltage fluctuation threshold and divides the result by the voltage fluctuation threshold to obtain the voltage fluctuation exceedance level. The diagnostic device performs a weighted fusion of the current fluctuation exceedance level and the voltage fluctuation exceedance level to obtain the DC component parameter exceedance level.

[0077] The degree of current fluctuation and voltage fluctuation are represented by current variance and voltage variance, respectively. The weights in the above weighted fusion are related to the target self-diagnostic conditions, and different target self-diagnostic conditions correspond to different weights.

[0078] D. The controller determines the degree to which the condition is met based on the degree to which environmental parameters, controller parameters, and DC component parameters exceed the limits.

[0079] In one possible implementation, the controller combines the degree to which the environmental parameter exceeds the limit, the degree to which the controller parameter exceeds the limit, and the degree to which the DC component parameter exceeds the limit to obtain the degree to which the condition is met.

[0080] Part Two: Based on the self-diagnostic conditions of the target and the degree to which those conditions are met, the diagnostic equipment determines the method for acquiring the self-diagnostic parameters of the target and the method for processing the self-diagnostic parameters of the target.

[0081] In one possible implementation, the diagnostic device performs condition transformation on the target operating environment conditions, target controller conditions, and target DC component conditions to obtain a condition description text for the target self-diagnostic conditions. Based on the condition description text and the degree to which the conditions are met, the diagnostic device determines the controller state and target self-diagnostic mode of the target DC controller. Based on the controller state and the target self-diagnostic mode, the diagnostic device determines the method for acquiring and processing the target self-diagnostic parameters.

[0082] For example, the diagnostic device concatenates the target operating environment conditions, target controller conditions, and target DC component conditions, and then extracts features to obtain the self-diagnostic condition features of the target. Based on these self-diagnostic condition features, the diagnostic device generates a condition description text for the target self-diagnostic conditions. The diagnostic device concatenates this condition description text and the degree of condition satisfaction, and then extracts features to obtain state prediction features and diagnostic mode prediction features. The diagnostic device performs a fully connected and normalized operation on the state prediction features to obtain a probability set, which includes multiple probabilities, each probability corresponding to a candidate controller state. The diagnostic device determines the candidate controller state corresponding to the highest probability in the probability set as the controller state of the target DC controller. The diagnostic device matches the diagnostic mode prediction features with the candidate self-diagnostic mode features of multiple candidate self-diagnostic modes to obtain the target self-diagnostic mode, which is the candidate self-diagnostic mode with the highest feature similarity between the candidate self-diagnostic mode features and the diagnostic mode prediction features. The diagnostic device uses the controller state and the target self-diagnostic mode to query a first relational table to obtain the target self-diagnostic parameter acquisition method and the target self-diagnostic parameter processing method.

[0083] Feature extraction refers to encoding based on an attention mechanism, and generating conditional description text based on self-diagnostic conditional features is obtained through multi-round iterative decoding using the attention mechanism. There are multiple candidate controller states, such as suspected abnormality, minor abnormality, abnormality, significant abnormality, and normality. The fully connected layer refers to multiplying the features with a fully connected matrix, which is obtained through multiple rounds of training. Normalization refers to processing using a normalization function, such as SoftMax or ReLU, which is not limited in this embodiment. The first relational table stores multiple controller states, multiple self-diagnostic modes, multiple self-diagnostic parameter acquisition methods, multiple self-diagnostic parameter processing methods, and their corresponding relationships. One self-diagnostic parameter acquisition method corresponds to one controller state and one self-diagnostic mode, and one self-diagnostic parameter processing method corresponds to one controller state and one self-diagnostic mode. The first relational table is configured by technicians according to actual conditions, and is not limited in this embodiment.

[0084] Part Three: The diagnostic equipment determines the set of self-diagnostic parameter types for the target based on the degree to which the condition is met, the controller type of the target DC controller, and the self-diagnostic conditions of the target.

[0085] The controller type is the result of classifying the target DC controller. For example, in the embodiments of this application, the controller type includes motor controllers and battery controllers.

[0086] In one possible implementation, the diagnostic device inputs the degree of condition satisfaction, the controller type of the target DC controller, and the target self-diagnostic conditions into a type prediction model. The type prediction model encodes the degree of condition satisfaction, the controller type of the target DC controller, and the target self-diagnostic conditions to obtain type prediction features. The diagnostic device then uses the type prediction model to iteratively decode these type prediction features multiple times to obtain the target self-diagnostic parameter type set.

[0087] In this context, encoding refers to an attention-based encoding process, while multi-round iterative decoding refers to a multi-round iterative decoding process based on the attention mechanism. Multi-round iterative decoding yields multiple diagnostic parameter types, which together form a set of self-diagnostic parameter types for the target. Optional diagnostic parameter types include controller temperature, controller input current, controller input voltage, controller output current, controller output voltage, and controller continuous operating time for the target DC controller, as well as component temperature, component current, component voltage, component vibration frequency, component vibration intensity, component power, and component remaining capacity for the target DC component. The set of self-diagnostic parameter types obtained varies depending on the degree of condition satisfaction, the controller type of the target DC controller, and the self-diagnostic conditions, thus enabling personalized self-diagnosis of the target DC component. This type of prediction model includes an encoder and a decoder. The encoder is used for encoding, and the decoder is used for multi-round iterative decoding. The encoder is an attention-based encoder, such as the encoder in the BERT model, and the decoder is an attention-based decoder, such as the decoder in the BERT model. When training this type of prediction model, a supervised learning approach is used. This involves inputting the sample condition satisfaction level, sample controller type, and sample self-diagnosis conditions into the prediction model. The model then processes these inputs to obtain a set of predicted self-diagnosis parameter types. The prediction model is trained based on the differences between this set and the labeled set of self-diagnosis parameter types. The labeled set of self-diagnosis parameter types comprises the set of self-diagnosis parameter types corresponding to the sample condition satisfaction level, sample controller type, and sample self-diagnosis conditions.

[0088] 303. The diagnostic device acquires multiple first target self-diagnostic parameters whose parameter types belong to the target self-diagnostic parameter type set based on the target self-diagnostic parameter acquisition method. The multiple first target self-diagnostic parameters include multiple first self-diagnostic parameters and multiple second self-diagnostic parameters. The multiple first self-diagnostic parameters are self-diagnostic parameters related to the target DC component, and the multiple second self-diagnostic parameters are self-diagnostic parameters related to the target DC controller.

[0089] Among them, the parameter type of the first target self-diagnostic parameter belongs to the target self-diagnostic parameter type set. The first self-diagnostic parameter is related to the target DC component, in other words, it is the component parameter of the target DC component. The second self-diagnostic parameter is related to the target DC controller, in other words, it is the controller parameter of the target DC controller. The idea of ​​obtaining multiple first self-diagnostic parameters is because the target DC controller directly controls the target DC component, so the condition of the target DC component can actually reflect whether the target DC controller is abnormal to a certain extent.

[0090] In one possible implementation, the diagnostic device determines the target parameter source and parameter acquisition frequency indicated by the target self-diagnostic parameter acquisition method. The diagnostic device acquires multiple initial self-diagnostic parameters from the target parameter source according to the parameter acquisition frequency. The diagnostic device then identifies the output diagnostic parameters whose parameter type belongs to the target self-diagnostic parameter type set among these multiple initial self-diagnostic parameters as target self-diagnostic parameters, thereby obtaining the multiple first target self-diagnostic parameters.

[0091] In this context, the target parameter source refers to the origin of the acquired parameter. For the same parameter, there may be at least two parameter sources. For example, when the target DC component is a motor, the motor's input current can be obtained directly from the motor's current sensor or from the target DC controller. The target parameter source clarifies the source of the parameter. The target parameter source is a collection of parameter sources; that is, it includes the parameter sources corresponding to each parameter in the optional diagnostic parameter types. For example, if the optional diagnostic parameter types include controller temperature and controller input current, then the target parameter source includes the parameter sources corresponding to controller temperature and controller input current. The parameter acquisition frequency indicates how frequently parameters are acquired; a higher acquisition frequency indicates higher frequency, and a lower acquisition frequency indicates lower frequency.

[0092] 304. The diagnostic equipment uses the target self-diagnostic parameter processing method to process the multiple first target self-diagnostic parameters to obtain multiple second target self-diagnostic parameters and multiple third target self-diagnostic parameters of the target DC controller. The multiple second target self-diagnostic parameters and the multiple third target self-diagnostic parameters correspond to different self-diagnostic dimensions.

[0093] The second and third target self-diagnostic methods are obtained by processing the multiple first target self-diagnostic parameters using a target self-diagnostic parameter processing method, and can be used in subsequent self-diagnostic processes. Different self-diagnostic dimensions refer to different data dimensions.

[0094] In one possible implementation, the target self-diagnostic parameter processing method includes a first self-diagnostic parameter processing method, a second self-diagnostic parameter processing method, and a third self-diagnostic parameter processing method. The diagnostic device uses the first self-diagnostic parameter processing method to process multiple first self-diagnostic parameters from among the multiple first target self-diagnostic parameters, obtaining multiple component self-diagnostic processing parameters for the target DC component. The diagnostic device uses the second self-diagnostic parameter processing method to process multiple second self-diagnostic parameters from among the multiple first target self-diagnostic parameters, obtaining multiple controller self-diagnostic processing parameters for the target DC controller. The diagnostic device uses the third self-diagnostic parameter processing method to process the multiple first self-diagnostic parameters and the multiple second self-diagnostic parameters, determining multiple fused self-diagnostic processing parameters. Based on the multiple component self-diagnostic processing parameters and the multiple fused self-diagnostic processing parameters, the diagnostic device determines multiple second target self-diagnostic parameters for the target DC controller. Based on the multiple controller self-diagnostic processing parameters and the multiple fused self-diagnostic processing parameters, the diagnostic device determines multiple third target self-diagnostic parameters for the target DC controller.

[0095] Among them, the first self-diagnostic parameter processing method, the second self-diagnostic parameter processing method, and the third self-diagnostic parameter processing method are different parameter processing methods. By using multiple second target self-diagnostic parameters and multiple third target self-diagnostic parameters obtained through the first self-diagnostic parameter processing method, the second self-diagnostic parameter processing method, and the third self-diagnostic parameter processing method, a relatively accurate self-diagnostic result can be obtained.

[0096] To provide a clearer explanation of the above embodiments, the following description is divided into several parts.

[0097] The first part describes how the diagnostic equipment uses the first self-diagnostic parameter processing method to process multiple first self-diagnostic parameters among the multiple first target self-diagnostic parameters, thereby obtaining multiple component self-diagnostic processing parameters for the target DC component.

[0098] Among them, the first self-diagnostic parameter is a self-diagnostic parameter related to the target DC component, and the processing method of the first self-diagnostic parameter is a parameter processing method that matches the target DC component and the target diagnostic conditions.

[0099] In one possible implementation, the diagnostic device preprocesses the plurality of first self-diagnostic parameters using the preprocessing method indicated by the first self-diagnostic parameter processing method, obtaining the plurality of preprocessed first self-diagnostic parameters. The diagnostic device inputs the plurality of preprocessed first self-diagnostic parameters into the first parameter processing model indicated by the first self-diagnostic parameter processing method, and encodes and decodes the plurality of preprocessed first self-diagnostic parameters to obtain the plurality of component self-diagnostic processing parameters.

[0100] Preprocessing is used to remove abnormal parameters from the first self-diagnostic parameters. The preprocessing method indicated by the first self-diagnostic parameter processing method is one of multiple candidate preprocessing methods, and the preprocessing accuracy varies among different candidate preprocessing methods. The function of the first parameter processing model is to convert one parameter sequence into another parameter sequence. In the above method, this means converting the sequence composed of multiple preprocessed first self-diagnostic parameters into a sequence composed of multiple component self-diagnostic processing parameters. Sequence conversion is to convert the parameters into a specified form. In this embodiment, there are multiple candidate first parameter processing models, and the first parameter processing model indicated by the first self-diagnostic parameter processing method is one of these multiple candidate first parameter processing models. Different candidate first parameter processing models have different parameter processing effects. That is, in the above implementation, the first self-diagnostic parameter processing method can be used to select a first parameter processing model from multiple candidate first parameter processing models, and this first parameter processing model can be used to implement parameter processing to meet the parameter processing requirements of the current scenario. The first parameter processing model is a sequence encoding / decoding model, such as an encoding / decoding model based on a Long Short-Term Memory (LSTM) network, or an encoding / decoding model based on an attention mechanism; this embodiment does not limit this.

[0101] The second part describes how the diagnostic equipment uses the second self-diagnostic parameter processing method to process multiple second self-diagnostic parameters among the multiple first target self-diagnostic parameters, thereby obtaining multiple controller self-diagnostic processing parameters for the target DC controller.

[0102] The second self-diagnostic parameter is a self-diagnostic parameter related to the target DC controller, and the processing method of the second self-diagnostic parameter is a parameter processing method that matches the target DC controller and the target diagnostic conditions.

[0103] In one possible implementation, the diagnostic device preprocesses the plurality of second self-diagnostic parameters using the preprocessing method indicated by the second self-diagnostic parameter processing method, obtaining the plurality of preprocessed second self-diagnostic parameters. The diagnostic device inputs the plurality of preprocessed second self-diagnostic parameters into the second parameter processing model indicated by the second self-diagnostic parameter processing method, and encodes and decodes the plurality of preprocessed second self-diagnostic parameters to obtain the plurality of controller self-diagnostic processing parameters.

[0104] The preprocessing step is to remove abnormal parameters from the second self-diagnostic parameters. The preprocessing method indicated by the second self-diagnostic parameter processing method is one of several candidate preprocessing methods, and the preprocessing accuracy varies among different candidate methods. The function of the second parameter processing model is to transform one parameter sequence into another. In the above method, this means transforming the sequence of multiple preprocessed second self-diagnostic parameters into a sequence of multiple controller self-diagnostic processing parameters. Sequence transformation is to convert the parameters into a specified form. In this embodiment, there are multiple candidate second parameter processing models, and the second parameter processing model indicated by the second self-diagnostic parameter processing method is one of these multiple candidate second parameter processing models. Different candidate second parameter processing models have different parameter processing effects. That is, in the above embodiment, the second self-diagnostic parameter processing method can be used to select a second parameter processing model from multiple candidate second parameter processing models, and this second parameter processing model can be used to implement parameter processing to meet the parameter processing requirements of the current scenario. Similar to the first parameter processing model, the second parameter processing model is a sequence encoding and decoding model, such as an encoding and decoding model based on a Long Short-Term Memory (LSTM) network, or an encoding and decoding model based on an attention mechanism. This application does not limit this.

[0105] The third part describes how the diagnostic equipment uses the third self-diagnostic parameter processing method to process the multiple first self-diagnostic parameters and the multiple second self-diagnostic parameters to determine multiple fusion self-diagnostic processing parameters.

[0106] In one possible implementation, the diagnostic device preprocesses the plurality of first self-diagnostic parameters and the plurality of second self-diagnostic parameters using a preprocessing method indicated by the third self-diagnostic parameter processing method, resulting in preprocessed plurality of first self-diagnostic parameters and preprocessed plurality of second self-diagnostic parameters. Based on the parameter types of the preprocessed plurality of first self-diagnostic parameters and the preprocessed plurality of second self-diagnostic parameters, the diagnostic device determines multiple self-diagnostic parameter pairs. Each self-diagnostic parameter pair includes one first self-diagnostic parameter and one second self-diagnostic parameter, and the type similarity between the parameter types of the first self-diagnostic parameter and the second self-diagnostic parameter is greater than or equal to the similarity threshold indicated by the third self-diagnostic parameter processing method. The diagnostic device inputs the multiple self-diagnostic parameter pairs into the third parameter processing model indicated by the third self-diagnostic parameter processing method, and encodes and decodes the multiple self-diagnostic parameter pairs to obtain the multiple fused self-diagnostic processing parameters.

[0107] The preprocessing step involves removing abnormal parameters from the first and second self-diagnostic parameters. The preprocessing method indicated by the third self-diagnostic parameter processing method is one of several candidate preprocessing methods, each with varying preprocessing precision. The third parameter processing model transforms one parameter sequence into another; in the above method, it transforms the sequence of preprocessed self-diagnostic parameter pairs into a sequence of fused self-diagnostic processing parameters. This sequence transformation converts the parameters into a specified form. In this embodiment, multiple candidate third parameter processing models exist, and the third parameter processing model indicated by the third self-diagnostic parameter processing method is one of these candidate models. Different candidate third parameter processing models have different parameter processing effects. In other words, in the above implementation, the third self-diagnostic parameter processing method can be used to select a third parameter processing model from multiple candidate models, and this third parameter processing model can be used to implement parameter processing to meet the parameter processing requirements of the current scenario. Similar to the first parameter processing model, the third parameter processing model is a sequence encoding and decoding model, such as an encoding and decoding model based on a Long Short-Term Memory (LSTM) network, or an encoding and decoding model based on an attention mechanism. This application does not limit this to any particular model.

[0108] Part Four: The diagnostic equipment determines multiple second target self-diagnostic parameters of the target DC controller based on the multiple component self-diagnostic processing parameters and the multiple fused self-diagnostic processing parameters.

[0109] Among them, the self-diagnostic processing parameters of the aforementioned components and the fusion self-diagnostic processing parameters are all intermediate variables in the data processing process and do not have specific physical meaning.

[0110] In one possible implementation, the diagnostic device determines a plurality of first parameter correction coefficients based on the plurality of component self-diagnostic processing parameters, each first parameter correction coefficient corresponding to one component self-diagnostic processing parameter. Based on the plurality of first parameter correction coefficients and the plurality of fused self-diagnostic processing parameters, the diagnostic device obtains a plurality of second target self-diagnostic parameters, the number of the plurality of first parameter correction coefficients being the same as the number of the plurality of fused self-diagnostic processing parameters.

[0111] The first parameter correction coefficient is used to correct the fusion self-diagnostic parameters, thereby obtaining the corresponding second target self-diagnostic parameters.

[0112] For example, the diagnostic device performs a full connection on the self-diagnostic processing parameters of the multiple components to obtain multiple first parameter correction coefficients. The diagnostic device multiplies these multiple first parameter correction coefficients with the multiple fused self-diagnostic processing parameters to obtain the multiple second target self-diagnostic parameters.

[0113] The purpose of full connectivity is to convert multiple component self-diagnostic processing parameters into a matrix composed of multiple first parameter correction coefficients, and then multiply the multiple first parameter correction coefficients with the multiple fusion self-diagnostic processing parameters, that is, to multiply the matrix composed of the multiple first parameter correction coefficients with the matrix composed of the multiple fusion self-diagnostic processing parameters.

[0114] Part 5: The diagnostic equipment determines multiple third target self-diagnostic parameters of the target DC controller based on the multiple controller self-diagnostic processing parameters and the multiple fused self-diagnostic processing parameters.

[0115] Among them, the aforementioned controller self-diagnostic processing parameters and fusion self-diagnostic processing parameters are all intermediate variables in the data processing process and do not have specific physical meaning.

[0116] In one possible implementation, the diagnostic device determines a plurality of second parameter correction coefficients based on the plurality of controller self-diagnostic processing parameters, each second parameter correction coefficient corresponding to one controller self-diagnostic processing parameter. Based on the plurality of second parameter correction coefficients and the plurality of fused self-diagnostic processing parameters, the diagnostic device obtains a plurality of third target self-diagnostic parameters, wherein the number of the plurality of second parameter correction coefficients is the same as the number of the plurality of fused self-diagnostic processing parameters.

[0117] The second parameter correction coefficient is used to correct the fusion self-diagnostic parameters, thereby obtaining the corresponding third target self-diagnostic parameters.

[0118] For example, the diagnostic device performs full connection and normalization on the multiple controller self-diagnostic processing parameters to obtain multiple second parameter correction coefficients. The diagnostic device multiplies these multiple second parameter correction coefficients with the multiple fused self-diagnostic processing parameters to obtain the multiple third target self-diagnostic parameters.

[0119] The purpose of full connectivity is to convert multiple controller self-diagnostic processing parameters into a matrix composed of multiple second parameter correction coefficients, and then multiply the multiple second parameter correction coefficients with the multiple fused self-diagnostic processing parameters. In other words, the matrix composed of the multiple second parameter correction coefficients is multiplied with the matrix composed of the multiple fused self-diagnostic processing parameters.

[0120] 305. The diagnostic device determines the target self-diagnostic result of the target DC controller based on the plurality of second target self-diagnostic parameters and the plurality of third target self-diagnostic parameters. The target self-diagnostic result is used to indicate whether the target DC controller has a fault.

[0121] Among them, the target self-diagnosis result is the final self-diagnosis result obtained by performing self-diagnosis on the target DC controller. Compared with the self-diagnosis result obtained by using the self-diagnosis program built into the target DC controller, the target self-diagnosis result is more accurate.

[0122] In one possible implementation, the diagnostic device determines an auxiliary diagnostic result for the target DC controller based on the plurality of second target self-diagnostic parameters. The diagnostic device determines an initial diagnostic result based on the plurality of third target self-diagnostic parameters. The diagnostic device then determines the target self-diagnostic result for the target DC controller based on the auxiliary diagnostic result and the initial diagnostic result.

[0123] For example, the diagnostic device extracts features from multiple second-target self-diagnostic parameters to obtain auxiliary diagnostic result prediction features. The diagnostic device performs a fully connected and normalized operation on these auxiliary diagnostic result prediction features to obtain the auxiliary result classification value corresponding to the auxiliary diagnostic result. The diagnostic device extracts features from multiple third-target self-diagnostic parameters to obtain initial diagnostic result prediction features. The diagnostic device performs a fully connected and normalized operation on these initial diagnostic result prediction features to obtain the initial result classification value corresponding to the initial diagnostic result. The diagnostic device performs a weighted sum of the auxiliary result classification value and the initial result classification value to obtain the target classification value. If the target classification value is greater than or equal to a classification value threshold, the diagnostic device determines the target diagnostic result as the first diagnostic result, which indicates that the target DC controller has a fault. If the target classification value is less than the classification value threshold, the diagnostic device determines the target diagnostic result as the second diagnostic result, which indicates that the target DC controller does not have a fault.

[0124] The weight corresponding to the auxiliary result classification value is less than the weight corresponding to the initial result classification value. Preferably, the weight corresponding to the auxiliary result classification value is one-quarter of the weight corresponding to the initial result classification value, that is, the weight corresponding to the auxiliary result classification value is 0.2 and the weight corresponding to the initial result classification value is 0.8. In the experiment, the target diagnosis result obtained using such weights had the highest accuracy. The classification value threshold is the candidate classification value threshold that matches the self-diagnosis conditions of the target among multiple candidate classification value thresholds.

[0125] Optionally, in addition to the above-described embodiments, the diagnostic device may also perform the following steps to determine the target self-diagnostic result.

[0126] In one possible implementation, the diagnostic device acquires the original self-diagnostic result of the target DC controller, a first anomaly description information of the target DC component, and a second anomaly description information of the target DC controller. The original self-diagnostic result is the self-diagnostic result obtained through the self-diagnostic program of the target DC controller. Based on the original self-diagnostic result, the first anomaly description information, and the second anomaly description information, the diagnostic device determines a reference self-diagnostic result of the target DC controller. Based on the auxiliary diagnostic result, the initial diagnostic result, and the reference self-diagnostic result, the diagnostic device determines a target self-diagnostic result of the target DC controller.

[0127] Both the first and second anomaly descriptions were filled in by technical personnel, and both were in natural language format.

[0128] The following describes how the diagnostic device in the above embodiments determines the reference self-diagnostic result of the target DC controller based on the original self-diagnostic result, the first anomaly description information, and the second anomaly description information.

[0129] In one possible implementation, the diagnostic device inputs the initial self-diagnosis result, the first anomaly description information, and the second anomaly description information into a diagnostic result prediction model. The model extracts features from both the first and second anomaly description information to obtain first descriptive features and second descriptive features, respectively. The diagnostic device then fuses these features using the prediction model to obtain a diagnostic result prediction feature. Finally, the model performs a fully connected and normalized process on the predicted feature to obtain a reference result classification value corresponding to the reference self-diagnosis result.

[0130] The diagnostic result prediction model is a large language model with natural language processing capabilities. Utilizing this natural language processing capability, abnormal description information can be encoded into descriptive features, thereby enabling the subsequent acquisition of reference result classification values. This diagnostic result prediction model can be any type of large language model; this application embodiment does not limit its application to this type.

[0131] For example, the diagnostic device inputs the initial self-diagnosis result, the first anomaly description information, and the second anomaly description information into a diagnostic result prediction model. This model, based on an attention mechanism, encodes the first and second anomaly description information separately, obtaining first and second descriptive features for the first and second anomaly description information, respectively. The diagnostic device then fuses these three features using the diagnostic result prediction model to obtain a predicted diagnostic result feature. Finally, the diagnostic device performs a fully connected and normalized process on this predicted feature to obtain a reference result classification value corresponding to the reference self-diagnosis result.

[0132] The following describes how the diagnostic device in the above embodiments determines the target self-diagnostic result of the target DC controller based on the auxiliary diagnostic result, the initial diagnostic result, and the reference self-diagnostic result.

[0133] In one possible implementation, the diagnostic device performs a weighted sum of the auxiliary result classification value, the reference result classification value, and the initial result classification value to obtain a target classification value. If the target classification value is greater than or equal to a classification value threshold, the diagnostic device determines this target diagnostic result as a first diagnostic result, which indicates a fault in the target DC controller. If the target classification value is less than the classification value threshold, the diagnostic device determines this target diagnostic result as a second diagnostic result, which indicates that the target DC controller is not faulty.

[0134] The weights corresponding to the auxiliary result classification value and the reference result classification value are less than the weight corresponding to the initial result classification value. Preferably, the weight corresponding to the auxiliary result classification value is 0.1, the weight corresponding to the reference result classification value is 0.2, and the weight corresponding to the initial result classification value is 0.7. In the experiment, the target diagnosis result obtained using such weights had the highest accuracy. The classification value threshold is the candidate classification value threshold that matches the self-diagnosis conditions of the target among multiple candidate classification value thresholds.

[0135] 306. When the target self-diagnosis result indicates that the target DC controller is faulty, the diagnostic equipment determines the cause of the fault in the target DC controller based on the multiple second target self-diagnosis parameters and the multiple third target self-diagnosis parameters.

[0136] In one possible implementation, when the target self-diagnostic result indicates a fault in the target DC controller, the diagnostic device inputs the second target self-diagnostic parameter and the plurality of third target self-diagnostic parameters into a fault cause prediction model. The fault cause prediction model then encodes these parameters using an attention mechanism to obtain fault cause prediction features. The diagnostic device then iteratively decodes these features using the fault cause prediction model based on the attention mechanism to determine the fault cause.

[0137] The fault cause prediction model is an encoding and decoding model based on the attention mechanism. For example, it can be a model that is fine-tuned based on the BERT model, or a model that is fine-tuned based on other encoding and decoding models based on the attention mechanism. This application does not limit this.

[0138] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0139] The technical solution provided in this application determines the target self-diagnostic parameter acquisition method, target self-diagnostic parameter processing method, and target self-diagnostic parameter type set when the target DC controller meets the target self-diagnostic conditions. Based on the target self-diagnostic parameter acquisition method, multiple first target self-diagnostic parameters whose parameter types belong to the target self-diagnostic parameter type set are acquired, thereby realizing the acquisition of basic self-diagnostic parameters. The target self-diagnostic parameter processing method is used to process the multiple first target self-diagnostic parameters to obtain multiple second target self-diagnostic parameters and multiple third target self-diagnostic parameters with different self-diagnostic dimensions. Based on the multiple second target self-diagnostic parameters and multiple third target self-diagnostic parameters, the target self-diagnostic result of the target DC controller is determined. Compared with the self-diagnostic results obtained by the self-diagnostic methods in related technologies, the accuracy of the target self-diagnostic result is higher due to the combination of richer data and the adoption of appropriate data processing methods.

[0140] Figure 4 This is a schematic diagram of a self-diagnostic processing device for a DC controller provided in an embodiment of this application. See also... Figure 4 The device includes: a determination module 401, an acquisition module 402, a processing module 403, and a diagnosis module 404.

[0141] The determination module 401 is used to determine the target self-diagnostic parameter acquisition method and target self-diagnostic parameter processing method corresponding to the target self-diagnostic condition when the target DC controller of the target DC component meets the target self-diagnostic condition among multiple candidate self-diagnostic conditions, and to determine the target DC controller and the target self-diagnostic parameter type set corresponding to the target self-diagnostic condition. The target self-diagnostic condition includes target operating environment conditions, target controller conditions and target DC component conditions.

[0142] The acquisition module 402 is used to acquire multiple first target self-diagnostic parameters whose parameter types belong to the target self-diagnostic parameter type set based on the target self-diagnostic parameter acquisition method. The multiple first target self-diagnostic parameters include multiple first self-diagnostic parameters and multiple second self-diagnostic parameters. The multiple first self-diagnostic parameters are self-diagnostic parameters related to the target DC component, and the multiple second self-diagnostic parameters are self-diagnostic parameters related to the target DC controller.

[0143] The processing module 403 is used to process the multiple first target self-diagnostic parameters using the target self-diagnostic parameter processing method to obtain multiple second target self-diagnostic parameters and multiple third target self-diagnostic parameters of the target DC controller. The multiple second target self-diagnostic parameters and the multiple third target self-diagnostic parameters correspond to different self-diagnostic dimensions.

[0144] The diagnostic module 404 is used to determine the target self-diagnostic result of the target DC controller based on the plurality of second target self-diagnostic parameters and the plurality of third target self-diagnostic parameters. The target self-diagnostic result is used to indicate whether the target DC controller has a fault.

[0145] In one possible implementation, the determining module 401 is configured to determine the degree to which the target DC controller meets the target self-diagnostic condition among multiple candidate self-diagnostic conditions, whereby the target DC controller of the target DC component meets the target self-diagnostic condition. This degree of condition satisfaction indicates the extent to which the target DC controller exceeds the target self-diagnostic condition. Based on the target self-diagnostic condition and the degree of condition satisfaction, the module determines the target self-diagnostic parameter acquisition method and the target self-diagnostic parameter processing method. Based on the degree of condition satisfaction, the controller type of the target DC controller, and the target self-diagnostic condition, the module determines the target self-diagnostic parameter type set.

[0146] In one possible implementation, the determining module 401 is configured to determine the degree of satisfaction of a condition based on the operating environment parameters of the target DC controller and the environmental condition parameter threshold corresponding to the target operating environment condition, the controller parameters of the target DC controller and the controller condition parameter threshold corresponding to the target controller condition, and the DC component parameters of the target DC component and the component condition parameter threshold corresponding to the target DC component condition, when the target DC controller of the target DC component satisfies the target self-diagnostic condition among multiple candidate self-diagnostic conditions. The operating environment parameters are used to match the target operating environment condition, the controller parameters are used to match the target controller condition, and the DC component parameters are used to match the target DC component condition.

[0147] In one possible implementation, the determining module 401 is used to perform condition transformation on the target operating environment conditions, target controller conditions, and target DC component conditions to obtain a condition description text of the target self-diagnostic conditions. Based on the condition description text and the degree to which the conditions are met, the controller state and target self-diagnostic mode of the target DC controller are determined. Based on the controller state and the target self-diagnostic mode, the method for obtaining the target self-diagnostic parameters and the method for processing the target self-diagnostic parameters are determined.

[0148] In one possible implementation, the acquisition module 402 is used to determine the target parameter source and parameter acquisition frequency indicated by the target self-diagnostic parameter acquisition method. Multiple initial self-diagnostic parameters are acquired from the target parameter source according to the parameter acquisition frequency. Output diagnostic parameters whose parameter type belongs to the target self-diagnostic parameter type set among the multiple initial self-diagnostic parameters are determined as target self-diagnostic parameters to obtain the multiple first target self-diagnostic parameters.

[0149] In one possible implementation, the target self-diagnostic parameter processing method includes a first self-diagnostic parameter processing method, a second self-diagnostic parameter processing method, and a third self-diagnostic parameter processing method. The processing module 403 is used to process multiple first self-diagnostic parameters from a plurality of first target self-diagnostic parameters using the first self-diagnostic parameter processing method to obtain multiple component self-diagnostic processing parameters for the target DC component. The second self-diagnostic parameter processing method is used to process multiple second self-diagnostic parameters from a plurality of first target self-diagnostic parameters to obtain multiple controller self-diagnostic processing parameters for the target DC controller. The third self-diagnostic parameter processing method is used to process the plurality of first and second self-diagnostic parameters to determine multiple fused self-diagnostic processing parameters. Based on the multiple component self-diagnostic processing parameters and the multiple fused self-diagnostic processing parameters, multiple second target self-diagnostic parameters for the target DC controller are determined. Based on the multiple controller self-diagnostic processing parameters and the multiple fused self-diagnostic processing parameters, multiple third target self-diagnostic parameters for the target DC controller are determined.

[0150] In one possible implementation, the processing module 403 is configured to determine a plurality of first parameter correction coefficients based on the plurality of component self-diagnostic processing parameters, wherein each first parameter correction coefficient corresponds to one component self-diagnostic processing parameter. Based on the plurality of first parameter correction coefficients and the plurality of fusion self-diagnostic processing parameters, a plurality of second target self-diagnostic parameters are obtained, wherein the number of the plurality of first parameter correction coefficients is the same as the number of the plurality of fusion self-diagnostic processing parameters.

[0151] The processing module 403 is used to determine multiple second parameter correction coefficients based on the multiple controller self-diagnostic processing parameters, where each second parameter correction coefficient corresponds to one controller self-diagnostic processing parameter. Based on the multiple second parameter correction coefficients and the multiple fused self-diagnostic processing parameters, multiple third target self-diagnostic parameters are obtained, where the number of the multiple second parameter correction coefficients is the same as the number of the multiple fused self-diagnostic processing parameters.

[0152] In one possible implementation, the diagnostic module 404 is configured to determine an auxiliary diagnostic result for the target DC controller based on the plurality of second target self-diagnostic parameters; determine an initial diagnostic result based on the plurality of third target self-diagnostic parameters; and determine a target self-diagnostic result for the target DC controller based on the auxiliary diagnostic result and the initial diagnostic result.

[0153] In one possible implementation, the acquisition module 402 is further configured to acquire the original self-diagnostic result of the target DC controller, the first anomaly description information of the target DC component, and the second anomaly description information of the target DC controller. The original self-diagnostic result is the self-diagnostic result obtained through the self-diagnostic program of the target DC controller. Based on the original self-diagnostic result, the first anomaly description information, and the second anomaly description information, a reference self-diagnostic result of the target DC controller is determined.

[0154] The diagnostic module 404 is also used to determine the target self-diagnostic result of the target DC controller based on the auxiliary diagnostic result, the initial diagnostic result, and the reference self-diagnostic result.

[0155] It should be noted that the self-diagnostic processing device for DC controllers provided in the above embodiments is only illustrated by the division of the above functional modules during self-diagnosis. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the self-diagnostic processing device for DC controllers provided in the above embodiments and the self-diagnostic processing method embodiments for DC controllers belong to the same concept, and their specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0156] The technical solution provided in this application determines the target self-diagnostic parameter acquisition method, target self-diagnostic parameter processing method, and target self-diagnostic parameter type set when the target DC controller meets the target self-diagnostic conditions. Based on the target self-diagnostic parameter acquisition method, multiple first target self-diagnostic parameters whose parameter types belong to the target self-diagnostic parameter type set are acquired, thereby realizing the acquisition of basic self-diagnostic parameters. The target self-diagnostic parameter processing method is used to process the multiple first target self-diagnostic parameters to obtain multiple second target self-diagnostic parameters and multiple third target self-diagnostic parameters with different self-diagnostic dimensions. Based on the multiple second target self-diagnostic parameters and multiple third target self-diagnostic parameters, the target self-diagnostic result of the target DC controller is determined. Compared with the self-diagnostic results obtained by the self-diagnostic methods in related technologies, the accuracy of the target self-diagnostic result is higher due to the combination of richer data and the adoption of appropriate data processing methods.

[0157] Figure 5This is a schematic diagram of a diagnostic device 500 provided in an embodiment of this application. The diagnostic device 500 can vary significantly due to differences in configuration or performance. It may include one or more Central Processing Units (CPUs) 501 and one or more memories 502. The one or more memories 502 store at least one computer program, which is loaded and executed by the one or more processors 501 to implement the methods provided in the various method embodiments described above. Of course, the diagnostic device 500 may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The diagnostic device 500 may also include other components for implementing device functions, which will not be elaborated upon here.

[0158] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including a computer program that can be executed by a processor to perform the self-diagnostic processing method for a DC controller in the above embodiments. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0159] In an exemplary embodiment, a computer program product or computer program is also provided, which includes program code stored in a computer-readable storage medium. A processor of a computer device reads the program code from the computer-readable storage medium and executes the program code, causing the computer device to perform the self-diagnostic processing method for a DC controller described above.

[0160] In some embodiments, the computer program involved in the present application embodiments may be deployed and executed on a computer device, or executed on multiple computer devices located in one location, or executed on multiple computer devices distributed in multiple locations and interconnected through a communication network. Multiple computer devices distributed in multiple locations and interconnected through a communication network may constitute a blockchain system.

[0161] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0162] The above are merely optional embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A self-diagnostic processing method for a DC controller, characterized in that, The method includes: When the target DC controller of the target DC component meets the target self-diagnostic condition among multiple candidate self-diagnostic conditions, the target self-diagnostic parameter acquisition method and target self-diagnostic parameter processing method corresponding to the target self-diagnostic condition are determined, and the target self-diagnostic parameter type set corresponding to the target DC controller and the target self-diagnostic condition is determined. The target self-diagnostic condition includes target operating environment conditions, target controller conditions and target DC component conditions. Based on the target self-diagnostic parameter acquisition method, multiple first target self-diagnostic parameters whose parameter types belong to the target self-diagnostic parameter type set are acquired. The multiple first target self-diagnostic parameters include multiple first self-diagnostic parameters and multiple second self-diagnostic parameters. The multiple first self-diagnostic parameters are self-diagnostic parameters related to the target DC component, and the multiple second self-diagnostic parameters are self-diagnostic parameters related to the target DC controller. The target self-diagnostic parameter processing method is used to process the plurality of first target self-diagnostic parameters to obtain a plurality of second target self-diagnostic parameters and a plurality of third target self-diagnostic parameters of the target DC controller. The plurality of second target self-diagnostic parameters and the plurality of third target self-diagnostic parameters correspond to different self-diagnostic dimensions. Based on the plurality of second target self-diagnostic parameters and the plurality of third target self-diagnostic parameters, the target self-diagnostic result of the target DC controller is determined, and the target self-diagnostic result is used to indicate whether the target DC controller has a fault.

2. The method according to claim 1, characterized in that, When the target DC controller of the target DC component satisfies the target self-diagnostic condition among multiple candidate self-diagnostic conditions, the method for obtaining the target self-diagnostic parameters and the method for processing the target self-diagnostic parameters corresponding to the target self-diagnostic condition are determined, and the set of target self-diagnostic parameter types corresponding to the target DC controller and the target self-diagnostic condition is determined, including: If the target DC controller of the target DC component satisfies the target self-diagnostic condition among multiple candidate self-diagnostic conditions, the condition satisfaction degree of the target DC controller is determined, and the condition satisfaction degree is used to indicate the extent to which the target DC controller exceeds the target self-diagnostic condition; Based on the target self-diagnosis conditions and the degree to which the conditions are met, the method for obtaining the target self-diagnosis parameters and the method for processing the target self-diagnosis parameters are determined. Based on the degree to which the conditions are met, the controller type of the target DC controller, and the target self-diagnostic conditions, the set of target self-diagnostic parameter types is determined.

3. The method according to claim 2, characterized in that, The step of determining the degree to which the target DC controller satisfies the target self-diagnostic condition among multiple candidate self-diagnostic conditions, when the target DC controller of the target DC component satisfies the target self-diagnostic condition, includes: If the target DC controller of the target DC component meets the target self-diagnostic condition among multiple candidate self-diagnostic conditions, the degree of condition satisfaction is determined based on the operating environment parameters of the target DC controller and the environmental condition parameter threshold corresponding to the target operating environment condition, the controller parameters of the target DC controller and the controller condition parameter threshold corresponding to the target controller condition, and the DC component parameters of the target DC component and the component condition parameter threshold corresponding to the target DC component condition. The operating environment parameters are used to match the target operating environment conditions, the controller parameters are used to match the target controller conditions, and the DC component parameters are used to match the target DC component conditions.

4. The method according to claim 2, characterized in that, The step of determining the target self-diagnostic parameter acquisition method and the target self-diagnostic parameter processing method based on the target self-diagnostic conditions and the degree to which the conditions are met includes: The target operating environment conditions, target controller conditions, and target DC component conditions are transformed to obtain the condition description text of the target self-diagnostic conditions; Based on the condition description text and the degree to which the condition is met, the controller state and target self-diagnosis mode of the target DC controller are determined; Based on the controller state and the target self-diagnosis mode, the method for obtaining the target self-diagnosis parameters and the method for processing the target self-diagnosis parameters are determined.

5. The method according to claim 1, characterized in that, The method for obtaining target self-diagnostic parameters, which acquires multiple first target self-diagnostic parameters whose parameter types belong to the target self-diagnostic parameter type set, includes: Determine the target parameter source and parameter acquisition frequency indicated by the target self-diagnostic parameter acquisition method; Multiple initial self-diagnostic parameters are acquired from the target parameter source according to the parameter acquisition frequency. The output diagnostic parameters whose parameter type belongs to the target self-diagnostic parameter type set among the plurality of initial self-diagnostic parameters are determined as target self-diagnostic parameters to obtain the plurality of first target self-diagnostic parameters.

6. The method according to claim 1, characterized in that, The target self-diagnostic parameter processing method includes a first self-diagnostic parameter processing method, a second self-diagnostic parameter processing method, and a third self-diagnostic parameter processing method. The step of processing the plurality of first target self-diagnostic parameters using the target self-diagnostic parameter processing method to obtain a plurality of second target self-diagnostic parameters and a plurality of third target self-diagnostic parameters of the target DC controller includes: The first self-diagnostic parameter processing method is used to process the multiple first self-diagnostic parameters among the multiple first target self-diagnostic parameters to obtain multiple component self-diagnostic processing parameters of the target DC component; The second self-diagnostic parameter processing method is used to process the multiple second self-diagnostic parameters among the multiple first target self-diagnostic parameters to obtain multiple controller self-diagnostic processing parameters of the target DC controller; The third self-diagnostic parameter processing method is used to process the plurality of first self-diagnostic parameters and the plurality of second self-diagnostic parameters to determine a plurality of fusion self-diagnostic processing parameters; Based on the multiple component self-diagnostic processing parameters and the multiple fused self-diagnostic processing parameters, multiple second target self-diagnostic parameters of the target DC controller are determined; Based on the multiple controller self-diagnostic processing parameters and the multiple fused self-diagnostic processing parameters, multiple third target self-diagnostic parameters of the target DC controller are determined.

7. The method according to claim 6, characterized in that, The determination of multiple second target self-diagnostic parameters of the target DC controller based on the multiple component self-diagnostic processing parameters and the multiple fused self-diagnostic processing parameters includes: Based on the multiple component self-diagnosis processing parameters, multiple first parameter correction coefficients are determined, and each first parameter correction coefficient corresponds to a component self-diagnosis processing parameter. Based on the plurality of first parameter correction coefficients and the plurality of fusion self-diagnostic processing parameters, the plurality of second target self-diagnostic parameters are obtained, wherein the number of the plurality of first parameter correction coefficients is the same as the number of the plurality of fusion self-diagnostic processing parameters; The determination of multiple third target self-diagnostic parameters of the target DC controller based on the multiple controller self-diagnostic processing parameters and the multiple fused self-diagnostic processing parameters includes: Based on the multiple controller self-diagnostic processing parameters, multiple second parameter correction coefficients are determined, and each second parameter correction coefficient corresponds to one controller self-diagnostic processing parameter. Based on the plurality of second parameter correction coefficients and the plurality of fusion self-diagnostic processing parameters, the plurality of third target self-diagnostic parameters are obtained, wherein the number of the plurality of second parameter correction coefficients is the same as the number of the plurality of fusion self-diagnostic processing parameters.

8. The method according to any one of claims 1-7, characterized in that, The determination of the target self-diagnostic result of the target DC controller based on the plurality of second target self-diagnostic parameters and the plurality of third target self-diagnostic parameters includes: Based on the multiple second target self-diagnostic parameters, the auxiliary diagnostic results of the target DC controller are determined; Based on the aforementioned multiple third-target self-diagnostic parameters, the initial diagnostic result is determined; Based on the auxiliary diagnostic results and the initial diagnostic results, the target self-diagnostic results of the target DC controller are determined.

9. The method according to claim 8, characterized in that, Before determining the target self-diagnostic result of the target DC controller based on the auxiliary diagnostic result and the initial diagnostic result, the method further includes: The original self-diagnostic result of the target DC controller, the first abnormality description information of the target DC component, and the second abnormality description information of the target DC controller are obtained. The original self-diagnostic result is the self-diagnostic result obtained through the self-diagnostic program of the target DC controller. Based on the original self-diagnostic results, the first anomaly description information, and the second anomaly description information, a reference self-diagnostic result for the target DC controller is determined. The determination of the target self-diagnostic result of the target DC controller based on the auxiliary diagnostic result and the initial diagnostic result includes: Based on the auxiliary diagnostic results, the initial diagnostic results, and the reference self-diagnostic results, the target self-diagnostic result of the target DC controller is determined.

10. A self-diagnostic processing device for a DC controller, characterized in that, The device includes: The determination module is used to determine the target self-diagnostic parameter acquisition method and target self-diagnostic parameter processing method corresponding to the target self-diagnostic condition when the target DC controller of the target DC component meets the target self-diagnostic condition among multiple candidate self-diagnostic conditions, and to determine the target self-diagnostic parameter type set corresponding to the target DC controller and the target self-diagnostic condition. The target self-diagnostic condition includes target operating environment conditions, target controller conditions and target DC component conditions. The acquisition module is used to acquire multiple first target self-diagnostic parameters whose parameter types belong to the target self-diagnostic parameter type set based on the target self-diagnostic parameter acquisition method. The multiple first target self-diagnostic parameters include multiple first self-diagnostic parameters and multiple second self-diagnostic parameters. The multiple first self-diagnostic parameters are self-diagnostic parameters related to the target DC component, and the multiple second self-diagnostic parameters are self-diagnostic parameters related to the target DC controller. The processing module is used to process the plurality of first target self-diagnostic parameters using the target self-diagnostic parameter processing method to obtain a plurality of second target self-diagnostic parameters and a plurality of third target self-diagnostic parameters of the target DC controller, wherein the plurality of second target self-diagnostic parameters and the plurality of third target self-diagnostic parameters correspond to different self-diagnostic dimensions; The diagnostic module is used to determine the target self-diagnostic result of the target DC controller based on the plurality of second target self-diagnostic parameters and the plurality of third target self-diagnostic parameters. The target self-diagnostic result is used to indicate whether the target DC controller has a fault.

Images