Fault device control method, electronic device, storage medium and program product

Abstract

The embodiment of the invention provides a control method of fault equipment, electronic equipment, a storage medium and a program product. The method comprises the following steps: acquiring historical fault information in a preset historical time period, a fault category corresponding to the historical fault information, and acquiring current fault information of to-be-controlled equipment; wherein the fault information represents the condition of a fault generated in the operation process of the equipment, and the fault category represents whether the fault is misjudged; determining target fault information from the historical fault information according to the historical fault information and a fault category corresponding to the historical fault information; determining the fault type of the current fault information according to the target fault information and the current fault information of the to-be-controlled equipment; and performing reset control on the to-be-controlled equipment according to the fault type of the current fault information. The method is used for achieving the effects of determining whether the alarm of the transformer substation is misjudged or not and remotely resetting the protection measurement and control device of the transformer substation.

Description

Technical Field

[0001] The present application relates to the field of device control, and in particular to a control method for a faulty device, an electronic device, a storage medium, and a program product. Background Art

[0002] Substations are the locations in power systems where electrical energy is received and distributed. They are equipped with a large number of devices used to transmit and distribute electrical energy. During power transmission, if an equipment anomaly in the substation triggers the protection and control devices, the devices enter an alarm state and alert the power dispatch station. In this alarm state, the devices no longer monitor substation equipment anomalies or send additional alarm signals to the power dispatch station. Staff must visit the substation to confirm the cause of the alarm and manually reset the protection and control devices to restore their monitoring functions.

[0003] However, due to the large number of equipment in the substation, the protection and measurement and control devices may misjudge the monitoring of abnormalities. If a misjudgment occurs, staff still need to go to the substation to confirm and restore, which is time-consuming and labor-intensive. Moreover, since the protection and measurement and control devices no longer monitor the equipment in the substation after entering the alarm state, it is difficult for staff to grasp the actual status of the substation after the misjudgment.

[0004] Therefore, how to accurately determine whether the substation alarm is a misjudgment and remotely reset the substation protection and control device has become an urgent problem to be solved. Summary of the Invention

[0005] The embodiments of the present application provide a control method for faulty equipment, an electronic device, a storage medium, and a program product, which are used to determine whether a substation alarm is misjudged and to remotely restore the substation's protection and measurement and control device.

[0006] In a first aspect, an embodiment of the present application provides a method for controlling a faulty device, including:

[0007] Obtain historical fault information within a preset historical time period, the fault category corresponding to the historical fault information, and the current fault information of the device to be controlled; wherein the fault information represents the fault situation generated during the operation of the device, and the fault category represents whether the fault is a false positive;

[0008] determining target fault information from the historical fault information according to the historical fault information and the fault category corresponding to the historical fault information;

[0009] Determine the fault category of the current fault information based on the target fault information and the current fault information of the device to be controlled;

[0010] Perform restoration control on the controlled device according to the fault type of the current fault information.

[0011] In a possible implementation, determining target fault information from the historical fault information according to the historical fault information and the fault category corresponding to the historical fault information includes:

[0012] Preprocessing the historical fault information to obtain preprocessed fault information; wherein the preprocessing includes at least one of missing value supplementation processing and abnormal value screening processing;

[0013] According to the pre-processed fault information and the corresponding fault category, target fault information is determined from the pre-processed fault information.

[0014] In a possible implementation, determining target fault information from the preprocessed fault information according to the preprocessed fault information and the corresponding fault category includes:

[0015] Determine an objective function based on the preprocessed fault information and the corresponding fault category; wherein the objective function represents a computational function that maximizes the geometric interval between the preprocessed fault information and a hyperplane, and the hyperplane represents a decision boundary that divides the preprocessed fault information into mutually exclusive regions according to the fault category;

[0016] According to the objective function, target fault information is determined from the preprocessed fault information.

[0017] In a possible implementation, determining an objective function based on the preprocessed fault information and the corresponding fault category includes:

[0018] Determine a penalty factor based on the preprocessed fault information; wherein the penalty factor represents the intensity of the penalty for the classification error;

[0019] The objective function is determined based on the penalty factor, the preprocessed fault information, and the corresponding fault category.

[0020] In one possible implementation, the pre-processed fault information includes fault content, which is at least one piece of alarm data generated by the device from the time the fault occurs to the time the fault is resolved. Determining a penalty factor based on the pre-processed fault information includes:

[0021] Get the preset number of iterations and iteration step size;

[0022] For each pre-processed fault information, initializing the fault content in the pre-processed fault information to obtain target alarm data corresponding to the pre-processed fault information;

[0023] Determine a target difference value based on each target alarm data; wherein the target difference value represents the difference between the maximum value and the minimum value of all target alarm data;

[0024] The penalty factor is determined based on the target difference, the preset number of iterations and the iteration step size.

[0025] In a possible implementation, determining target fault information from preprocessed fault information according to an objective function includes:

[0026] According to the objective function, a multiplier value of each pre-processed fault information is obtained; wherein the multiplier value represents the size of the geometric interval between the pre-processed fault information and the hyperplane;

[0027] If the multiplier value is greater than a preset multiplier threshold, the pre-processed fault information corresponding to the multiplier value is determined as the target fault information.

[0028] In a possible implementation, determining the fault category of the current fault information according to the target fault information and the current fault information of the device to be controlled includes:

[0029] Determine the fault category corresponding to the target fault information;

[0030] The fault category of the current fault information is determined according to the target fault information, the fault category corresponding to the target fault information, the multiplier value corresponding to the target fault information, and the current fault information of the device to be controlled.

[0031] In one possible implementation, determining the fault category of the current fault information according to the target fault information, the fault category corresponding to the target fault information, the multiplier value corresponding to the target fault information, and the current fault information of the device to be controlled includes:

[0032] Determine a decision function based on target fault information, a fault category corresponding to the target fault information, and a multiplier value corresponding to the target fault information; wherein the decision function is used to determine the fault category of the fault information based on the fault information;

[0033] Determine the fault category of the current fault information based on the fault information of the device to be controlled and the decision function.

[0034] In a second aspect, an embodiment of the present application provides a control device for a faulty device, comprising:

[0035] An acquisition unit is configured to acquire historical fault information within a preset historical time period, the fault category corresponding to the historical fault information, and current fault information of the device to be controlled; wherein the fault information represents the condition of the fault generated during the operation of the device, and the fault category represents whether the fault is a false positive;

[0036] a first determining unit, configured to determine target fault information from the historical fault information according to the historical fault information and the fault category corresponding to the historical fault information;

[0037] A second determining unit is configured to determine a fault category of the current fault information based on the target fault information and the current fault information of the device to be controlled;

[0038] The restoration unit is used to perform restoration control on the device to be controlled according to the fault type of the current fault information. In a third aspect, an embodiment of the present application provides a control device for a faulty device, comprising: a memory, a processor;

[0039] The memory stores computer-executable instructions;

[0040] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0041] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the above first aspect and / or various possible implementations of the first aspect.

[0042] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0043] The control method, electronic device, storage medium and program product of the faulty equipment provided in the embodiments of the present application obtain historical fault information, fault categories of the historical fault information, and current fault information of the equipment to be controlled within a preset time period, and determine multiple target fault information from the historical fault information according to the historical fault information and the fault categories corresponding to the historical fault information, and determine the fault category of the current fault information according to the multiple target fault information and the current fault information of the equipment to be controlled, and control whether the equipment to be controlled is restored according to the fault category of the current fault information, thereby achieving rapid and accurate judgment on whether the current fault information of the equipment to be controlled is a misjudgment, and controlling the restoration of the equipment to be controlled according to the obtained fault category, thereby reducing waste of human resources and improving the efficiency of responding to equipment failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0045] Figure 1A flowchart of a method for controlling a faulty device provided by an embodiment of the present disclosure;

[0046] Figure 2 A flowchart of a method for controlling a faulty device provided by an embodiment of the present disclosure;

[0047] Figure 3 A structural block diagram of a control device for a faulty device provided in an embodiment of the present disclosure;

[0048] Figure 4 A structural block diagram of a control device for a faulty device provided in an embodiment of the present disclosure;

[0049] Figure 5 A structural block diagram of an electronic device provided in an embodiment of the present disclosure;

[0050] Figure 6 It is a block diagram of an electronic device according to an exemplary embodiment.

[0051] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0052] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0053] First, let’s explain the terms involved in this application:

[0054] Hyperplane: In n-dimensional space, a hyperplane is an (n-1)-dimensional subspace. For example, in two-dimensional space, a hyperplane is a straight line. In three-dimensional space, a hyperplane is a plane. The hyperplane is responsible for demarcating the feature space, allowing data points to be correctly classified.

[0055] Decision Boundary: All points on one side of the decision boundary are classified as belonging to one class, and all points on the other side are classified as belonging to the other class. If the decision surface is a hyperplane, then the classification problem is linear and the classes are linearly separable.

[0056] Gaussian function: An exponential function that is concentrated in the center and falls off gently on both sides and is symmetrical.

[0057] Decision function: A decision function is a mathematical rule used to map input data (such as feature vectors) to output results (such as class labels or predicted values). It is essentially the core expression of the model and achieves the decision goal by selecting the optimal model from the hypothesis space.

[0058] Cosine similarity: Cosine similarity, also known as cosine similarity, evaluates the similarity between two vectors by calculating the cosine of the angle between them. In high-dimensional data space, cosine similarity can effectively measure the similarity between vectors.

[0059] Kernel function: A kernel function is a mathematical tool that converts input data from a low-dimensional space to a high-dimensional space through implicit mapping. Its core value lies in avoiding explicit calculation of nonlinear transformations and completing tasks such as classification and regression in high-dimensional space directly through inner product operations.

[0060] Substations are the locations within power systems that receive and distribute electrical energy. They are equipped with a large number of devices for transmitting electrical energy. With the development of new energy and other technologies, the number of lines connected to substations is increasing, and the probability of equipment failure within substations is also increasing. When equipment within a substation fails, the protection and measurement and control devices used to monitor and protect the equipment will issue an alarm to the power dispatching master station. This alarm state will remain in effect until it is restored, with no further alarms being sent to the power dispatching master station. During this period, staff at the power dispatching master station will lose visibility into the substation's operations, making it difficult for them to respond promptly if other fault information is present. Furthermore, when equipment failures are misdiagnosed, staff still need to confirm and manually restore the fault, which is not only time-consuming but also consumes significant manpower and material resources.

[0061] Currently, determining whether a device failure is a misjudgment and restoring the device's alarm status require manual on-site visits, which is inefficient and costly, making it difficult to cope with the development of the power system.

[0062] The control method for faulty equipment, electronic equipment, storage medium and program product provided in this application are intended to solve the above problems in the prior art.

[0063] The application scenario of this application is the fault information classification of substation equipment and the remote restoration of the alarm status of substation equipment. It is specifically used to determine the target fault information from the historical fault information based on the historical fault information and fault category within a preset historical time period, and the current fault information of the equipment to be controlled, and determine the fault category of the current fault information based on the target fault information and the current fault information of the equipment to be controlled, and perform corresponding control according to the fault category.

[0064] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0065] Figure 1 A flowchart of a method for controlling a faulty device provided in an embodiment of the present disclosure is provided. The method can be executed by a control device of the faulty device.

[0066] like Figure 1 As shown, the method includes the following steps:

[0067] S101. Obtain historical fault information within a preset historical time period, the fault category corresponding to the historical fault information, and obtain current fault information of the device to be controlled; wherein the fault information represents the fault situation generated by the device during operation, and the fault category represents whether the fault is a misjudgment.

[0068] Exemplarily, historical fault information for all substation equipment within a preset historical time period is obtained, as well as current fault information for the currently faulted device to be controlled. Fault information represents the fault conditions that occurred during the operation of the equipment and may include the faulty device, fault details, and fault cause. The controlled device refers to the operating equipment in the substation, and may include power supply equipment, protection and measurement and control equipment, etc. The faulty device represents the device where the fault occurred. Each substation device has a one-to-one correspondence with a preset device number. The faulty device is the device number of the device where the fault occurred. For example, if the fault occurred in a protection device, the faulty device is the device number of the protection device. The fault content represents the specific content of the fault generated by the device. After a fault occurs, the device will periodically generate and upload alarm data at a preset time interval. The alarm data is a string representing the specific content of the fault. For historical fault information, the fault content is at least one piece of alarm data generated by the device from the time the fault occurs to the time the fault condition is resolved after personnel have addressed it. For current fault information, the fault content is at least one piece of alarm data issued by the device from the time the fault occurs to the time the fault information is acquired. The fault cause is automatically generated by the device when a fault occurs. The fault cause represents the cause of the fault. The fault cause corresponds to the preset cause number one by one. For example, if the fault cause is that the preset value is unreasonable, the fault cause is the cause number corresponding to the unreasonable preset value.

[0069] Obtain the fault category corresponding to the historical fault information. The fault category is the category of historical fault information obtained after staff processing. The fault category indicates whether the device fault is a false positive. If the device fault is a false positive, remote restoration can be performed. If it is not a false positive, on-site staff intervention is required.

[0070] S102: Determine target fault information from the historical fault information according to the historical fault information and the fault category corresponding to the historical fault information.

[0071] Exemplarily, target fault information is determined from the historical fault information based on historical fault information and the fault category corresponding to the historical fault information. For example, for a certain fault category, the historical fault information for that fault category is determined, and the fault device and fault cause of the historical fault information are determined. If there are multiple historical fault information pieces corresponding to the same fault device and fault cause, the frequency of occurrence of historical fault information with the same fault device and fault cause in all historical fault information for that fault category is determined, and historical fault information with an occurrence frequency exceeding a preset frequency threshold is determined as the target fault information for that fault category. For example, if historical fault information with a fault category of misjudgment has multiple historical fault information pieces with the same fault cause and fault device, and the frequency of occurrence of historical fault information with the same fault device and fault cause in all historical fault information for that fault category is greater than a preset frequency threshold, then that historical fault information is determined as the target fault information.

[0072] S103: Determine the fault category of the current fault information according to the target fault information and the current fault information of the device to be controlled.

[0073] Exemplarily, after obtaining multiple different target fault information, the fault category of the current fault information is determined based on the target fault information and the current fault information of the device to be controlled. For example, the cosine similarity between each target fault information and the current fault information of the device to be controlled can be calculated to obtain the cosine similarity corresponding to each target fault information. The fault category of the target fault information with the highest cosine similarity is determined as the fault category of the current fault information.

[0074] S104: Perform restoration control on the device to be controlled according to the fault type of the current fault information.

[0075] For example, according to the fault category of the current fault information, the controlled device is controlled accordingly; if the fault category of the current fault information is a misjudgment, remote restoration control is performed on the controlled device; if the fault category of the current fault information is not a misjudgment, the staff will go to the site to handle the fault of the equipment and restore it after the processing is completed.

[0076] The control method, electronic device, storage medium and program product of the faulty equipment provided in the embodiments of the present application obtain historical fault information, fault categories of the historical fault information, and current fault information of the equipment to be controlled within a preset time period, and determine multiple target fault information from the historical fault information according to the historical fault information and the fault categories corresponding to the historical fault information, and determine the fault category of the current fault information according to the multiple target fault information and the current fault information of the equipment to be controlled, and control whether the equipment to be controlled is restored according to the fault category of the current fault information, thereby achieving rapid and accurate judgment on whether the current fault information of the equipment to be controlled is a misjudgment, and controlling the restoration of the equipment to be controlled according to the obtained fault category, thereby reducing waste of human resources and improving the efficiency of responding to equipment failures.

[0077] Figure 2 A flowchart of a method for controlling a faulty device provided in an embodiment of the present disclosure.

[0078] In this embodiment, target fault information is determined from the historical fault information based on the historical fault information and the fault category corresponding to the historical fault information, including: preprocessing the historical fault information to obtain preprocessed fault information; wherein the preprocessing includes at least one of missing value supplementation processing and abnormal value screening processing; and determining the target fault information from the preprocessed fault information based on the preprocessed fault information and the corresponding fault category.

[0079] like Figure 2 As shown, the method includes the following steps:

[0080] S201. Obtain historical fault information within a preset historical time period, the fault category corresponding to the historical fault information, and obtain current fault information of the device to be controlled; wherein the fault information represents the fault situation generated by the device during operation, and the fault category represents whether the fault is a misjudgment.

[0081] For example, this step may refer to the above-mentioned step S101 and will not be described in detail.

[0082] S202 : Preprocess the historical fault information to obtain preprocessed fault information; wherein the preprocessing includes at least one of missing value supplementation processing and abnormal value screening processing.

[0083] Exemplarily, historical fault information is preprocessed. If there are missing values in the fault content of a certain historical fault information, the missing values are supplemented, which may be supplemented by the average value of the fault content of the historical fault information. The missing values in the fault content may be missing values in the time sequence of the alarm data in the fault content. For example, if the preset alarm data sending cycle is once per minute, but in a certain historical fault information, there is no alarm data for a certain minute or several minutes, the average value of all the alarm data in the fault content of the historical fault information may be used to fill in the missing parts to make the data more complete.

[0084] If there is an abnormal value in a certain historical fault information, the historical fault information with the abnormal value will be screened out. For example, there may be a preset correlation between the fault cause and the faulty device, that is, some fault causes can only be caused by the corresponding device, for example, a knife fault can only be caused by a knife; if there is no correlation between the faulty device and the fault cause of a certain historical fault information, it is determined that there is an abnormal value in the historical fault information, and the historical fault information will be screened out.

[0085] The beneficial effect of this setting is that by filling in missing values and screening out outliers, it effectively solves the integrity and logical consistency problems in historical fault information, making the data more complete and the quality of historical fault information higher, providing high-quality input for subsequent classification, and improving prediction accuracy and system reliability.

[0086] S203 : Determine target fault information from the preprocessed fault information according to the preprocessed fault information and the corresponding fault category.

[0087] Exemplarily, target fault information is determined from the preprocessed fault information based on the fault category corresponding to the preprocessed fault information. For example, for a certain fault category, the preprocessed fault information of that fault category is determined, and the fault device and fault cause of the preprocessed fault information are determined. If there is multiple pieces of preprocessed fault information corresponding to the same fault device and fault cause, the frequency of occurrence of preprocessed fault information with the same fault device and fault cause in all preprocessed fault information of that fault category is determined, and the preprocessed fault information with an occurrence frequency exceeding a preset frequency threshold is determined as the target fault information of that fault category. For example, if, among preprocessed fault information with a fault category of misjudgment, there are multiple pieces of preprocessed fault information with the same fault cause and fault device, and the frequency of occurrence of preprocessed fault information with the same fault device and fault cause in all preprocessed fault information of that fault category is greater than a preset frequency threshold, then the preprocessed fault information is determined as the target fault information.

[0088] The beneficial effect of this setting is that by determining the target fault information from the pre-processed fault information, it is possible to focus on the key faulty equipment and fault causes, thereby improving the accuracy of classification.

[0089] In this embodiment, target fault information is determined from the preprocessed fault information based on the preprocessed fault information and the corresponding fault category, including: determining an objective function based on the preprocessed fault information and the corresponding fault category; wherein the objective function represents a computational function that maximizes the geometric interval between the preprocessed fault information and a hyperplane, and the hyperplane represents a decision boundary that divides the preprocessed fault information into mutually exclusive regions according to the fault category; and determining the target fault information from the preprocessed fault information based on the objective function.

[0090] Specifically, an objective function is determined based on the preprocessed fault information and the corresponding fault category. For example, a preset penalty factor and mapping function may be obtained. The preset penalty factor is used to control the tolerance for classification errors. A larger penalty factor value indicates a stricter classification, while a smaller penalty factor value indicates a looser classification. The preset mapping function is used to map the preprocessed fault information into a high-dimensional space.

[0091] The objective function is determined based on a preset penalty factor, a mapping function, preprocessed fault information, and the corresponding fault category. The objective function represents a computational function that maximizes the geometric separation between the preprocessed fault information and the hyperplane. That is, the objective function can be used to calculate the preprocessed fault information with the largest geometric separation from the hyperplane. The hyperplane represents the decision boundary that divides the preprocessed fault information into mutually exclusive regions based on fault category. That is, fault information on one side of the hyperplane is considered a misclassification, while fault information on the other side of the hyperplane is considered a valid misclassification.

[0092] The objective function to be determined can be, for example:

[0093]

[0094]

[0095] in, is the normal vector of the hyperplane, The smaller the modulus, the larger the geometric interval; is the intercept of the hyperplane equation, which determines the translation of the geometric position of the hyperplane. The value of needs to ensure that the geometric interval is symmetric about the hyperplane, so as to maximize the classification interval on each side. The classification interval represents the sum of the maximum geometric intervals on each side of the hyperplane. is the number of fault information after preprocessing, is the position in the pre-processed fault information; The value obtained by passing the pre-processed fault information through the mapping function, that is, the value obtained by inputting the pre-processed fault information into the mapping function, To be the first The pre-processed fault information is input into the mapping function and the value is obtained; is the fault type of the pre-processed fault information. If it is a misjudgment, then Take 1, if it is not a misjudgment, Take -1, For the Fault category of the pre-processed fault information; For the A slack variable of fault information, which represents the degree of violation of the classification interval by the pre-processed fault information; The value range is greater than or equal to 0; is a preset penalty factor that controls the penalty intensity of the function on the pre-processed fault information of misclassification. The larger it is, the lower the tolerance to misclassified fault information after preprocessing, and the more complex the hyperplane is; The smaller the value, the greater the tolerance to the fault information after misclassification preprocessing, and the simpler the hyperplane. This formula represents that the objective function is under the constraint condition When , solve the function to get the minimum and .

[0096] The beneficial effect of this setting is that by using the penalty factor in the objective function to control the degree of penalty for misclassified preprocessed fault samples, and using the mapping function to map the preprocessed fault information to a high-dimensional space, the flexibility and robustness of the fault information classification are improved, which can adapt to the needs of different scenarios, enable the classification to cope with a variety of different complex scenarios, and improve the classification efficiency and accuracy.

[0097] In this embodiment, an objective function is determined based on the preprocessed fault information and the corresponding fault category, including: determining a penalty factor based on the preprocessed fault information; wherein the penalty factor represents the intensity of the penalty for the classification error; and determining the objective function based on the penalty factor, the preprocessed fault information, and the corresponding fault category.

[0098] Specifically, the penalty factor is determined based on the preprocessed fault information. For example, a sequence of penalty factors to be determined and a function to be determined may be pre-set, where the function to be determined is the target function for which the penalty factor has not yet been determined. The preprocessed fault information is divided into a training set and a test set in a ratio of seven to three. The training set and the function to be determined are used to traverse the values in the sequence of penalty factors to be determined, and a classification decision function corresponding to each value is obtained. The decision function is then verified using the test set to obtain the accuracy corresponding to each value in the sequence of penalty factors to be determined. The sequence value in the sequence of penalty factors to be determined with the highest accuracy is determined as the penalty factor.

[0099] After the penalty factor is determined, the objective function is determined based on the penalty factor, all pre-processed fault information, and the corresponding fault category.

[0100] The beneficial effect of this setting is that by dividing the preprocessed fault information and verifying the decision function corresponding to the numerical value in the penalty factor sequence to be determined, the numerical value with the highest accuracy is determined as the penalty factor, which can effectively reduce the deviation caused by improper selection of the penalty factor, select a penalty factor with stronger generalization ability, and use all the preprocessed fault information and the corresponding fault category to participate in the determination of the objective function, so that the objective function can classify subsequent fault information more accurately.

[0101] In this embodiment, the preprocessed fault information includes fault content, which is at least one alarm data generated by the device from the time the fault occurs to the time the fault is eliminated; determining a penalty factor based on the preprocessed fault information, including: obtaining a preset number of iterations and an iteration step; for each preprocessed fault information, initializing the fault content in the preprocessed fault information to obtain target alarm data corresponding to the preprocessed fault information; determining a target difference based on each target alarm data; wherein the target difference represents the difference between the maximum value and the minimum value of all target alarm data; and determining the penalty factor based on the target difference, the preset number of iterations, and the iteration step.

[0102] Specifically, a preset number of iterations and an iteration step size are obtained, wherein the number of iterations represents the number of times the penalty factor needs to be iterated, and the iteration step size represents the magnitude of each iteration.

[0103] Obtain preset adjustment parameters, which are used to optimize the calculation process of data initialization and improve the target alarm information. For each pre-processed fault information, determine the number of alarm data in the fault content of the fault information, the maximum value of the alarm data, and the average value of the alarm data. Based on the number of alarm data, the maximum value of the alarm data, and the average value of the alarm data, initialize the fault content in the pre-processed fault information based on a preset initialization formula to obtain the target alarm data corresponding to the pre-processed fault information. The preset initialization formula can be, for example:

[0104]

[0105] in, Provide target warning data; The maximum value of the alarm data; The number of alarm data in the fault content of the historical fault information; Characterizes the order in the alarm data, The fault content is Alarm data; It is a preset adjustment parameter used to adjust the size of target alarm data; is the average value of the alarm data in the fault content; this formula indicates that the target alarm data is equal to the maximum value of the alarm data minus the product of the standard deviation of the alarm data and the adjustment parameter.

[0106] After obtaining the target alarm data corresponding to each preprocessed fault information, determine the maximum value of the target alarm data and the minimum value of the target alarm data, and determine the target difference based on the maximum value of the target alarm data and the minimum value of the target alarm data. The target difference is the difference between the maximum value and the minimum value of the target alarm data.

[0107] The penalty factor is determined based on the preset penalty factor iteration formula according to the target difference, the preset number of iterations and the iteration step size.

[0108] The preset penalty factor determination formula may be, for example:

[0109]

[0110] in, Represents the current number of iterations, The number of iterations for the next iteration, the maximum number of iterations is the preset number of iterations, Characterization The penalty factor for the iteration, Characterization The penalty factor of the iteration; when When the number of iterations reaches the preset value, the iteration is stopped and Determined as penalty factor ; Characterize the iteration step size; Characterize the target difference; Represents the Gaussian function; this formula represents, The penalty factor for the iteration is equal to The penalty factor of the iteration is added to the product of the target difference and the Gaussian function, where the input of the Gaussian function is 0 and , when the formula is the first iteration, is 0.

[0111] The beneficial effect of this setting is that multiple alarm data in each preprocessed fault information are initialized to obtain target alarm data, which can ensure data consistency and obtain target alarm data with good performance. The penalty factor is iterated according to the target alarm data, which can make the performance of the penalty factor better, balance the accuracy of classification and the complexity of the classification process, and ensure accurate classification effect while improving fault tolerance.

[0112] In this embodiment, target fault information is determined from the preprocessed fault information based on the objective function, including: obtaining a multiplier value for each piece of preprocessed fault information based on the objective function; wherein the multiplier value represents the size of the geometric interval between the preprocessed fault information and the hyperplane; if the multiplier value is greater than a preset multiplier threshold, then determining the preprocessed fault information corresponding to the multiplier value as the target fault information.

[0113] Specifically, the objective function is solved according to the objective function. For example, the Lagrange multiplier method can be used to solve the objective function and solve the minimum and Convert to the dual problem and solve the Lagrange multiplier , solving for the multiplier value of each preprocessed fault information. The multiplier value is the size of the Lagrange multiplier, which represents the size of the geometric interval between the preprocessed fault information and the hyperplane. If the multiplier value is greater than 0, the preprocessed fault information corresponding to the multiplier value is the fault information located at the boundary of the geometric interval; if the multiplier value is equal to 0, the preprocessed fault information corresponding to the multiplier value has no effect on the classification.

[0114] A multiplier value greater than a preset multiplier threshold is determined, and the preprocessed fault information corresponding to the multiplier value greater than the preset multiplier threshold is determined as target fault information. The preset multiplier threshold is a value greater than or equal to 0, and the preset multiplier threshold can be, for example, a value such as 0 or 1.

[0115] The beneficial effect of this setting is that the multiplier value screening mechanism based on the Lagrange multiplier method, combined with the dual problem transformation, realizes efficient classification of fault information. It can quickly and accurately determine the target fault information from the preprocessed fault information. The introduction of the multiplier threshold can also be more adaptable to data with more dimensions such as preprocessed fault information, thereby improving the accuracy of classification.

[0116] S204: Determine the fault category corresponding to the target fault information.

[0117] Exemplarily, the fault category corresponding to the target fault information is determined from all fault categories.

[0118] The beneficial effect of such a setting is that the fault category corresponding to the target fault information can be determined, which facilitates the subsequent classification of the current fault information according to the fault category of the target fault information.

[0119] S205 : Determine the fault category of the current fault information according to the target fault information, the fault category corresponding to the target fault information, the multiplier value corresponding to the target fault information, and the current fault information of the device to be controlled.

[0120] Exemplarily, the fault category of the current fault information is determined based on the target fault information, the fault category corresponding to the target fault information, the multiplier value corresponding to the target fault information, and the current fault information of the device to be controlled. For example, a decision function may be determined based on the target fault information, the fault category corresponding to the target fault information, and the multiplier value corresponding to the target fault information. The fault category of the current fault information is determined based on the current fault information of the device to be controlled and based on a preset decision function. The decision function is used to determine the fault category of the fault information based on the fault information.

[0121] The beneficial effect of this setting is that

[0122] In this embodiment, the fault category of the current fault information is determined based on the target fault information, the fault category corresponding to the target fault information, the multiplier value corresponding to the target fault information, and the current fault information of the device to be controlled, including: determining a decision function based on the target fault information, the fault category corresponding to the target fault information, and the multiplier value corresponding to the target fault information; wherein the decision function is used to determine the fault category of the fault information based on the fault information; and determining the fault category of the current fault information based on the fault information of the device to be controlled and the decision function.

[0123] Specifically, a preset kernel function is obtained. The preset kernel function is used to map low-dimensional data to a high-dimensional space to achieve nonlinear classification. A decision function is determined based on the target fault information, the fault category corresponding to the target fault information, the preset kernel function, and the multiplier value corresponding to the target fault information. The decision function can be, for example:

[0124]

[0125] in, Represents the decision function, the input of the decision function is , that is, current fault information; The function is a symbolic function; is the number of target fault information, is the order in the target fault information; is the multiplier value, For the The multiplier value of each target fault information; is the fault category of the target fault information. If it is a misjudgment, then Take 1, if it is not a misjudgment, Take -1, For the Fault category of target fault information; is a preset kernel function, for example, it can be a Gaussian kernel function; is the intercept, which is derived from the multiplier value of the target fault information and the constraints of the objective function. This formula indicates that the decision function is the product of the multiplier value of each target fault information, the fault category of the target fault information, and the result of the kernel function input of the target fault information and the current fault information, plus the intercept, and then input into the sign function to obtain the result.

[0126] The fault information of the device to be controlled is input into the decision function to obtain the value of the decision function, and the fault category of the current fault information is determined based on the value. For example, if the value of the decision function is 1, the fault category of the current fault information is determined to be a false positive.

[0127] The beneficial effect of this setting is that by using the kernel function, the fault information in the low-dimensional space is mapped to the high-dimensional space, so that the originally linearly inseparable fault features can be linearly separable in the high-dimensional space, and the accurate classification of complex fault modes can be achieved. By using the decision function determined according to a variety of information to classify the fault information, the efficiency, accuracy and robustness of the fault classification can be achieved, which is suitable for real-time fault classification in complex scenarios such as power grid transmission.

[0128] S206: Perform restoration control on the device to be controlled according to the fault type of the current fault information.

[0129] For example, this step may refer to the above-mentioned step S104 and will not be described in detail.

[0130] The control method, electronic device, storage medium and program product of the faulty equipment provided in the embodiments of the present application obtain historical fault information, fault categories of the historical fault information, and current fault information of the equipment to be controlled within a preset time period, and determine multiple target fault information from the historical fault information according to the historical fault information and the fault categories corresponding to the historical fault information, and determine the fault category of the current fault information according to the multiple target fault information and the current fault information of the equipment to be controlled, and control whether the equipment to be controlled is restored according to the fault category of the current fault information, thereby achieving rapid and accurate judgment on whether the current fault information of the equipment to be controlled is a misjudgment, and controlling the restoration of the equipment to be controlled according to the obtained fault category, thereby reducing waste of human resources and improving the efficiency of responding to equipment failures.

[0131] Figure 3 This is a structural block diagram of a control device for a faulty device provided in an embodiment of the present disclosure.

[0132] For ease of explanation, only the parts related to the embodiments of the present disclosure are shown. Figure 3 The control device 300 for the faulty equipment includes: an acquisition unit 301 , a first determination unit 302 , a second determination unit 303 and a restoration unit 304 .

[0133] The acquisition unit 301 is configured to acquire historical fault information within a preset historical time period, the fault category corresponding to the historical fault information, and current fault information of the device to be controlled; wherein the fault information represents the fault condition generated during the operation of the device, and the fault category represents whether the fault is a false positive;

[0134] A first determining unit 302 is configured to determine target fault information from the historical fault information based on the historical fault information and the fault category corresponding to the historical fault information;

[0135] The second determining unit 303 is configured to determine the fault category of the current fault information based on the target fault information and the current fault information of the device to be controlled;

[0136] The restoration unit 304 is configured to perform restoration control on the device to be controlled according to the fault type of the current fault information.

[0137] Figure 4 This is a structural block diagram of a control device for a faulty device provided in an embodiment of the present disclosure.

[0138] exist Figure 3 Based on the embodiment shown, Figure 4 As shown, the first determining unit 302 includes a pre-processing module 3021 and a target module 3022 .

[0139] A preprocessing module 3021 is used to preprocess historical fault information to obtain preprocessed fault information; wherein the preprocessing includes at least one of missing value supplementation processing and abnormal value screening processing;

[0140] The target module 3022 is configured to determine target fault information from the pre-processed fault information according to the pre-processed fault information and the corresponding fault category.

[0141] In one example, the target module 3022 includes:

[0142] A function submodule is configured to determine an objective function based on the preprocessed fault information and the corresponding fault category. The objective function represents a computational function that maximizes the geometric separation between the preprocessed fault information and a hyperplane, and the hyperplane represents a decision boundary that divides the preprocessed fault information into mutually exclusive regions according to fault category.

[0143] The target submodule is used to determine target fault information from the preprocessed fault information according to the target function.

[0144] In an example, the function submodule is specifically used for:

[0145] Determine a penalty factor based on the preprocessed fault information; wherein the penalty factor represents the intensity of the penalty for the classification error;

[0146] The objective function is determined based on the penalty factor, the preprocessed fault information, and the corresponding fault category.

[0147] In an example, the function submodule is specifically used for:

[0148] Get the preset number of iterations and iteration step size;

[0149] For each pre-processed fault information, initializing the fault content in the pre-processed fault information to obtain target alarm data corresponding to the pre-processed fault information;

[0150] Determine a target difference value based on each target alarm data; wherein the target difference value represents the difference between the maximum value and the minimum value of all target alarm data;

[0151] The penalty factor is determined based on the target difference, the preset number of iterations and the iteration step size.

[0152] In one example, the target submodule is specifically used for:

[0153] According to the objective function, a multiplier value of each pre-processed fault information is obtained; wherein the multiplier value represents the size of the geometric interval between the pre-processed fault information and the hyperplane;

[0154] If the multiplier value is greater than a preset multiplier threshold, the pre-processed fault information corresponding to the multiplier value is determined as the target fault information.

[0155] In one example, the second determining unit 303 includes:

[0156] The first category module is used to determine the fault category corresponding to the target fault information;

[0157] The second category module is used to determine the fault category of the current fault information according to the target fault information, the fault category corresponding to the target fault information, the multiplier value corresponding to the target fault information, and the current fault information of the device to be controlled.

[0158] In one example, the second category modules include:

[0159] A decision function submodule is used to determine a decision function based on target fault information, a fault category corresponding to the target fault information, and a multiplier value corresponding to the target fault information; wherein the decision function is used to determine the fault category of the fault information based on the fault information;

[0160] The category submodule is used to determine the fault category of the current fault information based on the fault information of the device to be controlled and the decision function.

[0161] Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present disclosure. The electronic device may be a terminal device or a server. Figure 5 As shown, the electronic device 500 includes: at least one processor 502; and a memory 501 communicatively connected to the at least one processor 502; wherein the memory stores instructions that can be executed by the at least one processor 502, and the instructions are executed by the at least one processor 502 to enable the at least one processor 502 to execute the control method of the fault device disclosed in the present invention.

[0162] The electronic device 500 further includes a receiver 503 and a transmitter 504. The receiver 503 is used to receive instructions and data sent by other devices, and the transmitter 504 is used to send instructions and data to external devices.

[0163] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0164] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, which includes: a computer program, the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device executes the solution provided by any of the above embodiments.

[0165] Figure 6 This is a block diagram of an electronic device according to an exemplary embodiment. The device may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0166] Device 600 may include one or more of the following components: a processing component 602 , a memory 604 , a power component 606 , a multimedia component 608 , an audio component 611 , an input / output (I / O) interface 612 , a sensor component 614 , and a communication component 616 .

[0167] The processing component 602 generally controls the overall operation of the device 600, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 602 may include one or more processors 620 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 602 may include one or more modules to facilitate interaction between the processing component 602 and other components. For example, the processing component 602 may include a multimedia module to facilitate interaction between the multimedia component 608 and the processing component 602.

[0168] The memory 604 is configured to store various types of data to support operations on the device 600. Examples of such data include instructions for any application or method operating on the device 600, contact data, phone book data, messages, pictures, videos, etc. The memory 604 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0169] The power supply component 606 provides power to the various components of the device 600. The power supply component 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 600.

[0170] The multimedia component 608 includes a screen that provides an output interface between the device 600 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, it may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensors can not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide action. In some embodiments, the multimedia component 608 includes a front-facing camera and / or a rear-facing camera. When the device 600 is in an operating mode, such as a capture mode or a video mode, the front-facing camera and / or the rear-facing camera can receive external multimedia data. Each front-facing camera and the rear-facing camera can have a fixed optical lens system or have focal length and optical zoom capabilities.

[0171] The audio component 610 is configured to output and / or input audio signals. For example, the audio component 610 includes a microphone (MIC) that is configured to receive external audio signals when the device 600 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 604 or transmitted via the communication component 616. In some embodiments, the audio component 610 also includes a speaker for outputting audio signals.

[0172] I / O interface 612 provides an interface between processing component 602 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0173] The sensor assembly 614 includes one or more sensors for providing various aspects of the status assessment of the device 600. For example, the sensor assembly 614 can detect the open / closed state of the device 600, the relative positioning of components, such as the display and keypad of the device 600. The sensor assembly 614 can also detect changes in the position of the device 600 or a component of the device 600, the presence or absence of user contact with the device 600, the orientation or acceleration / deceleration of the device 600, and temperature changes of the device 600. The sensor assembly 614 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 614 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 may also include an accelerometer, a gyroscope, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0174] The communication component 616 is configured to facilitate wired or wireless communication between the device 600 and other devices. The device 600 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 616 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0175] In an exemplary embodiment, the device 600 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0176] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 604 including instructions, which can be executed by the processor 620 of the device 600 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0177] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of a terminal device, enables the terminal device to execute the above-mentioned control method for a faulty device.

[0178] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0179] It should be further noted that, although the various steps in the flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps may be performed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily to be performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0180] It should be understood that the above-described device embodiments are merely illustrative, and the device of the present application may also be implemented in other ways. For example, the division of units / modules in the above-described embodiments is merely a logical functional division, and actual implementations may employ other division methods. For example, multiple units, modules, or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0181] In addition, unless otherwise specified, the functional units / modules in the various embodiments of the present application may be integrated into a single unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The aforementioned integrated units / modules may be implemented in the form of hardware or software program modules.

[0182] If an integrated unit / module is implemented in hardware, the hardware may be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor may be any appropriate hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC. Unless otherwise specified, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc.

[0183] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk, or optical disk, etc., various media that can store program code.

[0184] In the above embodiments, the description of each embodiment has its own focus. For parts not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0185] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0186] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for controlling a faulty device, characterized in that: include: Obtain historical fault information within a preset historical time period, the fault category corresponding to the historical fault information, and current fault information of the device to be controlled; wherein the fault information represents the fault condition generated during the operation of the device, and the fault category represents whether the fault is a false positive; determining target fault information from the historical fault information according to the historical fault information and the fault category corresponding to the historical fault information; Determining a fault category of the current fault information according to the target fault information and the current fault information of the device to be controlled; Perform restoration control on the device to be controlled according to the fault type of the current fault information.

2. The method according to claim 1, characterized in that Determining target fault information from the historical fault information according to the historical fault information and the fault category corresponding to the historical fault information includes: Preprocessing the historical fault information to obtain preprocessed fault information; wherein the preprocessing includes at least one of missing value supplementation processing and abnormal value screening processing; According to the pre-processed fault information and the corresponding fault category, target fault information is determined from the pre-processed fault information.

3. The method according to claim 2, characterized in that Determining target fault information from the preprocessed fault information according to the preprocessed fault information and the corresponding fault category includes: Determining an objective function based on the preprocessed fault information and the corresponding fault category; wherein the objective function represents a computational function that maximizes a geometric interval between the preprocessed fault information and a hyperplane, and the hyperplane represents a decision boundary that divides the preprocessed fault information into mutually exclusive regions according to the fault category; Target fault information is determined from the pre-processed fault information according to the objective function.

4. The method according to claim 3, characterized in that Determining an objective function based on the pre-processed fault information and the corresponding fault category includes: Determining a penalty factor based on the pre-processed fault information; wherein the penalty factor represents the intensity of the penalty for the classification error; The objective function is determined according to the penalty factor, the pre-processed fault information, and the corresponding fault category.

5. The method according to claim 4, characterized in that The pre-processed fault information includes fault content, which is at least one piece of alarm data generated by the device from the time the fault occurs to the time the fault is eliminated; Determining a penalty factor based on the pre-processed fault information includes: Get the preset number of iterations and iteration step size; For each piece of pre-processed fault information, initializing the fault content in the pre-processed fault information to obtain target alarm data corresponding to the pre-processed fault information; Determine a target difference value based on each of the target alarm data; wherein the target difference value represents the difference between the maximum value and the minimum value of all the target alarm data; The penalty factor is determined according to the target difference, the preset number of iterations and the iteration step size.

6. The method according to claim 3, characterized in that Determining target fault information from the preprocessed fault information according to the objective function includes: According to the objective function, a multiplier value of each of the pre-processed fault information is obtained; wherein the multiplier value represents the size of the geometric interval between the pre-processed fault information and the hyperplane; If the multiplier value is greater than a preset multiplier threshold, the pre-processed fault information corresponding to the multiplier value is determined as target fault information.

7. The method according to claim 6, characterized in that Determining a fault category of the current fault information according to the target fault information and the current fault information of the device to be controlled includes: Determining a fault category corresponding to the target fault information; The fault category of the current fault information is determined according to the target fault information, the fault category corresponding to the target fault information, the multiplier value corresponding to the target fault information, and the current fault information of the device to be controlled.

8. The method according to claim 7, characterized in that Determining the fault category of the current fault information according to the target fault information, the fault category corresponding to the target fault information, the multiplier value corresponding to the target fault information, and the current fault information of the device to be controlled includes: Determining a decision function based on the target fault information, the fault category corresponding to the target fault information, and the multiplier value corresponding to the target fault information; wherein the decision function is used to determine the fault category of the fault information based on the fault information; The fault category of the current fault information is determined according to the fault information of the device to be controlled and the decision function.

9. A control device for a faulty device, characterized in that: include: an acquisition unit, configured to acquire historical fault information within a preset historical time period, a fault category corresponding to the historical fault information, and current fault information of the device to be controlled; wherein the fault information represents a fault condition generated during operation of the device, and the fault category represents whether the fault is a false positive; a first determining unit, configured to determine target fault information from the historical fault information according to the historical fault information and the fault category corresponding to the historical fault information; a second determining unit, configured to determine a fault category of the current fault information according to the target fault information and the current fault information of the device to be controlled; A restoration unit is used to perform restoration control on the device to be controlled according to the fault type of the current fault information.

10. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

12. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 8 when the computer program is executed by a processor.

Images