Controller fault diagnosis processing method and system, electronic equipment and storage medium
By building a fault diagnosis model and dynamically adjusting the test strategy, the problem of insufficient efficiency and accuracy in the fault diagnosis of intelligent area controllers is solved, and more efficient fault detection and processing is achieved.
Patent Information
- Application Number
- CN202411184444.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-11-12
AI Technical Summary
In the prior art, fault diagnosis of intelligent area controllers is difficult to meet the requirements of efficiency and accuracy, especially due to the lack of adaptability and flexibility of fixed testing strategies.
By obtaining the preset parameter data of the controller to be monitored, building a model data set and training a neural network model, establishing a fault diagnosis model, dynamically adjusting the test strategy based on historical prediction results, and performing adaptive fault diagnosis and repair processing.
It improves the efficiency and accuracy of controller fault diagnosis, enhances the flexibility and adaptability of diagnosis, and achieves more accurate and timely fault detection and processing.
Smart Images

Figure CN118938877A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of fault diagnosis, and in particular to a controller fault diagnosis and processing method, system, electronic device and storage medium. Background Art
[0002] With the widespread application of smart devices and systems, smart zone controllers play a key role in managing and controlling multiple devices or systems. However, smart zone controllers may fail due to environmental factors, device aging, or software errors. In related technologies, fault testing is usually performed based on fixed test strategies, which is difficult to meet the requirements of fault diagnosis efficiency and accuracy.
[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the invention
[0004] The main purpose of the embodiments of the present application is to propose a controller fault diagnosis and processing method, system, electronic device and storage medium, which can realize adaptive controller fault diagnosis testing and processing, and effectively improve the fault diagnosis efficiency and accuracy.
[0005] To achieve the above object, an embodiment of the present application provides a controller fault diagnosis and processing method in one aspect, the method comprising the following steps:
[0006] Acquiring preset parameter data of the controller to be monitored to construct a model data set according to the preset parameter data;
[0007] Performing model training on a preset neural network model using the model data set to construct a preset fault diagnosis model;
[0008] According to a preset test strategy, the controller to be monitored is diagnosed and analyzed by the preset fault diagnosis model to obtain a fault prediction result; wherein the preset test strategy is determined by the historical prediction result of the preset fault diagnosis model;
[0009] A corresponding fault repair processing operation is performed according to the fault prediction result.
[0010] In some embodiments, obtaining preset parameter data of the controller to be monitored to construct a model data set according to the preset parameter data includes:
[0011] Dynamically obtain controller data; wherein the controller data includes processor usage, memory occupancy and communication connection status;
[0012] Acquire historical fault data through a preset data source; wherein the preset data source includes fault diagnosis records or system logs;
[0013] The controller data and the historical fault data are preprocessed to construct the model data set; wherein the data preprocessing includes data cleaning processing, denoising processing and standardization processing.
[0014] In some embodiments, the method of training a preset neural network model using the model data set to construct a preset fault diagnosis model includes:
[0015] Build a preset bilinear pooling convolutional network model;
[0016] Dividing the model data set into a training data set and a test data set;
[0017] The preset bilinear pooling convolutional network model is trained by using the training data set to obtain an initial fault diagnosis model;
[0018] The performance of the initial fault diagnosis model is evaluated using the test data set to obtain the preset fault diagnosis model.
[0019] In some embodiments, the diagnostic analysis of the controller to be monitored is performed using the preset fault diagnosis model according to the preset test strategy to obtain a fault prediction result, including:
[0020] Dynamically acquiring the operating status data of the controller to be monitored according to the preset test strategy;
[0021] Inputting the operating state data into the preset fault diagnosis model for prediction to obtain current state prediction data;
[0022] The predicted behavior data is compared and analyzed with the operating status data to obtain preset fault data; wherein the predicted behavior data is obtained by predicting the preset fault diagnosis model.
[0023] In some embodiments, after performing the comparative analysis of the predicted behavior data and the operating status data to obtain the preset fault data, the method further includes:
[0024] When it is determined that the distance between the predicted behavior data and the operating status data is greater than a preset threshold, determining an alarm level according to a preset alarm mechanism to perform a corresponding alarm operation;
[0025] The preset test strategy is dynamically updated and adjusted according to the alarm level and the frequency data of executing the alarm operation.
[0026] In some embodiments, performing corresponding fault repair processing operations according to the fault prediction result includes:
[0027] Analyze the fault prediction result through a preset fault isolation method to determine fault information data; wherein the fault information data includes fault location information, fault type, fault cause and fault level;
[0028] Execute the corresponding fault repair processing operation according to the fault information data to obtain repair operation data;
[0029] The fault information data and the repair operation data are fed back to the preset fault diagnosis model to optimize and update the preset fault diagnosis model.
[0030] In some embodiments, after performing the corresponding fault repair processing operation according to the fault prediction result, the method further includes:
[0031] Construct a test report and store the test report in a preset storage module; wherein the test report includes fault detection information, fault isolation information, fault verification information and fault recovery information.
[0032] To achieve the above object, another aspect of the embodiment of the present application provides a controller fault diagnosis and processing system, the system comprising:
[0033] The first module is used to obtain preset parameter data of the controller to be monitored, so as to construct a model data set according to the preset parameter data;
[0034] The second module is used to perform model training on a preset neural network model through the model data set to construct a preset fault diagnosis model;
[0035] The third module is used to perform diagnostic analysis on the controller to be monitored through the preset fault diagnosis model according to the preset test strategy to obtain a fault prediction result; wherein the preset test strategy is determined by the historical prediction result of the preset fault diagnosis model;
[0036] The fourth module is used to perform corresponding fault repair processing operations according to the fault prediction result.
[0037] To achieve the above objective, another aspect of an embodiment of the present application provides an electronic device, the electronic device comprising:
[0038] at least one processor;
[0039] at least one memory for storing at least one program;
[0040] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.
[0041] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.
[0042] The embodiments of the present application include at least the following beneficial effects: The present application provides a controller fault diagnosis and processing method, system, electronic device and storage medium. The scheme obtains preset parameter data of the controller to be monitored to construct a model data set according to the preset parameter data, and then trains the preset neural network model through the model data set to construct a preset fault diagnosis model. Then, the embodiment of the present invention performs diagnostic analysis on the controller to be monitored through the preset fault diagnosis model according to the preset test strategy, obtains the fault prediction result, and then performs the corresponding fault repair processing operation according to the fault prediction result to realize the controller fault diagnosis test and processing. It is easy to understand that the preset test strategy in the embodiment of the present invention is determined by the historical prediction results of the fault diagnosis model, that is, the current preset test strategy is adaptively adjusted by the historical prediction results of the fault diagnosis model, and the diagnostic analysis is performed in combination with the preset fault diagnosis model obtained by training, which can effectively improve the flexibility and adaptability of the controller fault diagnosis test and processing, thereby effectively improving the efficiency and accuracy of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 is a flowchart of the steps of the controller fault diagnosis and processing method provided by an embodiment of the present invention;
[0044] Figure 2 yes Figure 1 The step flow chart of step S110 in FIG.
[0045] Figure 3 yes Figure 1 The step flow chart of step S120 in FIG.
[0046] Figure 4 is a structural diagram of a fault feature extraction module provided by an embodiment of the present invention;
[0047] Figure 5 yes Figure 1 The step flow chart of step S130 in FIG.
[0048] Figure 6 It is a flowchart of the steps of dynamically updating and adjusting the preset test strategy provided by an embodiment of the present invention;
[0049] Figure 7 yes Figure 1 Flow chart of step S140 in FIG.
[0050] Figure 8is a flow chart of generating a test report provided by an embodiment of the present invention;
[0051] Fig. 9 It is a schematic diagram of the overall flow of the controller fault diagnosis and processing method provided in an embodiment of the present application;
[0052] Fig.10 It is a framework diagram of an adaptive fault diagnosis system for an intelligent regional controller provided in an embodiment of the present application;
[0053] Fig.11 is a structural diagram of a controller fault diagnosis and processing system provided in an embodiment of the present application;
[0054] Fig.12 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION
[0055] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.
[0056] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".
[0057] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.
[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.
[0059] Before describing the embodiments of the present application in detail, some nouns and terms involved in the embodiments of the present application are first described. The nouns and terms involved in the embodiments of the present application are subject to the following explanations.
[0060] Intelligent zone controller: It is an electrical system that can monitor and control all equipment in a specific area. It is a core component for implementing customized automation solutions. Among them, the intelligent zone controller (Zone Control Unit, ZCU) in the vehicle is a core component in the automotive electronic and electrical architecture. It plays the role of regional data center, IO center and distribution center. The intelligent zone controller is not only responsible for data processing, signal control and power distribution in terms of vehicle power, sensor management, infotainment, etc., but also provides guarantee for the stable operation and efficient coordination of intelligent networked vehicles through efficient data processing capabilities and precise control strategies.
[0061] With the widespread application of smart devices and systems, smart zone controllers play a key role in managing and controlling multiple devices or systems. However, smart zone controllers may fail due to environmental factors, device aging, or software errors. In related technologies, fault testing is usually based on fixed test strategies, which is difficult to meet the requirements of fault diagnosis efficiency and accuracy. For example, traditional fault diagnosis test methods are usually based on fixed test strategies, lack adaptability and flexibility, and are difficult to meet the needs of practical applications.
[0062] In view of this, a controller fault diagnosis and processing method, system, electronic device and storage medium are provided in the embodiments of the present application. The scheme obtains preset parameter data of the controller to be monitored to construct a model data set according to the preset parameter data, and then trains the preset neural network model through the model data set to construct a preset fault diagnosis model. Next, the embodiment of the present invention performs diagnostic analysis on the controller to be monitored through the preset fault diagnosis model according to the preset test strategy to obtain a fault prediction result, wherein the preset test strategy is determined by the historical prediction results of the preset fault diagnosis model. Finally, the corresponding fault repair processing operation is performed according to the fault prediction result to realize the controller fault diagnosis test and processing, which effectively improves the efficiency and accuracy of fault diagnosis.
[0063] The controller fault diagnosis and processing method provided in the embodiment of the present application relates to the field of fault diagnosis technology. The controller fault diagnosis and processing method provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or it can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements the controller fault diagnosis and processing method, etc., but is not limited to the above forms.
[0064] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.
[0065] Figure 1 is an optional flowchart of the controller fault diagnosis and processing method provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S110 to S140.
[0066] Step S110: obtaining preset parameter data of the controller to be monitored, so as to construct a model data set according to the preset parameter data.
[0067] Step S120: training a preset neural network model using a model data set to construct a preset fault diagnosis model.
[0068] Step S130: Perform diagnostic analysis on the controller to be monitored through a preset fault diagnosis model according to a preset test strategy to obtain a fault prediction result, wherein the preset test strategy is determined by the historical prediction results of the fault diagnosis model.
[0069] Step S140: Execute corresponding fault repair processing operations according to the fault prediction result.
[0070] During the working process of this specific embodiment, the embodiment of the present invention first obtains the preset parameter data of the controller to be monitored, so as to construct a model data set through the preset parameter data. Specifically, the controller to be monitored in the embodiment of the present invention refers to a controller that needs to be tested and processed for fault diagnosis, such as an intelligent zone controller, a vehicle controller, etc. Correspondingly, the preset parameter data in the embodiment of the present invention refers to the relevant parameters of the controller to be monitored, such as the state parameters and historical fault data of the controller to be monitored. The embodiment of the present invention obtains the preset parameter data and then organizes the preset parameter data to construct a model data set for training a preset fault diagnosis model. Then, the embodiment of the present invention trains the preset neural network model through the model data set to construct a preset fault diagnosis model. Specifically, the embodiment of the present invention first constructs a preset neural network model, such as a bilinear pooling convolutional network model, an attention mechanism network model, and a recurrent neural network model. Correspondingly, the embodiment of the present invention inputs the constructed model data set into the preset neural network model to train the preset neural network model, thereby obtaining a preset fault diagnosis model. Further, the embodiment of the present invention performs diagnostic analysis on the controller to be monitored through the preset fault diagnosis model according to the preset test strategy to obtain a fault prediction result. Specifically, the preset test strategy in the embodiment of the present invention refers to the strategy for performing fault diagnosis test on the controller to be monitored, such as test frequency, test depth and test range. Accordingly, the preset test strategy in the embodiment of the present invention is determined by the historical prediction results of the fault diagnosis model. Among them, the historical prediction results refer to the fault prediction results predicted by the preset fault diagnosis model in the last controller fault diagnosis process. The embodiment of the present invention adaptively adjusts the current preset test strategy through the last fault prediction result, so that the corresponding fault diagnosis processing mode can be adaptively adjusted according to the fault condition of the controller to be monitored, thereby effectively improving the accuracy and efficiency of the fault diagnosis processing. Accordingly, the embodiment of the present invention performs fault diagnosis analysis on the controller to be monitored according to the preset fault diagnosis model obtained by training according to the determined preset test strategy, so as to obtain the fault prediction result, such as whether the current operating state of the controller to be detected is normal and whether there is a fault. The embodiment of the present invention performs diagnostic analysis through the preset fault diagnosis model obtained by training, which can effectively improve the flexibility and adaptability of the controller fault diagnosis test and processing, thereby effectively improving the efficiency and accuracy of fault diagnosis. Finally, the embodiment of the present invention performs the corresponding fault repair processing operation according to the fault prediction result. Specifically, the fault repair processing operation in the embodiment of the present invention refers to the repair measures taken for the diagnosed fault. Accordingly, when it is determined that the preset fault diagnosis model detects that a fault exists in the controller to be monitored, the embodiment of the present invention takes corresponding fault repair measures, i.e., fault repair processing operations, based on the corresponding fault prediction results to repair the corresponding fault and complete the fault diagnosis and processing of the controller.
[0071] Reference Figure 2 In some embodiments of the present invention, obtaining preset parameter data of the controller to be monitored to construct a model data set according to the preset parameter data includes but is not limited to the following steps:
[0072] Step S210: dynamically obtain controller data, wherein the controller data includes processor usage, memory occupancy, and communication connection status.
[0073] Step S220: Obtain historical fault data through a preset data source, wherein the preset data source includes fault diagnosis records or system logs.
[0074] Step S230: preprocess the controller data and historical fault data to construct a model data set, wherein the data preprocessing includes data cleaning, denoising and standardization.
[0075] In this specific embodiment, the embodiment of the present invention first dynamically obtains controller data, and obtains historical fault data through a preset data source, and then performs data preprocessing on the controller data and historical fault data to construct a model data set. Specifically, the controller data in the embodiment of the present invention includes processor usage, memory occupancy, and communication connection status. Among them, the processor usage refers to the percentage of the controller to be monitored that is busy executing instructions within a preset time period, reflecting the workload of the controller. In addition, the memory occupancy refers to the percentage of the currently used part of the system memory. At the same time, the communication connection status refers to the status of the communication link between the controller to be monitored and other devices or systems. Accordingly, the embodiment of the present invention first determines the controller to be monitored and the corresponding parameter information, such as processor usage, memory occupancy, and communication connection status, and then sets a data collection module to obtain the corresponding controller data from the controller to be monitored in real time through the data collection module. At the same time, the preset data source in the embodiment of the present invention includes a fault diagnosis record or a system log. Among them, the fault diagnosis record refers to a database obtained by recording relevant fault information through the fault diagnosis process. Accordingly, the embodiment of the present invention obtains historical fault data by collecting from the fault diagnosis record or the system log. Furthermore, the embodiment of the present invention performs data preprocessing on the acquired controller data and historical fault data to facilitate subsequent model training and improve the accuracy of model training. Among them, the data preprocessing in the embodiment of the present invention includes data cleaning processing, denoising processing and standardization processing. The embodiment of the present invention first uses data cleaning technology to remove abnormal values, duplicate values or missing values from the acquired controller data and historical fault data. Then, the embodiment of the present invention denoises the data after data cleaning through a preset denoising algorithm, such as wavelet denoising or a filter, to reduce the noise in the data. Finally, the embodiment of the present invention performs data standardization processing on the denoised data to make it conform to the normal distribution, and constructs a model data set, thereby improving the accuracy of subsequent model training.
[0076] Reference Figure 3 In some embodiments of the present invention, a preset neural network model is trained using a model data set to construct a preset fault diagnosis model, including but not limited to the following steps:
[0077] Step S310: construct a preset bilinear pooling convolutional network model.
[0078] Step S320: Divide the model data set into a training data set and a test data set.
[0079] Step S330: Train the preset bilinear pooling convolutional network model using a training data set to obtain an initial fault diagnosis model.
[0080] Step S340: Performing a performance evaluation on the initial fault diagnosis model using a test data set to obtain a preset fault diagnosis model.
[0081] In this specific embodiment, the embodiment of the present invention first constructs a preset bilinear pooling convolutional network model. Specifically, the embodiment of the present invention adopts a compact bilinear pooling convolutional network model to learn the normal behavior and failure mode of the controller through historical data to construct a preset fault diagnosis model. Figure 4 , the fault feature extraction module constructed by the embodiment of the present invention, that is, the preset fault diagnosis model, includes two side branches and a middle part. Among them, one side branch is sequentially provided with a global pooling module, a first fully connected module, a linear rectified function (Rectified Linear Unit, ReLU) module, a second fully connected module and a sigmoid activation function layer, and the other side branch is sequentially provided with three convolution (Conv) modules and ReLU module combinations (the convolution kernels are all 1×1, and the number of channels is 64, 16, and 8, respectively), and is connected with a convolution module (the convolution kernel is 1×1, the number of channels is 1), a sigmoid activation function layer and a convolution module (the convolution kernel is 1×1, and the number of channels is 2048). Accordingly, in the embodiment of the present invention, a first-order convolutional network model is selected, and two CNN networks from different sources are used as feature extractors in the loss function, and both CNNs are ResNet50. The two side branch networks use loss functions Loss1 and Loss2. These two losses can assist the network in auxiliary training of the two side branches respectively. At the same time, the middle part is the feature vector obtained by compact bilinear pooling, and its loss function after the fully connected layer and Softmax is Loss cbp The final loss function is shown in formula (1):
[0082] Loss = (1-α) Loss cbp +α(Loss1+Loss2) (1)
[0083] Among them, α is a hyperparameter in the loss function, which represents the proportion of the two side branches in the entire loss function. Accordingly, by adjusting the size of parameter α, the degree of assistance of the two side branches to the entire CNN training can be controlled.
[0084] Next, the embodiment of the present invention divides the model data set to obtain a training data set and a test data set. Specifically, the embodiment of the present invention randomly divides the model data set according to a preset division ratio, such as dividing the model data set into a training data set and a test data set according to a ratio of 7:3. Among them, the training data set is used to train the constructed bilinear pooling convolutional network model, and the test data set is used to test and verify the initial fault diagnosis model obtained by training. Further, the embodiment of the present invention trains the preset bilinear pooling convolutional network model through the training data set to obtain the initial fault diagnosis model. Specifically, the embodiment of the present invention inputs the data of the training data set into the preset bilinear pooling convolutional network model to learn the normal behavior and abnormal behavior of the controller to be monitored, adjusts the relevant network parameters of the model, and obtains the initial fault diagnosis model. Next, the embodiment of the present invention evaluates the performance of the initial fault diagnosis model through the test data set to obtain the preset fault diagnosis model. Specifically, after the initial fault diagnosis model is obtained through training, the embodiment of the present invention evaluates the performance of the initial fault diagnosis model through the corresponding evaluation index. When the performance of the initial fault diagnosis model meets the preset performance index, the corresponding initial fault diagnosis model is determined as the preset fault diagnosis model. Among them, the embodiment of the present invention uses accuracy, precision rate, recall rate, and F1 value as evaluation indicators of the model. Among them, all samples are divided into positive and negative classes. The classification model (preset fault diagnosis model) will assign corresponding prediction probabilities to each sample, which will produce four situations, namely true positive class (TP), false negative class (FN), false positive class (FP), and true negative class (TN). Correspondingly, the accuracy rate is the proportion of all correctly predicted samples to the total samples, as shown in the following formula (2):
[0085]
[0086] In addition, the accuracy rate (precision rate) refers to the ratio of samples correctly predicted as positive to all samples predicted as positive, as shown in the following formula (3):
[0087]
[0088] In addition, the recall rate (recall rate) refers to the proportion of samples correctly predicted as positive to all samples that are actually positive, as shown in the following formula (4):
[0089]
[0090] In addition, the F1 value in the embodiment of the present invention is an indicator combining precision and recall, and is obtained by dividing the arithmetic mean by the geometric mean, as shown in the following formula (5):
[0091]
[0092] Reference Figure 5 In some embodiments of the present invention, a fault diagnosis model is used to diagnose and analyze the controller to be monitored according to a preset test strategy to obtain a fault prediction result, including but not limited to the following steps:
[0093] Step S410: dynamically acquiring the operating status data of the controller to be monitored according to a preset test strategy.
[0094] Step S420: input the operating status data into a preset fault diagnosis model for prediction to obtain current status prediction data.
[0095] Step S430: Compare and analyze the predicted behavior data with the running state data to obtain preset fault data, wherein the predicted behavior data is obtained by prediction of a preset fault diagnosis model.
[0096] In this specific embodiment, the embodiment of the present invention first dynamically obtains the operating status data of the controller to be monitored according to the preset test strategy. Specifically, the preset test strategy in the embodiment of the present invention is determined by the historical prediction results of the preset fault diagnosis model, such as the diagnostic test depth, cycle and range of the controller to be monitored. Correspondingly, the embodiment of the present invention obtains the corresponding operating status data, such as processor usage, memory occupancy and communication connection status, from the controller to be monitored in real time through the deployed real-time monitoring module according to the determined preset test strategy. Then, the embodiment of the present invention inputs the operating status data into the preset fault diagnosis model for prediction to obtain the current state prediction data. Specifically, the embodiment of the present invention inputs the dynamically collected operating status data into the trained preset fault diagnosis model, and the preset fault diagnosis model performs fault diagnosis prediction based on these data to predict the current operating state of the controller to be monitored, such as whether the controller to be monitored is operating normally, whether there is a potential fault risk, etc., to obtain the current state prediction data of the controller to be monitored. Further, the embodiment of the present invention compares and analyzes the predicted behavior data with the operating status data to obtain the preset fault data. Specifically, the predicted behavior data in the embodiment of the present invention refers to the normal behavior data predicted by the model, which is predicted by the preset fault diagnosis model. The embodiment of the present invention compares the real-time monitoring data (operating state data) with the normal behavior data (predicted behavior data) predicted by the model to determine whether there is a difference between the real-time monitoring data and the normal behavior data predicted by the model, thereby obtaining the corresponding preset fault data. For example, when there is a difference between the real-time monitoring data and the normal behavior data predicted by the model, it means that the controller to be monitored is not currently in its normal working state, and a fault or abnormality may have occurred. Accordingly, the embodiment of the present invention determines the final fault prediction result through the obtained preset fault data and the current state prediction data. It is easy to understand that the embodiment of the present invention first inputs the real-time monitored data into the trained preset fault diagnosis model so that the model performs a prediction calculation based on these data and outputs a prediction result, such as the classification of the current state of the controller (such as "normal", "mild fault", "serious fault", etc.) or a numerical value or vector representing the probability of the controller state. Then, based on the prediction result, the embodiment of the present invention compares the real-time monitoring data with the normal behavior data predicted by the model (normal behavior learned inside the model) to verify whether the prediction result is accurate, that is, to determine whether the controller is really in the predicted state, thereby obtaining the final fault prediction result.
[0097] Reference Figure 6 In some embodiments of the present invention, after performing comparative analysis of the predicted behavior data and the running status data to obtain the preset fault data, the controller fault diagnosis and processing method provided by the embodiment of the present invention further includes but is not limited to the following steps:
[0098] Step S510: When it is determined that the distance between the predicted behavior data and the running status data is greater than a preset threshold, an alarm level is determined according to a preset alarm mechanism to perform a corresponding alarm operation.
[0099] Step S520: dynamically update and adjust the preset test strategy according to the alarm level and the frequency data of executing the alarm operation.
[0100] In this specific embodiment, the embodiment of the present invention determines whether an alarm operation is required by judging whether the distance between the predicted behavior data and the running state data is greater than a preset threshold. Specifically, after the embodiment of the present invention compares and analyzes the normal behavior data (predicted behavior data) predicted by the model with the running state data of the controller to be monitored collected in real time, and obtains the preset fault data, it determines whether the difference between the predicted behavior data and the running state data is greater than the preset threshold. When it is determined that the distance (difference value) between the predicted behavior data and the running state data is greater than the preset threshold, it means that the controller to be monitored is currently in an abnormal state. The embodiment of the present invention determines the corresponding alarm level according to the preset alarm mechanism combined with the difference data between the predicted behavior data and the running state data, and performs the corresponding alarm operation. Next, the embodiment of the present invention dynamically updates and adjusts the preset test strategy according to the alarm level and the frequency data of executing the alarm operation, that is, determines the corresponding preset test strategy through the historical prediction results of the preset fault diagnosis model. Specifically, the frequency data in the embodiment of the present invention refers to the frequency of judging that the controller to be monitored is in an abnormal state and performing the corresponding alarm operation. The embodiment of the present invention dynamically updates and adjusts the subsequent preset test strategy by combining the alarm level (alarm severity) triggered each time by the controller to be monitored and the frequency of triggering the alarm, such as increasing the test frequency, expanding the test scope or changing the test method, so as to adaptively adjust the fault diagnosis processing of the controller to be monitored, effectively improve the accuracy and efficiency of the controller fault diagnosis test, and by adaptively adjusting the test strategy and resource allocation, the method can reduce the test cost and time consumption while ensuring the test quality. For example, when it is detected that the probability of a module failing is high, the test frequency or depth of the module is increased, or when the overall operation of the system is stable, the test intensity is appropriately reduced to save resources.
[0101] Reference Figure 7 In some embodiments of the present invention, corresponding fault repair processing operations are performed according to the fault prediction results, including but not limited to the following steps:
[0102] Step S610: Analyze the fault prediction result in a preset fault isolation method to determine fault information data, wherein the fault information data includes fault location information, fault type, fault cause and fault level.
[0103] Step S620: Execute corresponding fault repair processing operations according to the fault information data to obtain repair operation data.
[0104] Step S630: Feedback the fault information data and the repair operation data to the preset fault diagnosis model to optimize and update the preset fault diagnosis model.
[0105] In this specific embodiment, the embodiment of the present invention first analyzes the fault prediction result through a preset fault isolation method to determine the fault information data. Specifically, the fault information data in the embodiment of the present invention includes fault location information, fault type, fault cause, and fault level. Accordingly, when a fault is detected, the embodiment of the present invention determines the specific location and cause of the fault through fault isolation technology, such as rule-based reasoning or causal graph. Accordingly, the specific location and cause of the fault are further used to obtain information such as the fault type and fault level. Next, the embodiment of the present invention performs corresponding fault repair processing operations according to the fault information to obtain repair operation data. Specifically, after performing adaptive fault diagnosis, the embodiment of the present invention determines corresponding fault repair suggestions according to the fault information data obtained by diagnosis, and performs corresponding fault repair processing operations according to the corresponding fault repair suggestions to repair the fault. For example, the embodiment of the present invention takes corresponding repair measures according to the fault type and fault severity (fault level), such as restarting the controller, replacing the faulty module, or performing other repair operations. Accordingly, the repair operation data in the embodiment of the present invention refers to all data in the fault repair process. When the embodiment of the present invention performs the fault repair processing operation, the data in the process is recorded to obtain the repair operation data. Then, the embodiment of the present invention feeds back the fault information and repair operation data to the preset fault diagnosis model to optimize and update the fault diagnosis model. Specifically, the embodiment of the present invention feeds back the data recorded during the fault diagnosis and repair process to the preset fault diagnosis model to continuously optimize and update the preset fault diagnosis model, thereby effectively improving the prediction accuracy and reliability of the preset fault diagnosis model.
[0106] It should be noted that in some embodiments of the present invention, the test strategy is regularly evaluated and adjusted so that the preset test strategy can adapt to changes in system performance and environment, and the controller fault diagnosis and processing method is periodically evaluated and adjusted according to actual application requirements and system performance changes. Among them, the embodiment of the present invention regularly analyzes the performance of the controller to be monitored to evaluate its stability and reliability, obtains performance analysis results, and then updates and upgrades the system accordingly according to the performance analysis results and corresponding user needs, thereby improving the ability of fault diagnosis and control.
[0107] Combination Figure 1 , refer to Figure 8In some embodiments of the present invention, after executing the corresponding fault repair processing operation according to the fault prediction result, the controller fault diagnosis processing method provided by the embodiment of the present invention also includes but is not limited to the following steps:
[0108] Step S710: construct a test report and store the test report in a preset storage module, wherein the test report includes fault detection information, fault isolation information, fault verification information and fault recovery information.
[0109] In this specific embodiment, after implementing the fault repair, the embodiment of the present invention constructs a test report and stores the test report in a preset storage module. Specifically, after completing the fault repair, the embodiment of the present invention generates a detailed test report, including fault detection information, fault isolation information, fault verification information, and fault recovery information. Among them, the fault detection information in the embodiment of the present invention refers to the data for fault diagnosis and analysis through a preset fault diagnosis model, the fault isolation information refers to the relevant data for determining the fault location and cause through fault isolation technology, and the fault recovery information refers to the relevant data for fault repair suggestions, that is, the test report in the embodiment of the present invention includes a complete record of fault detection, isolation, verification and recovery suggestions. Accordingly, the embodiment of the present invention stores the test report in the preset storage module of the system in the form of an electronic document, and can be shared with relevant personnel through the network to facilitate subsequent analysis, troubleshooting and system improvement. It is easy to understand that the test report generated by the embodiment of the present invention provides rich fault information and suggestions, which can effectively help operators quickly solve problems and optimize the system.
[0110] The following is a detailed description and explanation of the solution of the embodiment of the present invention in conjunction with a specific application example of control fault diagnosis and processing:
[0111] For example, refer to Fig. 9 , Fig. 9 Schematic diagram of the overall flow of the controller fault diagnosis and processing method provided in an embodiment of the present invention. Specifically, the embodiment of the present invention first performs real-time status monitoring of the monitored controller to obtain corresponding operating status data, such as processor usage, memory occupancy, and communication connection status, and stores them in real time. Next, the embodiment of the present invention extracts fault features from the operating status data, such as fault frequency, fault duration, and fault impact range, so as to perform adaptive fault diagnosis through a preset fault diagnosis model to obtain a fault prediction result. Accordingly, the embodiment of the present invention determines the corresponding fault repair suggestion based on the determined fault prediction result, and then performs the corresponding fault repair processing operation (implements fault repair). Finally, the embodiment of the present invention organizes the data in the entire fault diagnosis and repair process to generate a test report. Accordingly, if Fig.10 As shown, Fig.10The framework diagram of the intelligent zone controller adaptive fault diagnosis system provided by the embodiment of the present invention is to apply the controller fault diagnosis processing method to the fault diagnosis of the intelligent zone controller. Specifically, the embodiment of the present invention dynamically obtains the processor usage rate, memory occupancy rate and communication connection status of the intelligent zone controller through the state detection module according to the predetermined preset test strategy. Then the obtained processor usage rate, memory occupancy rate and communication connection status are input into the trained fault feature extraction module, such as Figure 4 As shown, feature extraction is performed, and fault diagnosis is performed through an adaptive fault diagnosis module based on the extracted feature information to obtain corresponding fault diagnosis results. Among them, the adaptive fault diagnosis module in the embodiment of the present invention combines the controller fault diagnosis processing system (expert system) and the corresponding preset rules to perform diagnostic analysis on the acquired feature information. Furthermore, the embodiment of the present invention performs fault repair for the determined fault through the fault repair module, and adaptively adjusts the preset test strategy according to the corresponding fault parameters, such as fault frequency, fault alarm level, etc. At the same time, after the fault is repaired, the embodiment of the present invention generates a corresponding test report.
[0112] It is easy to understand that the embodiment of the present invention collects and processes data related to the intelligent zone controller for subsequent fault diagnosis. At the same time, the embodiment of the present invention uses a machine learning algorithm to train a fault pattern recognition model, that is, a preset fault diagnosis model, so that faults can be automatically identified and diagnosed without human intervention, and the accuracy and efficiency of fault diagnosis are improved by generating adaptive test sequences according to different fault types and severity. The embodiment of the present invention monitors the operating state of the intelligent zone controller in real time, and adaptively adjusts the test strategy by comparing with the pre-trained model, so as to achieve accurate diagnosis of controller faults, and adaptively adjusts the test strategy and resource allocation mode, so as to reduce the test cost and time consumption while ensuring the test quality. At the same time, the embodiment of the present invention collects and processes a large amount of controller operation data, so as to more accurately reflect the actual operating state of the controller and improve the accuracy of fault diagnosis. Accordingly, the embodiment of the present invention monitors the state of the controller in real time and dynamically adjusts the test strategy according to the real-time data, so as to achieve adaptive fault diagnosis, making the fault diagnosis more timely and effective. In addition, the embodiment of the present invention can be easily extended to other types of intelligent control systems and fault diagnosis scenarios, and has good versatility and scalability.
[0113] See also Fig.11 The embodiment of the present application further provides a controller fault diagnosis and processing system, which can implement the above controller fault diagnosis and processing method, and the system includes:
[0114] The first module 810 is used to obtain preset parameter data of the controller to be monitored, so as to construct a model data set according to the preset parameter data.
[0115] The second module 820 is used to perform model training on a preset neural network model through a model data set to construct a preset fault diagnosis model.
[0116] The third module 830 is used to perform diagnostic analysis on the controller to be monitored through a preset fault diagnosis model according to a preset test strategy to obtain a fault prediction result. The preset test strategy is determined by the historical prediction results of the preset fault diagnosis model.
[0117] The fourth module 840 is used to perform corresponding fault repair processing operations according to the fault prediction result.
[0118] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0119] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above controller fault diagnosis and processing method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.
[0120] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0121] See also Fig.12 , Fig.12 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:
[0122] The processor 910 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;
[0123] The memory 920 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 920 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 920, and the processor 910 calls and executes the controller fault diagnosis processing method of the embodiment of this application;
[0124] Input / output interface 930, used to implement information input and output;
[0125] Communication interface 940, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);
[0126] bus 950 , which transmits information between the various components of the device (e.g., processor 910 , memory 920 , input / output interface 930 , and communication interface 940 );
[0127] The processor 910 , the memory 920 , the input / output interface 930 , and the communication interface 940 are connected to each other in communication within the device via a bus 950 .
[0128] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned controller fault diagnosis and processing method is implemented.
[0129] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0130] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0131] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0132] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.
[0133] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0134] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.
[0135] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0136] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0137] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0138] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0139] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0140] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. 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, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.
[0141] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.
Claims
1. A controller fault diagnosis and processing method, It is characterized in that The method comprises the following steps: Acquiring preset parameter data of the controller to be monitored to construct a model data set according to the preset parameter data; The preset neural network model is trained by using the model data set to construct a preset fault diagnosis model; According to a preset test strategy, the controller to be monitored is diagnosed and analyzed by the preset fault diagnosis model to obtain a fault prediction result; wherein the preset test strategy is determined by the historical prediction result of the preset fault diagnosis model; A corresponding fault repair processing operation is performed according to the fault prediction result.
2. The method according to claim 1, It is characterized in that The step of obtaining preset parameter data of the controller to be monitored to construct a model data set according to the preset parameter data includes: Dynamically obtain controller data; wherein the controller data includes processor usage, memory occupancy and communication connection status; Acquire historical fault data through a preset data source; wherein the preset data source includes fault diagnosis records or system logs; The controller data and the historical fault data are preprocessed to construct the model data set; wherein the data preprocessing includes data cleaning processing, denoising processing and standardization processing.
3. The method according to claim 1, It is characterized in that The method of training a preset neural network model through the model data set to construct a preset fault diagnosis model includes: Build a preset bilinear pooling convolutional network model; Dividing the model data set into a training data set and a test data set; The preset bilinear pooling convolutional network model is trained using the training data set to obtain an initial fault diagnosis model; The performance of the initial fault diagnosis model is evaluated using the test data set to obtain the preset fault diagnosis model.
4. The method according to claim 1, It is characterized in that The method of performing diagnostic analysis on the controller to be monitored by using the preset fault diagnosis model according to the preset test strategy to obtain a fault prediction result includes: Dynamically acquiring the operating status data of the controller to be monitored according to the preset test strategy; Inputting the operating state data into the preset fault diagnosis model for prediction to obtain current state prediction data; The predicted behavior data is compared and analyzed with the operating status data to obtain preset fault data; wherein the predicted behavior data is predicted by the preset fault diagnosis model.
5. The method according to claim 4, It is characterized in that After performing the comparative analysis of the predicted behavior data and the operating status data to obtain the preset fault data, the method further includes: When it is determined that the distance between the predicted behavior data and the operating status data is greater than a preset threshold, determining an alarm level according to a preset alarm mechanism to perform a corresponding alarm operation; The preset test strategy is dynamically updated and adjusted according to the alarm level and the frequency data of executing the alarm operation.
6. The method according to claim 4, It is characterized in that The performing of corresponding fault repair processing operations according to the fault prediction result includes: Analyze the fault prediction result through a preset fault isolation method to determine fault information data; wherein the fault information data includes fault location information, fault type, fault cause and fault level; Execute the corresponding fault repair processing operation according to the fault information data to obtain repair operation data; The fault information data and the repair operation data are fed back to the preset fault diagnosis model to optimize and update the preset fault diagnosis model.
7. The method according to claim 1, It is characterized in that After executing the corresponding fault repair processing operation according to the fault prediction result, the method further includes: Construct a test report and store the test report in a preset storage module; wherein the test report includes fault detection information, fault isolation information, fault verification information and fault recovery information.
8. A controller fault diagnosis and processing system, It is characterized in that The system comprises: The first module is used to obtain preset parameter data of the controller to be monitored, so as to construct a model data set according to the preset parameter data; The second module is used to perform model training on a preset neural network model through the model data set to construct a preset fault diagnosis model; The third module is used to perform diagnostic analysis on the controller to be monitored through the preset fault diagnosis model according to the preset test strategy to obtain a fault prediction result; wherein the preset test strategy is determined by the historical prediction result of the preset fault diagnosis model; The fourth module is used to perform corresponding fault repair processing operations according to the fault prediction result.
9. An electronic device, It is characterized in that include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Method and apparatus for controlling appliance device based on failure prediction
CN110011881A
Regional controller fault detection method and device
CN113467420A
Data-driven SDN controller fault automatic diagnosis system and method
CN117008569A
Preventive maintenance method and system for PLC controller network based on artificial intelligence
CN118092404A
Detection and Correction of Robotic Process Automation Failures
US20220357733A1
Cited By
Controller performance test method and system
CN119690052A
Fault diagnosis method and fault diagnosis system for CAN bus communication failure
CN121187275A
