Flexible anode fault detection method and system

Abstract

The invention discloses a flexible anode fault detection method and system, and relates to the technical field of intelligent monitoring and fault diagnosis, and the method comprises the steps: collecting the operation data of a flexible anode in real time, and carrying out the preprocessing of the collected operation data; based on the preprocessed data, a fault prediction model is constructed, and fault prediction is carried out on the flexible anode; according to the prediction result, fault identification is carried out on the flexible anode; transmitting a detection signal to the flexible anode based on an analysis result, and detecting a fault point of the flexible anode by analyzing a reflection mode of the signal; and generating a fault detection report by combining the fault point detection result of the flexible anode and the prediction result of the fault prediction model. By constructing a flexible anode fault detection system, real-time data acquisition, intelligent analysis and prediction and accurate determination are integrated, the system safety is remarkably enhanced, the maintenance efficiency is improved, the cost is effectively reduced, continuous optimization and upgrading are promoted, and the stability and high efficiency of industrial operation are comprehensively guaranteed.

Description

Technical Field

[0001] The invention relates to the technical field of intelligent monitoring and fault diagnosis, and in particular to a flexible anode fault detection method and system. Background Art

[0002] As an important component of the cathodic protection system, flexible anode technology has been widely used in marine engineering, oil and gas pipelines, chemical industry and other fields in recent years. It is favored for its excellent flexibility and adaptability. With the rapid development of the Internet of Things, big data and artificial intelligence technology, the position of intelligent monitoring systems in the industrial field has become increasingly prominent. In the field of flexible anode fault detection, traditional detection methods mainly rely on manual inspections or periodic maintenance, which are inefficient and easily affected by subjective factors, and it is difficult to meet the needs of modern industrial production for high reliability and immediate response. In recent years, data-driven fault prediction based on sensor networks has gradually become a research hotspot. It achieves early warning of potential faults by real-time monitoring of structural health status.

[0003] Despite this, the current flexible anode fault detection technology still has obvious shortcomings. On the one hand, most systems rely on only a single type of sensor for data collection, which cannot fully capture the multi-dimensional information of the flexible anode in a complex working environment, resulting in limited accuracy and coverage of fault detection. On the other hand, the existing technology lacks effective noise suppression and feature extraction methods in the data preprocessing stage, so that the noise and redundant information in the original data directly affect the subsequent fault prediction accuracy. More importantly, traditional fault prediction models are often limited to static analysis, and it is difficult to capture the dynamic process and long-term trend of flexible anode failures, especially when dealing with nonlinear and complex fault modes. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a flexible anode fault detection method and system to solve the problems caused by single sensor information, insufficient data preprocessing, static limitations of prediction models, low fault detection accuracy, small coverage, inaccurate prediction and low efficiency.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a flexible anode fault detection method, which includes collecting operating data of the flexible anode in real time and preprocessing the collected operating data; constructing a fault prediction model based on the preprocessed data to predict the fault of the flexible anode; identifying the fault of the flexible anode according to the prediction result; based on the analysis result, emitting a detection signal to the flexible anode, and detecting the fault point of the flexible anode by analyzing the reflection pattern of the signal; and generating a fault detection report by combining the fault point detection result of the flexible anode and the prediction result of the fault prediction model.

[0008] As a preferred solution of the flexible anode fault detection method of the present invention, the specific steps of real-time collection of flexible anode operation data are as follows:

[0009] Deploy various types of sensors at key locations of the flexible anode, including temperature sensors, current sensors, voltage sensors, and fiber Bragg grating sensors;

[0010] Through the deployment of various types of sensors, the operation data of the flexible anode is collected in real time.

[0011] As a preferred solution of the flexible anode fault detection method of the present invention, the preprocessing of the collected operation data is carried out in the following specific steps:

[0012] Wavelet transform is used for multi-scale analysis to decompose the signal into different frequency components, retaining useful information while removing high-frequency random noise;

[0013] Fill missing values ​​using time series model predictions;

[0014] Use Z-score standardization to convert the running data to the same magnitude;

[0015] Use FFT to convert the time signal into a spectrum, analyze the frequency components of the signal, and extract the main frequency and frequency band energy characteristics;

[0016] Each extracted main frequency and frequency band feature is taken as a dimension, and a multi-dimensional feature space is constructed by horizontal splicing.

[0017] As a preferred solution of the flexible anode fault detection method of the present invention, wherein: based on the preprocessed data, a fault prediction model is constructed to predict the fault of the flexible anode. The specific steps are as follows:

[0018] Use long short-term memory network to build a fault prediction model;

[0019] Divide the preprocessed dataset into training set, validation set and test set;

[0020] Use the training set data to train the model, optimize the model weights through the back propagation algorithm, and minimize the loss function;

[0021] Evaluate model performance on the validation set and adjust hyperparameters;

[0022] Evaluate the generalization ability of the model on an independent test set;

[0023] The preprocessed data set is input into the trained fault prediction model to predict the failure probability of the flexible anode. The expression is:

[0024]

[0025] in, represents the probability of failure of the flexible anode at time point t, W out is the weight matrix of the fully connected layer, b out is the bias vector of the fully connected layer, σ represents the sigmoid function, D(t) represents the preprocessed dataset at time point t, and S is a feature transformation function.

[0026] As a preferred solution of the flexible anode fault detection method of the present invention, the flexible anode fault is identified according to the prediction result, and the specific steps are as follows:

[0027] Based on the analysis of fault records in historical data, a safety warning threshold T is defined, and the probability of flexible anode failure is compared. and the size of the safety warning threshold T to identify faults;

[0028] when When , it is considered that there is no fault in the flexible anode;

[0029] when When , the flexible anode is considered to be faulty.

[0030] As a preferred solution of the flexible anode fault detection method of the present invention, wherein: based on the analysis result, a detection signal is emitted to the flexible anode, and the fault point of the flexible anode is detected by analyzing the reflection mode of the signal. The specific steps are as follows:

[0031] When it is identified that the flexible anode is faulty, a detection signal is transmitted to the flexible anode through an electromagnetic signal transmitter;

[0032] Using a receiving device, receiving a detection signal reflected from the flexible anode and carrying information about the anode structure and state, and dividing the received reflected signal into a plurality of sub-signal segments, each signal segment corresponding to a different physical position of the flexible anode;

[0033] Design a position mapping function to determine the specific location of the fault point and convert the high-dimensional feature space into interpretable physical preliminary position coordinates. The expression is:

[0034]

[0035] Where z(t) is the initial position coordinate of the flexible anode fault point at time t, W loc is the weight matrix of the position mapping layer, b loc is the bias vector of the position mapping layer, P(z(t)) represents the position coordinates of the fault point obtained by the position mapping function P based on the position feature vector z(t) at time point t, V is the propagation speed of the detection signal in the flexible anode, and Δt is the time difference from the emission to the reflection of the detection signal.

[0036] Import the preliminary position coordinates of the fault point provided by P(z(t)) into the signal analysis system as the key area for analysis;

[0037] Use FFT to extract the frequency characteristics of the signal and observe whether there are new frequency components and changes in the intensity of the original components. Compare the extracted signal characteristics with the historical fault mode data to find similar characteristic patterns. Combine the preliminary position coordinates provided by P(z(t)) and the signal analysis results to generate the final fault point location.

[0038] As a preferred solution of the flexible anode fault detection method of the present invention, wherein: the fault report includes the time and location of the fault and the systems and components involved;

[0039] In-depth analysis of the root cause of the failure, providing detailed failure cause analysis;

[0040] The report provides detailed handling measures, including emergency response steps, fault repair process and corrective measures taken, and also puts forward prevention and improvement suggestions.

[0041] In a second aspect, the present invention provides a flexible anode fault detection system, including a data acquisition and preprocessing module, a fault prediction module, a fault identification module, a fault point location module and a fault detection report generation module; the data acquisition and preprocessing module is used to collect the operating data of the flexible anode in real time and preprocess the collected operating data; the fault prediction module constructs a fault prediction model based on the preprocessed data to predict the fault of the flexible anode; the fault identification module is used to identify the fault of the flexible anode according to the prediction result; the fault point location module is used to transmit a detection signal to the flexible anode based on the analysis result, and detect the fault point of the flexible anode by analyzing the reflection pattern of the signal; the fault detection report generation module is used to generate a fault detection report by combining the fault point detection result of the flexible anode and the prediction result of the fault prediction model.

[0042] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the flexible anode fault detection method as described in the first aspect of the present invention is implemented.

[0043] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the flexible anode fault detection method as described in the first aspect of the present invention is implemented.

[0044] The beneficial effects of the present invention are as follows: by collecting and preprocessing the operating data of the flexible anode in real time, comprehensive monitoring of its operating status and improvement of data quality are achieved, and then a fault prediction model is constructed based on the processed data, achieving early warning of potential faults and improving the preventive maintenance capability of the system. Next, fault identification is performed based on the prediction results to ensure the accuracy of fault judgment, and then the fault point is accurately located by emitting detection signals and analyzing the reflection pattern, thereby enhancing the accuracy and response speed of fault diagnosis. Finally, a detailed fault report is generated based on the comprehensive fault detection results, providing fault handling measures and prevention suggestions, and improving the safety and reliability of the flexible anode system as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0046] Figure 1 This is a flow chart of the flexible anode fault detection method in Example 1.

[0047] Figure 2 This is a flow chart of the flexible anode fault detection system in Example 1. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0050] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0051] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a flexible anode fault detection method, comprising the following steps:

[0052] S1. Collect the operation data of the flexible anode in real time and pre-process the collected operation data.

[0053] Furthermore, multiple types of sensors are deployed at key locations of the flexible anode, including temperature sensors, current sensors, voltage sensors, and fiber Bragg grating sensors for structural health monitoring. The design of the sensor network takes into account the geometry and material properties of the anode to ensure that all potential high-prone areas of failure are covered;

[0054] By deploying various types of sensors, the operating data of the flexible anode is collected in real time, including temperature, current, and voltage data.

[0055] It should be noted that key locations refer specifically to those specific areas that have a decisive influence on the overall performance, safety and long-term reliability of the anode. These locations include but are not limited to the locations with the highest current density, the greatest mechanical stress, the most drastic temperature changes, the strongest chemical activity and the closest connection to other structural parts. By deploying sensors such as temperature, current, voltage and fiber Bragg gratings at these points, it is possible to fully monitor the health of the flexible anode and promptly capture subtle changes that may indicate early failures, thereby providing important data support for preventive maintenance and ensuring the stability and safety of system operation.

[0056] Wavelet transform is used for multi-scale analysis to decompose the signal into different frequency components, retaining useful information while removing high-frequency random noise;

[0057] Fill missing values ​​using time series model predictions;

[0058] It should be noted that first, the time series data is analyzed to identify the missing values. Then, a suitable time series prediction model is selected, such as autoregression (AR), moving average (MA), autoregression integrated moving average (ARIMA) or long short-term memory network (LSTM), which can predict future trends based on the existing time series data. By learning from historical data, the model can infer the possible values ​​of the missing time points. After the model training is completed, it is applied to the location of the missing values ​​to predict and fill in these missing values. This method can maintain the temporal continuity of the data and provide a more complete and accurate data set for subsequent fault prediction.

[0059] Use Z-score standardization to convert the running data to the same level to facilitate model training;

[0060] It should be noted that, first, the mean and standard deviation of each set of data are calculated. Then, each observation is standardized. In this way, data of different magnitudes and units are converted to a standard normal distribution with a mean of 0 and a standard deviation of 1. This standardization process eliminates the influence of dimension, allowing different types of sensor data to be effectively compared and fused on the same scale, improving the accuracy and reliability of subsequent analysis.

[0061] Use FFT to convert the time signal into a spectrum, analyze the frequency components of the signal, and extract the main frequency and frequency band energy characteristics;

[0062] It should also be noted that this process first applies FFT to the original time signal to obtain a spectrum diagram, which contains the amplitude information of the signal at each frequency component. By analyzing the spectrum diagram, the dominant frequency of the signal, that is, the frequency component with the largest energy in the signal, and the energy distribution in different frequency bands can be identified. The dominant frequency and band energy characteristics are key indicators in signal analysis. They can reveal whether there are periodic patterns in the signal, whether it is affected by specific frequency noise, and the health status or failure mode of the signal. This information is crucial for fault prediction and diagnosis, and can help identify possible problems in flexible anodes, such as material fatigue, cracks or corrosion, thereby guiding maintenance decisions.

[0063] Each extracted main frequency and frequency band feature is taken as a dimension, and a multi-dimensional feature space is constructed by horizontal splicing. Each point in this space represents the state of the flexible anode at a certain moment.

[0064] S2. Based on the preprocessed data, a fault prediction model is constructed to predict the failure of the flexible anode.

[0065] Furthermore, in view of the complexity and nonlinearity of flexible anode fault prediction, a long short-term memory network is used to construct a fault prediction model. The long short-term memory network can effectively capture the long-term dependencies in time series data.

[0066] The preprocessed data set is divided into training set, validation set and test set, and the ratio can be set to 70%, 15%, and 15%;

[0067] Use the training set data to train the model, optimize the model weights through the back propagation algorithm, minimize the loss function, such as the mean square error (MSE), and improve the prediction accuracy of the model;

[0068] It should be noted that the backpropagation algorithm is the core mechanism used in deep learning and neural networks to optimize model weights. After the model predicts, the value of the loss function is calculated, which represents the prediction error under the current model parameter configuration. The backpropagation algorithm determines how to adjust the weights to reduce the loss by calculating the gradient of the loss function relative to each weight (that is, how the loss function changes as the weight changes). This process starts from the output layer and traverses the entire network in reverse to the input layer, calculating the gradient using the chain rule. After the gradient is obtained, the weight update is performed according to a specific learning rate, which determines the magnitude of the weight adjustment. The weight update follows the principle of gradient descent, that is, moving in the negative direction of the gradient of the loss function until the minimum value of the loss function is found, which means that the model has found an optimal set of parameters that minimizes the prediction error.

[0069] Minimizing the loss function is the main goal of training a neural network. At each iteration, the model adjusts its parameters based on the calculated gradients, trying to make the value of the loss function as low as possible. As training progresses, the model's predictive power gradually improves and the value of the loss function gradually decreases. Ideally, the training process converges to a stable minimum point, at which point the model parameters are considered optimal, fit the training data well, and have a certain degree of generalization ability to make accurate predictions on new data that has not been seen.

[0070] Evaluate model performance on the validation set, adjust hyperparameters, prevent overfitting, and ensure the generalization ability of the model;

[0071] Evaluate the generalization ability of the model on an independent test set to ensure the model's prediction accuracy on unknown data;

[0072] The preprocessed data set is input into the trained fault prediction model to predict the failure probability of the flexible anode. The expression is:

[0073]

[0074] in, represents the probability of failure of the flexible anode at time point t, W out is the weight matrix of the fully connected layer, b out is the bias vector of the fully connected layer, σ represents the sigmoid function, D(t) represents the preprocessed data set at time point t including the measured values ​​of temperature, current, voltage and fiber Bragg grating sensor, and S is a feature transformation function;

[0075] It should be noted that the function of S can be divided into two steps: 1. Standardization: This part is to standardize the data D(t). The purpose of standardization is to scale the data to zero mean and unit variance, which helps to improve numerical stability, accelerate model training, and make comparisons between different features fairer. 2. Nonlinear transformation: After standardization, the data passes through the ReLU activation function. This step is to introduce nonlinearity so that the model can learn and represent more complex feature relationships. The ReLU function sets all negative values ​​to zero and leaves positive values ​​unchanged, which helps to solve the limitations of linear models and enables the model to better fit nonlinear data distributions. The expression is:

[0076]

[0077] where a is the mean of the data set D(t) and a is the standard deviation of the data set D(t).

[0078] Design a position mapping function to parse the position-related feature vector output by the model and determine the specific location of the potential fault point, converting the high-dimensional feature space into interpretable physical location coordinates. The expression is:

[0079] P(z(t))=L·argmax(ReLU(W loc z(t)+b loc ));

[0080] Where z(t) is the position feature vector of the flexible anode fault point at time t, W loc is the weight matrix of the position mapping layer, b loc is the bias vector of the position mapping layer, L is the mapping matrix that converts the index into the actual position coordinate, and P(z(t)) represents the position coordinate of the fault point obtained by the position mapping function P based on the position feature vector z(t) at time point t.

[0081] It should also be noted that the mapping function P is based on the position feature vector z(t) at time point t, through the weight matrix W of the neural network loc and the bias vector b locA linear transformation is performed, followed by the application of the ReLU activation function to highlight key features and eliminate negative values. Next, the maximum value index in the transformed feature vector is found by calculating the "argmax" function, which corresponds to the potential location of the fault point. Finally, the mapping matrix L is used to convert this index into actual physical coordinates, thereby obtaining the specific location of the fault point on the flexible anode, achieving an accurate conversion from high-dimensional feature space to interpretable physical coordinates.

[0082] S3. According to the prediction results, the flexible anode is fault-identified.

[0083] Furthermore, based on the analysis of fault records in historical data, a safety warning threshold T is defined. and the size of T, for fault identification;

[0084] when When , it is considered that there is no fault in the flexible anode;

[0085] when When , it is considered that the flexible anode is faulty;

[0086] It should also be noted that the specific value range of the safety warning threshold T depends on the characteristics of the flexible anode system of the specific application and the statistical characteristics of the selected features. For example, if a feature follows a normal distribution under normal operation, T may be set to the mean of the feature plus 3 times the standard deviation, which means that approximately 99.7% of normal data points will fall below T, thereby keeping the false alarm rate at a low level. In actual operation, T may be fine-tuned based on field testing and maintenance experience to adapt to specific operating conditions and maintenance strategies.

[0087] S4. Based on the analysis result, a detection signal is transmitted to the flexible anode, and the fault point of the flexible anode is detected by analyzing the reflection pattern of the signal.

[0088] Furthermore, when it is identified that the flexible anode is faulty, a detection signal is transmitted to the flexible anode via an electromagnetic signal transmitter;

[0089] Using a receiving device, receiving a detection signal reflected from the flexible anode and carrying information about the structure and state of the anode;

[0090] Design a position mapping function to determine the specific location of the fault point and convert the high-dimensional feature space into interpretable physical preliminary position coordinates. The expression is:

[0091]

[0092] Where z(t) is the position feature vector of the flexible anode fault point at time t, W loc is the weight matrix of the position mapping layer, bloc is the bias vector of the position mapping layer, P(z(t)) represents the position coordinates of the fault point obtained by the position mapping function P based on the position feature vector z(t) at time point t, V is the propagation speed of the detection signal in the flexible anode, and Δt is the time difference from the emission to the reflection of the detection signal.

[0093] Pre-process the received reflected signal, including filtering, noise reduction and signal enhancement, to eliminate interference and improve signal quality;

[0094] Import the fault point location coordinates provided by P(z(t)) into the signal analysis system as the key area for analysis;

[0095] The specific process includes passing the position coordinates P(z(t)) to the signal analysis system, which marks these coordinates as the key analysis area so as to focus on analyzing the signal reflection pattern in this area and determine the specific location of the fault point more accurately.

[0096] Use FFT to extract the frequency characteristics of the signal and observe whether there are new frequency components and changes in the intensity of the original components, which are related to material fatigue, crack extension or corrosion; compare the extracted signal characteristics with the known fault mode database to find similar characteristic patterns to determine the possible fault type (such as cracks, corrosion, wear, etc.) and severity, providing a basis for subsequent maintenance decisions, and combining the precise location information provided by P(z(t) and the signal analysis results to further narrow the location range of the fault point.

[0097] It should be noted that a signal containing potential fault information is first collected, usually an electromagnetic signal. Then, this time domain signal is converted into a frequency domain representation through FFT, that is, the signal is decomposed into its various frequency components. On the spectrum graph, each peak corresponds to a specific frequency, and its height reflects the intensity of the frequency component. By carefully examining the spectrum, it can be observed whether new frequency components appear and whether the intensity of the original frequency components has changed. These changes may indicate material fatigue, crack expansion, or corrosion, because faults often introduce additional frequencies into the signal or change the amplitude of existing frequencies, thereby revealing the abnormal state of the flexible anode structure. Through a detailed analysis of the frequency components, the type and severity of the fault can be diagnosed more accurately, providing a scientific basis for maintenance decisions.

[0098] S5. Generate a fault detection report by combining the fault point detection result of the flexible anode and the prediction result of the fault prediction model.

[0099] Furthermore, the fault report includes the time and location of the fault and the systems and components involved;

[0100] In-depth analysis of the root causes of failures, providing detailed failure cause analysis, which helps identify the source of the problem;

[0101] The report provides detailed handling measures, including emergency response steps, fault repair process and corrective measures taken, and also puts forward prevention and improvement suggestions to avoid the recurrence of similar faults.

[0102] It should also be noted that the fault report not only details the specific details of the fault, such as the time of occurrence, precise location and affected system components, but also deeply analyzes the root cause of the fault, aiming to trace the source of the problem. The report includes a comprehensive response strategy, from immediate response to emergency situations to specific steps for fault repair, and then to the implementation of corrective measures to prevent future risks. In addition, the report also proactively proposes preventive maintenance suggestions and system optimization solutions, and is committed to building a long-term mechanism to prevent similar faults from happening again and ensure the continued stability and efficiency of system operation.

[0103] This embodiment also provides a flexible anode fault detection system, including: a data acquisition and preprocessing module, a fault prediction module, a fault identification module, a fault point location module and a fault detection report generation module;

[0104] A data acquisition and preprocessing module is used to collect the operating data of the flexible anode in real time and preprocess the collected operating data;

[0105] The fault prediction module builds a fault prediction model based on the preprocessed data to predict the fault of the flexible anode;

[0106] A fault identification module is used to identify the fault of the flexible anode according to the prediction result;

[0107] A fault point location module is used to transmit a detection signal to the flexible anode based on the analysis result, and detect the fault point of the flexible anode by analyzing the reflection mode of the signal;

[0108] The fault detection report generation module is used to generate a fault detection report by combining the fault point detection result of the flexible anode and the prediction result of the fault prediction model.

[0109] This embodiment also provides a computer device, which is applicable to the flexible anode fault detection method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the flexible anode fault detection method proposed in the above embodiment.

[0110] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0111] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the flexible anode fault detection method proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0112] In summary, the present invention realizes comprehensive monitoring of the operating status and improvement of data quality by real-time collection and pre-processing of the operating data of the flexible anode, and then constructs a fault prediction model based on the processed data, realizes early warning of potential faults, and improves the preventive maintenance capability of the system. Next, fault identification is performed based on the prediction results to ensure the accuracy of fault judgment, and then the fault point is accurately located by emitting detection signals and analyzing the reflection pattern, thereby enhancing the accuracy and response speed of fault diagnosis. Finally, a detailed fault report is generated based on the comprehensive fault detection results, and fault handling measures and prevention suggestions are provided, which improves the safety and reliability of the flexible anode system as a whole.

[0113] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A flexible anode fault detection method, characterized in that: include, Collect the operating data of the flexible anode in real time and pre-process the collected operating data; Based on the preprocessed data, a fault prediction model is constructed to predict the failure of the flexible anode; According to the prediction results, the flexible anode is fault-identified; Based on the analysis result, a detection signal is emitted to the flexible anode, and a fault point of the flexible anode is detected by analyzing the reflection pattern of the signal; The fault detection report is generated by combining the fault point detection results of the flexible anode and the prediction results of the fault prediction model.

2. The flexible anode fault detection method according to claim 1, characterized in that: The specific steps of real-time collection of the operating data of the flexible anode are as follows: Deploy various types of sensors at key locations of the flexible anode, including temperature sensors, current sensors, voltage sensors, and fiber Bragg grating sensors; Through the deployment of various types of sensors, the operation data of the flexible anode is collected in real time.

3. The flexible anode fault detection method according to claim 2, characterized in that: The specific steps of preprocessing the collected operation data are as follows: Wavelet transform is used for multi-scale analysis to decompose the signal into different frequency components, retaining useful information while removing high-frequency random noise; Fill missing values ​​using time series model predictions; Use Z-score standardization to convert the running data to the same magnitude; Use FFT to convert the time signal into a spectrum, analyze the frequency components of the signal, and extract the main frequency and frequency band energy characteristics; Each extracted main frequency and frequency band feature is taken as a dimension, and a multi-dimensional feature space is constructed by horizontal splicing.

4. The flexible anode fault detection method according to claim 3, characterized in that: Based on the preprocessed data, a fault prediction model is constructed to predict the fault of the flexible anode. The specific steps are as follows: Use long short-term memory network to build a fault prediction model; Divide the preprocessed dataset into training set, validation set and test set; Use the training set data to train the model, optimize the model weights through the back propagation algorithm, and minimize the loss function; Evaluate model performance on the validation set and adjust hyperparameters; Evaluate the generalization ability of the model on an independent test set; The preprocessed data set is input into the trained fault prediction model to predict the failure probability of the flexible anode. The expression is: in, represents the probability of failure of the flexible anode at time t, W out is the weight matrix of the fully connected layer, b out is the bias vector of the fully connected layer, σ represents the sigmoid function, D(t) represents the preprocessed dataset at time point t, and S is a feature transformation function.

5. The flexible anode fault detection method according to claim 4, characterized in that: According to the prediction results, the flexible anode is identified for faults. The specific steps are as follows: Based on the analysis of fault records in historical data, a safety warning threshold T is defined, and the probability of flexible anode failure is compared. and the size of the safety warning threshold T to identify faults; when When , it is considered that there is no fault in the flexible anode; when When , the flexible anode is considered to be faulty.

6. The flexible anode fault detection method according to claim 5, characterized in that: Based on the analysis result, a detection signal is emitted to the flexible anode, and the fault point of the flexible anode is detected by analyzing the reflection mode of the signal. The specific steps are as follows: When it is identified that the flexible anode is faulty, a detection signal is transmitted to the flexible anode through an electromagnetic signal transmitter; Using a receiving device, receiving a detection signal reflected from the flexible anode and carrying information about the anode structure and state, and dividing the received reflected signal into a plurality of sub-signal segments, each signal segment corresponding to a different physical position of the flexible anode; Design a position mapping function to determine the specific location of the fault point and convert the high-dimensional feature space into interpretable physical preliminary position coordinates. The expression is: Where z(t) is the initial position coordinate of the flexible anode fault point at time t, W loc is the weight matrix of the position mapping layer, b loc is the bias vector of the position mapping layer, P(z(t)) represents the position coordinates of the fault point obtained by the position mapping function P based on the position feature vector z(t) at time point t, V is the propagation speed of the detection signal in the flexible anode, and Δt is the time difference from the emission to the reflection of the detection signal. Import the preliminary position coordinates of the fault point provided by P(z(t)) into the signal analysis system as the key area for analysis; Use FFT to extract the frequency characteristics of the signal and observe whether there are new frequency components and changes in the intensity of the original components. Compare the extracted signal characteristics with the historical fault mode data to find similar characteristic patterns. Combine the preliminary position coordinates provided by P(z(t)) and the signal analysis results to generate the final fault point location.

7. The flexible anode fault detection method according to claim 6, characterized in that: The fault report includes the time and location of the fault and the systems and components involved; In-depth analysis of the root cause of the failure, providing detailed failure cause analysis; The report provides detailed handling measures, including emergency response steps, fault repair process and corrective measures taken, and also puts forward prevention and improvement suggestions.

8. A flexible anode fault detection system, based on the flexible anode fault detection method according to any one of claims 1 to 7, characterized in that: It includes data acquisition and preprocessing module, fault prediction module, fault identification module, fault point location module and fault detection report generation module; A data acquisition and preprocessing module is used to collect the operating data of the flexible anode in real time and preprocess the collected operating data; The fault prediction module builds a fault prediction model based on the preprocessed data to predict the fault of the flexible anode; A fault identification module, used for identifying the fault of the flexible anode according to the prediction result; A fault point location module is used to transmit a detection signal to the flexible anode based on the analysis result, and detect the fault point of the flexible anode by analyzing the reflection mode of the signal; The fault detection report generation module is used to generate a fault detection report by combining the fault point detection result of the flexible anode and the prediction result of the fault prediction model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the flexible anode fault detection method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the flexible anode fault detection method according to any one of claims 1 to 7 are implemented.

Images