Air valve fault detection method, system and equipment and medium

Abstract

The invention discloses an air valve fault detection method, system and device and a medium, and the method comprises the steps: firstly collecting various performance parameters of an air valve through a sensor, then carrying out the corresponding preprocessing and feature extraction processing of the various performance parameters, and finally carrying out the fault classification through employing a support vector machine algorithm optimized by an ocean food grammer, the air valve fault detection system realizes rapid and accurate detection of air valve faults, has high anti-interference capability, can adapt to complex industrial environments and variable working conditions, is easy to integrate and expand, effectively improves reliability and maintenance efficiency of equipment, reduces downtime and reduces production cost. The working state of the air valve can be accurately detected in real time, potential fault problems can be found in advance, and the fault detection precision and response speed of the air valve are greatly improved.

Description

Technical Field

[0001] This application relates to the technical field of air valve fault detection, and particularly to a method, system, device and medium for detecting air valve faults. Background Art

[0002] Air valves are widely used in many industrial equipment, such as automated production lines, pulp air bags, pneumatic equipment, etc. The normal operation of air valves is the key to ensuring the stability and safety of equipment. However, various faults may occur during the long-term use of air valves, such as air flow blockage, valve jamming, leakage, etc. These faults are often not easily detected. Once they occur, they may cause equipment shutdown, efficiency decline, and even safety accidents.

[0003] Existing air valve fault detection methods mostly rely on manual regular inspections or traditional sensor signal acquisitions, but these methods often have disadvantages such as long detection cycles, poor real-time performance, and susceptibility to external interference. Therefore, a new type of air valve fault detection method is urgently needed. Summary of the Invention

[0004] The purpose of this application is to provide a method, system, device and medium for detecting air valve faults, so as to solve the problems in the related art that the detection method of air valve faults has a long detection cycle, poor real-time performance, and is easily affected by external interference.

[0005] To achieve the above purpose, this application provides the following technical solutions:

[0006] In the first aspect, a method for detecting air valve faults provided by this application includes:

[0007] Obtain various performance parameters of the air valve during operation, and construct a first set of performance parameters according to the various performance parameters;

[0008] Preprocess each performance parameter in the first set of performance parameters to obtain a second set of performance parameters;

[0009] Extract characteristic parameters from the second set of performance parameters to obtain a set of characteristic parameters;

[0010] Construct a fault prediction classification model based on a support vector machine optimized by marine predator optimization according to the set of characteristic parameters;

[0011] Obtain real-time data of various performance parameters of the air valve during operation, and input the real-time data into the fault prediction classification model to obtain the result of fault prediction classification.

[0012] Further, the extracting characteristic parameters from the second set of performance parameters to obtain a set of characteristic parameters includes:

[0013] Standardize the performance parameters in the second set of performance parameters;

[0014] Calculate the maximum correlation and minimum redundancy of the standardized performance parameters;

[0015] Sort the performance parameters according to the calculation results of the maximum correlation and minimum redundancy;

[0016] Select the first N performance parameters as feature parameters according to the sorting results, where N is a positive integer greater than or equal to 1;

[0017] Form a set of feature parameters according to the feature parameters.

[0018] Further, the following calculation formula is used for standardizing the performance parameters in the second set of performance parameters:

[0019]

[0020] where μ is the mean of each performance parameter, and σ is the standard deviation of each performance parameter.

[0021] Further, the following calculation formula is used for calculating the maximum correlation and minimum redundancy of the standardized performance parameters:

[0022] Maximum correlation:

[0023] Relevance(x i ,y)=MI(x i ,y)

[0024] Minimum redundancy:

[0025] Redundancy(x i ,y i )=MI(x i ,y i )

[0026] where x i is each performance parameter, y is the target variable, and MI represents mutual information.

[0027] Further, the following calculation formula is used for sorting the performance parameters according to the calculation results of the maximum correlation and minimum redundancy:

[0028]

[0029] where x i is each performance parameter, and y is the target variable.

[0030] Further, based on the set of characteristic parameters, an optimized support vector machine fault prediction classification model for marine predators is constructed, using the following calculation formula:

[0031] X i = [C i , γ i

[0032] F i = Accuracy(C i , γ i )

[0033]

[0034] where C i and γ i are respectively the SVM hyperparameters of the i-th predator, X best is the position of the predator with the highest fitness, α is the step factor, β is the control parameter, and rand is a random number.

[0035] Further, the method further includes:

[0036] Evaluating the results of the fault prediction classification model, and the evaluation metrics include: precision and recall rate;

[0037] The calculation formula for the precision is as follows:

[0038]

[0039] The calculation formula for the recall rate is as follows:

[0040]

[0041] where True Positives (TP) is the number of samples correctly predicted as faults by the model, False Positives (FP) is the number of normal samples mispredicted as faults by the model, and False Negatives (FN) is the number of fault samples mispredicted as normal by the model.

[0042] In a second aspect, the present application further provides a detection system for air valve faults, including:

[0043] A data acquisition module, configured to acquire various performance parameters of the air valve during operation, and construct a first set of performance parameters based on the various performance parameters;

[0044] A preprocessing module, configured to preprocess each performance parameter in the first set of performance parameters to obtain a second set of performance parameters;

[0045] ​A feature parameter extraction module, configured to extract feature parameters from the second performance parameter set to obtain a feature parameter set;

[0046] A construction module, configured to construct a fault prediction classification model based on a support vector machine optimized by marine predator optimization according to the feature parameter set;

[0047] A fault prediction classification module, configured to obtain real-time data of various performance parameters of the air valve during operation, and input the real-time data into the fault prediction classification model to obtain a fault prediction classification result.

[0048] In a third aspect, the present application further provides a computer electronic device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the air valve fault detection method described in any one of the above are implemented.

[0049] In a fourth aspect, the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the air valve fault detection method described in any one of the above are implemented.

[0050] The air valve fault detection method, system, device, and medium provided by the present application have the beneficial effects that:

[0051] The air valve fault detection method of the present application can accurately and real-time detect the working state of the air valve through the collaborative work of multiple sensors, combined with signal processing and data analysis technologies, and can discover potential fault problems in advance, greatly improving the detection accuracy and response speed of air valve faults. In addition, the support vector machine algorithm optimized by marine predators is used for fault pattern recognition, enabling the detection system to adaptively adjust according to different working environments and air valve types, improving the versatility and robustness of the system. Description of the Drawings

[0052] Figure 1 is a flowchart of an air valve fault detection method in an embodiment of the present application;

[0053] Figure 2 is a structural diagram of an air valve fault detection system in an embodiment of the present application;

[0054] Figure 3 is a structural diagram of a computer electronic device in an embodiment of the present application. Detailed Embodiments

[0055] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0056] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly on the other element or there may also be an intermediate element. When an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be an intermediate element at the same time. On the contrary, when an element is referred to as being "directly on" another element, there is no intermediate element. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0057] In the present application, unless otherwise clearly defined and limited, the terms such as "installed", "connected", "connected", "fixed", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal communication of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0058] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, the meaning of "a plurality" is two or more unless otherwise specifically defined.

[0059] The terms used in one or more embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit one or more embodiments of the present application. The singular forms of "a", "the" and "said" used in one or more embodiments of the present application are also intended to include the plural forms unless the context clearly indicates otherwise.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used in the specification of this template herein are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0061] It should be understood that although the terms first, second, etc. may be used in one or more embodiments of the present application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of one or more embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while".

[0062] Currently, existing methods for detecting air valve failures mostly rely on manual regular inspections or traditional sensor signal acquisitions, but these methods often have drawbacks such as long detection cycles, poor real-time performance, and susceptibility to external interference.

[0063] The following uses specific embodiments to elaborate in detail on the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems. These several specific embodiments below can be combined with each other, and the same or similar concepts or processes will not be elaborated in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

[0064] Please refer to Figure 1 , a method for detecting air valve failures provided by an embodiment of the present application includes at least the following steps:

[0065] S10. Obtain various performance parameters of the air valve during operation, and construct a first set of performance parameters based on the various performance parameters.

[0066] Specifically, by arranging sensors, during the operation of the air valve, various sensors collect performance parameters such as the pressure at the intake end of the air valve, the pressure at the outlet end of the air valve, the air valve flow rate, and the air valve temperature in real time.

[0067] It can be understood that the above performance parameters can be historical data or data obtained from other professional data sources.

[0068] It should be noted that in this embodiment, the air valve state will be defined as a normal state, a leakage failure, a blockage failure, an overheat failure, and other failures.

[0069] S20. Preprocess each performance parameter in the first set of performance parameters to obtain a second set of performance parameters.

[0070] Specifically, the prediction operations include: denoising, filling missing values, standardizing, etc. for the collected data. After the data passes through the preprocessing operations, the quality and accuracy of the data can be guaranteed to facilitate the subsequent use of the data.

[0071] S30. Extract feature parameters from the second set of performance parameters to obtain a set of feature parameters.

[0072] Specifically, in this embodiment, the maximum relevance and minimum redundancy (mRMR) method is used to extract the key features related to the performance of the air valve from multi-dimensional data, providing a basis for subsequent evaluation. The specific steps are as follows:

[0073] S301. Standardize the performance parameters in the second set of performance parameters.

[0074] It can be understood that in the embodiment, the input data is standardized to eliminate the influence of different dimensions.

[0075] In a specific embodiment of the present application, the following calculation formula is specifically used for the standardization process:

[0076]

[0077] where μ is the mean of each performance parameter, and σ is the standard deviation of each performance parameter.

[0078] S302. Calculate the maximum relevance and minimum redundancy of the standardized performance parameters.

[0079] Specifically, the maximum relevance is defined as follows: Calculate the correlation (maximum relevance) between the feature and the target variable. The mutual information method is used to select the features that are highly correlated with the target variable (the failure type of the air valve). For each feature x i , calculate its correlation with the target variable y, and the specific calculation is as follows:

[0080] Relevance(x i , y) = MI(x i , y)

[0081] where MI represents mutual information.

[0082] The minimum redundancy is defined as follows: Calculate the redundancy (minimum redundancy) between the features. This step is achieved by calculating the similarity or correlation between the features and requires that the redundancy between the features be as small as possible. For each pair of features x i and y i , calculate their correlation using the following formula.

[0083] Redundancy(x i , y i ) = MI(x i , y i )

[0084] S303. Sort the performance parameters according to the calculation results of the maximum correlation and minimum redundancy.

[0085] Specifically, first, determine the objective function: According to the objective function of maximum correlation and minimum redundancy, select features that are highly correlated with the target variable and have a low redundancy. The selection criterion of this method is usually optimized through the following objective function.

[0086]

[0087] Among them, x i is each feature, and y is the target variable. The goal is to select features with high correlation but low redundancy.

[0088] Secondly, sort all feature parameters according to the objective function value of mRMR.

[0089] S304. According to the sorting result, select the top N performance parameters as feature parameters, where N is a positive integer greater than or equal to 1.

[0090] Specifically, select the features with higher rankings as the final feature set. Exemplarily, the top three, top four, or top five can be selected.

[0091] In a specific embodiment, through calculation, it is finally determined that the intake end pressure, outlet end pressure, valve temperature, and valve flow rate are the main feature parameters.

[0092] S305. Form a feature parameter set according to the feature parameters.

[0093] S40. Construct a fault prediction classification model based on the marine predator optimization support vector machine according to the feature parameter set.

[0094] Specifically, by optimizing the key parameters of the SVM model by marine predators, improve the classification performance of the model under different fault modes (such as leakage, blockage, and overheating, etc.), and the specific steps are as follows:

[0095] S401: Dataset division. Divide the training set and the test set according to the ratio of 8:2. The division of the dataset can adopt the random sampling method to ensure that the training set and the test set are representative under various fault states.

[0096] S402: Initialize the predator position. The position of the predator is represented as the hyperparameter configuration of the SVM (penalty factor C and kernel function parameter γ) in the solution space, and initialize it. Assume there are N predators (i.e., individuals), and the position of each predator is:

[0097] X i =[C i ,γi

[0098] Among them, C i and γ i are the SVM hyperparameters of the i-th predator respectively.

[0099] S43: Calculate the fitness function. In each iteration, the fitness of each predator is determined by the performance of its corresponding SVM classifier. The fitness function is evaluated by calculating the accuracy of the SVM through cross-validation. As shown in the following formula. The higher the fitness function, the better the SVM classification performance.

[0100] F i = Accuracy(C i , γ i )

[0101] S404: Update the predator position. According to the fitness value of each predator, update its position. Suppose there are N predators, and the position update formulas of each predator in the search and capture phases are as follows respectively.

[0102] Food search phase: The predator moves towards the direction of the food source, which is the position of the predator with the highest fitness.

[0103]

[0104] Among them, X best is the position of the predator with the highest fitness, and α is the step factor, usually set as a small constant to control the moving speed.

[0105] Food capture and exploitation phase: When the predator approaches the food source, a more refined search is carried out.

[0106]

[0107] Among them, β is another control parameter, and rand is a random number to ensure that the predator conducts random exploration within the solution space.

[0108] S405: Iteration termination. After each iteration, update the fitness and the predator position. When the algorithm converges or reaches the maximum number of iterations, select the position of the predator with the highest fitness as the optimal solution, that is, the optimal SVM parameters C and γ.

[0109] S50. Obtain the real-time data of various performance parameters of the air valve during operation, and input the real-time data into the fault prediction classification model to obtain the result of fault prediction classification.

[0110] ​Specifically, by inputting the real-time data during the operation of the air valve into the fault prediction classification model, the fault prediction classification model can identify potential fault types and send out warning messages in advance.

[0111] In one embodiment of the present application, the method further includes:

[0112] Evaluating the results of the fault prediction classification model, and the evaluation metrics include: precision and recall;

[0113] The calculation formula of the precision is as follows:

[0114]

[0115] The calculation formula of the recall is as follows:

[0116]

[0117] Where, True Positives (TP) is the number of samples correctly predicted as faults by the model, False Positives (FP) is the number of normal samples wrongly predicted as faults by the model, and False Negatives (FN) is the number of fault samples wrongly predicted as normal by the model.

[0118] In the specific implementation process, the model is tested with the following actual data. The air valve states are defined as normal state, leakage fault, blockage fault, overheat fault and other faults, which are represented by 0, 1, 2, 3, 4 respectively. A total of 200 groups of data are collected, as shown in Table 1.

[0119]

[0120] Through calculation, the precision of the model is 0.98 and the recall is 0.99, which indicates that the model performs very well in fault detection, has high prediction accuracy and fault identification ability, and can be effectively used for further fault diagnosis.

[0121] The beneficial effect of the air valve fault detection method provided by the present application is that: the air valve fault detection method and device of the present application can accurately and real-time detect the working state of the air valve through the collaborative work of multiple sensors, combined with modern signal processing and data analysis technologies, and can discover potential fault problems in advance, greatly improving the detection accuracy and response speed of air valve faults. In addition, the support vector machine algorithm optimized by the marine predator optimization is used for fault pattern recognition, so that the detection system can be adaptively adjusted according to different working environments and air valve types, improving the versatility and robustness of the system.

[0122] Please refer to Figure 2 , the present application also provides an air valve fault detection system 200, including:

[0123] The data acquisition module 201 is configured to acquire various performance parameters of the air valve during operation, and construct a first set of performance parameters according to the various performance parameters;

[0124] The preprocessing module 202 is configured to preprocess each performance parameter in the first set of performance parameters to obtain a second set of performance parameters;

[0125] The feature parameter extraction module 203 is configured to extract feature parameters from the second set of performance parameters to obtain a set of feature parameters;

[0126] The construction module 204 is configured to construct a fault prediction classification model based on the marine predator optimization support vector machine according to the set of feature parameters;

[0127] The fault prediction classification module 205 is configured to acquire real-time data of various performance parameters of the air valve during operation, and input the real-time data into the fault prediction classification model to obtain the result of fault prediction classification.

[0128] Please refer to Figure 3 , an embodiment of the present application further provides a computer electronic device 300, including a memory 303 and a processor 302. The memory 303 stores a computer program, and when the processor executes the computer program, the steps of the air valve fault detection method described in any one of the above are implemented.

[0129] Specifically, the electronic device 300 includes: a transceiver 301, a bus interface, and a processor 302. The processor 302 is configured to acquire various performance parameters of the air valve during operation, and construct a first set of performance parameters according to the various performance parameters; preprocess each performance parameter in the first set of performance parameters to obtain a second set of performance parameters; extract feature parameters from the second set of performance parameters to obtain a set of feature parameters; construct a fault prediction classification model based on the marine predator optimization support vector machine according to the set of feature parameters; acquire real-time data of various performance parameters of the air valve during operation, and input the real-time data into the fault prediction classification model to obtain the result of fault prediction classification.

[0130] In an embodiment of the present application, the electronic device 300 further includes: a memory 303. In Figure 3Among them, the bus architecture may include any number of interconnected buses and bridges, and various circuits of one or more processors represented by processor 302 and memory represented by memory 303 are specifically linked together. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, and thus will not be further described herein. The bus interface provides an interface. The transceiver 301 may be multiple components, that is, including a transmitter and a receiver, and provides a unit for communicating with various other devices on the transmission medium. The processor 302 is responsible for managing the bus architecture and general processing, and the memory 303 may store data used by the processor 302 when executing operations.

[0131] An embodiment of this application also provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the detection method for the gas valve failure described in any one of the above are implemented.

[0132] In this embodiment, the computer-readable storage medium may be a non-volatile storage medium or a volatile storage medium. For example, the computer storage medium may include but is not limited to: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs and other various media that can store program codes.

[0133] In all the examples shown and described here, any specific value should be construed as merely exemplary, rather than as a limitation. Therefore, other examples of the exemplary embodiments may have different values.

[0134] It should be noted that: similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0135] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and structural diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of this application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the blocks can occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the structural diagram and / or flowchart, as well as the combination of blocks in the structural diagram and / or flowchart, can be implemented by a dedicated hardware-based system that executes the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0136] In addition, each functional module or unit in various embodiments of this application can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0137] If the described function is implemented in the form of a software functional module 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 this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a terminal device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application.

[0138] As described above, the above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, and all of them should be covered within the protection scope of this application.

Claims

1. A method for detecting a gas valve fault, characterized in that Including: Obtain various performance parameters of the air valve during operation, and construct a first set of performance parameters according to the various performance parameters; Preprocess each performance parameter in the first set of performance parameters to obtain a second set of performance parameters; Extract characteristic parameters from the second set of performance parameters to obtain a set of characteristic parameters; Construct a fault prediction classification model based on a support vector machine optimized by marine predators according to the set of characteristic parameters; Obtain real-time data of various performance parameters of the air valve during operation, and input the real-time data into the fault prediction classification model to obtain the result of fault prediction classification.

2. The detection method for the gas valve failure according to claim 1, characterized in that The extracting characteristic parameters from the second set of performance parameters to obtain a set of characteristic parameters includes: Perform standardization processing on the performance parameters in the second set of performance parameters; Calculate the maximum correlation and minimum redundancy of the performance parameters after standardization processing; Sort the performance parameters according to the calculation results of the maximum correlation and minimum redundancy; According to the sorting result, select the first N performance parameters as characteristic parameters, where N is a positive integer greater than or equal to 1; Form a set of characteristic parameters according to the characteristic parameters.

3. The detection method of the gas valve failure according to claim 2, wherein The formula for performing standardization processing on the performance parameters in the second set of performance parameters is as follows: where μ is the mean of each performance parameter, and σ is the standard deviation of each performance parameter.

4. The detection method for air valve failure according to claim 2, characterized in that, The formula for calculating the maximum correlation and minimum redundancy of the performance parameters after standardization processing is as follows: Maximum correlation: Relevance(x i ,y) = MI(x i ,y) Minimum redundancy: Redundancy(x i ,y i ) = MI(x i ,y i ) where x i is each performance parameter, y is the target variable, and MI represents mutual information.

5. The detection method for the gas valve fault according to claim 2, characterized in that, The formula for sorting the performance parameters according to the calculation results of the maximum correlation and minimum redundancy is as follows: where x i is each performance parameter and y is the target variable.

6. The detection method for air valve failure according to claim 1, wherein The formula for constructing a fault prediction classification model based on a support vector machine optimized by marine predators according to the set of characteristic parameters is as follows: X i = [C i , γ i ​ F i = Accuracy(C i ,γ i ) Among them, C i and γ i are the SVM hyperparameters of the i-th predator respectively, X best is the position of the predator with the highest fitness, α is the step size factor, β is the control parameter, and rand is a random number.

7. The detection method for the gas valve fault according to claim 1, characterized in that, The method further includes: Evaluate the result of the fault prediction classification model, and the evaluation indexes include: precision and recall rate; The formula for the precision rate is as follows: The formula for the recall rate is as follows: where True Positives (TP) is the number of samples correctly predicted as faults by the model, False Positives (FP) is the number of normal samples wrongly predicted as faults by the model, and False Negatives (FN) is the number of fault samples wrongly predicted as normal by the model.

8. A detection system for air valve faults, characterized in that, Including: A data acquisition module, configured to obtain various performance parameters of the air valve during operation, and construct a first set of performance parameters according to the various performance parameters; A preprocessing module, configured to preprocess each performance parameter in the first set of performance parameters to obtain a second set of performance parameters; A characteristic parameter extraction module, configured to extract characteristic parameters from the second set of performance parameters to obtain a set of characteristic parameters; A construction module, configured to construct a fault prediction classification model based on a support vector machine optimized by marine predators according to the set of characteristic parameters; A fault prediction and classification module, configured to obtain real-time data of various performance parameters of the air valve during operation, and input the real-time data into the fault prediction and classification model to obtain the result of fault prediction and classification.

9. A computer electronic device, characterized in that, It includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of the air valve fault detection method according to any one of claims 1-7 are implemented.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of the air valve fault detection method according to any one of claims 1-7 are implemented.

Images