Method and system for identifying abnormal burst pressure of a cylinder

Abstract

The application provides a cylinder abnormal explosion pressure identification method and system, comprising: acquiring real-time monitoring data during equipment operation; wherein the real-time monitoring data comprises real-time monitoring diesel engine load data and cylinder explosion pressure data; inputting the real-time monitoring data into a pre-trained one-class support vector machine model to output a data type of the real-time monitoring data; the data type comprises equipment normal operation data and equipment abnormal operation data; when the real-time monitoring data is the equipment abnormal operation data, an equipment abnormality alarm is performed. In this way, the one-class support vector machine model can be constructed to detect the cylinder abnormal explosion pressure in real time and issue an abnormality alarm, so that the identification efficiency of the cylinder abnormal explosion pressure is improved, and the use safety of the marine diesel engine is improved.

Description

Technical Field

[0001] This invention relates to the field of diesel engine cylinder pressure explosion, and in particular to a method and system for identifying abnormal cylinder pressure explosion. Background Technology

[0002] The common method for checking the cylinder burst pressure of marine diesel engines is to measure the cylinder indicator diagram and make a qualitative judgment based on it. However, this method requires the crew to manually measure the indicator diagram. Due to interference from the external environment of the ship's engine room, the measurement results often have a certain deviation. In addition, because the indicator diagram needs to be measured periodically, the identification of abnormal cylinder burst pressure using the indicator diagram method is usually carried out on a periodic basis, and real-time monitoring of abnormal burst pressure is not possible, which creates a safety hazard. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a method and system for identifying abnormal cylinder burst pressure, which can detect abnormal cylinder burst pressure in real time and issue an alarm, thereby improving the identification efficiency of abnormal cylinder burst pressure and thus improving the safety of marine diesel engines.

[0004] In a first aspect, embodiments of the present invention provide a method for identifying abnormal cylinder burst pressure, comprising: acquiring real-time monitoring data during equipment operation; wherein the real-time monitoring data includes real-time monitored diesel engine load data and cylinder burst pressure data; inputting the real-time monitoring data into a pre-trained support vector machine model, and outputting the data type of the real-time monitoring data; the data type includes normal equipment operation data and abnormal equipment operation data; and issuing an equipment abnormality alarm when the real-time monitoring data is abnormal equipment operation data.

[0005] Furthermore, a first-class support vector machine model is trained through the following steps: obtaining an initial cylinder burst pressure dataset during normal equipment operation; wherein, the initial cylinder burst pressure dataset includes cylinder burst pressure data and corresponding diesel engine load data during ship navigation and normal equipment operation; dividing the initial cylinder burst pressure dataset into a training set and a validation set according to a preset ratio; training an initial first-class support vector machine model based on the training set until the preset training requirements are met, thus obtaining the first-class support vector machine model.

[0006] Furthermore, after the steps of constructing an initial first-class support vector machine model based on the training set and validating the initial first-class support vector machine model based on the validation set to obtain the first-class support vector machine model, the method further includes: optimizing the first-class support vector machine model according to the particle swarm optimization algorithm to obtain a second-class support vector machine model and the optimal hyperparameters of the second-class support vector machine model; validating the second-class support vector machine model based on the validation set until the preset validation requirements are met to obtain a first-class support vector machine model; and determining the cylinder burst pressure dataset during normal operation of the equipment based on the optimal hyperparameters.

[0007] Furthermore, the data in the initial cylinder burst pressure dataset is obtained after normalization processing.

[0008] Furthermore, the method also includes: when the real-time monitoring data is normal equipment operation data, optimizing a first-class support vector machine model and a cylinder explosion pressure dataset based on the real-time monitoring data to determine the type of the next real-time monitoring data. Further, the step of optimizing a first-class support vector machine model and a cylinder explosion pressure dataset based on the real-time monitoring data to determine the type of the next real-time monitoring data includes: adding the real-time monitoring data to the cylinder explosion pressure dataset to obtain a first cylinder explosion pressure dataset; training a first-class support vector machine model based on the first cylinder explosion pressure dataset to obtain a third-class support vector machine model; optimizing the third-class support vector machine model using a particle swarm optimization algorithm to obtain a fourth-class support vector machine model and its optimal hyperparameters; determining the fourth-class support vector machine model as a first-class support vector machine model, and determining the optimal hyperparameters of the fourth-class support vector machine model as the cylinder explosion pressure dataset.

[0009] Furthermore, the method also includes: when the number of data in the cylinder explosion pressure dataset exceeds the preset number of data, randomly deleting some data to make the number of data less than the preset number of data.

[0010] Secondly, embodiments of the present invention provide a system for identifying abnormal cylinder burst pressure, comprising: a data acquisition module for acquiring real-time monitoring data during equipment operation; wherein the real-time monitoring data includes real-time monitored diesel engine load data and cylinder burst pressure data; an analysis module for inputting the real-time monitoring data into a pre-trained support vector machine model and outputting the data type of the real-time monitoring data; the data type includes normal equipment operation data and abnormal equipment operation data; and an alarm module for issuing an equipment anomaly alarm when the real-time monitoring data is abnormal equipment operation data.

[0011] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the method described above.

[0012] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, the program code causing the processor to perform the method described above.

[0013] This invention provides a method and system for identifying abnormal cylinder burst pressure, comprising: acquiring real-time monitoring data during equipment operation; wherein the real-time monitoring data includes real-time monitored diesel engine load data and cylinder burst pressure data; inputting the real-time monitoring data into a pre-trained support vector machine model, and outputting the data type of the real-time monitoring data; the data type includes normal equipment operation data and abnormal equipment operation data; and issuing an equipment anomaly alarm when the real-time monitoring data is abnormal equipment operation data. In this method, by constructing a support vector machine model and continuously optimizing the model based on real-time data, abnormal cylinder burst pressure can be detected in real-time and accurately, and anomaly alarms can be issued, thereby improving the identification efficiency of abnormal cylinder burst pressure and thus enhancing the operational safety of marine diesel engines.

[0014] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0015] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a flowchart of the method for identifying abnormal cylinder burst pressure provided in Embodiment 1 of the present invention;

[0018] Figure 2 This is a flowchart of training a type of support vector machine model provided in Embodiment 1 of the present invention;

[0019] Figure 3 This is a flowchart of the optimization and verification of a support vector machine model provided in Embodiment 1 of the present invention;

[0020] Figure 4 This is a flowchart of incremental learning for a type of support vector machine model provided in Embodiment 1 of the present invention;

[0021] Figure 5 This is a schematic diagram of the cylinder abnormal burst pressure identification system provided in Embodiment 2 of the present invention.

[0022] Icons: 1-Data acquisition module; 2-Analysis module; 3-Alarm module. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] Existing technologies for identifying cylinder pressure anomalies mainly employ methods based on cylinder indicator diagrams, model-based methods, and expert knowledge base methods. Among these, the indicator diagram-based method requires crew members to manually measure and obtain indicator diagrams periodically, and cannot perform real-time pressure anomaly monitoring; the model-based method requires establishing a complex mechanistic model, and the identification accuracy heavily depends on the accuracy of the mechanistic model; the expert knowledge base-based method has limitations in knowledge acquisition and representation, and its knowledge propagation relies on the knowledge and experience of relevant professionals.

[0025] Based on this, the present invention provides a method and system for identifying abnormal cylinder burst pressure, which can detect abnormal cylinder burst pressure in real time and accurately and issue an abnormal alarm.

[0026] To facilitate understanding of this embodiment, the embodiments of the present invention will be described in detail below.

[0027] Example 1:

[0028] Figure 1 This is a flowchart of a method for identifying abnormal cylinder burst pressure provided in Embodiment 1 of the present invention.

[0029] Reference Figure 1 Methods for identifying abnormal cylinder burst pressure include:

[0030] Step S101: Obtain real-time monitoring data during equipment operation; wherein, the real-time monitoring data includes real-time monitored diesel engine load data and cylinder burst pressure data.

[0031] Here, diesel engine load data can be measured via a load display device, and cylinder combustion pressure data can be obtained via a combustion pressure sensor installed on the engine. Real-time monitoring data can be obtained online through an online system.

[0032] To ensure that the data can be read successfully, the real-time monitoring data can be normalized.

[0033] Step S102: Input the real-time monitoring data into a pre-trained support vector machine model and output the data type of the real-time monitoring data; the data type includes normal equipment operation data and abnormal equipment operation data.

[0034] Here, real-time monitoring data is input into a pre-trained support vector machine model, which outputs 0 or 1. 0 indicates that the data type of the real-time monitoring data is abnormal equipment operation data, and 1 indicates that the data type of the real-time monitoring data is normal equipment operation data.

[0035] In one embodiment, refer to Figure 2 In step S102, a support vector machine model is trained through the following steps:

[0036] Step S201: Obtain the initial cylinder burst pressure dataset when the equipment is running normally; wherein, the initial cylinder burst pressure dataset includes cylinder burst pressure data when the ship is sailing and the equipment is running normally and the corresponding diesel engine load data.

[0037] Here, the cylinder burst pressure data and corresponding diesel engine load data of the ship during navigation are obtained, and the cylinder burst pressure data is selected as the cylinder burst pressure data and corresponding diesel engine load data when the equipment is operating normally.

[0038] The data in the initial cylinder burst pressure dataset is obtained after normalization.

[0039] Step S202: Divide the initial cylinder burst pressure dataset into a training set and a validation set according to a preset ratio.

[0040] Here, the preset ratio can be set to 7:3, and the initial cylinder burst pressure dataset is randomly divided into training set and validation set according to the ratio of 7:3.

[0041] Step S203: Train an initial class of support vector machine model based on the training set until the preset training requirements are met, and obtain the first class of support vector machine model.

[0042] Here, an initial class of support vector machine model is created. Based on the training set, the initial class of support vector machine model is trained to find the decision function H(x), such that most of the samples in the training set are normal samples, i.e., H(x) = 1, and only a small portion of the samples are abnormal samples, i.e., H(x) = -1.

[0043] Specifically, the initial one-class support vector machine model predicts the data type of samples in the training set by simply calculating a decision function. If the result is positive, the predicted data type is 1; otherwise, it is 0. The decision boundary is the set of points where the decision function is 0. The line formed by the points with a decision function of 1 is parallel to the line formed by the points with a decision function of -1, and they are equidistant from the decision boundary, forming a margin. Training the initial one-class support vector machine model means finding the normal vector value w of the feature space hyperplane that maximizes this margin while avoiding margin violations (hard margin) or restricting them (soft margin).

[0044] The slope of the decision function is equal to the norm of w. If we divide this slope by 2, the points where the decision function equals ±1 will be twice as far from the original decision boundary. In other words, dividing the slope by 2 will double the margin. The smaller w is, the larger the margin. To avoid margin violations (hard margins), we need to minimize w to obtain the maximum margin.

[0045] To obtain the target of the soft margin, we need to apply a slack variable ζ to each sample. i , ζ i >0, i = 1, 2, ..., n represents the degree to which the slack variable is allowed to violate the rules. That is, the slack variable is made as small as possible to reduce the rule violation.

[0046] To simultaneously minimize the slack variable to reduce interval violations, and to make To minimize the margin, the hyperparameters are determined by the number of samples n in the training set and the proportion of erroneous samples v (0 < v < 1) to balance the two objectives, thus obtaining the objective function.

[0047]

[0048] The objective function is minimized by the following formula (1):

[0049]

[0050] Where, x i Here is the training set, w is the normal vector of the hyperplane in the feature space, and ζ is the training set. i Here, ρ is the slack variable, ρ is the hyperplane compensation in the feature space, n is the number of samples in the training set, v is the proportion of erroneous samples in the sample, and ψ(x) is the slack variable. i ) is the kernel space mapping function.

[0051] Introducing Lagrange multipliers, the duality of the characteristic space is calculated using the following formula (2):

[0052]

[0053] Where K(x) i ,x j ) is the kernel function, α i It is a Lagrange multiplier.

[0054] Based on formulas (1) and (2), the decision function of formula (3) can be derived as follows:

[0055]

[0056] In one embodiment, refer to Figure 3 After step S203, the following steps are also included:

[0057] Step S301: Optimize the first type of support vector machine model according to the particle swarm optimization algorithm to obtain the optimal hyperparameters of the second type of support vector machine model and the second type of support vector machine model.

[0058] Here, the first type of support vector machine model is optimized based on the particle swarm optimization algorithm to obtain the optimized second type of support vector machine model and the optimal hyperparameters, where the optimal hyperparameters are the optimal configuration variables used to determine the model.

[0059] Step S302: Validate the second type of support vector machine model based on the validation set until the preset validation requirements are met, and obtain a type of support vector machine model.

[0060] Here, the second type of support vector machine model is validated based on the samples in the validation set, and the second type of support vector machine model that passes the validation is determined as a type of support vector machine model.

[0061] Step S303: Based on the optimal hyperparameters, determine the cylinder burst pressure dataset.

[0062] Here, the cylinder burst pressure dataset is obtained to add a data type for real-time monitoring data during normal operation of the equipment in subsequent use.

[0063] Step S103: When the real-time monitoring data is abnormal equipment operation data, issue an equipment abnormality alarm.

[0064] Here, the alarm method for equipment abnormality can be set according to the actual situation. It can be an alarm method such as sound, light, or electricity, or it can be an alarm signal sent to the terminal.

[0065] In one embodiment, when the real-time monitoring data is normal equipment operation data, a support vector machine model and a cylinder burst pressure dataset are optimized based on the real-time monitoring data in order to determine the type of the next real-time monitoring data.

[0066] Here, when the real-time monitoring data is the normal operating data of the equipment, the real-time monitoring data is added to the cylinder burst pressure dataset, and a support vector machine model is optimized in real time based on the real-time monitoring data.

[0067] Specifically, when the number of data in the cylinder burst pressure dataset exceeds the preset number of data, some data is randomly deleted to make the number of data less than the preset number of data.

[0068] The preset data quantity can be set according to actual conditions. When the number of data in the cylinder explosion pressure dataset exceeds the preset data quantity, the algorithm's running speed decreases. Therefore, in order to maintain the high-speed operation of the algorithm, some data can be randomly deleted if necessary.

[0069] In one embodiment, refer to Figure 4 When the real-time monitoring data is normal equipment operation data, the steps of optimizing a support vector machine model and a cylinder burst pressure dataset based on the real-time monitoring data to determine the type of the next real-time monitoring data include:

[0070] Step S401: Add the real-time monitoring data to the cylinder burst pressure dataset to obtain the first cylinder burst pressure dataset.

[0071] Here, the cylinder burst pressure dataset is updated in real time based on real-time monitoring data to achieve incremental learning of the model.

[0072] Step S402: Train a first-class support vector machine model based on the first cylinder burst pressure dataset to obtain a third-class support vector machine model.

[0073] Here, incremental learning of a support vector machine model is achieved based on the updated first cylinder burst pressure dataset.

[0074] Step S403: Based on the particle swarm optimization algorithm, optimize the third type of support vector machine model to obtain the fourth type of support vector machine model and the optimal hyperparameters of the fourth type of support vector machine model.

[0075] Here, the updated third type of support vector machine model is optimized based on the particle swarm optimization algorithm, and the optimal hyperparameters are obtained after optimization.

[0076] Step S404: The fourth type of support vector machine model is determined as a type of support vector machine model.

[0077] Here, the fourth type of support vector machine model, which has been incrementally learned and optimized, is identified as a type of support vector machine model in order to achieve optimization of the type of support vector machine model, and then apply it to the judgment of the data type of the next real-time monitoring data.

[0078] This invention provides a method for identifying abnormal cylinder burst pressure, comprising: acquiring real-time monitoring data during equipment operation; wherein the real-time monitoring data includes real-time monitored diesel engine load data and cylinder burst pressure data; inputting the real-time monitoring data into a pre-trained support vector machine model, and outputting the data type of the real-time monitoring data; the data type includes normal equipment operation data and abnormal equipment operation data; and issuing an equipment anomaly alarm when the real-time monitoring data is abnormal equipment operation data. In this method, by constructing a support vector machine model and incrementally learning the model based on real-time data, abnormal cylinder burst pressure can be detected in real-time and accurately, and anomaly alarms can be issued, thereby improving the identification efficiency of abnormal cylinder burst pressure and thus enhancing the operational safety of marine diesel engines.

[0079] Example 2:

[0080] Figure 5 This is a schematic diagram of the cylinder abnormal burst pressure identification system provided in Embodiment 2 of the present invention.

[0081] Reference Figure 5 A system for identifying abnormal cylinder burst pressure, comprising:

[0082] Data acquisition module 1 is used to acquire real-time monitoring data during equipment operation; wherein, the real-time monitoring data includes real-time monitored diesel engine load data and cylinder explosion pressure data;

[0083] Analysis module 2 is used to input real-time monitoring data into a pre-trained support vector machine model and output the data types of real-time monitoring data; the data types include normal equipment operation data and abnormal equipment operation data;

[0084] Alarm module 3 is used to issue an alarm for equipment malfunction when the real-time monitoring data indicates abnormal equipment operation.

[0085] This invention provides a system for identifying abnormal cylinder burst pressure, comprising: acquiring real-time monitoring data during equipment operation; wherein the real-time monitoring data includes real-time monitored diesel engine load data and cylinder burst pressure data; inputting the real-time monitoring data into a pre-trained support vector machine model, and outputting the data type of the real-time monitoring data; the data type includes normal equipment operation data and abnormal equipment operation data; and issuing an equipment anomaly alarm when the real-time monitoring data is abnormal equipment operation data. In this method, by constructing a support vector machine model and incrementally learning the model based on real-time data, abnormal cylinder burst pressure can be detected in real-time and accurately, and anomaly alarms can be issued, thereby improving the identification efficiency of abnormal cylinder burst pressure and thus enhancing the operational safety of marine diesel engines.

[0086] This invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method for identifying abnormal cylinder burst pressure provided in the above embodiments.

[0087] This invention also provides a computer-readable storage medium storing a computer program. The computer program, when run by a processor, executes the steps of the cylinder abnormal burst pressure identification method described in the above embodiments.

[0088] The computer program product provided in this embodiment of the invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0089] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system and apparatus described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0090] Furthermore, in the description of the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances.

[0091] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the 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 cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0092] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0093] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for identifying abnormal burst pressure in a cylinder, characterized in that, include: Acquire real-time monitoring data during equipment operation; wherein, the real-time monitoring data includes real-time monitored diesel engine load data and cylinder combustion pressure data; The real-time monitoring data is input into a pre-trained support vector machine model, and the data type of the real-time monitoring data is output; the data type includes normal equipment operation data and abnormal equipment operation data. When the real-time monitoring data is abnormal operating data of the device, an equipment abnormality alarm is issued; The aforementioned support vector machine model is trained through the following steps: Obtain the initial cylinder burst pressure dataset when the equipment is operating normally; wherein, the initial cylinder burst pressure dataset includes cylinder burst pressure data when the ship is underway and the equipment is operating normally and the corresponding diesel engine load data; The initial cylinder burst pressure dataset is divided into a training set and a validation set according to a preset ratio; The initial first-class support vector machine model is trained based on the training set until the preset training requirements are met, thus obtaining the first-class support vector machine model. After the steps of constructing an initial first-class support vector machine model based on the training set and validating the initial first-class support vector machine model according to the validation set to obtain the first-class support vector machine model, the method further includes: Based on the particle swarm optimization algorithm, the first type of support vector machine model is optimized to obtain the second type of support vector machine model and the optimal hyperparameters of the second type of support vector machine model. The second type of support vector machine model is verified based on the verification set until the preset verification requirements are met, thus obtaining a type of support vector machine model. Based on the optimal hyperparameters, determine the cylinder burst pressure dataset during normal operation of the equipment; The method further includes: When the real-time monitoring data is the normal operating data of the equipment, the support vector machine model and the cylinder burst pressure dataset are optimized based on the real-time monitoring data in order to determine the type of the next real-time monitoring data; The step of optimizing the support vector machine model and the cylinder burst pressure dataset based on the real-time monitoring data when the real-time monitoring data is normal operating data of the equipment, in order to determine the type of the next real-time monitoring data, includes: The real-time monitoring data is added to the cylinder burst pressure dataset to obtain the first cylinder burst pressure dataset; The first type of support vector machine model is trained based on the first cylinder burst pressure dataset to obtain the third type of support vector machine model. Based on the particle swarm optimization algorithm, the third type of support vector machine model is optimized to obtain the fourth type of support vector machine model and the optimal hyperparameters of the fourth type of support vector machine model. The fourth type of support vector machine model is determined as a type of support vector machine model, and the optimal hyperparameter of the fourth type of support vector machine model is determined as the cylinder burst pressure dataset. The method further includes: When the number of data in the cylinder burst pressure dataset exceeds the preset number of data, some data is randomly deleted to make the number of data less than the preset number of data.

2. The method according to claim 1, characterized in that, The data in the initial cylinder burst pressure dataset is obtained after normalization processing.

3. A system for identifying abnormal burst pressure in a cylinder, characterized in that, A system for performing the method for identifying abnormal cylinder burst pressure as described in any one of claims 1-2; the system comprises: The data acquisition module is used to acquire real-time monitoring data during equipment operation; wherein, the real-time monitoring data includes real-time monitored diesel engine load data and cylinder combustion pressure data; The analysis module is used to input the real-time monitoring data into a pre-trained support vector machine model and output the data type of the real-time monitoring data; the data type includes normal equipment operation data and abnormal equipment operation data; The alarm module is used to issue an alarm for abnormal equipment operation when the real-time monitoring data is abnormal equipment operation data.

4. An electronic device, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the method described in any one of claims 1-2.

5. A computer-readable storage medium storing a computer program thereon, characterized in that, The computer program executes the steps of the method as described in any one of claims 1-2 when it runs.

Images