CN115898633A - Method and system for identifying abnormal explosion pressure of cylinder - Google Patents
Method and system for identifying abnormal explosion pressure of cylinder Download PDFInfo
- Publication number
- CN115898633A CN115898633A CN202211395776.9A CN202211395776A CN115898633A CN 115898633 A CN115898633 A CN 115898633A CN 202211395776 A CN202211395776 A CN 202211395776A CN 115898633 A CN115898633 A CN 115898633A
- Authority
- CN
- China
- Prior art keywords
- data
- real
- support vector
- vector machine
- machine model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The invention provides a method and a system for identifying abnormal explosion pressure of an air cylinder, which comprises the following steps: acquiring real-time monitoring data of equipment during operation; the real-time monitoring data comprises real-time monitoring diesel engine load data and cylinder explosion pressure data; inputting real-time monitoring data into a pre-trained support vector machine model of one type, and outputting the data type of the real-time monitoring data; the data type comprises equipment normal operation data and equipment abnormal operation data; and when the real-time monitoring data is abnormal operation data of the equipment, performing equipment abnormal alarm. In the mode, the abnormal explosion pressure of the cylinder can be detected in real time and an abnormal alarm is given out by constructing a support vector machine model, so that the recognition efficiency of the abnormal explosion pressure of the cylinder is improved, and the use safety of the marine diesel engine is further improved.
Description
Technical Field
The invention relates to the field of cylinder detonation pressure of diesel engines, in particular to a method and a system for identifying abnormal detonation pressure of a cylinder.
Background
The common method for checking the explosion pressure of the cylinder of the marine diesel engine is to measure a cylinder indicator diagram and qualitatively judge according to the cylinder indicator diagram. However, the method needs a crew to manually measure the indicator diagram, the measurement result often has a certain deviation due to the external environment interference of the marine engine room, and the indicator diagram needs to be measured regularly, so that the abnormal explosion pressure of the cylinder is identified by using the indicator diagram method, which is often performed regularly, and the real-time monitoring of the abnormal explosion pressure cannot be performed, thereby forming a potential safety hazard.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for identifying an abnormal explosion pressure of an air cylinder, which can detect the abnormal explosion pressure of the air cylinder in real time and send an alarm, so as to improve the efficiency of identifying the abnormal explosion pressure of the air cylinder, and further improve the safety of a marine diesel engine.
In a first aspect, an embodiment of the present invention provides a method for identifying an abnormal explosion pressure of a cylinder, including: acquiring real-time monitoring data of equipment during operation; the real-time monitoring data comprises real-time monitoring diesel engine load data and cylinder explosion pressure data; inputting real-time monitoring data into a pre-trained support vector machine model of one type, and outputting the data type of the real-time monitoring data; the data type comprises equipment normal operation data and equipment abnormal operation data; and when the real-time monitoring data are abnormal operation data of the equipment, performing equipment abnormal alarm.
Further, a type of support vector machine model is obtained by training through the following steps: acquiring an initial cylinder explosion pressure data set when equipment normally operates; the initial cylinder explosion pressure data set comprises cylinder explosion pressure data and diesel engine load data, wherein the cylinder explosion pressure data corresponds to the cylinder explosion pressure data when a ship sails and equipment normally runs; dividing an initial cylinder explosion pressure data set into a training set and a verification set according to a preset proportion; training the initial one-class support vector machine model based on the training set until the preset training requirement is met, and obtaining a first one-class support vector machine model.
Further, after the steps of constructing an initial one-class support vector machine model based on the training set and verifying the initial one-class support vector machine model according to the verification set to obtain a first one-class support vector machine model, the method further comprises: optimizing the first type of support vector machine model according to a particle swarm optimization algorithm to obtain a second type of support vector machine model and optimal hyper-parameters of the second type of support vector machine model; verifying the second type of support vector machine model based on the verification set until a preset verification requirement is met to obtain a first type of support vector machine model; and determining a cylinder explosion pressure data set when the equipment normally operates based on the optimal hyper-parameter.
Further, the data in the initial cylinder explosion pressure data set is data obtained after normalization processing.
Further, the method further comprises: and when the real-time monitoring data are normal operation data of the equipment, optimizing a type of support vector machine model and a cylinder explosion pressure data set based on the real-time monitoring data so as to judge the type of the next real-time monitoring data. Further, when the real-time monitoring data is normal operation data of the equipment, optimizing a type of support vector machine model and a cylinder explosion pressure data set based on the real-time monitoring data so as to judge the type of the next real-time monitoring data, wherein the step comprises the following steps of: adding the real-time monitoring data into an air cylinder explosion pressure data set to obtain a first air cylinder explosion pressure data set; training one type of support vector machine model based on the first cylinder explosion pressure data set to obtain a third type of support vector machine model; optimizing based on the third type of support vector machine model according to a particle swarm optimization algorithm to obtain the optimal hyperparameter of the fourth type of support vector machine model and the fourth type of support vector machine model; and determining the fourth type of support vector machine model as a first type of support vector machine model, and determining the optimal hyperparameter of the fourth type of support vector machine model as a cylinder explosion pressure data set.
Further, the method further comprises: when the number of data in the cylinder burst pressure data set exceeds a preset number of data, a part of the data is randomly deleted so that the number of data is smaller than the preset number of data.
In a second aspect, an embodiment of the present invention provides a system for identifying an abnormal cylinder explosion pressure, including: the data acquisition module is used for acquiring real-time monitoring data of equipment during operation; the real-time monitoring data comprises real-time monitoring diesel engine load data and cylinder explosion pressure data; the analysis module is used 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 comprises equipment normal operation data and equipment abnormal operation data; and the alarm module is used for giving an alarm when the real-time monitoring data is abnormal operation data of the equipment.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory and a processor, where the memory stores a computer program that is executable on the processor, and the processor implements the method described above when executing the computer program.
In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, where the program code causes the processor to execute the method described above.
The embodiment of the invention provides a method and a system for identifying abnormal explosion pressure of an air cylinder, which comprises the following steps: acquiring real-time monitoring data of equipment during operation; the real-time monitoring data comprises real-time monitoring diesel engine load data and cylinder explosion pressure data; inputting real-time monitoring data into a pre-trained support vector machine model of one type, and outputting the data type of the real-time monitoring data; the data type comprises equipment normal operation data and equipment abnormal operation data; and when the real-time monitoring data are abnormal operation data of the equipment, performing equipment abnormal alarm. In the mode, the support vector model is constructed and continuously optimized according to real-time data, so that the abnormal explosion pressure of the cylinder can be accurately detected in real time and an abnormal alarm is given out, the recognition efficiency of the abnormal explosion pressure of the cylinder is improved, and the use safety of the marine diesel engine is further improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for identifying an abnormal explosion pressure of a cylinder according to an embodiment of the present invention;
FIG. 2 is a flowchart of a type of support vector machine model training provided in accordance with an embodiment of the present invention;
FIG. 3 is a flow chart of a type of support vector machine model optimization and verification provided in accordance with an embodiment of the present invention;
FIG. 4 is a flowchart of incremental learning of a type of support vector machine model according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a system for identifying an abnormal explosion pressure of a cylinder according to a second embodiment of the present invention.
Icon: 1-a data acquisition module; 2-an analysis module; and 3, an alarm module.
Detailed Description
To make the objects, 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, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The existing technical method for identifying cylinder detonation pressure abnormity mainly uses a method based on a cylinder indicator diagram, a method based on a model and a method based on an expert knowledge base. The method is characterized in that a pilot diagram is obtained by regular manual measurement of a crew on the basis of the pilot diagram method, and real-time explosion pressure abnormity monitoring cannot be carried out; the model-based method needs to establish a set of complex mechanism models, and the recognition precision depends heavily on the precision of the mechanism models; based on an expert knowledge base method, the knowledge acquisition and representation of the method have limitations, and the knowledge thrust depends on the knowledge experience of related professionals.
Based on the above, the method and the system for identifying the abnormal explosion pressure of the cylinder provided by the embodiment of the invention can accurately detect the abnormal explosion pressure of the cylinder in real time and send an abnormal alarm.
For the understanding of the present embodiment, the following detailed description will be given of the embodiment of the present invention.
The first embodiment is as follows:
fig. 1 is a flowchart of a method for identifying an abnormal explosion pressure of a cylinder according to an embodiment of the present invention.
Referring to fig. 1, the method of identifying an abnormal explosion pressure of a cylinder includes:
step S101, acquiring real-time monitoring data of equipment during operation; the real-time monitoring data comprises real-time monitoring diesel engine load data and cylinder explosion pressure data.
Here, the diesel engine load data may be measured by a load display device, and the cylinder explosion pressure data may be obtained by measuring an explosion pressure sensor mounted on the engine. The real-time monitoring data can be obtained on line through an on-line system.
In order to ensure that the data can be read smoothly, the real-time monitoring data can be normalized.
Step S102, inputting real-time monitoring data into a pre-trained support vector machine model of one type, and outputting the data type of the real-time monitoring data; the data types comprise normal operation data of the equipment and abnormal operation data of the equipment.
Here, real-time monitoring data is input into a type of support vector machine model that has been trained in advance, and 0 or 1 is output. And 0 represents that the data type of the real-time monitoring data is abnormal operation data of the equipment, and 1 represents that the data type of the real-time monitoring data is normal operation data of the equipment.
In one embodiment, referring to fig. 2, in step S102, a type of support vector machine model is obtained by training the following steps:
step S201, acquiring an initial cylinder explosion pressure data set when equipment normally operates; the initial cylinder explosion pressure data set comprises cylinder explosion pressure data of a ship during normal operation of the ship and equipment and diesel engine load data corresponding to the cylinder explosion pressure data.
The method comprises the steps of acquiring cylinder explosion pressure data of a ship during navigation and diesel engine load data corresponding to the cylinder explosion pressure data, and selecting the cylinder explosion pressure data as the cylinder explosion pressure data of equipment during normal operation and the diesel engine load data corresponding to the cylinder explosion pressure data.
And the data in the initial cylinder explosion pressure data set is the data obtained after normalization processing.
Step S202, the initial cylinder explosion pressure data set is divided into a training set and a verification set according to a preset proportion.
Here, the preset ratio may be set to 7, and the initial cylinder burst pressure data set is randomly divided into a training set and a verification set in a ratio of 7.
Step S203, training the initial one-class support vector machine model based on the training set until a preset training requirement is met, and obtaining a first one-class support vector machine model.
Here, an initial one-class support vector machine model is created, and the initial one-class support vector machine model is trained on the basis of a training set to find a decision function H (x), so that most samples in the training set are normal samples, i.e., H (x) =1, and only a small portion of samples are abnormal samples, i.e., H (x) = -1.
Specifically, the initial support vector machine model predicts the data type of the sample in the training set by simply calculating a decision function, and if the result is positive, the predicted data type is 1, otherwise the predicted data type is 0. The decision boundary is the set of points for which the decision function is 0. The straight line formed by the points with the decision function of 1 is parallel to the straight line formed by the points with the decision function of-1, and the distances to the decision boundary are equal, so that an interval is formed. Training the initial class of support vector machine model means finding the feature space hyperplane normal vector values w to make this one interval as large as possible while either circumventing interval violations (hard intervals) or limiting them (soft intervals).
Wherein the slope of the decision function is equal to the norm of w. If we divide this slope by 2, the point where the decision function equals ± 1 will be twice as large from the original decision boundary. In other words, the slope divided by 2, the spacing would increase by a factor of two. The smaller w, the larger the spacing. To avoid gap violations (hard gaps), we need to minimize w to obtain the maximum gap.
To achieve the goal of soft spacing, we need to apply a relaxation variable ζ to each sample i ，ζ i > 0,i =1,2,. N denotes the extent to which the ith sample allows for a violation interval. I.e., the slack variable is as small as possible to reduce the spacing violation.
In order to simultaneously satisfy the requirement of making the slack variable as small as possible so as to reduce the interval violation, and
the interval is increased by minimizing the sample number n in the training set and the proportion value v (0 < v < 1) of error samples in the samples, and the hyperparameter is determined to balance between two targets, thereby obtaining an objective function
The minimization objective function is expressed by the following formula (1):
wherein x is i Is a training set, w is a feature space hyperplane normal vector, ζ i Is a relaxation variable, rho is the feature space hyperplane compensation, n is the number of samples in the training set, v is the error sample proportion value in the samples, psi (x) i ) Is a kernel space mapping function.
Introducing a Lagrange multiplier, and calculating the dual of the feature space by the following formula (2):
wherein, K (x) i ,x j ) Is a kernel function, α i Is a lagrange multiplier.
From equations (1) and (2), the decision function of equation (3) below can be derived:
in one embodiment, referring to fig. 3, after step S203, the method further includes the following steps:
step S301, optimizing the first type of support vector machine model according to a particle swarm optimization algorithm to obtain a second type of support vector machine model and optimal hyperparameters of the second type of support vector machine model.
And optimizing the first type of support vector machine model based on the particle swarm optimization algorithm to obtain an optimized second type of support vector machine model and an optimal hyperparameter, wherein the optimal hyperparameter is an optimal configuration variable for determining the model.
And S302, verifying the second type of support vector machine model based on the verification set until a preset verification requirement is met, and obtaining the first type of support vector machine model.
Here, the second-type support vector machine model is verified based on the samples in the verification set, and the verified second-type support vector machine model is determined as the first-type support vector machine model.
Step S303, determining a cylinder burst pressure data set based on the optimal hyperparameter.
Here, a cylinder burst pressure data set is acquired to add a data type to subsequent use as real-time monitoring data when the apparatus is operating normally.
And step S103, when the real-time monitoring data is abnormal operation data of the equipment, performing equipment abnormal alarm.
Here, the device abnormality alarm mode may be set according to an actual situation, and may be an alarm mode such as sound, light, electricity, or the like, or may be an alarm signal sent to the terminal.
In one embodiment, when the real-time monitoring data is normal operation data of the equipment, one type of support vector machine model and the cylinder explosion pressure data set are optimized based on the real-time monitoring data so as to judge the type of the next real-time monitoring data.
Here, when the real-time monitoring data is normal operation data of the equipment, the real-time monitoring data is added to the cylinder explosion pressure data set, and the one type of support vector machine model is optimized in real time according to the real-time monitoring data.
Wherein when the number of data in the cylinder burst pressure data set exceeds a preset number of data, a part of the data is randomly deleted so that the number of data is less than the preset number of data.
The preset data amount can be set according to actual conditions. When the number of data in the cylinder burst pressure data set exceeds a preset number of data, the operation speed of the algorithm is reduced, so in order to maintain high-speed operation of the algorithm, part of the data may be randomly deleted if necessary.
In one embodiment, referring to fig. 4, when the real-time monitoring data is normal operation data of the device, the step of optimizing one type of support vector machine model and the cylinder burst pressure data set based on the real-time monitoring data to determine the type of the next real-time monitoring data includes:
step S401, adding the real-time monitoring data to an air cylinder explosion pressure data set to obtain a first air cylinder explosion pressure data set.
Here, the cylinder burst pressure data set is updated in real time based on the real-time monitoring data to enable incremental learning of the model.
Step S402, training the first type of support vector machine model based on the first cylinder explosion pressure data set to obtain a third type of support vector machine model.
Here, incremental learning of a type of support vector machine model is implemented based on the updated first cylinder burst pressure data set.
Step S403, according to the particle swarm optimization algorithm, optimizing based on the third-class support vector machine model to obtain the optimal hyperparameter of the fourth-class support vector machine model and the fourth-class support vector machine model.
And optimizing the updated third-class support vector machine model according to the particle swarm optimization algorithm, and acquiring the optimized optimal hyper-parameter.
Step S404, determining the fourth type of support vector machine model as a type of support vector machine model.
The fourth type of support vector machine model after incremental learning and optimization is determined as a type of support vector machine model to realize optimization of the first type of support vector machine model, so that the method is applied to judgment of the next real-time monitoring data type.
The embodiment of the invention provides a method for identifying abnormal explosion pressure of an air cylinder, which comprises the following steps: acquiring real-time monitoring data of equipment during operation; the real-time monitoring data comprises real-time monitoring diesel engine load data and cylinder explosion pressure data; inputting 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 comprises equipment normal operation data and equipment abnormal operation data; and when the real-time monitoring data is abnormal operation data of the equipment, performing equipment abnormal alarm. In the method, one type of support vector machine model is constructed, and the support vector machine model is subjected to incremental learning according to real-time data, so that the abnormal explosion pressure of the cylinder can be detected accurately in real time, an abnormal alarm is given, the recognition efficiency of the abnormal explosion pressure of the cylinder is improved, and the use safety of the marine diesel engine is improved.
Example two:
fig. 5 is a schematic diagram of a system for identifying an abnormal explosion pressure of a cylinder according to a second embodiment of the present invention.
Referring to fig. 5, a system for identifying an abnormal explosion pressure of a cylinder includes:
the data acquisition module 1 is used for acquiring real-time monitoring data during the operation of equipment; the real-time monitoring data comprises real-time monitoring diesel engine load data and cylinder explosion pressure data;
the analysis module 2 is used for inputting the real-time monitoring data into a type of support vector machine model which is trained in advance and outputting the data type of the real-time monitoring data; the data type comprises equipment normal operation data and equipment abnormal operation data;
and the alarm module 3 is used for giving an alarm when the real-time monitoring data is abnormal operation data of the equipment.
The embodiment of the invention provides a system for identifying abnormal explosion pressure of an air cylinder, which comprises the following components: acquiring real-time monitoring data of equipment during operation; the real-time monitoring data comprises real-time monitoring diesel engine load data and cylinder explosion pressure data; inputting real-time monitoring data into a pre-trained support vector machine model of one type, and outputting the data type of the real-time monitoring data; the data type comprises equipment normal operation data and equipment abnormal operation data; and when the real-time monitoring data is abnormal operation data of the equipment, performing equipment abnormal alarm. In the method, one type of support vector machine model is constructed, and the support vector machine model is subjected to incremental learning according to real-time data, so that the abnormal explosion pressure of the cylinder can be detected accurately in real time, an abnormal alarm is given, the recognition efficiency of the abnormal explosion pressure of the cylinder is improved, and the use safety of the marine diesel engine is improved.
The embodiment of the invention further provides an electronic device, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor implements the steps of the method for identifying the abnormal explosion pressure of the cylinder provided by the embodiment when executing the computer program.
Embodiments of the present invention further provide a computer readable storage medium, on which a computer program is stored, and the computer program is stored, and when the computer program is executed by a processor, the steps of the method for identifying an abnormal explosion pressure of a cylinder according to the above embodiments are executed.
The computer program product provided in the embodiment of the present invention includes a computer readable storage medium storing a program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiment, and specific implementation may refer to the method embodiment, which is not described herein again.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In addition, in the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as being fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A method for identifying an abnormal explosion pressure of a cylinder, comprising:
acquiring real-time monitoring data of equipment during operation; 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 support vector machine model, and outputting the data type of the real-time monitoring data; the data types comprise equipment normal operation data and equipment abnormal operation data;
and when the real-time monitoring data are the abnormal operation data of the equipment, performing equipment abnormal alarm.
2. The method of claim 1, wherein the one type of support vector machine model is trained by:
acquiring an initial cylinder explosion pressure data set when the equipment normally operates; the initial cylinder explosion pressure data set comprises cylinder explosion pressure data and diesel engine load data corresponding to the cylinder explosion pressure data when a ship sails and the equipment normally runs;
dividing the initial cylinder explosion pressure data set into a training set and a verification set according to a preset proportion;
training the initial one-class support vector machine model based on the training set until a preset training requirement is met, and obtaining a first one-class support vector machine model.
3. The method according to claim 2, wherein after the steps of constructing an initial one-class support vector machine model based on the training set and verifying the initial one-class support vector machine model according to the verification set to obtain a first one-class support vector machine model, further comprising:
optimizing the first type of support vector machine model according to a particle swarm optimization algorithm to obtain a second type of support vector machine model and optimal hyper-parameters of the second type of support vector machine model;
verifying the second type of support vector machine model based on the verification set until a preset verification requirement is met to obtain a type of support vector machine model;
and determining a cylinder explosion pressure data set when the equipment normally operates based on the optimal hyper-parameter.
4. The method of claim 2, wherein the data in the initial cylinder burst pressure dataset is normalized.
5. The method of claim 1, further comprising:
and when the real-time monitoring data is normal operation data of the equipment, optimizing the one type of support vector machine model and the cylinder explosion pressure data set based on the real-time monitoring data so as to judge the type of the next real-time monitoring data.
6. The method of claim 5, wherein the step of optimizing the one type of support vector machine model and the cylinder burst pressure data set based on the real-time monitored data to determine the type of next real-time monitored data when the real-time monitored data is normal operation data of the plant comprises:
adding the real-time monitoring data into the cylinder explosion pressure data set to obtain a first cylinder explosion pressure data set;
training the first type of support vector machine model based on the first cylinder explosion pressure data set to obtain a third type of support vector machine model;
optimizing based on the third type of support vector machine model according to a particle swarm optimization algorithm to obtain a fourth type of support vector machine model and optimal hyper-parameters of the fourth type of support vector machine model;
and determining the fourth type of support vector machine model as a type of support vector machine model, and determining the optimal hyperparameter of the fourth type of support vector machine model as the cylinder explosion pressure data set.
7. The method of claim 6, further comprising:
randomly deleting a portion of the data to make the data amount smaller than a preset data amount when the data amount in the cylinder burst pressure data set exceeds the preset data amount.
8. A system for identifying an abnormal explosion pressure of a cylinder, comprising:
the data acquisition module is used for acquiring real-time monitoring data of equipment during operation; the real-time monitoring data comprises real-time monitoring diesel engine load data and cylinder explosion pressure data;
the analysis module is used 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 types comprise equipment normal operation data and equipment abnormal operation data;
and the alarm module is used for giving an alarm when the real-time monitoring data is the abnormal operation data of the equipment.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1-7 when executing the computer program.
10. A computer-readable storage medium, having stored thereon a computer program, characterized in that the computer program is operative to perform the steps of the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211395776.9A CN115898633A (en) | 2022-11-08 | 2022-11-08 | Method and system for identifying abnormal explosion pressure of cylinder |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211395776.9A CN115898633A (en) | 2022-11-08 | 2022-11-08 | Method and system for identifying abnormal explosion pressure of cylinder |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115898633A true CN115898633A (en) | 2023-04-04 |
Family
ID=86496544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211395776.9A Pending CN115898633A (en) | 2022-11-08 | 2022-11-08 | Method and system for identifying abnormal explosion pressure of cylinder |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115898633A (en) |
-
2022
- 2022-11-08 CN CN202211395776.9A patent/CN115898633A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5539382B2 (en) | Identify faults in aero engines | |
| US9122273B2 (en) | Failure cause diagnosis system and method | |
| US20180365089A1 (en) | Abnormality detection system, abnormality detection method, abnormality detection program, and method for generating learned model | |
| US20140365179A1 (en) | Method and Apparatus for Detecting and Identifying Faults in a Process | |
| US9754429B2 (en) | System for monitoring a set of components of a device | |
| US20200143292A1 (en) | Signature enhancement for deviation measurement-based classification of a detected anomaly in an industrial asset | |
| EP3761133A1 (en) | Diagnosis device and diagnosis method | |
| KR20190025474A (en) | Apparatus and Method for Predicting Plant Data | |
| KR102102346B1 (en) | System and method for condition based maintenance support of naval ship equipment | |
| CN110109428B (en) | Dangerous case monitoring system for laboratory equipment | |
| KR20170127430A (en) | Method and system for detecting, classifying and / or mitigating sensor error | |
| EP2135144B1 (en) | Machine condition monitoring using pattern rules | |
| US20210374634A1 (en) | Work efficiency evaluation method, work efficiency evaluation apparatus, and program | |
| CA3127100A1 (en) | Anomaly detection for predictive maintenance and deriving outcomes and workflows based on data quality | |
| WO2020162069A1 (en) | Abnormality sensing device | |
| EP4078315A1 (en) | Device and method for monitoring a system | |
| CN111555899B (en) | Alarm rule configuration method, equipment state monitoring method, device and storage medium | |
| JP2022082277A (en) | Detection program, detection device, and detection method | |
| CN115898633A (en) | Method and system for identifying abnormal explosion pressure of cylinder | |
| CN117171657A (en) | Wind power generation equipment fault diagnosis method and device, electronic equipment and storage medium | |
| CN115729761A (en) | Hard disk fault prediction method, system, device and medium | |
| CN116360384A (en) | System and method for diagnosing and monitoring anomalies in information physical systems | |
| US11775512B2 (en) | Data analysis apparatus, method and system | |
| WO2021140942A1 (en) | Diagnosing device, diagnosing method, and program | |
| US11228606B2 (en) | Graph-based sensor ranking |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |