CN116010809A - Abnormal state monitoring method and device for fuel flow meter of marine diesel engine - Google Patents
Abnormal state monitoring method and device for fuel flow meter of marine diesel engine Download PDFInfo
- Publication number
- CN116010809A CN116010809A CN202211367279.8A CN202211367279A CN116010809A CN 116010809 A CN116010809 A CN 116010809A CN 202211367279 A CN202211367279 A CN 202211367279A CN 116010809 A CN116010809 A CN 116010809A
- Authority
- CN
- China
- Prior art keywords
- training
- data
- abnormal
- real
- support vector
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000012544 monitoring process Methods 0.000 title claims abstract description 53
- 239000000446 fuel Substances 0.000 title claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 112
- 238000012706 support-vector machine Methods 0.000 claims abstract description 38
- 230000006870 function Effects 0.000 claims description 19
- 230000005856 abnormality Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 8
- 239000002283 diesel fuel Substances 0.000 claims description 5
- 238000012806 monitoring device Methods 0.000 claims description 5
- 108010046685 Rho Factor Proteins 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 230000001360 synchronised effect Effects 0.000 description 9
- 230000005291 magnetic effect Effects 0.000 description 5
- 230000003068 static effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 235000019800 disodium phosphate Nutrition 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005294 ferromagnetic effect Effects 0.000 description 1
Images
Landscapes
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The embodiment of the application provides a ship diesel engine fuel flow meter abnormal state monitoring method, a device, electronic equipment and a storage medium. The design method comprises the following steps: acquiring a training database, wherein the training database comprises training data representing the total power of a ship generator set and the normal flow rate of a flowmeter; training the support vector machines according to the training database to obtain trained support vector machines; performing anomaly monitoring on the real-time flow data according to the trained support vector machine to obtain an anomaly monitoring result; and responding to the abnormal monitoring result to represent the abnormal real-time flow data, and sending abnormal alarm information of the flowmeter. The abnormal state of the fuel flow meter of the marine diesel engine can be identified in real time, and the generator set does not need to be closed.
Description
Technical Field
The application relates to the technical field of ships, in particular to a ship diesel engine fuel flow meter abnormal state monitoring method, a device, electronic equipment and a storage medium.
Background
The ship generator supplies power for the whole ship power grid, and normally the ship generator continuously works all the time, and the generator set cannot be closed. Because the generator set continues to consume a constant amount of fuel, the generator meter fuel inlet rate is typically greater than the outlet rate, and thus it is difficult to identify meter anomalies such as the most common meter deviation faults. Due to the specificity of the ship generator set, it is often difficult to identify anomalies such as generator flow meter deviations. The common practice is to stop all ship generator sets, when the ship generator sets are connected to shore power, the load of the generator sets is zero, the deviation of the inlet/outlet speed of the flowmeter is checked, and when the deviation exceeds a set value, the flowmeter has deviation faults. However, this approach is too costly due to the need to shut down all of the ship generator sets.
Disclosure of Invention
In order to solve the problems, the embodiment of the application provides a ship diesel fuel flow meter abnormal state monitoring method, a device, electronic equipment and a storage medium.
In a first aspect, an embodiment of the present application provides a method for monitoring abnormal conditions of a fuel flow meter of a marine diesel engine, the method including:
acquiring a training database, wherein the training database comprises training data representing that the total power of a ship generator set and the flow rate of a flowmeter are normal;
training the support vector machines according to the training database to obtain trained support vector machines;
performing anomaly monitoring on the real-time flow data according to the trained support vector machines to obtain an anomaly monitoring result;
and responding to the abnormal monitoring result to represent the abnormal real-time flow data, and sending abnormal alarm information of the flowmeter.
In some alternative embodiments, the method further comprises:
and responding to the abnormal monitoring result to represent the real-time flow data policy, determining the real-time flow data as training data, and storing the training data into the training database.
In some alternative embodiments, the method further comprises:
determining a capacity of the training database in response to detecting that the real-time traffic data determined to be training data is saved to the training database;
in response to determining that the capacity of the training database exceeds a preset capacity threshold, deleting at least a portion of the data of the training database to cause the capacity of the training database to be below the preset capacity threshold.
In some alternative embodiments, the deleting at least a portion of the data of the training database includes:
at least part of the data of the training database is deleted randomly.
In some alternative embodiments, the deleting at least a portion of the data of the training database includes:
and deleting repeated parts for repeated data samples in the training database.
In some optional embodiments, the training a class of support vector machines according to the training data to obtain a class of trained support vector machines includes:
training a class of support vector machines, minimizing the following objective functions:
wherein x is i Is a training sample, w is a feature space hyperplane normal vector, ζ i Is a relaxation factor, ρ is a feature space hyperplane compensation, v is an erroneous sample ratio value in the total number of samples, 0<v<1, n is the number of training samples, ψ (·) is the kernel space mapping function;
and (3) introducing Lagrange multipliers, and solving the pair of the feature space:
wherein K (x i ,x j ) Is a kernel function, alpha i Is the Lagrangian multiplier;
deriving a decision function from the above:
wherein G (x) = 1 characterizes the current data as normal and G (x) = -1 characterizes the current data as abnormal.
In a second aspect, an embodiment of the present application provides a device for monitoring abnormal conditions of a fuel flow meter of a marine diesel engine, the device comprising:
a data acquisition unit configured to acquire a training database including training data characterizing a total power of the ship generator set and a flow rate of the flowmeter;
the training unit is configured to train the class-one support vector machines according to the training database to obtain the class-one support vector machines after training;
the identification unit is configured to perform anomaly monitoring on the real-time flow data according to the trained support vector machines to obtain an anomaly monitoring result;
and the alarm unit is configured to respond to the abnormal monitoring result to represent the real-time flow data abnormality and send flow meter abnormality alarm information.
In some alternative embodiments, the apparatus further comprises:
and the data processing unit is used for responding to the abnormal monitoring result to represent the real-time flow data policy, determining the real-time flow data as training data and storing the training data into the training database.
In a third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor, where the memory stores a computer program, where the computer program when executed by the processor causes the processor to perform the steps of the method according to any embodiment of the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the steps of the method according to any of the embodiments of the first aspect.
According to the embodiment, the abnormal state monitoring method for the fuel flow meter of the marine diesel engine comprises the following steps: acquiring a training database, wherein the training database comprises training data representing the total power of a ship generator set and the normal flow rate of a flowmeter; training the support vector machines according to the training database to obtain trained support vector machines; performing anomaly monitoring on the real-time flow data according to the trained support vector machine to obtain an anomaly monitoring result; and responding to the abnormal monitoring result to represent the abnormal real-time flow data, and sending abnormal alarm information of the flowmeter. The invention provides an on-line identification method for abnormal fuel flow meter of a ship generator, which is used for monitoring abnormal fuel flow meter of a ship generator set in real time. The invention can identify abnormal state of the flowmeter of the marine diesel engine in real time without closing the generator set. According to the invention, a support vector machine model is trained by using a two-dimensional data normal sample library composed of the power of the generator set and the flow meter speed, and the training model can effectively identify the abnormal state of the flow meter.
Drawings
The drawings illustrate generally, by way of example and not by way of limitation, various embodiments discussed herein.
FIG. 1 is a schematic flow chart of a method for monitoring abnormal states of a fuel flow meter of a marine diesel engine according to an embodiment of the application;
FIG. 2 is a flowchart of a method for real-time online detection of abnormal fuel flow meter of a ship on-board generator set in accordance with an embodiment of the present application;
fig. 3 is a schematic structural diagram of a device for monitoring abnormal states of a fuel flow meter of a marine diesel engine according to an embodiment of the present application;
fig. 4 is a schematic hardware structure of an electronic device according to an embodiment of the present application.
Detailed Description
For a more complete understanding of the features and technical content of the embodiments of the present application, reference should be made to the following detailed description of the embodiments of the present application, taken in conjunction with the accompanying drawings, which are for purposes of illustration only and not intended to limit the embodiments of the present application.
In the description of the embodiments of the present application, unless otherwise indicated and defined, the term "connected" should be construed broadly, and for example, may be an electrical connection, may be a communication between two elements, may be a direct connection, or may be an indirect connection via an intermediary, and it will be understood by those skilled in the art that the specific meaning of the term may be understood according to the specific circumstances.
It should be noted that, the term "first\second\third" in the embodiments of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that the embodiments of the present application described herein may be implemented in sequences other than those illustrated or described herein.
Fig. 1 is a schematic flow chart of a method for monitoring abnormal states of a fuel flow meter of a marine diesel engine according to an embodiment of the application. As shown in fig. 1, an embodiment of the present application provides a method for monitoring abnormal conditions of a fuel flow meter of a marine diesel engine, including:
And step 12, training the support vector machines according to the training database to obtain the trained support vector machines.
In some optional embodiments, training the class of support vector machines according to the training data to obtain a class of trained support vector machines, including:
training a class of support vector machines, minimizing the following objective functions:
wherein x is i Is a training sample, w is a feature space hyperplane normal vector, ζ i Is a relaxation factor, ρ is a feature space hyperplane compensation, v is an erroneous sample ratio value in the total number of samples, 0<v<1, n is the number of training samples, ψ (·) is the kernel space mapping function;
and (3) introducing Lagrange multipliers, and solving the pair of the feature space:
wherein K (x i ,x j ) Is a kernel function, alpha i Is the Lagrangian multiplier;
deriving a decision function from the above:
wherein G (x) = 1 characterizes the current data as normal and G (x) = -1 characterizes the current data as abnormal.
And step 13, carrying out anomaly monitoring on the real-time flow data according to the trained support vector machine, and obtaining an anomaly monitoring result.
And 14, responding to the abnormal monitoring result to represent real-time flow data abnormality, and sending abnormal alarm information of the flowmeter.
And step 15, responding to the abnormal monitoring result to represent the real-time flow data policy, determining the real-time flow data as training data, and storing the training data into a training database.
In some alternative embodiments, the method further comprises:
in response to detecting that real-time traffic data determined to be training data is saved to the training database, a capacity of the training database is determined.
In response to determining that the capacity of the training database exceeds the preset capacity threshold, deleting at least a portion of the data of the training database to bring the capacity of the training database below the preset capacity threshold.
Here, deleting at least a portion of the data of the training database may include one of:
at least part of the data of the training database is randomly deleted.
Alternatively, duplicates are deleted for duplicate data samples in the training database.
According to the technical scheme, the abnormal real-time monitoring method and the abnormal monitoring device can be used for monitoring the abnormal condition of the fuel flow meter of the ship generator set in real time, the principle is that the ship generator flow meter history normal data are utilized to train a support vector machine, the trained support vector machine can effectively classify normal samples into positive samples, the abnormal samples are classified into negative samples, and at the moment, the abnormal condition of the flow meter is identified. The normal sample is re-included in the normal sample database of the flowmeter, so that the diversity of the database is increased, and the identification efficiency is improved.
Fig. 2 is a flowchart of a method for online detecting abnormality of a fuel flow meter of a ship on-board generator set in real time according to an embodiment of the application.
A ship diesel engine fuel flow meter abnormal state monitoring method comprises the following steps:
step s1, collecting normal values of total power of a ship generator set and flow rate of a flowmeter, and constructing an original flowmeter normal data database, wherein database data exist in a two-dimensional form, namely each data sample consists of the total power of the generator set and the flow rate of the flowmeter; optionally, normalizing the data samples; raw flowmeter normal data database data is used as training samples for the model.
Step s2, given n trainingSample x i Training a class of support vector machine flowmeter anomaly recognition models, and searching for an optimal decision function G (x) so that most samples in training samples are normal samples, namely G (x) =1; only a small portion of the samples are classified as outlier samples, i.e., G (x) = -1. Here, the vast majority may be, for example, 99% or more, and correspondingly, only a small portion may be, for example, less than 1%; in practice the scaling of the vast majority and the corresponding only a small part can be determined based on the accuracy of the monitoring.
And step 3, monitoring the abnormality of the real-time flowmeter data, and inputting the real-time data into the trained flowmeter abnormality identification model. The trained flowmeter abnormality recognition model detects that the real-time data is abnormal data, namely when the abnormal data is input into the model, a flowmeter abnormality alarm is given; the trained abnormal flowmeter identification model detects that the real-time data is normal data, namely after the normal data is input into the identification model, the model gives a normal prompt of the flowmeter.
And step S4, filling the normal data identified by the model into a flow meter history normal data database, and updating and perfecting the database. If the database capacity exceeds the threshold, portions of the database data may be randomly deleted.
Further, in the step s2, the method for searching the optimal decision function G (x) is as follows:
(1) Training a class of support vector machines, minimizing the following objective functions:
s.t.w T ψ(x i )>ρ-ζ i ,ζ i >0,i＝1,2,…,n
wherein x is i Is a training sample, w is a feature space hyperplane normal vector, ζ i Is a relaxation factor, ρ is a feature space hyperplane compensation, v is an erroneous sample ratio value in the total number of samples, 0<v<1, n is the number of training samples, ψ (·) is the kernel space mapping function.
(2) And (3) introducing Lagrange multipliers, and solving the pair of the feature space:
wherein K (x i ,x j ) Is a kernel function, alpha i Is the lagrange multiplier.
Deriving a decision function from the above:
existing techniques for flow meter anomaly identification mainly include model-based methods and expert knowledge base-based methods. The method based on the model needs to establish a set of complex mechanism model, the identification accuracy is seriously dependent on the accuracy of the mechanism model, and the abnormal identification accuracy of the flowmeter which is difficult to establish some mechanism models is seriously reduced. Based on the expert knowledge base method, knowledge acquisition and representation have limitations, knowledge thrust has prosperity, and knowledge experience of related professionals is relied on.
The embodiment of the application overcomes the defects of the prior art, and provides a ship diesel fuel flowmeter abnormality identification method which can quickly and accurately identify the abnormal state of the flowmeter by utilizing the history sample of the ship diesel flowmeter. According to the technical scheme, a complex mechanism model is not required to be established, and an expert knowledge base is not required to be established. The training samples of the continuation scheme of the application are the label-free flowmeter normal samples which are easy to obtain.
The embodiment of the application provides a method for identifying abnormal states of fuel flow of a ship generator in real time, which is used for monitoring the abnormal states of the fuel flow meter of a ship generator set in real time.
Fig. 3 is a schematic structural diagram of an abnormal state monitoring device for a fuel flow meter of a marine diesel engine according to an embodiment of the application. The embodiment of the application provides a ship diesel fuel flow meter abnormal state monitoring device, which corresponds to the method embodiment shown in fig. 1, and can be particularly applied to various electronic equipment. As shown in fig. 3, a device for monitoring abnormal state of a fuel flow meter of a marine diesel engine according to an embodiment of the present application includes: a data acquisition unit 31, a training unit 32, an identification unit 33, an alarm unit 34 and a data processing unit 35. Wherein the data acquisition unit 31 is configured to acquire a training database comprising training data characterizing a ship generator set total power and a flow rate of the flow meter. The training unit 32 is configured to train the class of support vector machines according to the training database, and obtain a class of trained support vector machines. The identifying unit 33 is configured to perform anomaly monitoring on the real-time flow data according to the trained support vector machine, so as to obtain an anomaly monitoring result. An alarm unit 34 configured to send meter anomaly alarm information in response to the anomaly monitoring results characterizing real-time flow data anomalies. The data processing unit 34 characterizes the real-time traffic data policy in response to the anomaly monitoring result, determines the real-time traffic data as training data, and saves the training data to a training database.
In this embodiment, the specific processing of the data acquisition unit 31, the training unit 32, the identification unit 33, the alarm unit 34 and the data processing unit 35 of the abnormal state monitoring device for the fuel flow meter of the marine diesel engine and the technical effects brought by the specific processing may refer to the relevant descriptions of steps 11 to 15 in the corresponding embodiment of fig. 1, and are not repeated herein.
The embodiment of the application also provides electronic equipment. Fig. 4 is a schematic hardware structure of an electronic device according to an embodiment of the present application, as shown in fig. 4, including: a communication component 43 for data transmission, at least one processor 41 and a memory 42 for storing a computer program executable on the processor 41. The various components in the terminal are coupled together by a bus system 44. It is understood that the bus system 44 is used to enable connected communications between these components. The bus system 44 includes a power bus, a control bus, and a status signal bus in addition to the data bus. But for clarity of illustration the various buses are labeled as bus system 44 in fig. 4.
Wherein the processor 41 executes the computer program to perform at least the steps of the method for monitoring abnormal conditions of a marine diesel fuel flow meter according to the foregoing embodiment.
It will be appreciated that memory 42 may be volatile memory or nonvolatile memory, and may include both volatile and nonvolatile memory. Wherein the nonvolatile Memory may be Read Only Memory (ROM), programmable Read Only Memory (PROM, programmable Read-Only Memory), erasable programmable Read Only Memory (EPROM, erasable Programmable Read-Only Memory), electrically erasable programmable Read Only Memory (EEPROM, electrically Erasable Programmable Read-Only Memory), magnetic random access Memory (FRAM, ferromagnetic random access Memory), flash Memory (Flash Memory), magnetic surface Memory, optical disk, or compact disk Read Only Memory (CD-ROM, compact Disc Read-Only Memory); the magnetic surface memory may be a disk memory or a tape memory. The volatile memory may be random access memory (RAM, random Access Memory), which acts as external cache memory. By way of example, and not limitation, many forms of RAM are available, such as static random access memory (SRAM, static Random Access Memory), synchronous static random access memory (SSRAM, synchronous Static Random Access Memory), dynamic random access memory (DRAM, dynamic Random Access Memory), synchronous dynamic random access memory (SDRAM, synchronous Dynamic Random Access Memory), double data rate synchronous dynamic random access memory (ddr SDRAM, double Data Rate Synchronous Dynamic Random Access Memory), enhanced synchronous dynamic random access memory (ESDRAM, enhanced Synchronous Dynamic Random Access Memory), synchronous link dynamic random access memory (SLDRAM, syncLink Dynamic Random Access Memory), direct memory bus random access memory (DRRAM, direct Rambus Random Access Memory). The memory 42 described in the embodiments of the present application is intended to comprise, without being limited to, these and any other suitable types of memory.
The method disclosed in the embodiments of the present application may be applied to the processor 41 or implemented by the processor 41. The processor 41 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 41 or by instructions in the form of software. The processor 41 may be a general purpose processor, DSP, or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. Processor 41 may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present application. The general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed in the embodiments of the present application may be directly embodied in a hardware decoding processor or implemented by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium in a memory 42 and the processor 41 reads information in the memory 42 to perform the steps of the method described above in connection with its hardware.
In an exemplary embodiment, the related apparatus or classification system may be implemented by one or more application specific integrated circuits (ASIC, application Specific Integrated Circuit), DSPs, programmable logic devices (PLD, programmable Logic Device), complex programmable logic devices (CPLD, complex Programmable Logic Device), FPGAs, general purpose processors, controllers, MCUs, microprocessors, or other electronic elements for performing the foregoing training method and/or classification method of the classification model.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described as separate units may or may not be physically separate, and units displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware associated with program instructions, where the foregoing program may be stored in a computer readable storage medium, and when executed, the program performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the integrated units described above may be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially or partly contributing to the prior art, and the computer software product may be stored in a storage medium, and include several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The embodiment of the present application further provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor is at least used to implement the steps of the method for monitoring abnormal conditions of a fuel flowmeter of a marine diesel engine according to the foregoing embodiment. The computer readable storage medium may be a memory in particular. The memory may be memory 42 as shown in fig. 4.
The methods disclosed in the several method embodiments provided in the present application may be arbitrarily combined without collision to obtain a new method embodiment.
The features disclosed in the several product embodiments provided in the present application may be combined arbitrarily without conflict to obtain new product embodiments.
The features disclosed in the several method or apparatus embodiments provided in the present application may be arbitrarily combined without conflict to obtain new method embodiments or apparatus embodiments.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method for monitoring abnormal conditions of a marine diesel fuel flow meter, the method comprising:
acquiring a training database, wherein the training database comprises training data representing that the total power of a ship generator set and the flow rate of a flowmeter are normal;
training the support vector machines according to the training database to obtain trained support vector machines;
performing anomaly monitoring on the real-time flow data according to the trained support vector machines to obtain an anomaly monitoring result;
and responding to the abnormal monitoring result to represent the abnormal real-time flow data, and sending abnormal alarm information of the flowmeter.
2. The method according to claim 1, wherein the method further comprises:
and responding to the abnormal monitoring result to represent the real-time flow data policy, determining the real-time flow data as training data, and storing the training data into the training database.
3. The method according to claim 2, wherein the method further comprises:
determining a capacity of the training database in response to detecting that the real-time traffic data determined to be training data is saved to the training database;
in response to determining that the capacity of the training database exceeds a preset capacity threshold, deleting at least a portion of the data of the training database to cause the capacity of the training database to be below the preset capacity threshold.
4. A method according to claim 3, wherein said deleting at least part of the data of the training database comprises:
at least part of the data of the training database is deleted randomly.
5. A method according to claim 3, wherein said deleting at least part of the data of the training database comprises:
and deleting repeated parts for repeated data samples in the training database.
6. The method of claim 1, wherein training a class of support vector machines according to the training data to obtain a class of trained support vector machines comprises:
training a class of support vector machines, minimizing the following objective functions:
s.t.w T ψ(x i )>ρ-ζ i ,ζ i >0,i＝1,2,…,n
wherein x is i Is a training sample, w is a feature space hyperplane normal vector, ζ i Is a relaxation factor, ρ is a feature space hyperplane compensation, v is an erroneous sample ratio value in the total number of samples, 0<v<1, n is the number of training samples, ψ (·) is the kernel space mapping function;
and (3) introducing Lagrange multipliers, and solving the pair of the feature space:
wherein K (x i ,x j ) Is a kernel function, alpha i Is the Lagrangian multiplier;
deriving a decision function from the above:
wherein G (x) = 1 characterizes the current data as normal and G (x) = -1 characterizes the current data as abnormal.
7. An abnormal state monitoring device for a fuel flow meter of a marine diesel engine, the device comprising:
a data acquisition unit configured to acquire a training database including training data characterizing a total power of the ship generator set and a flow rate of the flowmeter;
the training unit is configured to train the class-one support vector machines according to the training database to obtain the class-one support vector machines after training;
the identification unit is configured to perform anomaly monitoring on the real-time flow data according to the trained support vector machines to obtain an anomaly monitoring result;
and the alarm unit is configured to respond to the abnormal monitoring result to represent the real-time flow data abnormality and send flow meter abnormality alarm information.
8. The apparatus of claim 7, wherein the apparatus further comprises:
and the data processing unit is used for responding to the abnormal monitoring result to represent the real-time flow data policy, determining the real-time flow data as training data and storing the training data into the training database.
9. An electronic device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the computer program, when executed by the processor, causes the processor to perform the steps of the method according to any of claims 1 to 6.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211367279.8A CN116010809A (en) | 2022-11-02 | 2022-11-02 | Abnormal state monitoring method and device for fuel flow meter of marine diesel engine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211367279.8A CN116010809A (en) | 2022-11-02 | 2022-11-02 | Abnormal state monitoring method and device for fuel flow meter of marine diesel engine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116010809A true CN116010809A (en) | 2023-04-25 |
Family
ID=86018158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211367279.8A Pending CN116010809A (en) | 2022-11-02 | 2022-11-02 | Abnormal state monitoring method and device for fuel flow meter of marine diesel engine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116010809A (en) |
-
2022
- 2022-11-02 CN CN202211367279.8A patent/CN116010809A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111177714B (en) | Abnormal behavior detection method and device, computer equipment and storage medium | |
| CN110766059A (en) | Transformer fault prediction method, device and equipment | |
| CN111240975A (en) | Artificial intelligence system risk detection method, device, computer equipment and medium | |
| CN109145030B (en) | Abnormal data access detection method and device | |
| CN115841255B (en) | On-site early warning method and system for building engineering based on-line analysis | |
| CN113449703B (en) | Quality control method and device for environment online monitoring data, storage medium and equipment | |
| CN114968633A (en) | Abnormal log detection method and device | |
| CN113837596A (en) | Fault determination method and device, electronic equipment and storage medium | |
| CN116089231B (en) | Fault alarm method and device, electronic equipment and storage medium | |
| CN115081673B (en) | Abnormality prediction method and device for oil and gas pipeline, electronic equipment and medium | |
| CN117807481B (en) | Fault identification method, training device, training equipment and training medium | |
| CN115952081A (en) | Software testing method, device, storage medium and equipment | |
| CN116450137A (en) | System abnormality detection method and device, storage medium and electronic equipment | |
| CN115793590A (en) | Data processing method and platform suitable for system safety operation and maintenance | |
| CN114548280A (en) | Fault diagnosis model training method, fault diagnosis method and electronic equipment | |
| CN116662793B (en) | Rotor crack fault diagnosis and model construction method and device | |
| CN116010809A (en) | Abnormal state monitoring method and device for fuel flow meter of marine diesel engine | |
| CN116381419A (en) | Transmission line fault processing method, device, computer equipment and storage medium | |
| CN111178037A (en) | Repeated defect report identification method and device and electronic equipment | |
| CN115047262A (en) | General equipment abnormal state identification method based on power quality data | |
| CN111754103A (en) | Enterprise risk image method, device, computer equipment and readable storage medium | |
| CN110659501A (en) | Vulnerability processing tracking method and device, computer system and readable storage medium | |
| CN118376974B (en) | Fault monitoring method, device and equipment of electric energy meter and storage medium | |
| CN116541713B (en) | Bearing fault diagnosis model training method based on local time-frequency characteristic transfer learning | |
| CN115599312B (en) | Big data processing method and AI system based on storage cluster |
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 |