CN115165044A - Fuel flow abnormity identification method and device and electronic equipment - Google Patents
Fuel flow abnormity identification method and device and electronic equipment Download PDFInfo
- Publication number
- CN115165044A CN115165044A CN202210787290.3A CN202210787290A CN115165044A CN 115165044 A CN115165044 A CN 115165044A CN 202210787290 A CN202210787290 A CN 202210787290A CN 115165044 A CN115165044 A CN 115165044A
- Authority
- CN
- China
- Prior art keywords
- deviation
- data
- flow
- flow data
- ship
- 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
- 238000000034 method Methods 0.000 title claims abstract description 74
- 239000000446 fuel Substances 0.000 title claims abstract description 63
- 238000012549 training Methods 0.000 claims description 64
- 230000006870 function Effects 0.000 claims description 36
- 238000012546 transfer Methods 0.000 claims description 21
- 230000005856 abnormality Effects 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 239000002283 diesel fuel Substances 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 abstract description 12
- 230000007246 mechanism Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 239000000295 fuel oil Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000010710 diesel engine oil Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F25/00—Testing or calibration of apparatus for measuring volume, volume flow or liquid level or for metering by volume
- G01F25/10—Testing or calibration of apparatus for measuring volume, volume flow or liquid level or for metering by volume of flowmeters
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02B—INTERNAL-COMBUSTION PISTON ENGINES; COMBUSTION ENGINES IN GENERAL
- F02B77/00—Component parts, details or accessories, not otherwise provided for
- F02B77/08—Safety, indicating, or supervising devices
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
- G01M15/04—Testing internal-combustion engines
- G01M15/042—Testing internal-combustion engines by monitoring a single specific parameter not covered by groups G01M15/06 - G01M15/12
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Combustion & Propulsion (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Fluid Mechanics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Mechanical Engineering (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The invention provides a method and a device for identifying abnormal fuel flow and electronic equipment, wherein the method comprises the following steps: acquiring underway flow data of a ship; the flow data comprises the inlet flow rate and the outlet flow rate of diesel engine fuel of the ship; inputting the flow data into a deviation fault recognition model trained in advance, reconstructing the flow data through the deviation fault recognition model, and outputting reconstructed data corresponding to the flow data; calculating a deviation value of the flow data and the reconstruction data; if the deviation value exceeds the preset deviation threshold value, the deviation fault of the diesel engine of the ship is determined, a complex mechanism model does not need to be established, an expert knowledge base does not need to be established, the deviation fault of the flowmeter can be identified rapidly and accurately, the method is simple and effective, the identification efficiency is high, and the deviation fault of the flowmeter can be monitored on line in real time.
Description
Technical Field
The invention relates to the technical field of flow monitoring, in particular to a method and a device for identifying abnormal fuel flow and electronic equipment.
Background
When a ship sails, a diesel engine of the ship runs under a certain load, and the diesel engine needs to continuously consume a certain amount of fuel output power to maintain the navigation of the ship. At this time, the diesel flow meter records the fuel inlet and outlet flow of the diesel engine. Diesel flow meters often experience drift faults during ongoing operation. Because diesel engines continuously consume a fixed amount of fuel, the diesel engine flow meter fuel inlet rate is typically greater than the outlet rate when the vessel is underway, and therefore, flow meter deviation failures are difficult to identify.
The common method is to select the deviation of the inlet and outlet speed of the flow meter when the load of the diesel engine is zero when the ship is stopped, and when the deviation value exceeds a set value, the flow meter has deviation faults. However, this approach has significant drawbacks. The time of ship's shut down in the air is uncertain, if the deviation trouble appears in the diesel engine flowmeter when boats and ships are on the air, can seriously influence the diesel engine oil consumption and calculate, causes unnecessary erroneous judgement for the crew, causes economic loss.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus, and an electronic device for identifying an abnormal fuel flow, which avoid depending on the accuracy of a mechanism model, and can quickly and accurately identify a deviation fault of a diesel flow meter only by using a history sample of the diesel flow meter of a ship.
In a first aspect, an embodiment of the present invention provides a method for identifying an abnormal fuel flow, where the method includes: acquiring underway flow data of a ship; the flow data comprises the inlet flow rate and the outlet flow rate of diesel engine fuel of the ship; inputting the flow data into a deviation fault recognition model trained in advance, reconstructing the flow data through the deviation fault recognition model, and outputting reconstructed data corresponding to the flow data; calculating a deviation value of the flow data and the reconstruction data; and if the deviation value exceeds a preset deviation threshold value, determining that the diesel engine of the ship has a deviation fault.
Further, the deviation fault identification model comprises an encoder, a hidden layer representation layer and a decoder which are connected in sequence.
Further, wherein the method further comprises: initializing a pre-established deviation fault identification model; obtaining a pre-constructed training sample, training a deviation fault recognition model according to the following iterative process until a preset training stop condition is met: inputting training samples to an encoder of the initialized deviation fault recognition model, and mapping the training samples to potential spaces corresponding to the hidden layer representation layer; reconstructing the training samples through a decoder, and outputting reconstructed samples corresponding to the training samples; calculating a loss function of the training sample and the reconstruction sample; wherein the training stopping condition comprises at least one of the following conditions: the number of iterations reaches a preset number, or the loss function converges.
Further, wherein the method further comprises: obtaining historical flow data of a ship in sailing, wherein the historical flow data comprise historical fuel inlet flow rate and historical fuel outlet flow rate of a diesel engine of the ship; and preprocessing the historical flow data to obtain a training sample, wherein the preprocessing process at least comprises data cleaning and data normalization processing.
Further, wherein the method further comprises: calculating residual error values of the training sample and the reconstruction sample; and performing kernel density analysis on the residual values to find out a deviation threshold value for representing the normality and the difference of the training samples.
Further, wherein the method comprises: the method further comprises the following steps: mapping the training samples to the potential space corresponding to the hidden layer representation layer by using the following formula:
h＝f(wx+b)
wherein f (wx + b) is a coding transfer function, x is a training sample, w is a coding weight of the coding transfer function, h is a characteristic value of the hidden layer representation layer, and b is a bias parameter of the coding transfer function.
Further, wherein the method comprises: the decoder reconstructs the training samples by using the following formula and outputs reconstructed samples corresponding to the training samples:
x'＝g(vh+b')
wherein g (vh + b ') is a decoding transfer function, x ' is a reconstructed sample, v is a decoding weight of the decoding transfer function, h is a characteristic value of the hidden layer representation layer, and b ' is a bias parameter of the decoding transfer function.
Further, wherein the loss function is expressed as the following equation:
L＝||x-x'|| 2
wherein x is a training sample, x' is a reconstruction sample, and L is a loss function.
In a second aspect, an embodiment of the present invention provides a fuel flow abnormality recognition apparatus, where the apparatus includes: the acquisition module is used for acquiring the underway flow data of the ship; the flow data comprises the inlet flow rate and the outlet flow rate of diesel engine fuel of the ship; the training module is used for inputting the flow data into a deviation fault recognition model trained in advance, reconstructing the flow data through the deviation fault recognition model and outputting reconstructed data corresponding to the flow data; the calculation module is used for calculating a deviation value of the flow data and the reconstruction data; and the determining module is used for determining that the diesel engine of the ship has deviation faults if the deviation value exceeds a preset deviation threshold value.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a processor and a memory, where the memory stores computer-executable instructions capable of being executed by the processor, and the processor executes the computer-executable instructions to implement any one of the above methods.
Additional features and advantages of the disclosure will be set forth in the description which follows, or in part may be learned by the practice of the above-described techniques of the disclosure, or may be learned by practice of the disclosure.
In order to make the aforementioned objects, features and advantages of the present disclosure more 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 embodiments or the prior art descriptions 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 flow chart of a fuel flow anomaly identification method provided by an embodiment of the invention;
FIG. 2 is a flow chart of another fuel flow anomaly identification method provided by the embodiment of the invention;
FIG. 3 is a block diagram of a deviation fault identification model according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a fuel flow abnormality recognition apparatus according to an embodiment of the present invention;
fig. 5 is a structural diagram of an electronic device according to an embodiment of the present invention.
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.
At present, a diesel engine flowmeter can record the flow of fuel oil in and out of a diesel engine. During continuous operation of the diesel engine flowmeter, deviation faults often occur, and because the diesel engine continuously consumes a fixed amount of fuel, the fuel inlet rate of the diesel engine flowmeter is generally greater than the fuel outlet rate when the ship sails, so that the deviation faults of the flowmeter are difficult to identify. The common method is to select the deviation of the inlet and outlet speed of the flow meter when the load of the diesel engine is zero when the ship is stopped, and when the deviation value exceeds a set value, the flow meter has deviation faults. Based on the method, the device and the electronic equipment for identifying the abnormal fuel flow, which are provided by the embodiment of the invention, the automatic encoder can be trained by using the historical normal data of the marine diesel flowmeter, normal data samples can be reconstructed, residual errors can be calculated, and the deviation fault threshold value can be estimated and set by using the nuclear density. According to the method and the device, the deviation fault of the diesel engine can be identified on line, and when the deviation obtained by inputting the normal flow data into the deviation fault identification model is smaller than the preset threshold value, the deviation fault of the diesel engine of the ship can be determined.
For the convenience of understanding the embodiment, a detailed description will be given to a fuel flow abnormality recognition method disclosed in the embodiment of the present invention.
The embodiment of the invention provides a method for identifying abnormal fuel flow, and fig. 1 is a flow chart of the method for identifying abnormal fuel flow, as shown in fig. 1, the method comprises the following steps:
step S101, acquiring the underway flow data of a ship; the flow data comprises the inlet flow rate and the outlet flow rate of the diesel engine fuel of the ship;
specifically, the diesel engine fuel inlet or outlet flow of the ship can be recorded by using a diesel engine flowmeter to obtain the underway flow data of the ship, the diesel engine fuel inlet flow rate and the outlet flow rate of the ship can be obtained without stopping the ship, the obtained flow data can be encoded by an automatic encoder, the original flow data is subjected to data cleaning and normalization processing, and the flow data which can be identified by the following deviation fault identification model is obtained.
Step S103, inputting the flow data into a deviation fault recognition model trained in advance, reconstructing the flow data through the deviation fault recognition model, and outputting reconstruction data corresponding to the flow data;
specifically, in order to process data, data may be input into a trained model to complete reconstruction of the data, and therefore, the trained deviation fault recognition model may be used to reconstruct the flow data and output corresponding reconstructed data to facilitate calculation of a subsequent deviation value.
Step S105, calculating a deviation value of the flow data and the reconstruction data;
in practical application, the deviation value can be obtained by utilizing the difference between the calculated flow data and the reconstructed data, that is, the theoretical difference of the reconstructed data obtained by utilizing the actual measured fuel inlet flow rate and outlet flow rate of the diesel engine of the ship and the deviation fault identification model can be utilized, so that the inlet and outlet flow deviation value of the diesel engine of the ship can be obtained.
And S107, if the deviation value exceeds a preset deviation threshold value, determining that the diesel engine of the ship has a deviation fault.
In practical application, a worker can determine the deviation threshold value based on historical data or parameters provided by a fuel meter manufacturer, compare the obtained deviation value of the inlet flow and the outlet flow of the diesel engine with a preset threshold value, and judge that the diesel engine has a deviation fault if the deviation value is greater than the flow threshold value.
The principle of the method for identifying the abnormal fuel flow provided by the embodiment of the invention is that a deviation fault identification model is trained by using historical normal data of a diesel oil flowmeter of a ship, a normal data sample is reconstructed, the residual error between the normal flow data and model reconstruction data of the normal flow data is calculated, a nuclear density estimation method is used for carrying out estimation operation on the parameters based on the historical data or provided by a fuel oil meter manufacturer so as to set a flowmeter deviation fault threshold value, the residual error of online real-time data is calculated, and when the deviation value obtained by inputting the flow data into the model is smaller than a preset threshold value, the diesel engine can be judged to have the deviation fault.
Fig. 2 shows a flow chart of another fuel flow abnormality identification method, which is implemented on the basis of the fuel flow abnormality identification method shown in fig. 1, and the method is mainly further explained with respect to a process of training a deviation fault identification model. Fig. 3 shows a block diagram of an offset fault recognition model, which includes an encoder, a hidden layer representation, and a decoder. As shown in fig. 2, the method comprises the steps of:
step S201, initializing a pre-established deviation fault identification model;
in order to train the deviation fault identification model, before the training operation, the initialization weight in the deviation fault identification model is as follows: and initializing the coding weight of the coding transfer function or the coding weight of the decoding transfer function in the deviation fault identification model, thereby carrying out subsequent training operation.
In the embodiment of the application, the identification of the fuel flow abnormality includes both the diesel engine fuel inlet flow rate and the diesel engine fuel outlet flow rate of the ship, so that the deviation thresholds of the outlet flow rate and the inlet flow rate can be set respectively, and the method for monitoring the inlet flow and the outlet flow can monitor both the inlet flow and the outlet flow simultaneously, or monitor any one of the inlet flow and the outlet flow simultaneously, and is not limited specifically here.
Step S203, obtaining a pre-constructed training sample, training a deviation fault recognition model according to the following iterative process until a preset training stop condition is met;
in order to enable the information of the flow data to be recognized by the deviation fault recognition model, the obtained historical normal flow data of the diesel engine can be selected by using an encoder in the deviation fault recognition model, and the obtained historical normal flow data is used for training the deviation fault recognition model.
Step S205, inputting a training sample to an encoder of the initialized deviation fault recognition model, and mapping the training sample to a potential space corresponding to the hidden layer representation layer; reconstructing the training samples through a decoder, and outputting reconstructed samples corresponding to the training samples; calculating a loss function of the training sample and the reconstruction sample;
wherein the training stopping condition comprises at least one of the following conditions: the number of iterations reaches a preset number, or the loss function converges.
In practical application, when the stopping condition for training the deviation fault identification model is met, it is proved that the deviation fault identification model can be put into practical application, and then the flow data in the embodiment of the application can be reconstructed, and the subsequent steps are executed.
Specifically, the training samples may be mapped to the potential space corresponding to the hidden layer representation layer by using the following formula:
h＝f(wx+b)
wherein f (wx + b) is a coding transfer function, x is a training sample, w is a coding weight of the coding transfer function, h is a characteristic value of the hidden layer representation layer, and b is a bias parameter of the coding transfer function.
In practical applications, the normal inlet flow rate and the outlet flow rate can be set to x respectively 1 And x 2 As training samples of the encoder, x can be selected 1 And x 2 Respectively obtaining corresponding hidden layer characteristic values h 1 And h 2 。
Specifically, the decoder reconstructs the training samples by using the following formula, and outputs reconstructed samples corresponding to the training samples:
x'＝g(vh+b')
wherein g (vh + b ') is a decoding transfer function, x ' is a reconstructed sample, v is a decoding weight of the decoding transfer function, h is a characteristic value of the hidden layer representation layer, and b ' is a bias parameter of the decoding transfer function.
In practical application, the corresponding h obtained by utilizing the inlet flow rate and the outlet flow rate 1 And h 2 The reconstructed data x 'of the inlet flow rate and the outlet flow rate can be obtained respectively when the data are input into the decoding transfer function' 1 And x' 2 。
Specifically, the loss function is expressed as the following equation:
L＝||x-x'|| 2
wherein x is a training sample, x' is a reconstruction sample, and L is a loss function.
When the above-mentioned loss function is determined to be converged, one of the training stop conditions can be achieved.
Step S207, obtaining historical flow data of the ship during sailing, wherein the historical flow data comprise historical fuel inlet flow rate and historical fuel outlet flow rate of a diesel engine of the ship;
in practical application, the historical flow data of the ship in the process of sailing can be utilized to carry out data sorting, so that the historical fuel inlet flow rate and the historical fuel outlet flow rate of the diesel engine in the normal operation process can be obtained, and whether the flow data of the ship in the process of sailing is abnormal or not can be judged by taking the historical data as a reference.
Step S209, preprocessing the historical flow data to obtain the training sample, wherein the preprocessing process at least comprises data cleaning and data normalization processing;
since the historical flow data of the ship during sailing is various and has certain repeated information or errors for the whole sample, the data cleaning technology can be used for reexamining and verifying the historical flow data, and the aims of deleting the repeated information, correcting the existing errors and providing the data consistency are fulfilled.
And because of the characteristics of the encoder, historical flow data needs to be changed from a dimensionless expression to a dimensionless expression, so that the historical flow data can be changed from a number to a decimal between (0 and 1), the data is mapped into a range of 0 to 1 for processing mainly for the convenience of data processing, and sample data in the model can be processed more conveniently and rapidly.
Step S211, calculating residual values of the training sample and the reconstruction sample;
in practical applications, the normal inlet flow rate and outlet flow rate settings may be used as x 1 And x 2 And reconstructed data x 'as training sample inlet flow rate and outlet flow rate of the encoder respectively' 1 And x' 2 And performing difference operation to obtain a residual error value res of the training sample and the reconstruction sample.
Step S213, performing kernel density analysis on the residual value, and finding out a deviation threshold value used for representing normality and difference of the training sample.
Specifically, a deviation threshold δ representing the normality and the difference of the training sample can be found by performing kernel density analysis on the residual error values, and the corresponding deviation thresholds of the inlet flow rate and the outlet flow rate are δ respectively 1 And delta 2 。
The nuclear density estimation is used for estimating an unknown density function in probability theory, belongs to one of nonparametric inspection methods, and can estimate the deviation threshold value by using a nuclear density estimation method due to the fact that the deviation threshold value delta is large in quantity and different values of the deviation threshold value delta possibly exist under the normal operation of a ship under the navigation, and accordingly data meeting the practical requirement are obtained.
Step S215, acquiring the underway flow data of the ship; wherein the flow data comprises a diesel fuel inlet flow rate and an outlet flow rate of the vessel;
in practical application, if the obtained inlet flow rate and the obtained outlet flow rate are set as y 1 And y 2 The real-time data can be directly reconstructed.
Step S217, inputting the flow data into a deviation fault recognition model trained in advance, reconstructing the flow data through the deviation fault recognition model, and outputting reconstruction data corresponding to the flow data;
in practical applications, based on the above process of reconstructing flow data using the deviation fault identification model, the inlet flow rate and the outlet flow rate are set to y 1 And y 2 The corresponding reconstructed data is y' 1 And y' 2 。
Step S219, calculating a deviation value between the flow data and the reconstruction data;
specifically, performing difference operation on the flow data and the reconstruction data to obtain a deviation value; then, let res be the deviation value, res = y-y', and the deviation value of the corresponding inlet flow rate is res 1 ＝y 1 -y' 1 The deviation value of the inlet flow rate is res 2 ＝y 2 -y' 2 The deviation fault recognition may be performed on the flow rate of the inlet or the flow rate of the outlet, or may be performed on both the inlet and the outlet simultaneously, which is not limited herein.
And step S221, if the deviation value exceeds a preset deviation threshold value, determining that the diesel engine of the ship has a deviation fault.
In particular, the above res can be utilized 1 And res 2 Respectively is equal to delta 1 And delta 2 Make a comparison if res 1 And res 2 One or both of which exceed the corresponding δ 1 And delta 2 And determining that the diesel engine of the ship has the deviation fault.
In practical application, the method can monitor the fuel inlet rate and the fuel outlet rate of the flowmeter of the diesel engine in real time when the ship is in operation, and when any one of the inlet rate and the outlet rate of the diesel engine of the ship is determined to have a deviation fault, corresponding fault alarm information of a fault position can be fed back to remind a worker to check the diesel engine.
Corresponding to the method embodiment, the embodiment of the invention provides a processing device for identifying abnormal fuel flow, fig. 4 shows a schematic structural diagram of the abnormal fuel flow identifying device, and as shown in fig. 4, the abnormal fuel flow identifying device includes:
the acquiring module 401 is used for acquiring the underway flow data of the ship; the flow data comprises the inlet flow rate and the outlet flow rate of diesel engine fuel of the ship;
the training module 402 is configured to input the flow data to a deviation fault recognition model trained in advance, reconstruct the flow data through the deviation fault recognition model, and output reconstructed data corresponding to the flow data;
a calculating module 403, configured to calculate a deviation value between the flow data and the reconstructed data;
and a determining module 404, configured to determine that a deviation fault occurs in the diesel engine of the ship if the deviation value exceeds a preset deviation threshold.
An embodiment of the present invention further provides an electronic device, as shown in fig. 5, which is a schematic structural diagram of the electronic device, where the electronic device includes a processor 51 and a memory 52, the memory 52 stores machine executable instructions capable of being executed by the processor 51, and the processor 51 executes the machine executable instructions to implement the method for identifying the fuel flow abnormality.
In the embodiment shown in fig. 5, the electronic device further comprises a bus 53 and a communication interface 54, wherein the processor 51, the communication interface 54 and the memory 52 are connected by the bus.
The Memory 52 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 54 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used. The bus may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 5, but this does not indicate only one bus or one type of bus.
The processor 51 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 51. The Processor 51 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by 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 ram, flash, rom, prom, or eprom, registers, etc. as is well known in the art. The storage medium is located in the memory, and the processor 51 reads the information in the memory 52, and completes the steps of the fuel flow abnormality identification method of the foregoing embodiment in combination with the hardware thereof.
The embodiment of the present invention further provides a machine-readable storage medium, where the machine-readable storage medium stores machine executable instructions, and when the machine executable instructions are called and executed by a processor, the machine executable instructions cause the processor to implement the method for identifying the fuel flow abnormality, and specific implementation may refer to the foregoing method embodiment, which is not described herein again.
The method, the apparatus, and the computer program product for identifying fuel flow abnormality provided in the embodiments of the present invention include a computer readable storage medium storing program codes, where instructions included in the program codes may be used to execute the method for identifying fuel flow abnormality described in the foregoing method embodiments, and specific implementation may refer to the method embodiments, which are not described herein again.
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 non-volatile computer-readable storage medium executable by a processor. 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 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 meaning either a fixed connection, a removable connection, or an integral connection; 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.
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 simplification of description, but do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific 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: those skilled in the art can still make modifications or changes to the embodiments described in the foregoing embodiments, or make equivalent substitutions for some features, within the scope of the 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 fuel flow anomaly identification method, characterized in that the method comprises:
acquiring the underway flow data of a ship; wherein the flow data comprises a diesel fuel inlet flow rate and an outlet flow rate of the vessel;
inputting the flow data into a deviation fault recognition model trained in advance, reconstructing the flow data through the deviation fault recognition model, and outputting reconstructed data corresponding to the flow data;
calculating a deviation value of the flow data and the reconstruction data;
and if the deviation value exceeds a preset deviation threshold value, determining that the diesel engine of the ship has deviation faults.
2. The fuel flow abnormality recognition method according to claim 1, characterized in that the deviation fault recognition model includes an encoder, a hidden layer representation layer and a decoder connected in sequence.
3. The fuel flow anomaly identification method as recited in claim 2, characterized in that the method further comprises:
initializing a pre-established deviation fault identification model;
obtaining a pre-constructed training sample, and training the deviation fault recognition model according to the following iterative process until a preset training stop condition is met:
inputting the training samples to an encoder of the initialized deviation fault identification model, and mapping the training samples to potential spaces corresponding to the hidden layer representation layer; reconstructing the training samples through the decoder, and outputting reconstructed samples corresponding to the training samples; calculating a loss function of the training samples and the reconstruction samples;
wherein the training stop condition comprises at least one of: the number of iterations reaches a preset number, or the loss function converges.
4. The fuel flow anomaly identification method as recited in claim 3, characterized in that the method further comprises:
obtaining historical flow data of the ship on the voyage, wherein the historical flow data comprise historical fuel inlet flow rate and historical fuel outlet flow rate of a diesel engine of the ship;
and preprocessing the historical flow data to obtain the training sample, wherein the preprocessing process at least comprises data cleaning and data normalization processing.
5. The fuel flow anomaly identification method as recited in claim 3, characterized in that the method further comprises:
calculating residual values of the training samples and the reconstruction samples;
and performing nuclear density analysis on the residual values to find out a deviation threshold value for representing the normality and the difference of the training samples.
6. The fuel flow anomaly identification method as recited in claim 3, characterized in that the method further comprises:
mapping the training samples to the potential space corresponding to the hidden layer representation layer by using the following formula:
h＝f(wx+b)
wherein f (wx + b) is a coding transfer function, x is the training sample, w is a coding weight of the coding transfer function, h is a characteristic value of the hidden layer representation layer, and b is a bias parameter of the coding transfer function.
7. The fuel flow anomaly identification method as recited in claim 3, characterized in that the method further comprises:
the decoder reconstructs the training samples by using the following formula and outputs reconstructed samples corresponding to the training samples:
x'＝g(vh+b')
wherein g (vh + b ') is a decoding transfer function, x ' is the reconstructed sample, v is a decoding weight of the decoding transfer function, h is a characteristic value of the hidden layer representation layer, and b ' is a bias parameter of the decoding transfer function.
8. The fuel flow abnormality recognition method according to claim 3, characterized in that the loss function is expressed as the following formula:
L＝||x-x'|| 2
wherein x is the training sample, x' is the reconstructed sample, and L is the loss function.
9. A fuel flow anomaly identification device, said device comprising:
the acquisition module is used for acquiring the underway flow data of the ship; wherein the flow data comprises a diesel fuel inlet flow rate and an outlet flow rate of the vessel;
the training module is used for inputting the flow data into a deviation fault recognition model trained in advance, reconstructing the flow data through the deviation fault recognition model and outputting reconstruction data corresponding to the flow data;
the calculation module is used for calculating a deviation value of the flow data and the reconstruction data;
and the determining module is used for determining that the diesel engine of the ship has deviation faults if the deviation value exceeds a preset deviation threshold value.
10. An electronic device comprising a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to implement the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210787290.3A CN115165044A (en) | 2022-07-04 | 2022-07-04 | Fuel flow abnormity identification method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210787290.3A CN115165044A (en) | 2022-07-04 | 2022-07-04 | Fuel flow abnormity identification method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115165044A true CN115165044A (en) | 2022-10-11 |
Family
ID=83491040
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210787290.3A Pending CN115165044A (en) | 2022-07-04 | 2022-07-04 | Fuel flow abnormity identification method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115165044A (en) |
-
2022
- 2022-07-04 CN CN202210787290.3A patent/CN115165044A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109469896B (en) | Industrial boiler fault diagnosis method and system based on time series analysis | |
| CN106368816B (en) | A kind of online method for detecting abnormality of marine low speed diesel engine based on baseline offset | |
| US7275018B2 (en) | Method of condition monitoring | |
| CN112101554B (en) | Abnormality detection method and apparatus, device, and computer-readable storage medium | |
| CN112766342A (en) | Abnormity detection method for electrical equipment | |
| CN110688617B (en) | Fan vibration abnormity detection method and device | |
| CN114239377A (en) | Method and system for evaluating health state of urban rail electromechanical equipment and storage medium | |
| WO2011049667A1 (en) | System and method for selecting a maintenance operation | |
| CN112581719B (en) | Semiconductor packaging process early warning method and device based on time sequence generation countermeasure network | |
| KR20170127430A (en) | Method and system for detecting, classifying and / or mitigating sensor error | |
| CN117270514B (en) | Production process whole-flow fault detection method based on industrial Internet of things | |
| Kato | Fault diagnosis of a propeller using sub-nyquist sampling and compressed sensing | |
| CN115186701A (en) | Bearing life prediction method, device, electronic device and storage medium | |
| CN115165044A (en) | Fuel flow abnormity identification method and device and electronic equipment | |
| CN111806645B (en) | Ship decontamination method and device and electronic equipment | |
| CN111881978B (en) | Ocean fixed-point buoy equipment fault diagnosis method and device and electronic equipment | |
| CN116070103B (en) | Rotating equipment health identification method and equipment based on multiple measuring points and multiple indexes | |
| CN109990803A (en) | The method, apparatus of method, apparatus and the sensor processing of detection system exception | |
| CN115788660A (en) | Ship main engine supercharger abnormity monitoring method, device, system, equipment and storage medium | |
| CN116862284A (en) | Marine diesel engine health state assessment method based on SOM network and rule fusion | |
| CN114676593B (en) | Abnormality detection method and related device for textile equipment | |
| CN113642123A (en) | Health assessment method and device for heat dissipation system of working machine and working machine | |
| CN112907114A (en) | Oil leakage fault detection method and device, electronic equipment and storage medium | |
| CN117469152B (en) | Fluid pump abnormality detection method, fluid pump abnormality detection device, electronic device, and storage medium | |
| Vanem et al. | Dynamical Linear Models for Condition Monitoring with Multivariate Sensor Data. |
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 |