CN116006275A - Turbocharger performance monitoring method and device and electronic equipment - Google Patents
Turbocharger performance monitoring method and device and electronic equipment Download PDFInfo
- Publication number
- CN116006275A CN116006275A CN202211580413.2A CN202211580413A CN116006275A CN 116006275 A CN116006275 A CN 116006275A CN 202211580413 A CN202211580413 A CN 202211580413A CN 116006275 A CN116006275 A CN 116006275A
- Authority
- CN
- China
- Prior art keywords
- turbocharger
- host
- data
- historical
- performance monitoring
- 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
- Y02T10/12—Improving ICE efficiencies
Landscapes
- Supercharger (AREA)
Abstract
The invention provides a turbocharger performance monitoring method, a turbocharger performance monitoring device and electronic equipment, wherein the method comprises the following steps: acquiring real-time operation data of a main engine and a main engine turbocharger of the ship; the real-time operation data are used for indicating the real-time operation states of the host and the host turbocharger; inputting the real-time operation data into a pre-trained turbocharger performance monitoring model, and outputting the performance parameters of the main engine turbocharger; the turbocharger performance monitoring model is obtained based on deep belief network training. According to the method, the performance monitoring model of the turbocharger is built through the deep belief network model so as to predict the performance parameters of the turbocharger of the host, so that the accuracy of the performance monitoring method of the turbocharger is improved, and the sailing safety of the ship is ensured.
Description
Technical Field
The present invention relates to the technical field of turbocharger performance monitoring, and in particular, to a turbocharger performance monitoring method, device and electronic equipment.
Background
The marine engine exhaust gas turbocharger can greatly improve the power of the marine engine and promote the development of the marine engine towards high power, miniaturization and low oil consumption. The exhaust gas turbocharger of the marine diesel engine is easy to generate various abnormalities due to the severe working environment, so that the expected function is lost, and even disastrous accidents occur. For safe and reliable navigation of ships, it is important to accurately predict the performance of the exhaust gas turbocharger of the marine diesel engine in time. The traditional statistical method can only process a small amount of influencing factors and sample data, has higher requirements on the stability of the original time sequence, and has the defect of low prediction precision when processing the time sequence prediction under a large data volume.
Overall, the accuracy of the existing monitoring method for the performance of the turbocharger of the ship is low, so that the navigation safety of the ship cannot be guaranteed.
Disclosure of Invention
The invention aims to provide a turbocharger performance monitoring method, a turbocharger performance monitoring device and electronic equipment, so that the accuracy of the turbocharger performance monitoring method is improved, and the sailing safety of a ship is ensured.
In a first aspect, an embodiment of the present invention provides a turbocharger performance monitoring method, including: acquiring real-time operation data of a main engine and a main engine turbocharger of the ship; the real-time operation data are used for indicating the real-time operation states of the host and the host turbocharger; inputting the real-time operation data into a pre-trained turbocharger performance monitoring model, and outputting the performance parameters of the main engine turbocharger; the turbocharger performance monitoring model is obtained based on deep belief network training.
With reference to the first aspect, the embodiment of the present invention provides a first possible implementation manner of the first aspect, wherein the turbocharger performance monitoring model is trained by: acquiring historical operation data of a host machine and a host machine turbocharger of a ship; the historical operation data is used for indicating the historical operation states of the host and the host turbocharger; and training a preset initial deep belief network by taking the historical operation data as input and taking the supercharger performance data corresponding to the historical operation data as output until a preset training requirement is met, so as to obtain the trained turbocharger performance monitoring model.
With reference to the first possible implementation manner of the first aspect, the embodiment of the present invention provides a second possible implementation manner of the first aspect, wherein the step of training a preset initial deep belief network with the historical operation data as input and the supercharger performance data corresponding to the historical operation data as output until a preset training requirement is reached, and obtaining the trained turbocharger performance monitoring model includes: preprocessing the historical operation data to obtain an initial training set; and training a preset initial deep belief network by taking the initial training set as input and taking supercharger performance data corresponding to the initial training set as output until a preset training requirement is met, so as to obtain the trained turbocharger performance monitoring model.
With reference to the second possible implementation manner of the first aspect, the embodiment of the present invention provides a third possible implementation manner of the first aspect, where after the step of preprocessing the historical operation data to obtain an initial training set, the method includes: and constructing the initial deep belief network based on the historical operation data.
With reference to the first possible implementation manner of the first aspect, an embodiment of the present invention provides a fourth possible implementation manner of the first aspect, wherein the historical operating data includes: historical host load data, historical host supercharger rotational speed data, historical host cylinder average burst pressure data, historical host supercharger compressor outlet temperature data, historical host supercharger compressor outlet pressure data, historical host scavenging temperature data, historical host scavenging pressure data, historical host supercharger exhaust outlet temperature data, historical host supercharger exhaust outlet pressure data, historical host supercharger filter screen pressure loss coefficient data and historical host scavenging passage pressure loss coefficient data.
With reference to the fourth possible implementation manner of the first aspect, the embodiment of the present invention provides a fifth possible implementation manner of the first aspect, wherein the step of constructing the initial deep belief network based on the historical operating data includes: taking values of the historical host load data, the historical host supercharger rotational speed data, the historical host cylinder average explosion pressure data, the historical host supercharger compressor outlet temperature data, the historical host supercharger compressor outlet pressure data, the historical host scavenging temperature data, the historical host scavenging pressure data, the historical host supercharger waste gas outlet temperature data, the historical host supercharger waste gas outlet pressure data, the historical host supercharger filter screen pressure loss coefficient data and the historical host scavenging passage pressure loss coefficient data as supercharger characteristic parameters; determining the number of input neurons of the initial deep belief network according to the supercharger characteristic parameters; taking the supercharger performance data corresponding to the historical operation data as the output of the initial deep belief network; the initial deep belief network is constructed based on the number of input neurons and the output of the initial deep belief network.
With reference to the first aspect, an embodiment of the present invention provides a sixth possible implementation manner of the first aspect, where after the step of inputting the real-time operation data into a pre-trained turbocharger performance monitoring model and outputting the performance parameter of the host turbocharger, the method further includes: calculating a prediction error of the turbocharger performance monitoring model; the prediction error includes: the mean square error of the turbocharger performance monitoring model and the absolute percentage error of the turbocharger performance monitoring model; screening target operation data within a preset error threshold value from the real-time operation data based on the prediction error; and updating the turbocharger performance monitoring model according to the target operation data to obtain an updated turbocharger performance monitoring model.
With reference to the sixth possible implementation manner of the first aspect, the embodiment of the present invention provides a seventh possible implementation manner of the first aspect, wherein after the step of updating the turbocharger performance monitoring model according to real-time operation data corresponding to the prediction error within a preset error threshold to obtain an updated turbocharger performance monitoring model, the method further includes: and inputting the real-time operation data into the updated turbocharger performance monitoring model, and outputting the real-time performance parameters of the host turbocharger.
In a second aspect, an embodiment of the present invention provides a turbocharger performance monitoring apparatus, including: the data acquisition module is used for acquiring real-time operation data of a host machine of the ship and a turbocharger of the host machine; the real-time operation data are used for indicating the real-time operation states of the host and the host turbocharger; the performance prediction module is used for inputting the real-time operation data into a pre-trained turbocharger performance monitoring model and outputting the performance parameters of the host turbocharger; the turbocharger performance monitoring model is obtained based on deep belief network training.
In a third aspect, an embodiment of the present invention provides an electronic device, where the electronic device includes a processor and a memory, where the memory stores machine executable instructions that are executable by the processor, and the processor executes the machine executable instructions to implement the turbocharger performance monitoring method according to any one of the seventh possible implementation manners of the first aspect to the first aspect.
The embodiment of the invention has the following beneficial effects:
the method and device for monitoring the performance of the turbocharger and the electronic equipment provided by the embodiment of the invention comprise the following steps: acquiring real-time operation data of a main engine and a main engine turbocharger of the ship; the real-time operation data are used for indicating the real-time operation states of the host and the host turbocharger; inputting the real-time operation data into a pre-trained turbocharger performance monitoring model, and outputting the performance parameters of the main engine turbocharger; the turbocharger performance monitoring model is obtained based on deep belief network training. According to the method, the performance monitoring model of the turbocharger is built through the deep belief network model so as to predict the performance parameters of the turbocharger of the host, so that the accuracy of the performance monitoring method of the turbocharger is improved, and the sailing safety of the ship is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a turbocharger performance monitoring method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a training method of a turbocharger performance monitoring model according to an embodiment of the present invention;
FIG. 3 is a schematic view of a turbocharger performance monitoring apparatus according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Icon: 31-a data acquisition module; a 32-performance prediction module; 41-memory; 42-a processor; 43-bus; 44-communication interface.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, 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 embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Currently, the performance of marine diesel exhaust gas turbochargers is predicted mainly by conventional statistical methods. The traditional statistical method can only process a small amount of influencing factors and sample data, has higher requirements on the stability of the original time sequence, and has the defect of low prediction precision when processing the time sequence prediction under a large data volume. Therefore, the accuracy of the existing monitoring method for the performance of the turbocharger of the ship is low, so that the navigation safety of the ship is not guaranteed.
Based on the above, the embodiment of the invention provides a turbocharger performance monitoring method, a device and electronic equipment, and the technology can improve the accuracy of the turbocharger performance monitoring method so as to ensure the navigation safety of ships. For the convenience of understanding the embodiments of the present invention, a method for monitoring turbocharger performance disclosed in the embodiments of the present invention will be described in detail.
Example 1
Fig. 1 is a schematic flow chart of a turbocharger performance monitoring method according to an embodiment of the present invention. As seen in fig. 1, the method comprises the steps of:
step S101: acquiring real-time operation data of a main engine and a main engine turbocharger of the ship; the real-time operation data is used for indicating the real-time operation states of the host and the host turbocharger.
In this embodiment, the real-time operation data of the host and the host turbocharger include: real-time host load data, real-time supercharger rotation speed data, real-time host cylinder average burst pressure data, real-time host compressor outlet temperature data, real-time host compressor outlet pressure data, real-time host scavenging temperature data, real-time host scavenging pressure data, real-time supercharger waste gas outlet temperature data, real-time supercharger waste gas outlet pressure data, real-time supercharger filter screen pressure loss coefficient data and historical host scavenging passage pressure loss coefficient data.
Step S102: inputting the real-time operation data into a pre-trained turbocharger performance monitoring model, and outputting the performance parameters of the main engine turbocharger; the turbocharger performance monitoring model is obtained based on deep belief network training.
In actual operation, the turbocharger performance monitoring model is trained based on historical operating data of the host machine and the host machine turbocharger. The historical operation data is used as input, the supercharger performance data corresponding to the historical operation data is used as output to train a preset initial deep belief network, the turbocharger performance monitoring model is obtained, and accordingly the real-time operation data is input into the pre-trained turbocharger performance monitoring model to output the performance parameters of the host turbocharger.
In one embodiment, the step S102 may be preceded by preprocessing the real-time operation data to obtain preprocessed data of the real-time operation data, and then inputting the preprocessed data of the real-time operation data into a pre-trained turbocharger performance monitoring model to output the performance parameters of the host turbocharger. Here, the preprocessing is to remove abnormal values in the real-time operation data based on preset parameters.
Further, after the step S102, the method further includes:
and generating failure information of the host turbocharger according to the performance parameters of the host turbocharger.
The embodiment of the invention provides a turbocharger performance monitoring method, which comprises the following steps: acquiring real-time operation data of a main engine and a main engine turbocharger of the ship; the real-time operation data are used for indicating the real-time operation states of the host and the host turbocharger; inputting the real-time operation data into a pre-trained turbocharger performance monitoring model, and outputting the performance parameters of the main engine turbocharger; the turbocharger performance monitoring model is obtained based on deep belief network training. According to the method, the performance monitoring model of the turbocharger is built through the deep belief network model so as to predict the performance parameters of the turbocharger of the host, so that the accuracy of the performance monitoring method of the turbocharger is improved, and the sailing safety of the ship is ensured.
Example 2
The present invention provides another turbocharger performance monitoring method based on the method shown in fig. 1, which focuses on the training process of the turbocharger performance monitoring model in step S102 in embodiment 1. As shown in fig. 2, fig. 2 is a schematic flow chart of a training method of a turbocharger performance monitoring model according to an embodiment of the present invention, and as shown in fig. 2, the turbocharger performance monitoring model is obtained through the following training steps:
step S201: acquiring historical operation data of a host machine and a host machine turbocharger of a ship; the historical operation data is used for indicating the historical operation states of the host and the host turbocharger.
In this embodiment, the above-described historical operation data includes: historical host load data, historical host supercharger rotational speed data, historical host cylinder average burst pressure data, historical host supercharger compressor outlet temperature data, historical host supercharger compressor outlet pressure data, historical host scavenging temperature data, historical host scavenging pressure data, historical host supercharger exhaust outlet temperature data, historical host supercharger exhaust outlet pressure data, historical host supercharger filter screen pressure loss coefficient data and historical host scavenging passage pressure loss coefficient data.
In one embodiment, after the step S201, the method includes: preprocessing the historical operation data to obtain an initial training set.
Step S202: and training a preset initial deep belief network by taking the historical operation data as input and taking the supercharger performance data corresponding to the historical operation data as output until a preset training requirement is met, so as to obtain the trained turbocharger performance monitoring model.
In one embodiment, the step S202 includes: and training a preset initial deep belief network by taking the initial training set as input and taking supercharger performance data corresponding to the initial training set as output until a preset training requirement is met, so as to obtain the trained turbocharger performance monitoring model.
After the step of preprocessing the historical operation data to obtain an initial training set, the method comprises the following steps: and constructing the initial deep belief network based on the historical operation data.
Further, based on the historical operation data, an initial deep belief network is constructed, which comprises the following steps A1-A4:
step A1: and taking the values of the historical host load data, the historical host supercharger rotating speed data, the historical host air cylinder average burst pressure data, the historical host supercharger air compressor outlet temperature data, the historical host supercharger air compressor outlet pressure data, the historical host scavenging temperature data, the historical host scavenging pressure data, the historical host supercharger waste gas outlet temperature data, the historical host supercharger waste gas outlet pressure data, the historical host supercharger filter screen pressure loss coefficient data and the historical host scavenging passage pressure loss coefficient data as supercharger characteristic parameters.
Step A2: and determining the number of input neurons of the initial deep belief network according to the supercharger characteristic parameters.
Step A3: and taking the supercharger performance data corresponding to the historical operation data as the output of the initial deep belief network.
Step A4: the initial deep belief network is constructed based on the number of input neurons and the output of the initial deep belief network.
In one embodiment, after step S202, the method further includes the following steps B2-B3:
step B1: calculating a prediction error of the turbocharger performance monitoring model; the prediction error includes: the mean square error of the turbocharger performance monitoring model and the absolute percentage error of the turbocharger performance monitoring model.
Step B2: and screening target operation data within a preset error threshold value from the real-time operation data based on the prediction error.
Step B3: and updating the turbocharger performance monitoring model according to the target operation data to obtain an updated turbocharger performance monitoring model.
Further, the method further comprises the following steps: and inputting the real-time operation data into the updated turbocharger performance monitoring model, and outputting the real-time performance parameters of the host turbocharger.
The embodiment of the invention provides a turbocharger performance monitoring method, which comprises the following steps: acquiring real-time operation data of a main engine and a main engine turbocharger of the ship; the real-time operation data are used for indicating the real-time operation states of the host and the host turbocharger; inputting the real-time operation data into a pre-trained turbocharger performance monitoring model, and outputting the performance parameters of the main engine turbocharger; the turbocharger performance monitoring model is obtained based on deep belief network training; the turbocharger performance monitoring model is obtained through training in the following mode: firstly, acquiring historical operation data of a host machine and a host machine turbocharger of a ship; the historical operation data is used for indicating the historical operation states of the host and the host turbocharger; and training a preset initial deep belief network by taking the historical operation data as input and taking the supercharger performance data corresponding to the historical operation data as output until a preset training requirement is met, so as to obtain the trained turbocharger performance monitoring model. According to the method, the initial deep belief network is trained through historical operation data of the host and the host turbocharger, so that the accuracy of the turbocharger performance monitoring method is further improved, and the sailing safety of the ship is ensured.
Example 3
The embodiment of the invention also provides a turbocharger performance monitoring device, as shown in fig. 3, and provides a schematic structural diagram of the turbocharger performance monitoring device. As can be seen in fig. 3, the device comprises:
a data acquisition module 31 for acquiring real-time operation data of a host of the ship and a turbocharger of the host; the real-time operation data is used for indicating the real-time operation states of the host and the host turbocharger.
The performance prediction module 32 is configured to input the real-time operation data into a pre-trained turbocharger performance monitoring model, and output performance parameters of the host turbocharger; the turbocharger performance monitoring model is obtained based on deep belief network training.
Wherein the data acquisition module 31 is connected to the performance prediction module 32.
In one embodiment, the apparatus further comprises: a model building module; the model building module is used for acquiring historical operation data of a main engine of the ship and a turbocharger of the main engine; the historical operation data is used for indicating the historical operation states of the host and the host turbocharger; and training a preset initial deep belief network by taking the historical operation data as input and taking the supercharger performance data corresponding to the historical operation data as output until a preset training requirement is met, so as to obtain the trained turbocharger performance monitoring model.
In one embodiment, the model building module is further configured to preprocess the historical operating data to obtain an initial training set; and training a preset initial deep belief network by taking the initial training set as input and taking supercharger performance data corresponding to the initial training set as output until a preset training requirement is met, so as to obtain the trained turbocharger performance monitoring model.
In one embodiment, the model building module is further configured to build an initial deep belief network based on the historical operating data.
In one embodiment, the model building module is further configured to use values of the historical host load data, the historical host supercharger speed data, the historical host cylinder average explosion pressure data, the historical host supercharger compressor outlet temperature data, the historical host supercharger compressor outlet pressure data, the historical host scavenging temperature data, the historical host scavenging pressure data, the historical host supercharger exhaust outlet temperature data, the historical host supercharger exhaust outlet pressure data, the historical host supercharger filter screen pressure loss coefficient data, and the historical host scavenging line pressure loss coefficient data as the supercharger characteristic parameters; determining the number of input neurons of the initial deep belief network according to the supercharger characteristic parameters; taking the supercharger performance data corresponding to the historical operation data as the output of the initial deep belief network; the initial deep belief network is constructed based on the number of input neurons and the output of the initial deep belief network.
In one embodiment, the model building module is further configured to calculate a prediction error of the turbocharger performance monitoring model; the prediction error includes: the mean square error of the turbocharger performance monitoring model and the absolute percentage error of the turbocharger performance monitoring model; screening target operation data within a preset error threshold value from the real-time operation data based on the prediction error; and updating the turbocharger performance monitoring model according to the target operation data to obtain an updated turbocharger performance monitoring model.
In one embodiment, the model building module is further configured to update the turbocharger performance monitoring model according to real-time operation data corresponding to the prediction error within a preset error threshold; the performance prediction module 32 is further configured to input the real-time operation data into the updated turbocharger performance monitoring model, and output the real-time performance parameters of the host turbocharger.
The turbocharger performance monitoring device provided by the embodiment of the invention has the same technical characteristics as the turbocharger performance monitoring method provided by the embodiment, so that the same technical problems can be solved, and the same technical effects can be achieved. It will be clear to those skilled in the art that, for convenience and brevity of description, reference may be made to the corresponding process in the foregoing method embodiment for the specific working process of the apparatus described above, which is not described herein again.
Example 4
The present embodiment provides an electronic device comprising a processor and a memory storing computer executable instructions executable by the processor to perform the steps of a turbocharger performance monitoring method.
Referring to fig. 4, a schematic structural diagram of an electronic device includes: the turbocharger performance monitoring method comprises a memory 41 and a processor 42, wherein a computer program capable of running on the processor 42 is stored in the memory, and the steps provided by the turbocharger performance monitoring method are realized when the processor executes the computer program.
As shown in fig. 4, the apparatus further includes: a bus 43 and a communication interface 44, the processor 42, the communication interface 44 and the memory 41 being connected by the bus 43; the processor 42 is arranged to execute executable modules, such as computer programs, stored in the memory 41.
The memory 41 may include a high-speed random access memory (RAM, random Access Memory), and may further include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. The communication connection between the system network element and at least one other network element is implemented via at least one communication interface 44 (which may be wired or wireless), which may use the internet, a wide area network, a local network, a metropolitan area network, etc.
The bus 43 may be an ISA bus, a PCI bus, an EISA bus, or the like. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 4, but not only one bus or type of bus.
The memory 41 is used for storing a program, and the processor 42 executes the program after receiving the execution instruction, so that any of the embodiments of the present invention described above discloses that the method executed by the turbocharger performance monitoring apparatus may be applied to the processor 42 or implemented by the processor 42. The processor 42 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuitry in hardware or instructions in software in the processor 42. The processor 42 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but may also be a digital signal processor (Digital Signal Processing, DSP for short), application specific integrated circuit (Application Specific Integrated Circuit, ASIC for short), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA for short), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks 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 embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory 41 and a processor 42 reads information in the memory 41 and in combination with its hardware performs the steps of the method described above.
Further, an embodiment of the present invention provides a computer storage medium storing a computer program comprising program instructions that, when executed by the processor 42, cause the processor 42 to perform implementing the turbocharger performance monitoring method.
The turbocharger performance monitoring device and the turbocharger performance monitoring method verification device provided by the embodiment of the invention have the same technical characteristics, so that the same technical problems can be solved, and the same technical effects can be achieved.
In addition, in the description of embodiments of the present invention, unless explicitly stated and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured 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.
Claims (10)
1. A turbocharger performance monitoring method, comprising:
acquiring real-time operation data of a main engine and a main engine turbocharger of the ship; the real-time operation data are used for indicating the real-time operation states of the host and the host turbocharger;
inputting the real-time operation data into a pre-trained turbocharger performance monitoring model, and outputting performance parameters of the host turbocharger; the turbocharger performance monitoring model is obtained based on deep belief network training.
2. The turbocharger performance monitoring method of claim 1, wherein the turbocharger performance monitoring model is trained by:
acquiring historical operation data of a host machine and a host machine turbocharger of a ship; wherein the historical operating data is used to indicate historical operating conditions of the host and the host turbocharger;
and training a preset initial deep belief network by taking the historical operation data as input and taking the supercharger performance data corresponding to the historical operation data as output until a preset training requirement is met, so as to obtain the trained turbocharger performance monitoring model.
3. The turbocharger performance monitoring method according to claim 2, wherein the step of taking the historical operation data as input and the supercharger performance data corresponding to the historical operation data as output to train a preset initial deep belief network until a preset training requirement is reached, and obtaining the trained turbocharger performance monitoring model comprises the steps of:
preprocessing the historical operation data to obtain an initial training set;
and training a preset initial deep belief network by taking the initial training set as input and taking supercharger performance data corresponding to the initial training set as output until a preset training requirement is met, so as to obtain the trained turbocharger performance monitoring model.
4. A turbocharger performance monitoring method according to claim 3, wherein after the step of preprocessing the historical operating data to obtain an initial training set, the method comprises:
and constructing the initial deep belief network based on the historical operating data.
5. The turbocharger performance monitoring method of claim 2, wherein the historical operating data comprises: historical host load data, historical host supercharger rotational speed data, historical host cylinder average burst pressure data, historical host supercharger compressor outlet temperature data, historical host supercharger compressor outlet pressure data, historical host scavenging temperature data, historical host scavenging pressure data, historical host supercharger exhaust outlet temperature data, historical host supercharger exhaust outlet pressure data, historical host supercharger filter screen pressure loss coefficient data and historical host scavenging passage pressure loss coefficient data.
6. The turbocharger performance monitoring method of claim 5, wherein the step of constructing the initial deep belief network based on the historical operating data comprises:
taking values of the historical host load data, the historical host supercharger rotating speed data, the historical host cylinder average explosion pressure data, the historical host supercharger compressor outlet temperature data, the historical host supercharger compressor outlet pressure data, the historical host scavenging temperature data, the historical host scavenging pressure data, the historical host supercharger waste gas outlet temperature data, the historical host supercharger waste gas outlet pressure data, the historical host supercharger filter screen pressure loss coefficient data and the historical host scavenging passage pressure loss coefficient data as supercharger characteristic parameters;
determining the number of input neurons of the initial deep belief network according to the supercharger characteristic parameters;
taking the supercharger performance data corresponding to the historical operation data as the output of the initial deep belief network;
and constructing the initial deep belief network according to the number of the input neurons and the output of the initial deep belief network.
7. The turbocharger performance monitoring method of claim 1, wherein, after the step of inputting the real-time operational data into a pre-trained turbocharger performance monitoring model and outputting the performance parameters of the host turbocharger, the method further comprises:
calculating a prediction error of the turbocharger performance monitoring model; the prediction error includes: the mean square error of the turbocharger performance monitoring model and the absolute percentage error of the turbocharger performance monitoring model;
screening target operation data within a preset error threshold value from the real-time operation data based on the prediction error;
and updating the turbocharger performance monitoring model according to the target operation data to obtain an updated turbocharger performance monitoring model.
8. The method of claim 7, wherein updating the turbocharger performance monitoring model according to real-time operation data corresponding to the prediction error within a preset error threshold, and after the step of obtaining an updated turbocharger performance monitoring model, the method further comprises:
and inputting the real-time operation data into the updated turbocharger performance monitoring model, and outputting the real-time performance parameters of the host turbocharger.
9. A turbocharger performance monitoring device, comprising:
the data acquisition module is used for acquiring real-time operation data of a host machine of the ship and a turbocharger of the host machine; the real-time operation data are used for indicating the real-time operation states of the host and the host turbocharger;
the performance prediction module is used for inputting the real-time operation data into a pre-trained turbocharger performance monitoring model and outputting the performance parameters of the host turbocharger; the turbocharger performance monitoring model is obtained based on deep belief network training.
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 turbocharger performance monitoring method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211580413.2A CN116006275A (en) | 2022-12-06 | 2022-12-06 | Turbocharger performance monitoring method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211580413.2A CN116006275A (en) | 2022-12-06 | 2022-12-06 | Turbocharger performance monitoring method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116006275A true CN116006275A (en) | 2023-04-25 |
Family
ID=86023851
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211580413.2A Pending CN116006275A (en) | 2022-12-06 | 2022-12-06 | Turbocharger performance monitoring method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116006275A (en) |
-
2022
- 2022-12-06 CN CN202211580413.2A patent/CN116006275A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113343500B (en) | Method for constructing digital twin system and computing equipment | |
| CN108009723A (en) | A kind of ship navigation state judges and energy efficiency state assessment system | |
| CN111042956A (en) | EGR flow fault judgment method, device and equipment | |
| CN112459971A (en) | Abnormal vibration detection method for tower of wind generating set | |
| CN111191838A (en) | Industrial equipment state control method and device integrating artificial intelligence algorithm | |
| CN112733455A (en) | Correction method, system, device and storage medium of water turbine modeling data | |
| CN113187592B (en) | Secondary air system monitoring method, device, equipment and storage medium | |
| CN107076018A (en) | Surge decision maker, surge decision method and program | |
| CN116006275A (en) | Turbocharger performance monitoring method and device and electronic equipment | |
| CN117195454A (en) | Method and device for constructing digital twin body of power grid, electronic equipment and storage medium | |
| CN112577724A (en) | Method for determining starting and stopping threshold value of mobile equipment, starting and stopping monitoring method and device | |
| CN115066693A (en) | Operation state classification system and operation state classification method | |
| CN116644508A (en) | Engine digital twin modeling method, system, electronic equipment and storage medium | |
| CN108132867B (en) | Equipment fault alarm method and computing equipment | |
| CN114607495B (en) | Method and device for determining concentration of nitrogen oxide, electronic equipment and storage medium | |
| CN115994414A (en) | Reciprocating compressor operation efficiency calculation method and system based on indicator diagram | |
| CN114544184A (en) | Fault diagnosis method, fault diagnosis device, electronic apparatus, storage medium, and engine | |
| CN115825752A (en) | Method and device for predicting residual life of ship power battery and electronic equipment | |
| CN117307500B (en) | Remote digital monitoring method, terminal, monitoring system and medium for slurry pump | |
| CN114837805B (en) | Method and device for determining sulfur content of fuel oil of vehicle, vehicle and storage medium | |
| CN109977726A (en) | Signal envelope extraction method and device and state monitoring method of wind turbine generator | |
| CN115263549B (en) | Surge recognition method and related device of turbocharger | |
| CN112819083B (en) | Hydraulic pump fault prediction method, device, electronic equipment and storage medium | |
| CN116428053A (en) | Boost pressure fault diagnosis method and device, electronic equipment and storage medium | |
| CN116221033A (en) | Fan fault management method and device |
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 |