A ship engine control method and system based on oil mist monitoring

By constructing a fuel atomization model and using a three-layer stacked bidirectional long and short-term memory neural network to predict oil mist concentration, combining the theoretical and actual values ​​of oil mist concentration, the ship engine is controlled, and engine damage caused by hysteresis in the existing technology is solved. The problem has been achieved to promptly detect and deal with abnormal oil mist concentrations to ensure the optimal operating state of the engine.

CN118793527BActive Publication Date: 2024-11-19FUJIAN BAIMA SHIP FACTORY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411273425.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-12
Publication Date
2024-11-19
Estimated Expiration
2044-09-12

AI Technical Summary

Technical Problem

The existing fuel engine control technology based on threshold control has a hysteresis and cannot predict and deal with the trend changes in the gradual increase in oil mist concentration in a timely manner, resulting in the engine that may cause irreversible damage before the alarm is triggered.

Method used

Using an oil mist monitoring method, the engine is predicted by constructing a fuel atomization model and using a three-layer stacked bidirectional long and short-term memory neural network, and combining the current oil mist concentration theoretical values ​​and actual values, the engine is controlled in real time and captured. Change trend of oil mist concentration, discover abnormalities in a timely manner and take corresponding measures.

Benefits of technology

It realizes timely detection of possible engine abnormalities, reduces the possibility of damage, ensures that the engine operates under optimal operating conditions, and avoids more serious failures caused by hysteresis control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118793527B_ABST
    Figure CN118793527B_ABST
Patent Text Reader

Abstract

The present invention provides a ship engine control method and system based on oil mist monitoring, which relates to the technical field of fuel engine control. The method includes: constructing a ship engine fuel atomization model; obtaining the current ship engine operating parameters; substituting the current ship engine operating parameters into the ship engine fuel atomization model to determine the theoretical value of the oil mist concentration at the current moment; obtaining the actual value of the oil mist concentration at the current moment through an oil mist detector; predicting the predicted value of the oil mist concentration at a future moment through a three-layer stacked bidirectional long short-term memory neural network according to the actual value of the oil mist concentration in the current period; controlling the ship engine according to the theoretical value of the oil mist concentration at the current moment, the actual value of the oil mist concentration and the predicted value of the oil mist concentration at a future moment. The present invention can capture the trend change of the gradually increasing oil mist concentration, timely discover possible abnormalities of the engine, and reduce the possibility of engine damage.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of fuel engine control, and in particular to a ship engine control method and system based on oil mist monitoring. Background Art

[0002] Oil mist concentration is indeed one of the key parameters for evaluating and controlling engine status, especially in diesel engines and certain types of gas turbines. For example, oil mist concentration reflects the quality of fuel atomization and the efficiency of the combustion process. If the oil mist concentration is abnormal, it may mean that there is a problem with the fuel injection system, such as injector clogging, wear or improper adjustment, which will cause incomplete combustion and thus affect the performance and efficiency of the engine. Therefore, changes in oil mist concentration can reflect the working condition and health status of the engine.

[0003] Current fuel engine control technology based on oil mist concentration often uses threshold control technology. When the oil mist concentration is greater than the alarm value, an alarm is issued and the fuel engine is controlled to reduce power or even shut down for maintenance. When the oil mist concentration is less than the alarm value, it continues to run.

[0004] However, threshold control has a certain hysteresis. When the oil mist concentration reaches the alarm threshold, the engine may have been in a non-optimal or damaged state for a period of time. This hysteresis may cause the fault to deteriorate to a more serious level, or even cause irreversible damage before the alarm is triggered. At the same time, threshold control often only focuses on whether it exceeds the warning line, but ignores the trend change of the gradually increasing oil mist concentration. It is difficult to detect the early fault sign of gradual change, unable to predict potential faults, detect engine faults in time, and take measures before the problem becomes serious, causing engine damage. Summary of the invention

[0005] In order to solve the problem that the current threshold control has a certain hysteresis, when the oil mist concentration reaches the alarm threshold, the engine may have been in a non-optimal or damaged state for a period of time. This hysteresis may cause the fault to deteriorate to a more serious degree, and even cause irreversible damage before the alarm is triggered. The threshold control often only focuses on whether it exceeds the warning line, but ignores the trend change of the gradually increasing oil mist concentration. It is difficult to detect the early fault sign of gradual change, unable to predict potential faults, timely discover engine faults, and take measures before the problem becomes serious, causing engine damage. The technical problem, the present invention provides a ship engine control method and system based on oil mist monitoring.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] First aspect:

[0008] An embodiment of the present invention provides a ship engine control method based on oil mist monitoring, comprising:

[0009] S1: Construct a fuel atomization model for ship engines;

[0010] S2: Obtain the current ship engine operating parameters;

[0011] S3: Substituting the current ship engine operating parameters into the ship engine fuel atomization model to determine the theoretical value of the oil mist concentration at the current moment;

[0012] S4: Obtain the actual value of the oil mist concentration at the current moment through the oil mist detector;

[0013] S5: Based on the actual value of the oil mist concentration in the current period, the predicted value of the oil mist concentration at the future moment is predicted through a three-layer stacked bidirectional long short-term memory neural network;

[0014] S6: Control the ship engine according to the theoretical value of the oil mist concentration at the current moment, the actual value of the oil mist concentration and the predicted value of the oil mist concentration at the future moment.

[0015] Second aspect:

[0016] An embodiment of the present invention provides a ship engine control system based on oil mist monitoring, comprising:

[0017] processor;

[0018] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the ship engine control method based on oil mist monitoring as described in the first aspect is implemented.

[0019] The third aspect:

[0020] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the ship engine control method based on oil mist monitoring as described in the first aspect is implemented.

[0021] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0022] In the present invention, the ship engine is controlled according to the theoretical value of the oil mist concentration at the current moment, the actual value of the oil mist concentration and the predicted value of the oil mist concentration at the future moment, so as to capture the trend change of the gradually increasing oil mist concentration, timely discover the possible abnormality of the engine, reduce the possibility of engine damage, and combine the theoretical value of the oil mist concentration with the actual value of the oil mist concentration to provide real-time feedback on the working status of the engine, evaluate the degree of engine abnormality and perform corresponding control to ensure that the engine operates under the best working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A schematic flow chart of a ship engine control method based on oil mist monitoring provided by an embodiment of the present invention;

[0025] Figure 2 A structural schematic diagram of a ship engine control method based on oil mist monitoring provided by an embodiment of the present invention;

[0026] Figure 3 A schematic structural diagram of a ship engine control system based on oil mist monitoring provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0028] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0029] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0030] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0031] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0032] Reference Manual Attached Figure 1, showing a flow chart of a ship engine control method based on oil mist monitoring provided by an embodiment of the present invention.

[0033] Reference Manual Attached Figure 2 , showing a structural schematic diagram of a ship engine control method based on oil mist monitoring provided by an embodiment of the present invention.

[0034] The embodiment of the present invention provides a ship engine control method based on oil mist monitoring, which can be implemented by a ship engine control device based on oil mist monitoring, and the ship engine control device based on oil mist monitoring can be a terminal or a server. The processing flow of the ship engine control method based on oil mist monitoring can include the following steps:

[0035] S1: Construct a fuel atomization model for a ship engine.

[0036] In a possible implementation, S1 specifically includes:

[0037] S101: Calculate the Weber number during fuel consumption:

[0038]

[0039] in, W e represents Weber number, U st represents the average outflow rate of fuel during spraying, d c Indicates the nozzle diameter, r f Indicates the fuel density, s f Indicates the surface tension of fuel.

[0040] The Weber number is a dimensionless number used in fluid mechanics, especially in describing the dynamic behavior of fluid systems such as droplets, bubbles, and liquid films. It reflects the relative magnitude between the inertial force and the surface tension of the fluid.

[0041] S102: Calculate fuel viscosity:

[0042]

[0043] in, M Indicates fuel viscosity, m f Indicates the dynamic viscosity of fuel.

[0044] S103: Calculate the amount of gas charged:

[0045]

[0046] in, M m Indicates the amount of gas filled. or vs represents the cylinder filling rate, p s Indicates the inlet pressure, V c represents the volume of the combustion chamber, T s Indicates the inlet temperature.

[0047] S104: Calculate the amount of gas at the end of compression:

[0048]

[0049] in, M v Indicates the amount of gas, c r Indicates the gas residual rate.

[0050] S105: Calculate the air density at the end of compression:

[0051]

[0052] in, r a represents the air density at the end of compression, m Indicates the molecular weight of the fuel mixture.

[0053] S106: Calculate the mixture density ratio:

[0054]

[0055] in, p represents the mixture density ratio, r a Indicates the air density at the end of compression.

[0056] S107: Calculate the oil mist boundary:

[0057]

[0058] in, l b represents the oil mist boundary, C k Indicates the injection coefficient.

[0059] Among them, those skilled in the art can set the injection coefficient according to actual conditions. C k The present invention does not limit the size.

[0060] S108: Calculate the oil mist angle:

[0061]

[0062] in, c 0 represents the spray angle, arctan represents the inverse tangent function, f c Represents a constant related to the nozzle properties.

[0063] S109: Calculate the injection volume:

[0064]

[0065] in, V s Indicates the injection volume.

[0066] S110: Calculate fuel mass flow rate:

[0067]

[0068] in, Indicates the fuel mass flow rate.

[0069] S111: Calculate the theoretical value of fuel concentration:

[0070]

[0071] in, C s Indicates the theoretical value of fuel concentration.

[0072] In the present invention, the fuel atomization model of the ship engine can be used to accurately calculate the theoretical value of the fuel concentration generated under the ideal state of normal engine operation, which can provide a reference basis for the subsequent determination of the engine operating status and improve the accuracy of the engine operating status detection.

[0073] S2: Obtain the current ship engine operating parameters.

[0074] Specifically, the nozzle model, fuel model, engine combustion chamber volume, etc. used by the current ship engine can be obtained.

[0075] S3: Substitute the current ship engine operating parameters into the ship engine fuel atomization model to determine the theoretical value of the oil mist concentration at the current moment.

[0076] S4: Obtain the actual value of the oil mist concentration at the current moment through the oil mist detector.

[0077] Among them, the oil mist detector is a device used to monitor the concentration of oil mist in the air. The principle of the oil mist detector can be based on light scattering method, light transmission method and electrochemical sensing method. Taking the light heat dissipation method as an example, a light source (usually a laser) irradiates the detection area. When the oil mist particles pass through the light beam, they scatter the light. The detector (usually a photodiode) receives the scattered light and converts it into an electrical signal. By analyzing the intensity and pattern of the scattered light signal, the oil mist concentration can be calculated.

[0078] S5: According to the actual value of the oil mist concentration in the current period, the predicted value of the oil mist concentration at the future moment is predicted through a three-layer stacked bidirectional long short-term memory neural network.

[0079] Among them, Bidirectional Long Short-Term Memory (BiLSTM) is a deep learning model used to process and predict time series-based data. It combines the advantages of bidirectional RNN and LSTM, and can effectively capture long-term dependencies in time series while taking into account contextual information.

[0080] Optionally, the three-layer stacked bidirectional long short-term memory neural network includes a first bidirectional long short-term memory neural network, a second bidirectional long short-term memory neural network and a third bidirectional long short-term memory neural network that are stacked.

[0081] Optionally, the input of the first bidirectional long short-term memory neural network is used to obtain the actual value of the oil mist concentration in the current period of time, the hidden connection of the first bidirectional long short-term memory neural network is the input of the second bidirectional long short-term memory neural network, the hidden connection of the second bidirectional long short-term memory neural network is the input of the third bidirectional long short-term memory neural network, and the output of the third bidirectional long short-term memory neural network is used to predict the predicted value of the oil mist concentration at a future moment based on the comprehensive hidden state.

[0082] It should be noted that each layer of the bidirectional long short-term memory neural network further extracts features based on the previous layer. The first layer of the bidirectional long short-term memory neural network can capture low-level features of time series data, such as short-term trends and patterns. As the data passes through multiple layers of the bidirectional long short-term memory neural network, the model can gradually extract higher-level features, such as long-term dependencies and complex time series patterns. This layer-by-layer feature extraction method can enhance the model's understanding of complex time series data.

[0083] In a possible implementation, S5 specifically includes:

[0084] S501: Input the actual value sequence of oil mist concentration in the current period into the first bidirectional long short-term memory neural network, and learn in the forward direction to obtain the first forward hidden state.

[0085] It should be noted that the forward dependency in the time series is initially extracted to obtain basic forward features, which helps to capture the dynamic changes in the recent moments in the time series.

[0086] Specifically, for a certain layer of bidirectional long short-term memory neural network, the hidden state is extracted h , when the bidirectional long short-term memory neural network is learning in the forward direction, the hidden state h is the forward hidden state, expressed as , when the bidirectional long short-term memory neural network is learned in the backward direction, the hidden state h is the backward hidden state, expressed as :

[0087]

[0088] in, I t express t The activation output vector of the input gate at the moment, Sigmoid () represents the Sigmoid activation function, W XI Represents the weight matrix between the word segmentation sequence and the input gate, X t express t The weighted word vector input at each moment, W HI represents the weight matrix between the hidden state and the input gate, b I represents the bias term of the input gate, F t express t Always forget the activation output vector of the gate, W XF Represents the weight matrix between the word segmentation sequence and the forget gate, W HF represents the weight matrix between the hidden state and the forget gate, b F represents the bias term of the forget gate, O t express t The activation output vector of the output gate at time t, W XO Represents the weight matrix between the word segmentation sequence and the output gate, W HO represents the weight matrix between the hidden state and the output gate, b O represents the bias term of the output gate, C t express tThe activation output vector of the cell storage unit at time instant, express t The candidate output vector of the cell storage unit at the moment, C t-1 express t -1 is the activation output vector of the cell storage unit, tanh() represents the tanh activation function, W XC Represents the weight matrix between the word segmentation sequence and the cell storage unit, W HC represents the weight matrix between the hidden state and the cell storage unit, b C represents the bias term of the cell storage unit, h t express t The hidden state of the moment, h t-1 express t The hidden state at time -1.

[0089] S502: Input the first forward hidden state into the second bidirectional long short-term memory neural network, and perform learning in the forward direction to obtain a second forward hidden state.

[0090] It should be noted that further processing and extracting higher-level forward features can enhance the model's understanding of complex time dependencies.

[0091] S503: Input the second forward hidden state into the third bidirectional long short-term memory neural network, and perform learning in the forward direction to obtain a third forward hidden state.

[0092] It should be noted that in-depth mining of forward features ensures that the model fully learns the forward information in the time series and improves the accuracy and stability of the prediction.

[0093] S504: Input the actual value sequence of the oil mist concentration in the current period into the first bidirectional long short-term memory neural network, and perform backward learning to obtain a first backward hidden state.

[0094] It should be noted that the backward dependency in the time series is initially extracted to obtain basic backward features, which helps to capture the dynamic changes at distant moments in the time series.

[0095] S505: Input the first backward hidden state into the second bidirectional long short-term memory neural network, and perform backward learning to obtain a second backward hidden state.

[0096] It should be noted that further processing and extracting higher-level backward features can enhance the model's understanding of complex temporal dependencies.

[0097] S506: Input the second backward hidden state into the third bidirectional long short-term memory neural network, perform backward learning, and obtain a third backward hidden state.

[0098] It should be noted that in-depth mining of backward features ensures that the model fully learns the backward information in the time series and improves the accuracy and stability of the prediction.

[0099] S507: Fusing the third forward hidden state with the third backward hidden state to obtain a comprehensive hidden state.

[0100] It should be noted that the forward and backward features are combined to obtain a comprehensive hidden state.

[0101] Optionally, S507 is specifically: according to the following formula, the third forward hidden state is merged with the third backward hidden state to obtain a comprehensive hidden state:

[0102]

[0103] in, H t represents the comprehensive hidden state, Sigmoid ( ) represents the Sigmoid activation function, W f represents the forward weight matrix, W b represents the backward weight matrix, represents the third forward hidden state, Represents the third backward hidden state.

[0104] S508: Predict the oil mist concentration at a future time based on the comprehensive hidden state.

[0105] It should be noted that the use of comprehensive integrated latent states for prediction can provide more accurate future oil mist concentration values, which helps to take measures in advance, optimize system operation and prevent potential problems.

[0106] Optionally, S508 is specifically: predicting the oil mist concentration prediction value at a future time according to the following formula:

[0107]

[0108] in, C y represents the predicted value of oil mist concentration at the future moment, Sigmoid ( ) represents the Sigmoid activation function, W h represents the weight matrix between the hidden layer and the classification layer, b h Represents the classification layer bias term.

[0109] In the present invention, the improved multi-layer bidirectional LSTM structure can better capture and understand the complex patterns and long-term dependencies in time series data. Layer-by-layer feature extraction and information integration can improve the prediction accuracy and stability of the model, while making full use of forward and backward information, making the model perform better in various application scenarios. This structure has a wide range of application prospects in time series prediction tasks and can provide strong technical support for various industrial and environmental monitoring.

[0110] Furthermore, in order to achieve accurate prediction of oil mist concentration, it is necessary to train the three-layer stacked bidirectional long-short time neural network. The specific training method is as follows:

[0111] Taking prediction accuracy as the goal, the oil mist concentration prediction loss function is constructed:

[0112]

[0113] in, J represents the oil mist concentration prediction loss function, i represents the network parameters of a three-layer stacked bidirectional long short-time neural network, express t The predicted value of oil mist concentration at time express t The actual value of oil mist concentration at the moment, T Represents the total observation time.

[0114] With the goal of minimizing the oil mist concentration prediction loss function, the model parameters of the lifting ring recognition model are optimized by the gradient descent method:

[0115]

[0116] in, i k+1 Indicates k +Model parameters at 1 iteration, i k Indicates k The network parameters at the iteration, or k Indicates k The adaptive learning rate at the iteration, Represents the oil mist concentration prediction loss function J For model parameters i k The gradient of β represents the momentum coefficient.

[0117] It should be noted that the momentum term can help the model avoid falling into the local optimum and smooth the optimization path by considering the previous update direction. The adaptive learning rate method can automatically adjust the learning rate according to the size of the gradient, ensuring that the learning rate is large in the early stage of training to accelerate convergence, and small when close to convergence to refine the search.

[0118] Furthermore, the adaptive learning rate is calculated as:

[0119]

[0120] in, or k Indicates k The adaptive learning rate at the iteration, or 0 represents the initial learning rate, Oil mist concentration prediction loss function J For model parameters i u The gradient of m represents a hyperparameter that prevents the denominator from being zero.

[0121] In the present invention, by calculating the cumulative sum of squares of the current gradient, the adaptive learning rate can be dynamically adjusted according to the actual situation during the training process. This means that in the early stage of training, when the gradient changes greatly, the learning rate will be higher, thereby accelerating the convergence speed; in the later stage of training, when the model is close to convergence, the learning rate will be reduced, thereby preventing oscillation and instability caused by excessive update step size. The adaptive learning rate can not only improve the training efficiency and stability of the model, but also improve the prediction accuracy, making the model perform better in complex practical application scenarios.

[0122] S6: Control the ship engine according to the theoretical value of the oil mist concentration at the current moment, the actual value of the oil mist concentration and the predicted value of the oil mist concentration at the future moment.

[0123] In a possible implementation, S6 specifically includes:

[0124] S601: and In this case, a first-level alarm is issued and the ship engine is controlled to reduce the operating power to the first level.

[0125] It should be noted that when the actual oil mist concentration is lower than the preset value but the future predicted value is higher than the preset value, measures should be taken in advance to prevent the oil mist concentration from exceeding the standard.

[0126] S602: and In this case, a second-level alarm is issued and the ship's engine is controlled to reduce operating power by a second magnitude.

[0127] It should be noted that when the oil mist concentration exceeds the preset value and is close to the theoretical value, it indicates that the situation is not particularly serious. Moderate power reduction measures should be taken to control the oil mist concentration by further reducing the power to avoid worsening of the situation.

[0128] S603: and In such case, a level 3 alarm was issued and the ship's engine was shut down for inspection.

[0129] It should be noted that when the oil mist concentration significantly exceeds the standard and is significantly different from the theoretical value, it indicates that there may be serious problems or abnormal conditions. At this time, the machine should be shut down for maintenance immediately to prevent further damage or safety accidents.

[0130] in, C r Indicates the actual value of oil mist concentration at the current moment. C y Indicates the predicted value of oil mist concentration at a future time, C s Indicates the theoretical value of oil mist concentration at the current moment, C 0 means the preset concentration value, Indicates the preset difference value.

[0131] In the present invention, different levels of response measures are gradually increased, from a small reduction in power to a complete shutdown, which ensures safety while minimizing the impact on normal operation. Through the three-level alarm system and corresponding control measures, the problem of excessive oil mist concentration can be discovered and handled in a timely manner, preventing sudden accidents and ensuring the safety of ship operation.

[0132] Optionally, the operating power reduced by the second magnitude is greater than the operating power reduced by the first magnitude.

[0133] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0134] In the present invention, the ship engine is controlled according to the theoretical value of the oil mist concentration at the current moment, the actual value of the oil mist concentration and the predicted value of the oil mist concentration at the future moment, so as to capture the trend change of the gradually increasing oil mist concentration, timely discover the possible abnormality of the engine, reduce the possibility of engine damage, and combine the theoretical value of the oil mist concentration with the actual value of the oil mist concentration to provide real-time feedback on the working status of the engine, evaluate the degree of engine abnormality and perform corresponding control to ensure that the engine operates under the best working conditions.

[0135] Reference Manual Attached Figure 3 , showing a structural schematic diagram of a ship engine control system based on oil mist monitoring provided by the present invention.

[0136] The present invention further provides a ship engine control system 20 based on oil mist monitoring, which is applied to the above-mentioned ship engine control method based on oil mist monitoring, comprising:

[0137] Processor 201;

[0138] The memory 202 stores computer-readable instructions, and when the computer-readable instructions are executed by the processor 201, the ship engine control method based on oil mist monitoring as described in the method embodiment is implemented.

[0139] The ship engine control system 20 based on oil mist monitoring provided by the present invention can execute the above-mentioned ship engine control method based on oil mist monitoring and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0140] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0141] In the present invention, the ship engine is controlled according to the theoretical value of the oil mist concentration at the current moment, the actual value of the oil mist concentration and the predicted value of the oil mist concentration at the future moment, so as to capture the trend change of the gradually increasing oil mist concentration, timely discover the possible abnormality of the engine, reduce the possibility of engine damage, and combine the theoretical value of the oil mist concentration with the actual value of the oil mist concentration to provide real-time feedback on the working status of the engine, evaluate the degree of engine abnormality and perform corresponding control to ensure that the engine operates under the best working conditions.

[0142] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0143] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0144] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0145] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0146] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0147] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0148] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0149] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0150] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0151] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0152] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0153] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0154] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the ship engine control method based on oil mist monitoring as described in the method embodiment is implemented.

[0155] A computer-readable storage medium provided by the present invention can implement the steps and effects of the ship engine control method based on oil mist monitoring of the above method embodiment. To avoid repetition, the present invention will not go into details.

[0156] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0157] In the present invention, the ship engine is controlled according to the theoretical value of the oil mist concentration at the current moment, the actual value of the oil mist concentration and the predicted value of the oil mist concentration at the future moment, so as to capture the trend change of the gradually increasing oil mist concentration, timely discover the possible abnormality of the engine, reduce the possibility of engine damage, and combine the theoretical value of the oil mist concentration with the actual value of the oil mist concentration to provide real-time feedback on the working status of the engine, evaluate the degree of engine abnormality and perform corresponding control to ensure that the engine operates under the best working conditions.

[0158] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0159] There are a few points to note:

[0160] (1) The drawings of the embodiments of the present invention only involve structures related to the embodiments of the present invention. Other structures may refer to conventional designs.

[0161] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the film or region is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a film, a region or a substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0162] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0163] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A ship engine control method based on oil mist monitoring, It is characterized in that include: S1: Construct a fuel atomization model for ship engines; S2: Obtain the current ship engine operating parameters; S3: Substituting the current ship engine operating parameters into the ship engine fuel atomization model to determine the theoretical value of the oil mist concentration at the current moment; S4: Obtain the actual value of the oil mist concentration at the current moment through the oil mist detector; S5: Based on the actual value of the oil mist concentration in the current period, the predicted value of the oil mist concentration at the future moment is predicted through a three-layer stacked bidirectional long short-term memory neural network; S6: Control the ship engine according to the theoretical value of the oil mist concentration at the current moment, the actual value of the oil mist concentration and the predicted value of the oil mist concentration at the future moment; Wherein, the S6 specifically includes: S601: and In the case of a fire, a first-level alarm is issued and the ship's engine is controlled to reduce operating power by the first amplitude; S602: and In the case of a second-level alarm, the ship's engine is controlled to reduce operating power by the second amplitude; S603: and In the event of a fire, a Level 3 alarm will be issued and the ship's engine will be shut down for inspection; in, C r Indicates the actual value of oil mist concentration at the current moment. C y Indicates the predicted value of oil mist concentration at a future time, C s Indicates the theoretical value of oil mist concentration at the current moment, C 0 Indicates the preset concentration value. Indicates the preset difference value.

2. The ship engine control method based on oil mist monitoring according to claim 1, It is characterized in that The S1 specifically includes: S101: Calculate the Weber number during fuel consumption: in, W e represents Weber number, U st represents the average outflow rate of fuel during spraying, d c Indicates the nozzle diameter, ρ f Indicates the fuel density, σ f Indicates the surface tension of fuel; S102: Calculate fuel viscosity: in, M Indicates fuel viscosity, μ f Indicates the dynamic viscosity of fuel; S103: Calculate the amount of gas charged: in, M m Indicates the amount of gas filled. η vs represents the cylinder filling rate, p s Indicates the inlet pressure, V c represents the volume of the combustion chamber, T s represents the inlet temperature; S104: Calculate the amount of gas at the end of compression: in, M v Indicates the amount of gas, γ r Indicates the gas residual rate; S105: Calculate the air density at the end of compression: in, ρ a represents the air density at the end of compression, m Indicates the molecular weight of the fuel mixture; S106: Calculate the mixture density ratio: in, p represents the mixture density ratio, ρ a Indicates the air density at the end point of compression; S107: Calculate the oil mist boundary: in, l b represents the oil mist boundary, C k represents the injection coefficient; S108: Calculate the oil mist angle: in, γ 0 represents the spray angle, arctan represents the inverse tangent function, f c represents a constant related to the properties of the nozzle; S109: Calculate the injection volume: in, V s represents the injection volume; S110: Calculate fuel mass flow rate: in, represents the fuel mass flow rate; S111: Calculate the theoretical value of fuel concentration: in, C s Indicates the theoretical value of fuel concentration.

3. The ship engine control method based on oil mist monitoring according to claim 1, It is characterized in that The three-layer stacked bidirectional long short-term memory neural network includes a first bidirectional long short-term memory neural network, a second bidirectional long short-term memory neural network and a third bidirectional long short-term memory neural network that are stacked.

4. The ship engine control method based on oil mist monitoring according to claim 3, It is characterized in that The input of the first bidirectional long short-term memory neural network is used to obtain the actual value of the oil mist concentration in the current period of time, the hidden connection of the first bidirectional long short-term memory neural network is the input of the second bidirectional long short-term memory neural network, the hidden connection of the second bidirectional long short-term memory neural network is the input of the third bidirectional long short-term memory neural network, and the output of the third bidirectional long short-term memory neural network is used to predict the predicted value of the oil mist concentration at a future moment based on the comprehensive hidden state.

5. The ship engine control method based on oil mist monitoring according to claim 4, It is characterized in that The S5 specifically includes: S501: inputting a sequence of actual values ​​of oil mist concentration within a current period of time into the first bidirectional long short-term memory neural network, and performing forward learning to obtain a first forward hidden state; S502: Input the first forward hidden state into the second bidirectional long short-term memory neural network, and perform learning in the forward direction to obtain a second forward hidden state; S503: inputting the second forward hidden state into the third bidirectional long short-term memory neural network, and performing learning in the forward direction to obtain a third forward hidden state; S504: inputting the actual value sequence of the oil mist concentration in the current period into the first bidirectional long short-term memory neural network, and performing backward learning to obtain a first backward hidden state; S505: inputting the first backward hidden state into the second bidirectional long short-term memory neural network, and performing backward learning to obtain a second backward hidden state; S506: inputting the second backward hidden state into the third bidirectional long short-term memory neural network, and performing backward learning to obtain a third backward hidden state; S507: Fusing the third forward hidden state with the third backward hidden state to obtain a comprehensive hidden state; S508: Predicting the oil mist concentration prediction value at a future time according to the comprehensive latent state.

6. The ship engine control method based on oil mist monitoring according to claim 5, It is characterized in that The S507 is specifically: According to the following formula, the third forward hidden state is fused with the third backward hidden state to obtain the comprehensive hidden state: in, H t represents the comprehensive hidden state, Sigmoid ( ) represents the Sigmoid activation function, W f represents the forward weight matrix, W b represents the backward weight matrix, represents the third forward hidden state, Represents the third backward hidden state.

7. The ship engine control method based on oil mist monitoring according to claim 6, It is characterized in that The S508 is specifically as follows: According to the following formula, the predicted value of oil mist concentration at the future time is predicted: in, C y represents the predicted value of oil mist concentration at the future moment, Sigmoid ( ) represents the Sigmoid activation function, W h represents the weight matrix between the hidden layer and the classification layer, b h Represents the classification layer bias term.

8. The ship engine control method based on oil mist monitoring according to claim 1, It is characterized in that The operating power reduced by the second amplitude is greater than the operating power reduced by the first amplitude.

9. A ship engine control system based on oil mist monitoring, It is characterized in that include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the ship engine control method based on oil mist monitoring as claimed in any one of claims 1 to 8 is implemented.