A ship engine control method and system based on fault detection

Abstract

The present invention provides a ship engine control method and system based on fault detection, which relates to the field of mechanical control technology. The method includes: collecting normal operation data of the ship engine; constructing a support vector data description model; collecting real-time operation data of the ship engine and the expected travel speed and actual travel speed of the ship under the real-time operation data; when the actual travel speed is less than the expected travel speed, judging whether there is abnormal operation data in the real-time operation data; when there is abnormal operation data, outputting the abnormal operation data and performing maintenance, otherwise, constructing a dynamic model about the ship travel speed; combining an extended state observer to estimate the real-time unknown disturbance of the ship, and outputting the control input of the dynamic model by minimizing the travel speed difference between the expected travel speed and the actual travel speed as the goal, so as to control the ship engine. The safety and reliability of ship engine control are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical control, and in particular to a ship engine control method and system based on fault detection. Background Art

[0002] Marine engine control refers to the use of electronic systems to regulate and optimize the operation of a ship's engine to ensure it can work efficiently and safely. This includes automatically adjusting fuel injection, engine speed control, etc. to suit different sailing needs and environments. This control system monitors various parameters of the engine through sensors, then analyzes this data and automatically makes adjustments or reminds operators to take necessary measures.

[0003] By controlling the ship's engines to improve fuel efficiency and environmental performance while ensuring reliable operation of the engines in all sea conditions, the control system helps avoid sudden failures and reduce unplanned downtime through preventive maintenance, thereby saving operating costs and protecting the environment. In addition, this system enhances the safety of the ship and reduces the risk of serious accidents by real-time monitoring of key parameters and timely response to possible problems.

[0004] However, when the actual output fails to reach the expected output, the existing engine control technology assumes that the external disturbance of the system is too large, without considering the problems caused by engine failure, and directly performs disturbance control compensation in a continuous cycle. In this case, it is very easy to cause irreversible damage to the engine and lead to safety accidents. In addition, the existing disturbance control compensation method often assumes that the engine system is a linear system, and often adds fixed disturbance compensation when performing disturbance compensation. It cannot cope with complex marine operating conditions and is not conducive to the safe operation of ships. Summary of the invention

[0005] In order to solve the technical problem that the existing engine control technology in the prior art assumes that the external disturbance of the system is too large when the actual output fails to reach the expected output, does not consider the problem caused by the engine failure, and directly performs disturbance control compensation in a continuous cycle, which can easily cause irreversible damage to the engine and lead to safety accidents, and in addition, the existing disturbance control compensation method often assumes that the engine system is a linear system by default, and often adds fixed disturbance compensation when performing disturbance compensation, which cannot cope with complex marine operating conditions and is not conducive to the safe operation of the ship, the present invention provides a ship engine control method and system based on fault detection.

[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 fault detection, comprising:

[0009] S1: Collect normal operation data of key components of ship engines under different working conditions;

[0010] S2: Construct a support vector data description model using the minimum prolate sphere to describe normal operation data;

[0011] S3: Collecting real-time operating data of the ship engine and the expected speed and actual speed of the ship under the real-time operating data;

[0012] S4: When the actual travel speed is less than the expected travel speed, determine whether there is abnormal operation data in the real-time operation data by using the support vector data description model;

[0013] S5: if there is abnormal operation data, output the abnormal operation data and enter S8; otherwise, enter S6;

[0014] S6: constructing a dynamic model about the ship's travel speed, wherein the control input of the dynamic model is the engine speed and the fuel flow rate;

[0015] S7: combining the extended state observer to estimate the real-time unknown disturbance of the ship, with the goal of minimizing the speed difference between the expected speed and the actual speed, outputting the control input of the dynamic model to control the ship engine;

[0016] S8: Repair key components corresponding to abnormal operating data.

[0017] Second aspect

[0018] An embodiment of the present invention provides a ship engine control system based on fault detection, comprising:

[0019] processor;

[0020] A memory having computer-readable instructions stored therein, wherein when the computer-readable instructions are executed by the processor, the ship engine control method based on fault detection as in the first aspect is implemented.

[0021] The third aspect

[0022] 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 fault detection as described in the first aspect is implemented.

[0023] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0024] In the present invention, the normal operating data of the ship engine which is relatively easy to obtain is used to construct a support vector data description model which uses the minimum prolate sphere to describe the normal operating data. The elliptical boundary is used to better adapt to the actual distribution of the data in the multidimensional space. Especially when the scales and importance of different features are quite different, by adjusting the ratio of the major axis to the minor axis, the prolate sphere can more effectively cover the main variation direction, reduce the misjudgment of normal data, and thus improve the accuracy and efficiency of the system in identifying abnormalities. The normal operating boundary of the engine is established more accurately, and then the abnormal operating data which is difficult to collect is reversely divided, thereby increasing the identifiable range of engine fault monitoring and improving the accuracy of fault identification. The system can improve the safety and reliability of the ship and perform fault detection before controlling the engine. Only after eliminating the engine fault will the dynamic model of the ship's travel speed be called. The terminal operating state of the ship is taken as the control target, and the travel speed difference is minimized. The factors that are difficult to model and ignore are estimated through the extended state observer to estimate the dynamic real-time unknown disturbance of the ship under various complex sea conditions, and then output the control input of the dynamic model under the real-time unknown disturbance. When eliminating non-engine faults, internal and external disturbances are compensated to avoid direct disturbance compensation to damage the engine. The control process is simplified, the complexity of engine control is greatly reduced, the rapid response capability of the ship system is improved, and navigation safety is ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] 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.

[0026] Figure 1 A schematic flow chart of a ship engine control method based on fault detection provided by an embodiment of the present invention;

[0027] Figure 2 A schematic structural diagram of a ship engine control system based on fault detection provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Reference Manual Attached Figure 1 , showing a flow chart of a ship engine control method based on fault detection provided by an embodiment of the present invention.

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

[0035] S1: Collect normal operation data of key components of ship engines under different working conditions.

[0036] It should be noted that collecting normal operating data of key components of ship engines under different working conditions is the basis for ensuring the effectiveness of the engine monitoring system. By recording engine data under various working conditions, a comprehensive normal performance baseline is established to determine whether the operating data is abnormal, ensuring that the engine maintains optimal performance and safe operation under changing marine conditions.

[0037] In a possible implementation, the key components include a turbine, a piston, a crankshaft and a combustion chamber. The operating conditions include full load conditions and idle conditions. Normal operating data include turbine normal operating data, piston normal operating data, crankshaft normal operating data, and combustion chamber normal operating data. Turbine normal operating data include turbine speed, turbine outlet temperature, turbine inlet temperature, turbine outlet pressure, turbine inlet pressure, and turbine bearing temperature. Piston normal operating data include piston stroke distance, piston temperature, and piston clearance. Crankshaft normal operating data include crankshaft speed, crankshaft torque, crankshaft position, and crankshaft vibration. Combustion chamber normal operating data include combustion chamber pressure and combustion chamber temperature.

[0038] It should be noted that the system records in detail the normal operating data of key components of ship engines under different working conditions to ensure an accurate monitoring and analysis basis for the performance of each component.

[0039] S2: Construct a support vector data description model that uses the minimum prolate sphere to describe normal operation data.

[0040] Among them, the minimum prolate sphere is the ellipsoid with the smallest volume that can surround all these points in the data point distribution. It is different from a completely symmetrical sphere. Its shape is more like a flat or extended ellipse, which makes it better adapt to the actual distribution of data in multidimensional space, especially those distributions with significant feature differences. It can more accurately capture the normal state mode of the data and reduce the possibility of misjudging normal data as abnormal. The minimum prolate sphere is the normal operating boundary of the engine. The data outside the minimum prolate sphere are the abnormal operating data that are difficult to collect. It greatly expands the recognition efficiency and accuracy of abnormal conditions. The establishment of the support vector data description model effectively monitors whether the various parameters of the key components of the ship engine meet the normal value range under various working conditions, so as to effectively monitor the ship engine. The support vector data description model is a method based on the principle of support vector machine for anomaly detection. By finding a minimum three-dimensional body to surround all training data points, a description of the normal state of the data is formed. The working principle is that during the training process, the model tries to find a center point and radius so that the minimum prolate sphere can contain as many data points as possible, and at the same time, a certain penalty is given to points that do not belong to this sphere or ellipsoid (i.e., abnormal points). This way, the model can distinguish which data points are normal and which are abnormal.

[0041] By using the Minimum Volume Ellipsoid (MVE) and Support Vector Data Description (SVDD) models to process and analyze normal operation data collected from key components of ship engines, the boundaries of normal operation are defined, allowing the system to identify abnormal behaviors that deviate from these boundaries.

[0042] In a possible implementation, S2 specifically includes:

[0043] S201: Standardize normal operation data.

[0044] S202: Introduce the Lagrangian function to establish the minimum long sphere solution function:

[0045]

[0046] in, Represents taking the function The center of the prolate sphere at the minimum and the prolate spheroid covariance matrix A , Indicates that the i Data points That is, the relaxation variable of the degree to which the normal operating data after standardization deviates from the prolate spheroid, Represents the covariance matrix A The determinant of C represents the penalty coefficient, n Represents the total number of data points, Represents about the center of the prolate sphere , the prolate spheroid covariance matrix A , slack variables ,constraint The first Lagrange multiplier of ,constraint The second Lagrange multiplier The Lagrangian function of Represents taking the function The first Lagrange multiplier at maximum, Represents data points The inner product of represents the double summation, that is, i Data points With j Data points The inner product between .

[0047] Among them, the prolate spheroid center and the prolate spheroid covariance matrix describe the specific structure of the minimum prolate spheroid.

[0048] S203: Input the normal operation data after standardization as training data into the support vector data description model for training, and obtain the minimum prolate spheroid according to the minimum prolate spheroid determination function.

[0049] It should be noted that by standardizing the normal operation data and using the Lagrangian function to construct the minimum prolate sphere solution function, the multidimensional data distribution of the normal operation status of the ship engine can be effectively captured and described, and the normal parameter range of the engine operation can be accurately defined. Based on this, a fine-tuned anomaly detection model is established through the support vector data description model. The minimum prolate sphere method better adapts to the actual distribution of data by optimizing the covariance matrix and the center point, thereby reducing false positives and false negatives and improving the accuracy and reliability of fault diagnosis. In addition, the optimization problem is solved by the Lagrangian multiplier method, which ensures the mathematical rigor of the model and the efficiency of the solution, making the engine monitoring system more robust and effective in practical applications.

[0050] S3: Collect the real-time operating data of the ship engine and the expected speed and actual speed of the ship under the real-time operating data.

[0051] The expected speed refers to the speed that the ship should reach calculated by the ship control system under real-time operating data, while the actual speed refers to the speed actually reached under real-time operating data. By comparing the expected and actual speeds, the engine's operating efficiency and the overall ship's navigation efficiency can be evaluated. If the actual speed is found to be continuously lower than the expected speed, it may indicate mechanical problems, adverse sea conditions, insufficient power output, or excessive external disturbances, and further judgments can be made.

[0052] S4: When the actual travel speed is lower than the expected travel speed, it is determined whether there is abnormal operation data in the real-time operation data by using the support vector data description model.

[0053] It should be noted that when the actual speed of the ship is lower than the expected speed set by the control system, the support vector data description model is used to analyze the real-time operating data to determine whether there is abnormal operating data, quickly identify performance deviations or failures of the engine or other key systems, and take timely measures to adjust or repair them, thereby ensuring the safety and efficiency of the ship's operation. In this way, the system can detect potential mechanical problems, adverse sea conditions or insufficient power output in advance, ensuring that the ship can operate according to expected performance in various environments.

[0054] In a possible implementation, S4 specifically includes:

[0055] S401: Inputting data points represented by real-time operation data into a support vector data description model.

[0056] S402: Calculate the interval distance between the data point represented by the real-time running data and the center of the prolate sphere of the minimum prolate sphere:

[0057]

[0058] in, Represents a data point in real-time running data With the center of the prolate spheroid The distance between Represents the inverse of the covariance matrix of the minimum prolate spheroid. The subscript T indicates the transpose.

[0059] S403: When the interval distance is greater than 1, the data point represented by the real-time operation data is output as abnormal operation data; otherwise, the data point represented by the real-time operation data is marked as normal operation data.

[0060] It should be noted that the process first inputs the real-time operating data into the support vector data description model, and then calculates the distance between the data point and the center of the minimum long sphere. In this way, the degree of deviation of each data point from the normal operating mode can be accurately quantified. If the interval distance is greater than 1, this indicates that the data point deviates significantly from the normal range, so it is marked as abnormal and further processed. The advantage of this method is that it provides a mathematically rigorous way to evaluate the operating status, enhances the accuracy and response speed of fault detection, and helps to take maintenance or adjustment measures in time to avoid potential mechanical failures or more serious consequences.

[0061] S5: When there is abnormal operation data, the abnormal operation data is output and the process goes to S8; otherwise, the process goes to S6.

[0062] It should be noted that the operating parameters of each key component collected by the sensor, when the operating parameters of the key component exceed the minimum long sphere, proves that the key component has an abnormality. At this time, the control link is directly skipped, and the faulty engine component is accurately located for maintenance. If there is no abnormality, it proves that the existence of disturbance factors has caused the engine output power loss, and then the ship's speed is insufficient. At this time, the control law is introduced to control the engine and compensate for the disturbance item to achieve the desired speed, thereby avoiding dangerous engine control when the key component is abnormal, which may lead to serious consequences.

[0063] S6: Construct a dynamic model of the ship's travel speed.

[0064] The control inputs of the dynamic model are engine speed and fuel flow rate.

[0065] It should be noted that a dynamic model involving the ship's speed was constructed. The model is specifically used to simulate and predict changes in the ship's speed and how these changes are affected by control inputs such as engine speed and fuel flow rate. Through this model, the engine output can be accurately adjusted to optimize the ship's navigation efficiency and performance. The adjustment of control inputs is based on the analysis of the model to ensure that the ship can achieve the optimal speed under various sea conditions and operating conditions.

[0066] In a possible implementation, the kinetic model is specifically:

[0067]

[0068] in, express t The rate of change of ship speed at the moment, p represents the proportionality coefficient, Indicates the ship speed V The engine speed is n oft Thrust output at all times, Indicates the ship speed V The resistance at time t, M Indicates the quality of the ship. express t The engine speed change rate at the moment, Indicates the engine speed is n、 The fuel flow rate is f of t Engine torque at the moment, express t The fuel flow rate at the moment, express t Engine speed at the moment, Indicates the ship speed V , engine speed is n of t The thruster load torque at the moment, J represents the moment of inertia of the engine shaft system, Represents pi.

[0069] It should be noted that the dynamic model simulates the changes in the ship's speed in detail by comprehensively considering key variables such as engine speed, fuel flow rate and ship speed. The advantage of the model is that it can accurately predict the performance of the ship under different engine speeds and fuel input conditions, thereby helping operators to adjust the control strategy in real time to achieve optimal fuel efficiency and speed performance. In addition, the model provides a direct calculation basis for the ship's propulsion efficiency by analyzing the relationship between the thruster load torque and the engine output torque, which helps to minimize energy consumption and operating costs while maintaining the stability and efficiency of the ship's operation. Therefore, this dynamic model not only improves the economy of ship operation, but also enhances the control and prediction capabilities of ship behavior under complex sea conditions.

[0070] S7: Combined with the extended state observer, the real-time unknown disturbance of the ship is estimated, and the speed difference between the expected speed and the actual speed is minimized, and the control input of the dynamic model is output to control the ship engine.

[0071] Among them, the extended state observer is used to estimate the internal state and external disturbance of the system in real time. By observing the system output and control input, the state variables and unknown disturbances that are not directly measurable are inferred, thereby providing more comprehensive system dynamic information. Real-time unknown disturbances refer to factors that affect system performance but have not been modeled or measured in advance, such as sudden environmental changes, equipment wear or operating errors, etc. These disturbances are difficult to predict and compensate in traditional control systems. Control input refers to external signals applied to the system to achieve the control target, such as engine speed and fuel flow rate in ship engine control. The extended state observer is used to estimate the real-time unknown disturbances of the ship, and the control input (engine speed and fuel flow rate) is adjusted through the dynamic model to minimize the difference between the expected travel speed and the actual travel speed. This method allows the ship engine to maintain optimal performance under various unknown disturbances, ensuring that the ship can sail safely and efficiently at the predetermined speed. By accurately controlling the engine parameters, not only the fuel efficiency is improved, but also the adaptability to adverse sea conditions or mechanical failures is enhanced.

[0072] In a possible implementation, S7 specifically includes:

[0073] S701: Introduce unknown disturbance terms and establish performance indicators between expected travel speed and actual travel speed:

[0074]

[0075] in, G Represents performance indicators, express t Always expect the speed of travel, express t The actual speed at any moment, express t The derivative of the actual speed at that moment, represents the integral symbol, represents the differential symbol, express t The unknown disturbance term at time, u Indicates control input.

[0076] S702: Establish an extended state observer to estimate real-time unknown disturbances.

[0077] In a possible implementation, the extended state observer is specifically:

[0078]

[0079] in, Indicates system status pertaining to fuel flow rate or engine speed, represents the derivative of the system state, represents the system matrix describing the dependencies between system states, represents the control input matrix describing the effect of control input on the system state, represents the disturbance matrix describing the influence of unknown disturbance on the system state, represents the real-time system state estimation, represents the derivative of the real-time system state estimate, represents the real-time unknown disturbance estimation, represents the derivative of the real-time unknown disturbance estimate, y represents the system output, i.e. the ship's speed. represents the output matrix describing how the system state affects the system output, represents the system state observer gain, represents the disturbance observer gain.

[0080] It should be noted that the design of the extended state observer allows real-time estimation and adjustment of system states caused by fuel flow rate or engine speed, as well as unknown disturbances caused by external and internal factors. The advantage of this observer is that it can provide a comprehensive dynamic view of system states and disturbances, allowing the control system to respond based on complete information. In addition, by accurately modeling the complex relationship between control inputs and system outputs, it helps optimize operational decisions, improves the adaptability and robustness of the system, and ensures that the optimal speed and overall performance of the ship can be maintained under various operating conditions, significantly improving the safety and efficiency of ship operations and reducing potential problems and risks caused by unforeseen disturbances.

[0081] S703: Under real-time unknown disturbance, with the goal of minimizing the speed difference between the desired speed and the actual speed, output the control input when the performance index is minimized.

[0082] It should be noted that by introducing unknown disturbance terms and using extended state observers to accurately estimate the disturbances existing in the ship, the ship control system can take into account external and internal unpredictable factors and more accurately adjust the control strategy to adapt to the actual sea conditions. By minimizing the difference between the expected speed and the actual speed, the system can optimize the ship's travel efficiency and fuel consumption, reduce energy waste, and improve navigation economy. In addition, when the system adjusts the control input to respond to unknown disturbances, it can ensure the stability and safety of the ship's operation, avoid potential risks caused by disturbances, and ensure the reliable operation of the ship under various conditions.

[0083] S8: Repair key components corresponding to abnormal operating data.

[0084] It should be noted that once the system identifies that the operating data of a component shows abnormal behavior, specific maintenance or replacement of the component will be carried out to ensure the normal operation of the engine and the ship and prevent further damage or failure. This step is a key component of preventive maintenance and helps to extend the service life of the ship's engine and improve its reliability.

[0085] In a possible implementation, it further includes:

[0086] The support vector data description model is updated at preset intervals.

[0087] It can be understood that regularly updating the support vector data description model can adapt to the performance changes or new operating conditions that may occur over time in the ship engine, thereby ensuring that the model always maintains a high degree of accuracy and relevance. This strategy ensures that the fault detection system can continuously and effectively monitor and identify abnormal behavior, thereby improving maintenance efficiency and reducing potential operational risks.

[0088] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0089] In the present invention, the normal operating data of the ship engine which is relatively easy to obtain is used to construct a support vector data description model which uses the minimum prolate sphere to describe the normal operating data. The elliptical boundary is used to better adapt to the actual distribution of the data in the multidimensional space. Especially when the scales and importance of different features are quite different, by adjusting the ratio of the major axis to the minor axis, the prolate sphere can more effectively cover the main variation direction, reduce the misjudgment of normal data, and thus improve the accuracy and efficiency of the system in identifying abnormalities. The normal operating boundary of the engine is established more accurately, and then the abnormal operating data which is difficult to collect is reversely divided, thereby increasing the identifiable range of engine fault monitoring and improving the accuracy of fault identification. The system can improve the safety and reliability of the ship and perform fault detection before controlling the engine. Only after eliminating the engine fault will the dynamic model of the ship's travel speed be called. The terminal operating state of the ship is taken as the control target, and the travel speed difference is minimized. The factors that are difficult to model and ignore are estimated through the extended state observer to estimate the dynamic real-time unknown disturbance of the ship under various complex sea conditions, and then output the control input of the dynamic model under the real-time unknown disturbance. When eliminating non-engine faults, internal and external disturbances are compensated to avoid direct disturbance compensation to damage the engine. The control process is simplified, the complexity of engine control is greatly reduced, the rapid response capability of the ship system is improved, and navigation safety is ensured.

[0090] Reference Manual Attached Figure 2 , showing a structural schematic diagram of a ship engine control system based on fault detection provided by the present invention.

[0091] The present invention further provides a ship engine control system 20 based on fault detection, which is applied to the above-mentioned ship engine control method based on fault detection, comprising:

[0092] Processor 201.

[0093] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, the ship engine control method based on fault detection as in the method embodiment is implemented.

[0094] The ship engine control system 20 based on fault detection provided by the present invention can execute the above-mentioned ship engine control method based on fault detection and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0095] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0096] In the present invention, the normal operating data of the ship engine which is relatively easy to obtain is used to construct a support vector data description model which uses the minimum prolate sphere to describe the normal operating data. The elliptical boundary is used to better adapt to the actual distribution of the data in the multidimensional space. Especially when the scales and importance of different features are quite different, by adjusting the ratio of the major axis to the minor axis, the prolate sphere can more effectively cover the main variation direction, reduce the misjudgment of normal data, and thus improve the accuracy and efficiency of the system in identifying abnormalities. The normal operating boundary of the engine is established more accurately, and then the abnormal operating data which is difficult to collect is reversely divided, thereby increasing the identifiable range of engine fault monitoring and improving the accuracy of fault identification. The system can improve the safety and reliability of the ship and perform fault detection before controlling the engine. Only after eliminating the engine fault will the dynamic model of the ship's travel speed be called. The terminal operating state of the ship is taken as the control target, and the travel speed difference is minimized. The factors that are difficult to model and ignore are estimated through the extended state observer to estimate the dynamic real-time unknown disturbance of the ship under various complex sea conditions, and then output the control input of the dynamic model under the real-time unknown disturbance. When eliminating non-engine faults, internal and external disturbances are compensated to avoid direct disturbance compensation to damage the engine. The control process is simplified, the complexity of engine control is greatly reduced, the rapid response capability of the ship system is improved, and navigation safety is ensured.

[0097] 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.

[0098] 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).

[0099] 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 a computer instruction or computer program is loaded or executed on a computer, a process or function according to an 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. 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, 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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 units is only a logical function division, and 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.

[0106] 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.

[0107] 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.

[0108] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it 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 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 of 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, etc., various media that can store program codes.

[0109] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements a ship engine control method based on fault detection as in a method embodiment.

[0110] A computer-readable storage medium provided by the present invention can implement the steps and effects of the ship engine control method based on fault detection in the above method embodiment. To avoid repetition, the present invention will not go into details.

[0111] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0112] In the present invention, the normal operating data of the ship engine which is relatively easy to obtain is used to construct a support vector data description model which uses the minimum prolate sphere to describe the normal operating data. The elliptical boundary is used to better adapt to the actual distribution of the data in the multidimensional space. Especially when the scales and importance of different features are quite different, by adjusting the ratio of the major axis to the minor axis, the prolate sphere can more effectively cover the main variation direction, reduce the misjudgment of normal data, and thus improve the accuracy and efficiency of the system in identifying abnormalities. The normal operating boundary of the engine is established more accurately, and then the abnormal operating data which is difficult to collect is reversely divided, thereby increasing the identifiable range of engine fault monitoring and improving the accuracy of fault identification. The system can improve the safety and reliability of the ship and perform fault detection before controlling the engine. Only after eliminating the engine fault will the dynamic model of the ship's travel speed be called. The terminal operating state of the ship is taken as the control target, and the travel speed difference is minimized. The factors that are difficult to model and ignore are estimated through the extended state observer to estimate the dynamic real-time unknown disturbance of the ship under various complex sea conditions, and then output the control input of the dynamic model under the real-time unknown disturbance. When eliminating non-engine faults, internal and external disturbances are compensated to avoid direct disturbance compensation to damage the engine. The control process is simplified, the complexity of engine control is greatly reduced, the rapid response capability of the ship system is improved, and navigation safety is ensured.

[0113] 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.

[0114] There are a few points to note:

[0115] (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.

[0116] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of layers or regions 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 layer, film, region or 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.

[0117] (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.

[0118] 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 fault detection, characterized in that: include: S1: Collecting normal operation data of key components of the ship engine under different working conditions; S2: constructing a support vector data description model using a minimum prolate sphere to describe the normal operating data; S3: collecting real-time operating data of the ship engine and the expected speed and actual speed of the ship under the real-time operating data; S4: when the actual travel speed is less than the expected travel speed, judging whether there is abnormal operation data in the real-time operation data by using the support vector data description model; S5: if the abnormal operation data exists, output the abnormal operation data and proceed to S8; otherwise, proceed to S6; S6: constructing a dynamic model for the ship's travel speed, wherein the control inputs of the dynamic model are the engine speed and the fuel flow rate; S7: estimating the real-time unknown disturbance of the ship in combination with the extended state observer, with the goal of minimizing the speed difference between the desired speed and the actual speed, outputting the control input of the dynamic model to control the ship engine; S8: Controlling the ship engine to reduce operating power or shut down, so as to inspect and repair key components corresponding to the abnormal operating data; The minimum prolate spheroid is an ellipsoid of the minimum volume including all normal operating data, wherein the minimum prolate spheroid is used to describe the normal operating boundary of the ship engine.

2. The ship engine control method based on fault detection according to claim 1, characterized in that: The key components include a turbine, a piston, a crankshaft and a combustion chamber; the operating conditions include a full load condition and an idle condition; the normal operating data include normal operating data of the turbine, normal operating data of the piston, normal operating data of the crankshaft, and normal operating data of the combustion chamber; the normal operating data of the turbine include turbine speed, turbine outlet temperature, turbine inlet temperature, turbine outlet pressure, turbine inlet pressure, and turbine bearing temperature; the normal operating data of the piston include piston stroke distance, piston temperature, and piston clearance; the normal operating data of the crankshaft include crankshaft speed, crankshaft torque, crankshaft position, and crankshaft vibration; the normal operating data of the combustion chamber include combustion chamber pressure and combustion chamber temperature.

3. The ship engine control method based on fault detection according to claim 1, characterized in that: The S2 specifically includes: S201: Standardizing the normal operating data; S202: Introduce the Lagrangian function to establish the minimum long sphere solution function: in, Represents taking the function The center of the prolate sphere at the minimum and the prolate spheroid covariance matrix A , Indicates that the i Data points That is, the relaxation variable of the degree to which the normal operating data after standardization deviates from the prolate spheroid, Represents the covariance matrix A The determinant of C represents the penalty coefficient, n Represents the total number of data points, Represents about the center of the prolate sphere , the prolate spheroid covariance matrix A , slack variables ,constraint The first Lagrange multiplier of ,constraint The second Lagrange multiplier The Lagrangian function of Represents taking the function The first Lagrange multiplier at maximum, Represents data points The inner product of represents the double summation, that is, i Data points With j Data points The inner product between S203: Inputting the normal operating data after standardization as training data into the support vector data description model for training, and obtaining the minimum prolate spheroid according to the minimum prolate spheroid determination function.

4. The ship engine control method based on fault detection according to claim 1, characterized in that: The S4 specifically includes: S401: inputting data points represented by the real-time operation data into the support vector data description model; S402: Calculate the interval distance between the data point represented by the real-time operation data and the center of the prolate sphere of the minimum prolate sphere: in, Represents a data point in the real-time operating data With the center of the prolate spheroid The distance between represents the inverse matrix of the covariance matrix of the minimum prolate spheroid, and the subscript T represents the transpose; S403: When the interval distance is greater than 1, the data point represented by the real-time operation data is output as abnormal operation data; otherwise, the data point represented by the real-time operation data is marked as normal operation data.

5. The ship engine control method based on fault detection according to claim 1, characterized in that: The kinetic model is specifically: in, express t The rate of change of ship speed at the moment, p represents the proportionality coefficient, Indicates the ship speed V The engine speed is n of t Thrust output at all times, Indicates the ship speed V The resistance at time t, M Indicates the quality of the ship. express t The engine speed change rate at the moment, Indicates the engine speed is n、 The fuel flow rate is f of t Engine torque at the moment, express t The fuel flow rate at the moment, express t Engine speed at the moment, Indicates the ship speed V , engine speed is n of t The thruster load torque at the moment, J represents the moment of inertia of the engine shaft system, Represents pi.

6. The ship engine control method based on fault detection according to claim 1, characterized in that: The S7 specifically includes: S701: Introduce an unknown disturbance term to establish a performance index between the expected travel speed and the actual travel speed: in, G represents the performance index, express t Always expect the speed of travel, express t The actual speed at any moment, express t The derivative of the actual speed at that moment, represents the integral symbol, represents the differential symbol, express t The unknown disturbance term at time, u represents the control input; S702: Establishing an extended state observer to estimate real-time unknown disturbances; S703: Under the real-time unknown disturbance, with the goal of minimizing the speed difference between the desired speed and the actual speed, output a control input when the performance index is minimized.

7. The ship engine control method based on fault detection according to claim 6, characterized in that: The extended state observer is specifically: in, Indicates system status pertaining to fuel flow rate or engine speed, represents the derivative of the system state, represents the system matrix describing the dependencies between system states, represents the control input matrix describing the effect of control input on the system state, represents the disturbance matrix describing the influence of unknown disturbance on the system state, represents the real-time system state estimation, represents the derivative of the real-time system state estimate, represents the real-time unknown disturbance estimation, represents the derivative of the real-time unknown disturbance estimate, y represents the system output, i.e. the ship's speed. represents the output matrix describing how the system state affects the system output, represents the system state observer gain, represents the disturbance observer gain.

8. The ship engine control method based on fault detection according to claim 1, characterized in that: Also includes: The support vector data description model is updated at preset time intervals.

9. A ship engine control system based on fault detection, 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 fault detection as claimed in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a ship engine control method based on fault detection as claimed in any one of claims 1 to 8 is implemented.

Images