A method and system for predicting the service life of a marine diesel engine piston ring

Abstract

The application discloses a kind of ship diesel engine piston ring life prediction method and system, it is related to ship diesel engine technical field, including the following steps: obtaining the historical power time sequence of ship diesel engine from start running to current date, and input the historical power time sequence to the degradation model of piston ring, obtain the current wear of piston ring on ship diesel engine;Difference is obtained between the set maximum wear of piston ring on ship diesel engine and current wear, to obtain future maximum wear;After the route and the season where the ship is located are encoded, input into the pre-trained power prediction model, to obtain future power time sequence;The remaining life of piston ring on ship diesel engine is solved based on future time sequence power and future maximum wear.The application considers the actual operating condition of diesel engine, improves the piston ring life prediction accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of marine diesel engines, in particular to a marine diesel engine piston ring life prediction method and system. BACKGROUND

[0002] The marine diesel engine piston ring is a core component that ensures the efficient operation of the diesel engine. When the marine diesel engine is running, the piston ring is in a complex environment of high temperature, high pressure, high corrosion and strong vibration, and it has to bear alternating loads for a long time. Therefore, the life of the piston ring needs to be predicted to determine whether it needs to be replaced.

[0003] Directly monitoring the real-time wear state of the piston ring (such as thickness change or surface damage, etc.) requires installing high-precision sensors inside the cylinder, which is technically difficult, costly, and the sensors are easily disturbed by harsh environments (such as signal distortion caused by oil stains and high temperature). At the same time, the life of the piston ring is affected by many factors such as fuel quality, lubrication conditions, combustion products (such as sulfides) and load fluctuations.

[0004] In engineering practice, the fixed life method is often used to determine the life of the marine diesel engine piston ring. This method simplifies the complex factors into a linear relationship of "time-life" by statistical data and experience, which deviates greatly from the actual situation, resulting in a great reduction in the accuracy of the final piston ring life prediction. SUMMARY

[0005] Based on the defects of the prior art, the present application provides a marine diesel engine piston ring life prediction method and system, which solves the problem of low accuracy in predicting the life of the marine diesel engine piston ring using the fixed life method.

[0006] The present application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a marine diesel engine piston ring life prediction method, comprising the following steps:

[0008] Obtain the historical power time sequence of the marine diesel engine from the start of operation to the current date, and input the historical power time sequence into the degradation model of the piston ring to obtain the current wear of the piston ring on the marine diesel engine; wherein the degradation model is constructed by the wear coefficient of the marine diesel engine, the time-varying power and the hardness of the piston ring;

[0009] Subtract the set maximum wear of the piston ring on the marine diesel engine from the current wear to obtain the future maximum wear;

[0010] Encode the route and season of the ship and input it into the pre-trained power prediction model to obtain the future power time sequence;

[0011] The remaining life of a piston ring on a marine diesel engine is solved based on future timing power and future maximum wear.

[0012] Preferably, the degradation model is specifically as follows:

[0013] ;

[0014] In the formula, is the wear of the piston ring from 0 to time t , is the wear coefficient, is the hardness of the piston ring, is the time-varying power, is the time variable.

[0015] Preferably, different wear coefficients are used for different types of diesel engines.

[0016] Preferably, the power prediction model is an LSTM model, and the pre-training of the LSTM model includes the following steps:

[0017] Extract power timing data under different routes and seasons from the historical operation database of the ship;

[0018] Encode different routes and seasons to obtain corresponding route features and seasonal features; train the LSTM model with different route features and seasonal features as input and corresponding power timing data as output to obtain a pre-trained power prediction model; the power prediction model is specifically as follows:

[0019] P = f ( R , S );

[0020] In the formula, R represents the route feature, S represents the seasonal feature, P is the power.

[0021] Preferably, the remaining life of the piston ring on the marine diesel engine is solved by a life solving formula, and the life solving formula is specifically as follows:

[0022] ;

[0023] In the formula, RUL is the remaining life, is the future power timing, is the future maximum wear, is the current date.

[0024] In a second aspect, the present application provides a ship diesel engine piston ring life prediction system, comprising:

[0025] an acquisition module configured to acquire a historical power time sequence of the ship diesel engine from the start of operation to the current date, and input the historical power time sequence into a degradation model of the piston ring to obtain a current wear amount of the piston ring on the ship diesel engine; wherein the degradation model is constructed by using a wear coefficient of the ship diesel engine, a time-varying power and a piston ring hardness;

[0026] a difference module configured to subtract the set maximum wear amount of the piston ring on the ship diesel engine from the current wear amount to obtain a future maximum wear amount;

[0027] a prediction module configured to input a route and a season where the ship is located after coding into a pre-trained power prediction model to obtain a future power time sequence;

[0028] a calculation module configured to solve the remaining life of the piston ring on the ship diesel engine based on the future time sequence power and the future maximum wear amount.

[0029] Compared with the prior art, the above at least one technical scheme of the present application can achieve the following beneficial effects:

[0030] The present application constructs a degradation model by using a wear coefficient of the ship diesel engine, a time-varying power and a piston ring hardness, first inputs a historical power time sequence of the ship diesel engine from the start of operation to the current date into the degradation model of the piston ring to obtain a current wear amount of the piston ring, and subtracts the set maximum wear amount from the current wear amount to obtain a future maximum wear amount. The present application dynamically quantifies the future allowable wear allowance by setting the difference value between the maximum allowable wear amount of the piston ring and the current wear amount. Then, the route and the season where the ship is located after coding are input into a pre-trained power prediction model to obtain a future power time sequence. In different routes and seasons, the operating conditions of the ship diesel engine are different, and the present application considers the influence of the route and the season on the operating conditions of the diesel engine to predict the power closer to the actual operating conditions. Finally, the remaining life of the piston ring is obtained based on the future time sequence power and the future maximum wear amount. The present application considers the actual operating conditions of the diesel engine, and improves the piston ring life prediction accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0032] Figure 1A flow chart of a ship diesel engine piston ring life prediction method. DETAILED DESCRIPTION

[0033] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts fall within the scope of the present application.

[0034] At present, in the ship operation and maintenance practice, the fixed life method is used to determine the life of the ship diesel engine piston ring, and then a fixed period is obtained. The piston ring is replaced according to the fixed period. This replacement mode does not consider the actual operation condition of the ship diesel engine. If the diesel engine is in good load working condition for a long time, the forced replacement of the piston ring according to the fixed period will cause waste of the piston ring and additional maintenance cost, and will also increase the risk of damage to the diesel engine due to improper disassembly and inspection operation; if the diesel engine is in severe or high load working condition for a long time, the forced replacement of the piston ring according to the fixed period will cause the piston ring to fail, resulting in serious diesel engine damage accident.

[0035] Referring to Figure 1 The present application provides a ship diesel engine piston ring life prediction method, comprising the following steps:

[0036] S1: obtaining the historical power time sequence of the ship diesel engine from the start of operation to the current date, and inputting the historical power time sequence into the degradation model of the piston ring to obtain the current wear amount of the piston ring on the ship diesel engine.

[0037] The piston ring wear amount calculation formula is shown in formula (1):

[0038] (1)

[0039] Wherein, is the piston ring wear amount; is the wear coefficient, which is a dimensionless parameter representing the material friction characteristic, and is affected by the lubrication condition, and the basic value is calibrated through a bench test; is the indicated power, which represents the effective power of a single cylinder of the diesel engine in a single cycle, and reflects the mechanical load strength; is the hardness of the piston ring, which is a material inherent property, measured by Rockwell Hardness C Scale (HRC), and the typical value is 50-60HRC.

[0040] For a multi-cylinder diesel engine, the first cylinder indicated power The calculation formula is shown in formula (2):

[0041] (2);

[0042] wherein, is the time-varying power, is the time variable.

[0043] From equation (1) and equation (2), the degradation model of the piston ring can be obtained, as shown in equation (3):

[0044] (3);

[0045] wherein, is the piston ring wear amount from 0 to time t .

[0046] This embodiment takes a two-stroke diesel engine as an example. For a two-stroke diesel engine, the wear coefficient k will be affected by the metal particle content in the fuel, the cylinder oil viscosity, and the oil injection rate. The corrected wear coefficient can be calculated by the following equation (4):

[0047] (4);

[0048] wherein, is the basic wear coefficient under the rated operating condition, is the metal particle concentration in the fuel, is the critical concentration threshold, is the actual viscosity, is the design viscosity, is the actual oil injection rate, is the rated oil injection rate, is the empirical index.

[0049] Calculate the current cumulative wear amount:

[0050] (5);

[0051] wherein, is the current cumulative wear amount, is the current date, is the historical power time sequence.

[0052] The historical power integral is calculated discretely using the trapezoidal method or Simpson's method to obtain the historical power time sequence .

[0053] S2: Subtract the current wear amount from the set maximum wear amount of the piston ring on the marine diesel engine to obtain the future maximum wear amount.

[0054] S3: Encode the route and season of the ship and input it into the pre-trained power prediction model to get the future power time series.

[0055] Data collection: Extract the main engine power time series data under different routes (such as coastal / ocean) and seasons (spring / summer / autumn / winter) from the ship historical operation database. Encode different routes and seasons to get corresponding route features and seasonal features.

[0056] Model structure: Use LSTM neural network, input layer is route feature and seasonal feature, output layer is future power sequence.

[0057] Training process: Use historical power time series and corresponding route and seasonal labels as training set, optimize model parameters by minimizing the mean square error (MSE) of predicted power and actual power.

[0058] Combine route features and seasonal features to establish diesel engine power prediction model, power prediction model is LSTM model, model function is shown in equation (6):

[0059] P = f ( R , S )(6);

[0060] In the formula, R represents route feature, S represents seasonal feature.

[0061] Use LSTM method to predict future power sequence in time period.

[0062] S4: Solve the remaining life of the piston ring on the ship diesel engine based on the future time series power and the future maximum wear.

[0063] Predict the remaining life RUL, the piston ring wear needs to meet the following life solving formula (7):

[0064] (7);

[0065] In the formula, is the maximum wear, is the current date. The solving method uses step-by-step cumulative future power integration until , piston ring failure.

[0066] Or, if the power is approximately constant , P 0 is the average value of predicted power, then:

[0067] (8)。

[0068] Embodiment

[0069] It is known that a certain container ship 2024 operating route is Shanghai-Ningbo-Shenzhen-Shanghai, 10 days a class, its running data is shown in Table 1. The hardness of the piston ring is 50HRC, the wear coefficient is: , the failure threshold is: .

[0070] Table 1 Certain container 2024 running data

[0071]

[0072] It is calculated by formula (5) that the current wear amount is: .

[0073] Suppose the corrected wear coefficient is: , the route is unchanged, and the average power of the main engine from January to March 2025 can be predicted as 6000KW. Then the predicted life of the piston ring is:

[0074] .

[0075] Based on the same concept, the application also provides a ship diesel engine piston ring life prediction system, comprising an acquisition module, a difference module, a prediction module and a calculation module.

[0076] The acquisition module is used to acquire the historical power time sequence of the ship diesel engine from the start of operation to the current date, and input the historical power time sequence into the degradation model of the piston ring to obtain the current wear amount of the piston ring on the ship diesel engine; wherein the degradation model is constructed by the wear coefficient of the ship diesel engine, the time-varying power and the hardness of the piston ring.

[0077] The difference module is used to subtract the set maximum wear amount of the piston ring on the ship diesel engine from the current wear amount to obtain the future maximum wear amount.

[0078] The prediction module is used to input the route and the season of the ship into the pre-trained power prediction model to obtain the future power time sequence.

[0079] The calculation module is used to solve the remaining life of the piston ring on the ship diesel engine based on the future time sequence power and the future maximum wear amount.

[0080] The present application avoids "over-maintenance" or "insufficient maintenance" caused by fixed period replacement by real-time sensing of diesel engine operating conditions (such as load, fuel quality and lubrication state, etc.), and dynamically predicting the remaining life of the piston ring. For example, when the diesel engine is in a low load good working condition for a long time, the replacement period can be extended to reduce unnecessary disassembly and inspection; when the working condition deteriorates, early warning and shortening of the replacement period can prevent sudden failures.

[0081] The piston ring life prediction method considering the operating conditions of the diesel engine can track the wear trend of the piston ring in real time, identify abnormal wear risks (such as rapid wear under high load) in advance, and avoid accidents such as cylinder gas leakage, fuel leakage, and mechanical damage caused by piston ring functional failure. Reducing unnecessary spare parts replacement and downtime improves ship operation efficiency.

[0082] Although preferred embodiments of the present application have been described, those skilled in the art can make further changes and modifications to these embodiments once they know the basic inventive concept. Therefore, the appended claims are intended to be interpreted as including all changes and modifications falling within the scope of the present application.

[0083] Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and changes of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and changes.

Claims

1. A method of predicting the service life of a marine diesel engine piston ring, characterized by, The method comprises the following steps: obtain the historical power time sequence of the marine diesel engine from the start of operation to the current date, and input the historical power time sequence into a degradation model of the piston ring to obtain the current wear of the piston ring on the marine diesel engine; wherein the degradation model is constructed by the wear coefficient of the marine diesel engine, the time-varying power and the hardness of the piston ring; difference the set maximum wear of the piston ring on the marine diesel engine from the current wear to obtain the future maximum wear; input the route and season of the ship into the pre-trained power prediction model after coding to obtain the future power time sequence; solve the remaining life of the piston ring on the marine diesel engine based on the future time sequence power and the future maximum wear; the degradation model is specifically as follows: ； wherein is the piston ring wear amount from 0 to time t is the piston ring wear amount from 0 to time is the wear coefficient, is the piston ring hardness, is the time-varying power, is the time variable; the power prediction model is an LSTM model, and the pre-training of the power prediction model comprises the following steps: extract the power time sequence data under different routes and seasons from the ship historical operation database; encode different routes and seasons to obtain corresponding route features and season features; train the LSTM model by taking different route features and season features as input and corresponding power time sequence data as output to obtain the pre-trained power prediction model; the power prediction model is specifically as follows: P = f （ R , S ）； wherein R represents a route feature, S represents a seasonal feature, P is power; solve the remaining life of the piston ring on the marine diesel engine by the life solving formula, and the life solving formula is specifically as follows: ； wherein RUL is the remaining life, is the future power schedule, is the future maximum wear amount, is the current date.

2. A method of predicting the service life of a marine diesel engine piston ring as claimed in claim 1, characterized in that, different wear coefficients need to be used for different types of diesel engines.

3. A marine diesel engine piston ring life prediction system, characterized by, comprise: an acquisition module, configured to acquire the historical power time sequence of the marine diesel engine from the start of operation to the current date, and input the historical power time sequence into a degradation model of the piston ring to obtain the current wear of the piston ring on the marine diesel engine; wherein the degradation model is constructed by the wear coefficient of the marine diesel engine, the time-varying power and the hardness of the piston ring; a difference module, configured to difference the set maximum wear of the piston ring on the marine diesel engine from the current wear to obtain the future maximum wear; a prediction module, configured to input the route and season of the ship into the pre-trained power prediction model after coding to obtain the future power time sequence; a calculation module, configured to solve the remaining life of the piston ring on the marine diesel engine based on the future time sequence power and the future maximum wear; the degradation model is specifically as follows: ； wherein is the piston ring wear from 0 to time t is the piston ring wear, is the wear coefficient, is the piston ring hardness, is the time varying power, is the time variable; the power prediction model is an LSTM model, and the pre-training of the power prediction model comprises the following steps: extract the power time sequence data under different routes and seasons from the ship historical operation database; encode different routes and seasons to obtain corresponding route features and season features; train the LSTM model by taking different route features and season features as input and corresponding power time sequence data as output to obtain the pre-trained power prediction model; the power prediction model is specifically as follows: P = f （ R , S ）； wherein R represents a route feature, S represents a seasonal feature, P is power; solve the remaining life of the piston ring on the marine diesel engine by the life solving formula, and the life solving formula is specifically as follows: ； wherein RUL is the remaining life, is the future power schedule, is the future maximum wear amount, is the current date.

Images