Lubrication control methods, devices, equipment, storage media and products
By acquiring lubricating oil monitoring data to generate health values and inputting them into a predictive control model, and dynamically matching the oil supply strategy, the problem of lubricating oil performance degradation in ship main gearboxes under extreme operating conditions is solved, and precise lubricating oil supply is achieved.
Patent Information
- Application Number
- CN202610429675.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-02
- Publication Date
- 2026-06-30
AI Technical Summary
Under extreme operating conditions, the performance of lubricating oil in the main gearbox of a ship deteriorates rapidly. Traditional solutions cannot achieve closed-loop adaptive adjustment of the oil supply, leading to lubrication failure.
By acquiring monitoring data of lubricating oil, a lubricating oil health value is generated, and this value is input into a predictive control model to generate an oil supply strategy, dynamically matching the oil supply amount to meet lubrication needs.
It enables forward-looking prediction of lubricant degradation trends and precise matching of oil supply, solving the problem of lubrication failure under complex working conditions.
Smart Images

Figure CN122305217A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of marine power transmission system technology, and in particular to a lubrication control method, device, equipment, storage medium and product. Background Technology
[0002] Marine main gearboxes operate under extreme conditions for extended periods, including impact loads, moisture, and silt contamination. The performance of their lubricating oil deteriorates rapidly due to the combined effects of multiple factors. Traditional solutions involve constructing hybrid intelligent models to assess lubrication and wear conditions and predict trends. However, these models only provide maintenance decision suggestions and cannot achieve closed-loop adaptive adjustment of the oil supply. Other solutions can monitor oil parameters online and perform simple threshold switching control, but their control logic is static and lagging, and they fail to reveal the quantitative mechanism of oil film failure under multi-factor coupling, making it difficult to compensate for lubrication performance degradation in a timely and accurate manner under complex operating conditions.
[0003] Therefore, how to achieve predictive and precise supply of lubricating oil is an urgent problem to be solved. Summary of the Invention
[0004] The main objective of this application is to provide a lubrication control method, apparatus, equipment, storage medium, and product, which aims to solve the technical problem of how to achieve predictive and precise supply of lubricating oil.
[0005] To achieve the above objectives, this application proposes a lubrication control method, which is applied to the lubrication control system of a ship's main gearbox, the method comprising: Obtain monitoring data for lubricating oil; A lubricating oil health value is generated based on the monitoring data; The health values are input into the predictive control model to generate the fuel supply strategy; The main gearbox of the ship is lubricated according to the oil supply strategy.
[0006] In one embodiment, the predictive control model includes a data prediction model and a lubrication model, and the step of inputting the health value into the predictive control model to generate an oil supply strategy includes: The health value is input into the data prediction model to obtain the time-varying trend of the health value; The time-varying trend of the health value is input into the lubrication model to obtain the critical film thickness; Dynamic matching rules are determined based on the health value and the critical film thickness. The fuel supply strategy is generated based on the dynamic matching rules and the predictive control algorithm.
[0007] In one embodiment, the step of generating the fuel supply strategy based on the dynamic matching rules and the predictive control algorithm includes: Obtain the time-varying trend of the health value and the current health value of the lubricating oil; Based on the current health value, the time-varying trend of the health value, and the dynamic matching rules, the optimal control sequence is determined within a preset time domain; The first control variable in the optimal control sequence is taken as the current fuel supply command, and the fuel supply strategy is generated based on the current fuel supply command.
[0008] In one embodiment, the step of inputting the time-varying trend of the health value into the lubrication model to obtain the critical film thickness further includes: Obtain the oil film thickness data of the sample lubricating oil; The lubrication model is calibrated based on the oil film thickness data.
[0009] In one embodiment, the step of generating a lubricating oil health value based on the monitoring data includes: The monitoring data is normalized to obtain normalized monitoring data; According to the preset weight allocation strategy, the normalized monitoring data is weighted and fused. The health value of the lubricating oil is obtained based on the weighted fusion results.
[0010] In one embodiment, the step of acquiring monitoring data of the lubricating oil includes: Collect data on the temperature, viscosity, moisture content, and particulate matter concentration of the lubricating oil; The temperature, viscosity, moisture content, and particulate matter concentration are subjected to outlier removal and time series alignment to obtain monitoring data.
[0011] Furthermore, to achieve the above objectives, this application also proposes a lubrication control device, the device comprising: The data acquisition module is used to acquire monitoring data of the lubricating oil; A health value generation module is used to generate a lubricating oil health value based on the monitoring data; The strategy generation module is used to input the health value into the predictive control model to generate a fuel supply strategy; The lubrication control module is used to supply lubrication to the ship's main gearbox according to the oil supply strategy.
[0012] In addition, to achieve the above objectives, this application also proposes a lubrication control device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the lubrication control method as described above.
[0013] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the lubrication control method described above.
[0014] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the lubrication control method described above.
[0015] This application provides a lubrication control method applied to the lubrication control system of a ship's main gearbox. The method includes: acquiring monitoring data of lubricating oil; generating a lubricating oil health value based on the monitoring data; inputting the health value into a predictive control model to generate an oil supply strategy; and supplying lubrication to the ship's main gearbox according to the oil supply strategy.
[0016] This application first acquires monitoring data of the lubricating oil. Then, it generates a lubricating oil health value based on the monitoring data. This health value is then input into a predictive control model to generate a lubrication supply strategy. Finally, lubrication is supplied to the ship's main gearbox according to the lubrication supply strategy. Compared to existing static threshold control or reactive maintenance methods, this application integrates multi-dimensional monitoring data into a health value and dynamically generates a lubrication supply strategy by combining a data prediction model and a lubrication model. This achieves proactive prediction of lubricating oil degradation trends and precise adaptation of lubrication supply, solving the lubrication failure problem caused by oil performance degradation under complex operating conditions. Attached Figure Description
[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0019] Figure 1 This is a schematic flowchart of the lubrication control method according to Embodiment 1 of this application; Figure 2 This is a schematic flowchart of Embodiment 2 of the lubrication control method of this application; Figure 3 This is a schematic flowchart of Embodiment 3 of the lubrication control method of this application; Figure 4 This is a schematic diagram of the module structure of the lubrication control device according to an embodiment of this application; Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the lubrication control method in the embodiments of this application.
[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.
[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.
[0023] The main solution of this application is as follows: Ship main gearboxes operate under extreme conditions such as impact loads, moisture, and silt contamination for extended periods, causing the lubricating oil performance to deteriorate rapidly due to the coupling effect of multiple factors. Traditional solutions assess lubrication and wear conditions and predict trends by constructing a hybrid intelligent model, but its output only provides maintenance decision suggestions and cannot achieve closed-loop adaptive adjustment of the oil supply. Other solutions can monitor oil parameters online and perform simple threshold switching control, but their control logic is static and lagging, and they do not reveal the quantitative mechanism of oil film failure under multi-factor coupling, making it difficult to compensate for lubrication performance degradation in a timely and accurate manner under complex operating conditions.
[0024] This application first acquires monitoring data of the lubricating oil. Then, it generates a lubricating oil health value based on the monitoring data. This health value is then input into a predictive control model to generate a lubrication supply strategy. Finally, lubrication is supplied to the ship's main gearbox according to the lubrication supply strategy. Compared to existing static threshold control or reactive maintenance methods, this application integrates multi-dimensional monitoring data into a health value and dynamically generates a lubrication supply strategy by combining a data prediction model and a lubrication model. This achieves proactive prediction of lubricating oil degradation trends and precise adaptation of lubrication supply, solving the lubrication failure problem caused by oil performance degradation under complex operating conditions.
[0025] It should be noted that the executing entity in the following embodiments can be a lubrication control device, or a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or a lubrication control device capable of performing the above functions. This embodiment does not specifically limit it in this way. The following uses a lubrication control device (hereinafter referred to as the device) as the executing entity to describe this embodiment and the following embodiments.
[0026] Based on this, this application proposes a lubrication control method according to a first embodiment, please refer to... Figure 1 , Figure 1This is a schematic flowchart of an embodiment of the lubrication control method of this application, wherein the method includes steps S10 to S40: Step S10: Obtain monitoring data of the lubricating oil.
[0027] It should be noted that the aforementioned monitoring data can refer to various measurable parameters reflecting the condition of the lubricating oil. For example, monitoring data may include one or more of the following: lubricating oil temperature, viscosity, moisture content, and particulate matter concentration.
[0028] The aforementioned lubricating oil may refer to the lubricating medium used in the main gearbox of a ship, which is used to form an oil film between the meshing surfaces of the gears to reduce friction and wear.
[0029] In practice, during operation, various physical and chemical parameters of the lubricating oil are actively collected at preset time intervals. Sensors connected to the lubricating oil pipeline or oil pan acquire the current temperature, viscosity, moisture content, and particulate matter concentration of the lubricating oil. These raw parameters are then stored as monitoring data for use in subsequent steps.
[0030] To facilitate understanding, the following example is used for explanation, but it does not impose specific limitations on this embodiment. For example, during a ship's voyage, lubricating oil parameters are collected every 10 seconds. In one collection cycle, the following monitoring data is obtained: lubricating oil temperature is 85 degrees Celsius, viscosity is 46 square millimeters per second, moisture content is 0.5%, and particulate matter concentration is 200 particles per milliliter. This data is saved as the monitoring data for the current moment to the internal memory.
[0031] Step S20: Generate lubricating oil health value based on the monitoring data.
[0032] It should be explained that the aforementioned lubricating oil health value refers to a numerical indicator used to quantitatively assess the current overall condition of the lubricating oil. The value of the lubricating oil health value can be a continuous value between 0 and 1, with higher values indicating better lubricating oil condition and superior lubrication performance. For example, a health value close to 1 indicates that the lubricating oil is in a good condition, almost like new oil, while a health value close to 0 indicates that the lubricating oil has severely deteriorated and is close to failure. This health value is a comprehensive indicator calculated based on the fusion of monitoring data from multiple dimensions, used to characterize the overall health of the lubricating oil under the coupled effects of multiple factors such as moisture contamination, particulate contamination, and oxidative aging.
[0033] In the specific implementation, after acquiring the lubricating oil monitoring data, the data is normalized. The original monitoring data with different dimensions (e.g., temperature, viscosity, moisture content, particulate matter concentration) are mapped to a unified numerical range to obtain normalized monitoring data. Next, according to a preset weighting strategy, the normalized monitoring data is weighted and fused. In this preset weighting strategy, each monitoring parameter corresponds to a weight coefficient, the magnitude of which reflects the parameter's contribution to the lubricating oil's health status. The normalized parameter values are multiplied by their corresponding weight coefficients and then summed to obtain the weighted fusion result. Subsequently, this weighted fusion result is mapped to a range of 0 to 1 to obtain the lubricating oil health value.
[0034] To facilitate understanding, the following examples are provided for illustration, but they do not impose specific limitations on this embodiment. For example, assume that the acquired monitoring data includes three parameters: viscosity, moisture content, and particulate matter concentration. First, these three parameters are normalized: the measured viscosity is 46, which is normalized to 0.8; the moisture content is 0.5%, which is normalized to 0.6; and the particulate matter concentration is 200 particles per milliliter, which is normalized to 0.7. The preset weighting strategy is: viscosity weight 0.5, moisture content weight 0.3, and particulate matter concentration weight 0.2. Then the weighted fusion result is 0.8×0.5+0.6×0.3+0.7×0.2=0.4+0.18+0.14=0.72. 0.72 is output as the lubricating oil health value at the current moment.
[0035] Step S30: Input the health value into the predictive control model to generate the fuel supply strategy.
[0036] It should be explained that the aforementioned predictive control model can refer to a mathematical model used to dynamically calculate the oil supply strategy based on the lubricating oil health value.
[0037] The aforementioned predictive control model can include a data prediction model and a lubrication model. The data prediction model can be used to predict the trend of health values over time, for example, predicting the trajectory of health value changes over a future period based on current and historical health value data. The lubrication model can be used to describe the lubrication behavior of lubricating oil during gear meshing, for example, calculating the oil film thickness on the gear surface based on the lubricating oil's health state parameters.
[0038] The aforementioned oil supply strategy can refer to a generated control scheme used to guide lubrication supply operations. This strategy may include oil supply timing and oil supply dosage. Oil supply timing indicates when to begin oil supply or adjust the oil supply amount, while oil supply dosage indicates the amount of lubricating oil required for each oil supply operation.
[0039] In its implementation, after the aforementioned health value is input into the predictive control model, the model performs a series of calculations based on this value. First, the health value is input into a data prediction model, which predicts the trend of the health value over a future period based on the current health value and historical health value sequences, thus obtaining a time-varying health value trend. Next, this time-varying health value trend is input into a lubrication model. Based on each predicted value in the time-varying health value trend, the lubrication model calculates the oil film thickness on the gear surface under each predicted health state and further determines the critical film thickness corresponding to the critical state where the oil film is about to rupture. Subsequently, based on the current health value and the critical film thickness, a dynamic matching rule is determined. This dynamic matching rule describes the correspondence between the health value and the lubrication demand; that is, the lower the health value and the closer the critical film thickness, the greater the lubrication demand. Finally, based on the dynamic matching rule and the predictive control algorithm, the timing and dosage of oil supply are optimized while meeting the lubrication demand, generating the aforementioned oil supply strategy.
[0040] To facilitate understanding, the following example is used for explanation, but it does not impose specific limitations on this embodiment. For example, assume that the current lubricating oil health value is calculated to be 0.72. The health value of 0.72 is input into the data prediction model. Based on the health value change trend over the past hour, the data prediction model predicts that the health value will decrease from 0.72 to 0.65 within the next 10 minutes. This time-varying health value trend is then input into the lubrication model, which calculates that when the health value is 0.72, the oil film thickness is 8 micrometers; when the health value decreases to 0.65, the oil film thickness will decrease to 5 micrometers, and the critical film thickness is 4.5 micrometers. Based on the health value of 0.72 and the critical film thickness of 4.5 micrometers, the dynamic matching rule is determined as follows: for every 0.01 decrease in the health value, the lubrication demand increases by 5%. According to the above dynamic matching rule, combined with the predictive control algorithm, it is calculated that the oil supply needs to be increased by 30% in the 4th minute within the next 10 minutes, and this scheme is output as the oil supply strategy.
[0041] Step S40: Lubricate the ship's main gearbox according to the oil supply strategy.
[0042] It should be explained that the aforementioned lubrication supply can refer to the execution of providing lubricating oil to the ship's main gearbox according to the generated oil supply strategy.
[0043] The aforementioned lubrication supply may include one or more actions such as starting oil supply, stopping oil supply, increasing oil supply, decreasing oil supply, and adjusting oil supply frequency. The aforementioned ship main gearbox may refer to a key mechanical component in a ship's power transmission system used to transmit power and change speed ratios. It contains meshing gear pairs and relies on lubricating oil to form an oil film between the gear surfaces to reduce friction and transfer heat.
[0044] In practical implementation, after generating the lubrication supply strategy, it is converted into control commands recognizable by the actuators. Based on the lubrication timing and dosage specified in the strategy, the required initiation point for the lubrication operation and the amount of lubricating oil to be supplied are determined. The lubrication dosage is converted into corresponding actuator action parameters, such as the oil pump speed, the solenoid valve opening duration, or the regulating valve opening degree. Then, when the specified lubrication timing arrives, the control commands are sent to the actuators. Responding to the control commands, the actuators supply lubricating oil to the lubrication points of the ship's main gearbox according to the specified dosage. After completing this lubrication supply operation, the lubrication oil monitoring data continues to be monitored, and the next control cycle begins.
[0045] To facilitate understanding, the following example is used for explanation, but it does not impose specific limitations on this embodiment. For example, suppose the generated oil supply strategy is: at the 4th minute after the current moment, increase the oil supply by 30% for a continuous oil supply time of 2 seconds. The above oil supply strategy is converted into a control command: set the oil pump speed to increase from 1000 rpm to 1300 rpm, start at the 4th minute after the current moment, run for 2 seconds, and then return to the original speed. At the 4th minute, the above control command is sent to the oil pump driver. The oil pump runs at 1300 rpm for 2 seconds, injecting an additional preset amount of lubricating oil into the gear meshing area of the ship's main gearbox. After 2 seconds, the oil pump returns to its normal operating state of 1000 rpm.
[0046] This embodiment first acquires lubricating oil monitoring data. Then, a lubricating oil health value is generated based on the monitoring data. This health value is then input into a predictive control model to generate an oil supply strategy. Finally, lubrication is supplied to the ship's main gearbox according to the oil supply strategy. Compared to existing static threshold control or reactive maintenance methods, this application integrates multi-dimensional monitoring data into a health value and dynamically generates an oil supply strategy by combining a data prediction model and a lubrication model. This achieves forward-looking prediction of lubricating oil degradation trends and precise adaptation of oil supply volume, solving the lubrication failure problem caused by oil performance degradation under complex operating conditions.
[0047] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. On this basis, a second embodiment of the lubrication control method of this application is proposed; please refer to... Figure 2 , Figure 2 This is a schematic flowchart illustrating Embodiment 2 of the lubrication control method of this application. To generate an oil supply strategy, such as... Figure 2 As shown, in this embodiment, the predictive control model includes a data prediction model and a lubrication model. The step of inputting the health value into the predictive control model to generate the oil supply strategy includes: Step S301: Input the health value into the data prediction model to obtain the time-varying trend of the health value.
[0048] It should be explained that the aforementioned data prediction model can refer to a mathematical model used to predict future trends based on historical and current data. This data prediction model can be built based on time-series prediction algorithms, such as Long Short-Term Memory networks or random forest algorithms. The aforementioned time-varying trend of health values can refer to the predicted trajectory of lubricating oil health values changing over time. This time-varying trend of health values can include predicted health values for multiple future time points, such as health value sequences for the next 5, 10, and 15 minutes.
[0049] In its implementation, after the aforementioned health value is input into the data prediction model, the model uses this health value as the input data for the current moment. The model reads historical health value records from its internal storage, including the health value corresponding to each collection moment within a past period. The model concatenates the current health value with the historical health value sequence to form a complete input feature vector. Next, the model calculates the input feature vector based on the trained model parameters, outputting the health value for each predicted moment within a preset future time period. The model arranges the health values for each predicted future moment in chronological order, forming the time-varying trend of the health value. This time-varying trend of the health value is obtained from the data prediction model for use in subsequent steps.
[0050] To facilitate understanding, the following example is used for explanation, but it does not impose specific limitations on this embodiment. For example, assume the current time is 10:00:00, and the calculated current lubricating oil health value is 0.72. The health value of 0.72 is input into a data prediction model built based on a Long Short-Term Memory (LSTM) network. The data prediction model reads historical health value data recorded every 10 seconds over the past 30 minutes, totaling 180 historical health values. The data prediction model combines the current health value of 0.72 with the 180 historical health values to form an input sequence of length 181. After calculation, the model outputs the predicted health value for the next 10 minutes, every 30 seconds. The predicted results include: a health value of 0.71 at 10:00:30, a health value of 0.70 at 10:01:00, a health value of 0.69 at 10:01:30, and so on until a health value of 0.62 at 10:10:00. The above series of predicted results is used as the time-varying trend of the health value.
[0051] Step S302: Input the time-varying trend of the health value into the lubrication model to obtain the critical film thickness.
[0052] It should be explained that the above-mentioned lubrication model can refer to a mathematical and physical model used to describe the formation of an oil film by lubricating oil in the gear meshing contact area and its bearing of load.
[0053] The above lubrication model can be constructed based on the elastohydrodynamic lubrication theory, expressing parameters such as the viscosity and film-forming ability of lubricating oil as dynamic functions of water content, particulate matter concentration, and aging time.
[0054] The critical film thickness mentioned above refers to the minimum thickness at which the lubricating oil film can maintain complete lubrication on the surface of the friction pair. When the oil film thickness is lower than the critical film thickness, direct metal-to-metal contact will occur between the meshing surfaces of the gears, and the lubrication state will change from full film lubrication to boundary lubrication, resulting in significantly increased wear.
[0055] In the specific implementation, after inputting the aforementioned time-varying trend of health values into the lubrication model, the lubrication model analyzes each predicted health value in the time-varying trend. Based on a preset mapping relationship, the lubrication model converts each predicted health value into corresponding lubricating oil viscosity parameters and film-forming ability parameters. This preset mapping relationship originates from a pre-completed gradient degradation experiment, which reveals the lubrication performance parameters corresponding to different health values. Next, the lubrication model substitutes the converted viscosity parameters and film-forming ability parameters into the elastohydrodynamic lubrication control equation for solution. This elastohydrodynamic lubrication control equation includes the Reynolds equation and the elastic deformation equation, used to calculate the oil film thickness distribution in the gear meshing region under given operating conditions (e.g., speed, load). The lubrication model extracts the minimum oil film thickness in the contact area from the solution results and compares this minimum oil film thickness with a preset safety factor to determine the oil film thickness value corresponding to the critical state where the oil film is about to rupture, which is then used as the critical film thickness. This critical film thickness is obtained from the lubrication model for use in subsequent steps.
[0056] To facilitate understanding, the following examples are provided for illustration, but they do not impose specific limitations on this embodiment. For instance, suppose the time-varying trend of health values is input into the lubrication model, and the time-varying trend of health values includes predicted results such as a health value of 0.71 at 10:00:30, a health value of 0.70 at 10:01:00, and a health value of 0.69 at 10:01:30. Based on the gradient degradation experimental data, the above lubrication model maps a health value of 0.71 to a viscosity of 42 mm² / s and a film-forming factor of 0.92; maps a health value of 0.70 to a viscosity of 40 mm² / s and a film-forming factor of 0.89; and maps a health value of 0.69 to a viscosity of 38 mm² / s and a film-forming factor of 0.86. The above lubrication model substitutes the parameters into the elastohydrodynamic lubrication control equation and, combined with the current operating conditions of a gearbox speed of 1500 rpm and a load torque of 500 Nm, calculates the minimum oil film thickness corresponding to each predicted healthy value as follows: healthy value 0.71 corresponds to 5.2 micrometers, healthy value 0.70 corresponds to 4.8 micrometers, and healthy value 0.69 corresponds to 4.5 micrometers. Based on a preset safety factor of 1.2, the above lubrication model determines the critical film thickness to be 4.2 micrometers. The critical film thickness is thus determined to be 4.2 micrometers.
[0057] Step S303: Determine the dynamic matching rules based on the health value and the critical film thickness.
[0058] It should be explained that the aforementioned dynamic matching rule can refer to a function or mapping table describing the correspondence between the lubricating oil's health value and the lubrication requirement. The core function of this dynamic matching rule is to dynamically calculate the amount of oil needed to maintain safe lubrication based on the current health state of the lubricating oil and the critical film thickness threshold at which the oil film is about to rupture. This dynamic matching rule can be an empirical formula or an interpolation lookup table, with input parameters including the current health value and the critical film thickness, and the output being the lubrication requirement. This lubrication requirement can refer to the additional amount of lubricating oil or the total oil supply required to maintain the oil film thickness above the critical film thickness.
[0059] In the specific implementation, after obtaining the aforementioned health value and critical film thickness, the dynamic matching rule is constructed based on these values. First, a baseline mapping relationship between the health value and lubrication demand is determined. This baseline mapping relationship originates from pre-completed gradient degradation experiment data. This gradient degradation experiment reveals how much more lubricating oil supply is needed to maintain the oil film thickness at a safe level under different health value levels. Next, the critical film thickness is introduced as a correction factor to dynamically adjust the baseline mapping relationship. The critical film thickness reflects the safety boundary of the lubrication system under current operating conditions; a smaller critical film thickness indicates a tighter lubrication safety margin, and the lubrication demand corresponding to the same health value needs to be increased accordingly. Using the aforementioned health value and critical film thickness as input variables, the lubrication demand is calculated through a preset fitting function, and the correspondence between the health value, critical film thickness, and lubrication demand is determined as the dynamic matching rule. This dynamic matching rule can be in the form of a piecewise linear function, an exponential function, or a lookup table interpolation.
[0060] To facilitate understanding, the following examples are provided for illustration, but do not impose specific limitations on this embodiment. For example, suppose the current lubricating oil health value is 0.72, and the critical film thickness is 4.2 micrometers. The preset baseline mapping relationship is: when the health value is between 0.7 and 0.8, the basic lubrication demand is 100% of the rated oil supply. Since the critical film thickness of 4.2 micrometers is close to the empirical safety value under this operating condition, the correction coefficient is 1.0, therefore the determined dynamic matching rule is: the lubrication demand equals 100% of the rated oil supply. As another example, suppose the critical film thickness is 3.8 micrometers, which is significantly lower than the safety threshold. In this case, the correction coefficient is 1.3, and the determined dynamic matching rule is: the lubrication demand equals 130% of the rated oil supply. The above correspondence is stored as a dynamic matching rule for the generation of subsequent oil supply strategies.
[0061] Step S304: Generate the fuel supply strategy according to the dynamic matching rules and the predictive control algorithm.
[0062] It should be explained that the aforementioned predictive control algorithm can refer to an advanced control algorithm based on model prediction of future behavior and rolling optimization of control inputs. The core of this predictive control algorithm lies in using a predictive model to estimate the future state changes of the system, determining the optimal control action at the current moment by solving an optimization problem within a finite time domain, and repeating this process at each sampling moment to achieve rolling optimization and feedback correction. The aforementioned fuel supply strategy can refer to the specific control scheme output by the predictive control algorithm that guides the actuator's actions. This fuel supply strategy can include a sequence of fuel supply commands to be executed in each control cycle within a preset future time window, such as a combination of fuel supply timing and fuel supply dosage.
[0063] In the specific implementation, after obtaining the aforementioned dynamic matching rules, these rules are embedded into the optimization objective function and constraints of the predictive control algorithm. First, the current health value of the lubricating oil and its time-varying trend are obtained, with the trend representing the predicted trajectory of the health value over a future period. Next, a preset time domain is defined, representing the length of the time window for planning the oil supply strategy. Based on the current health value, its time-varying trend, and the dynamic matching rules, an optimization problem is constructed within this preset time domain. The objective of this optimization problem is to ensure that the oil film thickness is always higher than the critical film thickness while minimizing the total lubricating oil consumption, all while satisfying lubrication supply constraints. Solving this optimization problem determines the optimal oil supply command sequence within the preset time domain, i.e., the optimal control sequence. The first control variable is extracted from the optimal control sequence as the oil supply command to be executed at the current moment, and the oil supply strategy is generated based on this command.
[0064] To facilitate understanding, the following example is used for explanation, but it does not impose specific limitations on this embodiment. For example, assume that the current health value is 0.72, and the time-varying trend of the health value shows that the health value will decrease from 0.72 to 0.65 in the next 10 minutes. The dynamic matching rule is that the lubrication demand increases by 5% for every 0.01 decrease in the health value. Set the preset time domain to 10 minutes and the control cycle to 30 seconds. Calculate the lubrication demand for each control cycle in the next 10 minutes according to the above dynamic matching rule, and solve for the optimal control sequence with the goal of minimizing the total oil supply, while satisfying the constraint that the oil film thickness in each cycle is higher than the critical film thickness. The solution is as follows: maintain the rated oil supply for the first 3 minutes, increase the oil supply by 25% from the 4th to the 6th minute, and increase the oil supply by 40% from the 7th to the 10th minute. Extract the first control quantity (maintain the rated oil supply for the first 30 seconds) as the current oil supply command, and generate an oil supply strategy that includes the current control cycle and the oil supply actions in the future predicted time domain.
[0065] Furthermore, in this embodiment, the step of generating the fuel supply strategy based on the dynamic matching rules and the predictive control algorithm includes: Step S3041: Obtain the time-varying trend of the health value and the current health value of the lubricating oil.
[0066] It should be explained that the aforementioned current health value refers to the lubricating oil health value calculated at the current moment. This current health value is a numerical indicator reflecting the overall condition of the lubricating oil at the current moment, and its value can be a continuous value between 0 and 1. The aforementioned time-varying trend of the health value refers to the predicted trajectory of the health value over a future period, output by the aforementioned data prediction model, and can include the predicted health values for multiple future time points.
[0067] In the specific implementation, during the generation of the oil supply strategy, the basic data required for generating the oil supply strategy is first obtained. The most recently calculated lubricating oil health value is read from the internal storage unit and used as the current health value. The current health value can be the health value calculated and stored at the end of the previous control cycle, or it can be the health value calculated in real time at the beginning of the current control cycle. Next, the time-varying trend of the health value is obtained from the data prediction model. The time-varying trend of the health value has been stored after the data prediction model has completed the prediction calculation, or it can be actively retrieved from the data prediction model when needed. The current health value and the time-varying trend of the health value are used as input data for subsequent optimization calculation steps.
[0068] To facilitate understanding, the following example is used for explanation, but it does not impose specific limitations on this embodiment. For example, suppose the current time is 10:00:00, and the lubricating oil health value calculated in the previous control cycle (9:59:30) is 0.72. This value is stored in the internal memory as the aforementioned current health value. The time-varying trend of the health value obtained from the above data prediction model is as follows: health value 0.71 at 10:00:30, health value 0.70 at 10:01:00, health value 0.69 at 10:01:30, until health value 0.62 at 10:10:00. The current health value of 0.72 and the above-mentioned time-varying trend of the health value (the predicted sequence of health values every 30 seconds in the next 10 minutes) are used together as input data for subsequently determining the optimal control sequence.
[0069] Step S3042: Determine the optimal control sequence within a preset time domain based on the current health value, the time-varying trend of the health value, and the dynamic matching rule.
[0070] It should be explained that the aforementioned preset time domain refers to the length of the future time window considered by the predictive control algorithm during optimization calculations. The length of the preset time domain can be set according to the sampling period and response speed of the control system, for example, it can be set to 10 minutes, 5 minutes, or a shorter time period. The aforementioned optimal control sequence refers to the set of optimal control commands obtained by the predictive control algorithm within the aforementioned preset time domain. The aforementioned optimal control sequence includes the control actions to be executed in each control cycle from the current moment to the end of the aforementioned preset time domain, such as the fuel injection rate or the opening value of the fuel injection valve in each control cycle.
[0071] In the specific implementation, after obtaining the current health value, the time-varying trend of the health value, and the dynamic matching rule, an optimization problem is constructed and solved within the preset time domain. First, the length of the preset time domain and the time interval of the control cycle are determined. The length of the preset time domain can be a fixed value or dynamically adjusted according to the current operating conditions. Next, the current health value is used as the initial state, and the time-varying trend of the health value is used as the prediction reference trajectory for the future state. According to the dynamic matching rule, the lubrication demand corresponding to each control cycle within the preset time domain is calculated. The lubrication demand is used as one of the constraints of the optimization problem, and the control objective is set as minimizing the total lubricating oil consumption while meeting the lubrication demand. Using the optimization solver in the predictive control algorithm, the optimization problem is solved within the preset time domain, resulting in a set of control command sequences that satisfy the constraints and optimize the control objective, which is taken as the optimal control sequence.
[0072] To facilitate understanding, the following explanation uses examples, but does not impose specific limitations on this embodiment. For example, assume the current health value is 0.72, and the time-varying trend of the health value shows that it will decrease from 0.72 to 0.65 within the next 10 minutes. The dynamic matching rule is that the lubrication demand increases by 5% for every 0.01 decrease in the health value. A preset time domain is set to 10 minutes, and the control cycle is 1 minute, meaning the preset time domain contains 10 control cycles. Based on the time-varying trend of the health value, the predicted health values for the 1st to 10th minutes are calculated to be 0.71, 0.70, 0.69, 0.68, 0.67, 0.66, 0.65, 0.64, 0.63, and 0.62, respectively. According to the dynamic matching rule, the lubrication demand corresponding to each cycle is calculated to be 105%, 110%, 115%, 120%, 125%, 130%, 135%, 140%, 145%, and 150% of the rated oil supply. With the objective of minimizing the total oil supply within 10 minutes, and under the constraint that the oil supply in each cycle is not less than the aforementioned lubrication demand, the optimal control sequence is solved. The solution may be as follows: oil supply at the rated rate in cycles 1-3; oil supply increased in advance in cycles 4-6 to meet subsequent demand; and oil supply at the lubrication demand in cycles 7-10. The oil supply command sequence for these 10 cycles is taken as the optimal control sequence.
[0073] Step S3043: Take the first control quantity in the optimal control sequence as the current fuel supply command, and generate the fuel supply strategy according to the current fuel supply command.
[0074] It should be explained that the aforementioned first control variable can refer to the control instruction corresponding to the first control cycle in the aforementioned optimal control sequence. The aforementioned optimal control sequence includes control instructions for multiple control cycles from the current moment to the end of the preset time domain, where the control instruction for the first control cycle is the aforementioned first control variable. The aforementioned current oil supply instruction can refer to the specific oil supply action instruction that needs to be executed immediately at the current moment. The aforementioned oil supply strategy can refer to the final output, complete control scheme used to guide the lubrication supply operation; the aforementioned oil supply strategy can include the aforementioned current oil supply instruction and the remaining control instructions in the aforementioned optimal control sequence.
[0075] In the specific implementation, after determining the optimal control sequence, the control command for the first control cycle is extracted from it. This first control cycle's control command is marked as the current lubrication command. The current lubrication command includes the lubrication action parameters to be executed within the current control cycle, such as the lubrication dosage, duration, or valve opening value. Then, based on the current lubrication command and the remaining control commands in the optimal control sequence, a complete lubrication strategy is generated. This lubrication strategy can include the lubrication command for each control cycle from the current moment to the end of a preset time domain. The lubrication strategy is output for subsequent lubrication supply operations. When the current lubrication command is executed and the next control cycle begins, the prediction and optimization process is repeated to obtain a new optimal control sequence and extract the new first control variable, achieving rolling optimization control.
[0076] To facilitate understanding, the following explanation uses examples, but does not impose specific limitations on this embodiment. For example, assume that the determined optimal control sequence contains 10 control cycles of oil supply commands, each control cycle being 1 minute. In the above optimal control sequence, the oil supply command corresponding to the 1st minute is to maintain the rated oil supply, the oil supply command corresponding to the 2nd minute is to increase the oil supply by 10%, the oil supply command corresponding to the 3rd minute is to increase the oil supply by 20%, and so on. The oil supply command for the 1st minute (maintaining the rated oil supply) is extracted from the above optimal control sequence as the current oil supply command. The above current oil supply command (maintaining the rated oil supply for the 1st minute) is combined with the oil supply commands from the 2nd to the 10th minute (increasing by 10%, increasing by 20%, etc., respectively) to generate a complete oil supply strategy. The above oil supply strategy is output to the actuator, and the actuator immediately begins to execute the lubrication supply operation according to the current oil supply command in the above oil supply strategy.
[0077] Furthermore, in order to calibrate the lubrication model, in this embodiment, the step of inputting the time-varying trend of the health value into the lubrication model to obtain the critical film thickness further includes: Step S3021: Obtain the oil film thickness data of the sample lubricating oil.
[0078] It should be explained that the aforementioned sample lubricating oil can refer to multiple sets of lubricating oil samples with different compositions or states, prepared in advance for calibrating the aforementioned lubrication model. The aforementioned sample lubricating oil can include experimental oil samples covering different degradation ranges prepared by adjusting moisture content, particulate matter concentration, and aging time. The aforementioned oil film thickness data can refer to the measured thickness of the lubricating oil film formed by the aforementioned sample lubricating oil under standard test conditions. The aforementioned oil film thickness data can be obtained through optical interferometry, for example, by using an optical interferometric oil film measurement device to collect the oil film thickness values of different sample lubricating oils under different operating conditions.
[0079] In the specific implementation, before calibrating the aforementioned lubrication model, sample data for calibration is acquired. Pre-stored oil film thickness data of the sample lubricating oils is read from local memory or external testing equipment. This oil film thickness data is measured in a laboratory or bench testing environment for multiple groups of sample lubricating oils with different moisture contents, particulate matter concentrations, and aging times, under standardized speed and load conditions. The oil film thickness data may include one or more oil film thickness measurements corresponding to each sample lubricating oil. After acquiring the oil film thickness data, it is associated with and stored along with the corresponding state parameters of the sample lubricating oil (e.g., moisture content, particulate matter concentration, aging time) for use in subsequent calibration steps.
[0080] To facilitate understanding, the following examples are provided for illustration, but do not impose specific limitations on this embodiment. For instance, assume that nine sets of sample lubricating oils were prepared in advance, corresponding to combinations of moisture content of 0.5%, 1%, and 2%, particulate matter concentration of 100 ppm, 200 ppm, and 500 ppm, and aging times of 0 hours, 100 hours, and 200 hours, respectively. In bench testing, the oil film thickness of each sample lubricating oil was measured using an optical interferometric oil film measurement device under conditions of 1500 rpm and 500 Nm load. The measurement results are as follows: the sample with 0.5% moisture, 100 ppm particulate matter, and 0 hours of aging corresponds to an oil film thickness of 8.2 micrometers; the sample with 1% moisture, 200 ppm particulate matter, and 100 hours of aging corresponds to an oil film thickness of 5.5 micrometers; and the sample with 2% moisture, 500 ppm particulate matter, and 200 hours of aging corresponds to an oil film thickness of 3.8 micrometers. The above nine sets of oil film thickness data were acquired, and each set of data was associated with and stored in relation to the corresponding sample lubricating oil state parameters.
[0081] Step S3022: Calibrate the lubrication model based on the oil film thickness data.
[0082] It should be explained that the aforementioned calibration refers to adjusting the parameters or functional relationships in the lubrication model to match the calculated output of the lubrication model with the measured data. The lubrication model may contain multiple adjustable parameters, such as viscosity decay coefficient and film-forming ability correction factor. The calibration optimizes these parameters by comparing the model output with the measured oil film thickness data.
[0083] In the specific implementation, after obtaining the oil film thickness data, this data is used as a baseline to calibrate the lubrication model. First, the state parameters of the sample lubricating oil are input into the lubrication model, which then calculates and outputs the corresponding oil film thickness value. These state parameters include the water content, particulate matter concentration, and aging time of the sample lubricating oil. Next, the calculated oil film thickness value is compared point-by-point with the measured value in the oil film thickness data, and the deviation between the two is calculated. Based on this deviation, a parameter identification algorithm is used to adjust the adjustable parameters in the lubrication model, making the calculated oil film thickness value as close as possible to the measured value in the oil film thickness data. This process of input, calculation, comparison, and adjustment is repeated until the deviation converges to a preset tolerance range. After calibration, the calibrated lubrication model is stored for subsequent critical film thickness calculations.
[0084] To facilitate understanding, the following example is used for explanation, but it does not impose specific limitations on this embodiment. For example, assume that in the obtained oil film thickness data, the measured oil film thickness of sample A (1% moisture, 200 ppm particles, aged for 100 hours) is 5.5 micrometers. The state parameters of sample A are input into the lubrication model before calibration. The lubrication model calculates an oil film thickness of 6.0 micrometers, which deviates from the measured value by 0.5 micrometers. The film-forming ability correction factor in the lubrication model is adjusted using the least squares method, changing the correction factor from 1.0 to 0.92. Using the adjusted parameters, the oil film thickness is recalculated to 5.6 micrometers, reducing the deviation to 0.1 micrometers. Other parameters are adjusted continuously. After multiple iterations, the oil film thickness output by the lubrication model stabilizes at 5.5 micrometers, consistent with the measured value. The lubrication model with adjusted parameters is stored as the calibrated lubrication model.
[0085] Based on the first and / or second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to that in embodiments one and two above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 , Figure 3 This is a schematic flowchart of Embodiment 3 of the lubrication control method of this application. To generate a lubricating oil health value, such as... Figure 3 As shown, in this embodiment, the step of generating a lubricating oil health value based on the monitoring data includes: Step S201: Normalize the monitoring data to obtain normalized monitoring data.
[0086] It should be explained that the above-mentioned normalization process refers to the mathematical transformation process of mapping data with different dimensions or orders of magnitude to the same numerical range. The purpose of the above-mentioned normalization process is to eliminate the influence of different units or value ranges of different monitoring parameters on subsequent weighted fusion. The above-mentioned normalized monitoring data can refer to the dimensionless value obtained after normalization transformation of the original monitoring data. The value range of the above-mentioned normalized monitoring data can be between 0 and 1, or between -1 and 1, or other preset numerical ranges.
[0087] In the specific implementation, after obtaining the aforementioned monitoring data, the normalization process is performed on each parameter in the monitoring data. First, a normalization reference parameter is determined for each monitoring parameter, which includes the theoretical lower limit and theoretical upper limit of the parameter. The theoretical lower limit and theoretical upper limit can be set according to the typical range of values of lubricating oil under normal working conditions, or determined according to the statistical distribution of historical data. Next, for each monitoring parameter, the original measured value is subtracted from the theoretical lower limit, and the difference is divided by the difference between the theoretical upper limit and the theoretical lower limit to obtain the normalized value corresponding to the parameter. The above calculation is repeated for all parameters in the monitoring data to obtain the normalized value corresponding to each parameter. All the above normalized values are combined to form the normalized monitoring data.
[0088] To facilitate understanding, the following examples are provided for illustration, but do not impose specific limitations on this embodiment. For example, assume that the acquired monitoring data includes: viscosity of 46 mm² / s, moisture content of 0.5%, and particulate matter concentration of 200 particles per milliliter. The normalization benchmarks for the preset viscosity parameters are: lower limit 20 mm² / s, upper limit 100 mm² / s; normalization benchmarks for moisture content are: lower limit 0%, upper limit 5%; normalization benchmarks for particulate matter concentration are: lower limit 0 particles per milliliter, upper limit 1000 particles per milliliter. The viscosity is normalized as follows: (46-20) / (100-20) = 26 / 80 = 0.325. The moisture content is normalized as follows: (0.5-0) / (5-0) = 0.5 / 5 = 0.1. The particulate matter concentration is normalized as follows: (200-0) / (1000-0) = 200 / 1000 = 0.2. Combining the three normalized values above, the normalized monitoring data are: viscosity 0.325, moisture content 0.1, and particulate matter concentration 0.2.
[0089] Step S202: According to the preset weight allocation strategy, the normalized monitoring data is weighted and fused.
[0090] It should be explained that the aforementioned preset weighting strategy refers to a set of weighting coefficients pre-defined for each monitoring parameter. These weighting coefficients reflect the degree of contribution or importance of different monitoring parameters to the health status of the lubricating oil. For example, the weight of viscosity change on lubrication performance can be set to a higher value, while the weight of temperature change can be set to a lower value. The aforementioned weighted fusion refers to the process of multiplying the normalized values of each monitoring parameter by their corresponding weighting coefficients and then summing the results to obtain a comprehensive value.
[0091] In the specific implementation, after obtaining the normalized monitoring data, the preset weight allocation strategy is read from the internal memory. This preset weight allocation strategy includes weight coefficients for each monitoring parameter; the sum of the weight coefficients for all monitoring parameters can be equal to 1, 100, or other values. Based on the preset weight allocation strategy, the weight coefficient corresponding to each parameter in the normalized monitoring data is extracted. Then, the normalized value of each parameter is multiplied by its corresponding weight coefficient to obtain the weighted value of each parameter. The weighted values of all parameters are summed to obtain the weighted fusion result.
[0092] To facilitate understanding, the following explanation uses examples, but does not impose specific limitations on this embodiment. For example, assume the normalized monitoring data is: viscosity 0.325, moisture content 0.1, particulate matter concentration 0.2. The preset weighting strategy is: viscosity weight 0.5, moisture content weight 0.3, and particulate matter concentration weight 0.2. Reading the weighting strategy, multiplying the normalized viscosity value of 0.325 by the viscosity weight 0.5 yields a weighted viscosity value of 0.1625. Multiplying the normalized moisture content value of 0.1 by the moisture content weight 0.3 yields a weighted moisture content value of 0.03. Multiplying the normalized particulate matter concentration value of 0.2 by the particulate matter concentration weight 0.2 yields a weighted particulate matter concentration value of 0.04. Adding these three weighted values gives a weighted fusion result of 0.1625 + 0.03 + 0.04 = 0.2325.
[0093] Step S203: Obtain the lubricating oil health value based on the weighted fusion result.
[0094] It should be explained that the aforementioned weighted fusion result refers to the comprehensive value obtained by weighting and summing the normalized monitoring data. This weighted fusion result typically falls within a specific numerical range, the range of which depends on the setting of the sum of weighting coefficients in the weighting strategy. The aforementioned lubricating oil health value refers to the final numerical indicator used to quantitatively assess the current overall condition of the lubricating oil. The value of the lubricating oil health value can be a continuous value between 0 and 1; a higher value indicates a better condition and superior lubrication performance of the lubricating oil.
[0095] In the specific implementation, after obtaining the weighted fusion result, a further mapping transformation is performed on the weighted fusion result to obtain the lubricating oil health value. First, the original numerical range of the weighted fusion result is determined. The lower limit of the original numerical range can be 0, and the upper limit can be the sum of all weight coefficients in the weight allocation strategy. A target numerical range is preset, which can be between 0 and 1, or between 0 and 100. Next, the weighted fusion result is mapped from the original numerical range to the target numerical range. This mapping transformation can use a linear mapping method, for example, subtracting the lower limit of the original range from the original value, dividing by the width of the original range, multiplying by the width of the target range, and then adding the lower limit of the target range. The value obtained after the mapping transformation is output and stored as the lubricating oil health value.
[0096] To facilitate understanding, the following examples are provided for illustration, but they do not impose specific limitations on this embodiment. For example, assume the calculated weighted fusion result is 0.2325. The original numerical range corresponding to the above weighted fusion result is 0 to 1, because the sum of the viscosity weight (0.5), moisture content weight (0.3), and particulate matter concentration weight (0.2) in the above weight allocation strategy is 1. The preset target numerical range is 0 to 1. Subtract the lower limit of the original range (0) from the original value 0.2325, divide by the original range width (1), and get 0.2325. Multiply by the target range width (1) and add the lower limit of the target range (0), and you still get 0.2325. Use 0.2325 as the above lubricating oil health value. As another example, assume the sum of the weight coefficients of the above weight allocation strategy is 100, the weighted fusion result is 23.25, the original numerical range is 0 to 100, and the target numerical range is 0 to 1. Divide 23.25 by 100 to get 0.2325, and use 0.2325 as the above lubricating oil health value.
[0097] Furthermore, in order to obtain monitoring data of the lubricating oil, in this embodiment, the step of obtaining monitoring data of the lubricating oil includes: Step S101: Collect the temperature, viscosity, moisture content, and particulate matter concentration of the lubricating oil.
[0098] It should be explained that the above temperature can refer to the current temperature of the lubricating oil, and the unit can be degrees Celsius. The above viscosity can refer to the kinematic viscosity or dynamic viscosity of the lubricating oil, used to characterize the flow properties and oil film forming ability of the lubricating oil. The above water content can refer to the mass percentage or volume percentage of water mixed in the lubricating oil, used to characterize the degree of water contamination of the lubricating oil. The above particulate matter concentration can refer to the number or mass of suspended solid particles in the lubricating oil, used to characterize the degree of solid particle contamination of the lubricating oil, and the unit of particulate matter concentration can be parts per milliliter or parts per million.
[0099] In practical implementation, data acquisition is performed using various sensors connected to the lubricating oil lines or oil pan. A temperature sensor contacts the lubricating oil to measure its current temperature and convert it into an electrical signal. A viscosity sensor, such as a vibratory viscometer or a capillary viscometer, acquires the viscosity of the lubricating oil. A moisture sensor, such as a capacitive or infrared moisture sensor, acquires the moisture content of the lubricating oil. A particulate matter concentration sensor, such as a laser particle counter or an inductive particle sensor, acquires the particulate matter concentration of the lubricating oil. The analog or digital signals acquired by these sensors are read and analyzed to obtain the temperature, viscosity, moisture content, and particulate matter concentration values. These values are stored as raw data for subsequent processing steps.
[0100] To facilitate understanding, the following explanation uses examples, but does not impose specific limitations on this embodiment. For example, assume that the ship's main gearbox is operating normally and a data acquisition cycle is initiated. The temperature sensor reads the current lubricating oil temperature as 85 degrees Celsius. The viscometer measures the lubricating oil viscosity as 46 mm² / s. The capacitive moisture sensor detects a moisture content of 0.5%. A laser particle counter counts 200 particles larger than 5 micrometers in diameter in the lubricating oil per milliliter. These four sets of data (temperature 85 degrees Celsius, viscosity 46 mm² / s, moisture content 0.5%, and particle concentration 200 particles per milliliter) are stored as the raw lubricating oil data collected in this instance.
[0101] Step S102: Perform outlier removal and time series alignment processing on the temperature, viscosity, moisture content, and particulate matter concentration to obtain monitoring data.
[0102] It should be explained that the outlier removal mentioned above refers to the process of identifying and removing abnormal data points that significantly deviate from the normal range in the collected data. The purpose of outlier removal is to eliminate the impact of sensor noise, transient interference, or acquisition errors on data quality. The time series alignment process mentioned above refers to the process of arranging and synchronizing data collected by different sensors within the same time period according to a unified time reference. Since different sensors may have different sampling frequencies, or there may be delays in data transmission, the time series alignment process can ensure that the data at each time point remains consistent in the time dimension.
[0103] In the specific implementation, after acquiring the raw data for the aforementioned temperature, viscosity, moisture content, and particulate matter concentration, the above-mentioned outlier removal process is first performed on the raw data. For each parameter, the acquired data points are compared with a preset normal value range. The preset normal value range can be set according to the typical fluctuation range of lubricating oil under normal working conditions. Data points that exceed the above normal value range are identified, marked as outliers, and removed from the data sequence. Next, the above-mentioned time series alignment process is performed on the data after outlier removal. The acquisition timestamp of each parameter is obtained, and the acquired data of each parameter is assigned to the corresponding time node according to the preset reference time interval (e.g., every 1 second or every 10 seconds). For missing data at a certain time node, interpolation methods can be used to fill in the missing data, such as linear interpolation or nearest neighbor interpolation. After completing the above-mentioned outlier removal and time series alignment processes, the processed data is output and stored as the above-mentioned monitoring data.
[0104] To facilitate understanding, the following example is used for explanation, but it does not impose specific limitations on this embodiment. For example, suppose 10 sets of data are continuously collected within 10 seconds, each set containing four parameters: temperature, viscosity, moisture content, and particulate matter concentration. In these 10 sets of data, one set has a temperature value of 150 degrees Celsius, significantly exceeding the preset normal range (60 to 120 degrees Celsius). This temperature value is marked as an outlier and removed. The temperature sensor samples 10 times per second, and the viscosity sensor samples once per second. Time series alignment is performed every second. For the first second, the temperature sensor provides 10 data points, and the average of these 10 data points is taken as the temperature value for the first second; the viscosity sensor provides one data point, which is directly used as the viscosity value for the first second. The above process is repeated for the second second. The aligned data sequence is used as the monitoring data.
[0105] This application also provides a lubrication control device, please refer to... Figure 4 The device includes: The data acquisition module 10 is used to acquire monitoring data of the lubricating oil; Health value generation module 20 is used to generate lubricating oil health value based on the monitoring data; Strategy generation module 30 is used to input the health value into the predictive control model to generate a fuel supply strategy; The lubrication control module 40 is used to supply lubrication to the ship's main gearbox according to the oil supply strategy.
[0106] The lubrication control device provided in this application, employing the lubrication control method in the above embodiments, can solve the technical problem of how to achieve predictive and precise supply of lubricating oil. Compared with the prior art, the beneficial effects of the lubrication control device provided in this application are the same as those of the lubrication control method provided in the above embodiments, and other technical features in the lubrication control device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.
[0107] This application provides a lubrication control device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the lubrication control method in Embodiment 1 above.
[0108] The following is for reference. Figure 5 The diagram illustrates a structural schematic suitable for implementing the lubrication control device in the embodiments of this application. The lubrication control device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The lubrication control device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this application.
[0109] like Figure 5As shown, the lubrication control device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the lubrication control device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the lubrication control device to communicate wirelessly or wiredly with other devices to exchange data. Although the figures show lubrication control devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.
[0110] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.
[0111] The lubrication control device provided in this application, employing the lubrication control method described in the above embodiments, can solve the technical problem of how to achieve predictive and precise supply of lubricating oil. Compared with the prior art, the beneficial effects of the lubrication control device provided in this application are the same as those of the lubrication control method provided in the above embodiments, and other technical features of this lubrication control device are the same as those disclosed in the previous embodiment method, and will not be repeated here.
[0112] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.
[0113] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0114] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the lubrication control method in the above embodiments.
[0115] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.
[0116] The aforementioned computer-readable storage medium may be included in the lubrication control device; or it may exist independently and not assembled into the lubrication control device.
[0117] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the lubrication control device, cause the lubrication control device to: acquire monitoring data of the lubricating oil; Based on the monitoring data, a lubricating oil health value is generated; the health value is input into a predictive control model to generate an oil supply strategy; and lubrication is supplied to the ship's main gearbox according to the oil supply strategy.
[0118] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, and conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0119] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0120] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.
[0121] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described lubrication control method, thereby solving the technical problem of how to achieve predictive and precise supply of lubricating oil. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the lubrication control method provided in the above embodiments, and will not be repeated here.
[0122] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the lubrication control method described above.
[0123] The computer program product provided in this application can solve the technical problem of how to achieve predictive and precise supply of lubricating oil. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the lubrication control method provided in the above embodiments, and will not be repeated here.
[0124] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.
Claims
1. A lubrication control method, characterized in that, The method is applied to the lubrication control system of a ship's main gearbox, and the method includes: Obtain monitoring data for lubricating oil; A lubricating oil health value is generated based on the monitoring data; The health values are input into the predictive control model to generate the fuel supply strategy; The main gearbox of the ship is lubricated according to the oil supply strategy.
2. The method as described in claim 1, characterized in that, The predictive control model includes a data prediction model and a lubrication model. The step of inputting the health value into the predictive control model to generate the oil supply strategy includes: The health value is input into the data prediction model to obtain the time-varying trend of the health value; The time-varying trend of the health value is input into the lubrication model to obtain the critical film thickness; Dynamic matching rules are determined based on the health value and the critical film thickness. The fuel supply strategy is generated based on the dynamic matching rules and the predictive control algorithm.
3. The method as described in claim 2, characterized in that, The step of generating the fuel supply strategy based on the dynamic matching rules and the predictive control algorithm includes: Obtain the time-varying trend of the health value and the current health value of the lubricating oil; Based on the current health value, the time-varying trend of the health value, and the dynamic matching rules, the optimal control sequence is determined within a preset time domain; The first control variable in the optimal control sequence is taken as the current fuel supply command, and the fuel supply strategy is generated based on the current fuel supply command.
4. The method as described in claim 2, characterized in that, Before the step of inputting the time-varying trend of the health value into the lubrication model to obtain the critical film thickness, the method further includes: Obtain the oil film thickness data of the sample lubricating oil; The lubrication model is calibrated based on the oil film thickness data.
5. The method as described in claim 1, characterized in that, The step of generating a lubricating oil health value based on the monitoring data includes: The monitoring data is normalized to obtain normalized monitoring data; According to the preset weight allocation strategy, the normalized monitoring data is weighted and fused. The health value of the lubricating oil is obtained based on the weighted fusion results.
6. The method as described in claim 1, characterized in that, The steps for obtaining monitoring data of the lubricating oil include: Collect data on the temperature, viscosity, moisture content, and particulate matter concentration of the lubricating oil; The temperature, viscosity, moisture content, and particulate matter concentration are subjected to outlier removal and time series alignment to obtain monitoring data.
7. A lubrication control device, characterized in that, The device includes: The data acquisition module is used to acquire monitoring data of the lubricating oil; A health value generation module is used to generate a lubricating oil health value based on the monitoring data; The strategy generation module is used to input the health value into the predictive control model to generate a fuel supply strategy; The lubrication control module is used to supply lubrication to the ship's main gearbox according to the oil supply strategy.
8. A lubrication control device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the lubrication control method as described in any one of claims 1 to 6.
9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the lubrication control method as described in any one of claims 1 to 6.
10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the lubrication control method as described in any one of claims 1 to 6.
