Dynamic baseline-based power equipment operation method, system, device and medium

Abstract

The present application relates to the field of power equipment control, and provides a power equipment operation method, system, device and medium based on a dynamic baseline, comprising: obtaining first historical data and second historical data; fitting the first historical data and the second historical data to obtain a plurality of initial regression curves, calculating a fitting evaluation parameter of the initial regression curve, and selecting a current regression curve; obtaining a re-fitting trigger parameter, obtaining update data according to the re-fitting trigger parameter, updating the current regression curve, and obtaining an iterative regression curve; obtaining a deviation early warning indication according to the current regression curve and the iterative regression curve, obtaining current operation data, and obtaining a fault early warning through the deviation early warning indication, the current operation data and the iterative regression curve; selecting a fault disposal scheme from a fault disposal plan based on the fault early warning and sludge generation, and controlling a fuel treatment device and a fuel oil line, so that the present application can complete the control of the power equipment.

Description

Technical Field

[0001] This invention relates to the field of power equipment control technology, and in particular to power equipment operation methods, systems, equipment and media based on dynamic baselines. Background Technology

[0002] Marine equipment, such as main engines, auxiliary engines, turbochargers, and pump sets, is central to the safe and efficient operation of a ship. Its operational status directly impacts navigational safety, energy efficiency, and operating costs. Therefore, real-time and accurate condition monitoring and early fault warning of marine equipment are crucial for implementing predictive maintenance, avoiding major failures, and extending equipment lifespan.

[0003] Currently, ship equipment condition monitoring mainly relies on the following methods, but all of them have limitations to varying degrees.

[0004] 1. Regular inspection and experience-based judgment: This refers to crew members conducting regular on-site inspections to determine equipment malfunctions. This method relies heavily on personal experience regarding changes in equipment parameters, which is highly subjective and cannot achieve real-time, continuous monitoring. It is also prone to missing sudden equipment malfunctions and early signs of abnormalities.

[0005] 2. Alarm monitoring based on fixed thresholds: Fixed upper and lower limits for alarms are preset for various key parameters of the equipment. When the real-time data collected by the sensors exceeds these static thresholds, the system triggers an alarm. However, this method only focuses on whether the absolute value of a single parameter exceeds the limit, ignoring the fact that the equipment is an organic whole, and there are inherent physical connections and couplings between its various parameters, making it difficult to locate the root cause of the fault.

[0006] 3. Predictive Maintenance Based on Static Data Models: By collecting historical data from the equipment during sea trials or bench tests, a performance baseline model for each parameter during stable operation is established using machine learning or related statistical methods—this is the static baseline. Subsequently, real-time collected data is compared with this baseline model, and the current state is determined by calculating residuals or deviations. However, the correction or retraining of the static baseline usually requires manual intervention, which is cumbersome and untimely, making it impossible to achieve adaptive evolution of the baseline and accurately reflect the current performance status of the equipment.

[0007] To overcome the shortcomings of fixed thresholds and static baselines, methods for constructing dynamic baselines have emerged. These methods, referencing the point-based approach, establish an initial baseline and then use a sliding probabilistic neural network model to adaptively update it. The updated baseline is then processed to obtain the final dynamic baseline. However, this method focuses on the temporal changes of a single signal, and the resulting dynamic baseline is merely an optimization of the reasonableness of the fixed threshold, remaining close to the static baseline. In actual operation, ship equipment experiences slow, natural data drift under normal operating conditions due to factors such as long-term wear, component replacement, and oil quality changes. Static baselines cannot capture this drift, leading to an increasing false alarm rate and eventual model failure over time. Furthermore, with the increasing automation of modern ocean-going vessels, the number of crew members has significantly decreased. This means that when a power system fault warning occurs, there may not be enough manpower available to handle it immediately. Therefore, the power system needs to be able to autonomously respond to fault signals to reduce the probability of a fault warning turning into an actual fault, until maintenance personnel arrive to eliminate the potential hazard. Summary of the Invention

[0008] This invention aims to at least solve one of the technical problems existing in related technologies. To this end, this invention provides a method, system, equipment, and medium for operating power equipment based on dynamic baselines, enabling the generation of dynamic baselines for fault identification of ships, and the control of power equipment based on fault warnings.

[0009] This invention provides a method for operating power equipment based on a dynamic baseline, comprising: S1: Identify the target vessel, obtain the historical operating data of the target vessel, and select the first historical data and the second historical data from the historical operating data; S2: Determine the data fitting method, fit the first historical data and the second historical data using the data fitting method to obtain multiple initial regression curves, calculate the fitting evaluation parameters of the initial regression curves, and select the current regression curve based on the fitting evaluation parameters; S3: Obtain the refit trigger parameters, obtain updated data based on the refit trigger parameters, update the current regression curve with the updated data, and obtain the iterative regression curve; S4: Obtain the deviation index based on the current regression curve and the iterative regression curve, obtain the deviation warning indication based on the deviation index, acquire the current operating data, and obtain the fault warning through the deviation warning indication, the current operating data, and the iterative regression curve; S5: Obtain the sludge generation amount, determine the fault handling plan, select the fault handling scheme from the fault handling plan based on the fault warning and sludge generation amount, and control the fuel processing equipment and fuel oil circuit of the power equipment through the fault handling scheme, thereby completing the control of the power equipment.

[0010] According to the dynamic baseline-based power equipment operation method provided by the present invention, step S1 further includes: S11: Determine the target vessel and its historical operating cycle, acquire the operating data of the target vessel within the historical operating cycle, and perform data cleaning to obtain the historical operating data; S12: Perform correlation analysis on the historical operating data to obtain data correlation, take the output power of the target ship's power system as the first historical data, and select the second historical data related to the first historical data according to the data correlation.

[0011] According to the power equipment operation method based on dynamic baseline provided by the present invention, step S2 further includes: S21: Determine the data fitting method including the multinomial regression algorithm, the natural cubic spline regression algorithm, and the kernel ridge regression algorithm; S22: Each data fitting method fits the first historical data and the second historical data respectively to obtain their respective initial regression curves; S23: Calculate the root mean square error, average determination error, and coefficient of determination for each initial regression curve; perform a weighted summation of the root mean square error, average determination error, and coefficient of determination to obtain the fitting evaluation parameters; and select the current regression curve based on the fitting evaluation parameters.

[0012] According to the power equipment operation method based on dynamic baseline provided by the present invention, step S3 further includes: S31: Detect the equipment maintenance status to obtain the refitting trigger parameter; wherein, after the equipment maintenance is completed, the refitting trigger parameter is set to 1, otherwise it is set to 0; S32: When the refitting trigger parameter is set to 1, the operation data of the target ship equipment after maintenance is obtained as the updated data, and the current regression curve is updated by the updated data to obtain the iterative regression curve; otherwise, the current regression curve is used as the iterative regression curve.

[0013] According to the power equipment operation method based on dynamic baseline provided by the present invention, step S4 further includes: S41: Select benchmark update data, obtain the current curve prediction value corresponding to the benchmark update data on the current regression curve, and obtain the iterative curve prediction value corresponding to the benchmark update data on the iterative regression curve; S42: Obtain the deviation index based on the predicted value of the iterative curve and the predicted value of the current curve, obtain the deviation warning indication based on the deviation index, acquire the current operating data, obtain the fault indication value based on the current operating data and the iterative regression curve, and obtain the fault warning through the deviation warning indication and the fault indication value.

[0014] According to the power equipment operation method based on dynamic baseline provided by the present invention, step S5 further includes: S51: Determine the sludge monitoring time interval, obtain the amount of sludge generated by the power system of the target ship within the sludge monitoring time interval, and obtain the amount of sludge generated; S52: Determine a fault handling plan including a first fault handling plan and a second fault handling plan, wherein the first fault handling plan controls the fuel processing equipment and the second fault handling plan controls the fuel oil circuit. S53: When the amount of sludge generated exceeds the preset sludge generation threshold and the fault warning indication is faultless, the first fault handling plan shall be adopted first. If the amount of sludge generated in the next sludge monitoring time interval still exceeds the sludge generation threshold, the first fault handling plan and the second fault handling plan shall be adopted simultaneously. When a fault warning indicates that the fuel processing equipment has malfunctioned, the second fault handling plan shall be implemented. When a fault warning indicates that the power equipment has malfunctioned and the amount of sludge generated has not exceeded the preset sludge generation threshold, the first fault handling plan shall be adopted. When the fault warning indicates that a fault still exists, the fuel delivery amount shall be reduced while maintaining the first fault handling plan. When a fault warning indicates that the power equipment has malfunctioned and the amount of sludge generated exceeds the preset sludge generation threshold, both the first fault handling plan and the second fault handling plan will be implemented simultaneously.

[0015] According to the power equipment operation method based on dynamic baseline provided by the present invention, in step S52, the first fault handling plan is to increase the centrifugal equipment speed and increase the heating tube temperature of the fuel processing equipment. The second fault handling plan is to determine the alternative fuel tank, obtain the alternative fuel in the alternative fuel tank, mix the alternative fuel with the existing fuel in the fuel line, and gradually increase the proportion of the alternative fuel in the fuel delivered to the power equipment.

[0016] The present invention also provides a power equipment operation system based on a dynamic baseline, comprising: Historical data module: used to identify the target vessel, obtain the target vessel's historical operating data, and select the first historical data and the second historical data from the historical operating data; Current regression curve module: used to determine the data fitting method, fit the first historical data and the second historical data using the data fitting method to obtain multiple initial regression curves, calculate the fitting evaluation parameters of the initial regression curves, and select the current regression curve based on the fitting evaluation parameters; Iterative Regression Curve Module: Used to obtain refit trigger parameters, obtain updated data based on refit trigger parameters, update the current regression curve with the updated data, and obtain the iterative regression curve; Fault warning module: used to obtain the deviation index based on the current regression curve and the iterative regression curve, obtain the deviation warning indication based on the deviation index, obtain the current operating data, and obtain fault warning through the deviation warning indication, the current operating data, and the iterative regression curve; Fault handling module: Used to obtain sludge generation amount, determine fault handling plan, select fault handling scheme from the fault handling plan based on fault warning and sludge generation amount, and control the fuel handling equipment and fuel oil circuit of power equipment through fault handling scheme, thereby completing the control of power equipment.

[0017] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the dynamic baseline-based power equipment operation method as described above.

[0018] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the power equipment operation method based on dynamic baseline as described above.

[0019] The above-described one or more technical solutions in the embodiments of the present invention have at least one of the following technical effects: The present invention provides a dynamic baseline-based method, system, device, and medium for operating power equipment. By integrating the deviations of a pair of related parameters under a single device, a current regression curve is obtained, avoiding the need to integrate the deviations of multiple related parameters under a single device. Furthermore, instead of using fixed historical data to establish a permanent baseline, this application refits the baseline, enabling it to adaptively track the natural drift and slow degradation of equipment performance. This allows the baseline to adapt to changes in equipment operating status, improving the accuracy of fault warnings. In addition, it enables the equipment to automatically implement fault handling plans based on fault warnings, taking measures to reduce the occurrence of faults even with limited maintenance personnel.

[0020] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating the power equipment operation method based on dynamic baseline provided by the present invention.

[0023] Figure 2 This is a schematic diagram of the structure of the power equipment operation system based on dynamic baseline provided by the present invention.

[0024] Figure 3 This is a schematic diagram of the structure of the power equipment operation device based on dynamic baseline provided by the present invention.

[0025] Figure label: 100. Historical data module; 200. Current regression curve module; 300. Iterative regression curve module; 400. Fault warning module; 500. Fault handling module; 810. Processor; 820. Communication interface; 830. Memory; 840. Communication bus. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention. The following embodiments are used to illustrate this invention but cannot be used to limit the scope of this invention.

[0027] In the description of the embodiments of the present invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of the present invention based on the specific circumstances.

[0028] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0029] The following is combined with Figures 1 to 3 Specific embodiments of the present invention are described below. Figure 1 This is a flowchart illustrating the power equipment operation method based on dynamic baseline provided by the present invention, including: S1: Identify the target vessel, obtain the historical operating data of the target vessel, and select the first historical data and the second historical data from the historical operating data; Furthermore, the objective of this stage is to acquire historical data, thereby selecting the first historical data and the second historical data. Step S1 further includes: S11: Determine the target vessel and its historical operating cycle, acquire the operating data of the target vessel within the historical operating cycle, and perform data cleaning to obtain the historical operating data; S12: Perform correlation analysis on the historical operating data to obtain data correlation, take the output power of the target ship's power system as the first historical data, and select the second historical data related to the first historical data according to the data correlation.

[0030] The specific implementation method for the above steps in this embodiment is as follows: First, the target vessel needs to be identified. Then, for the target vessel's propulsion system, a time period for acquiring historical operational data is determined as the historical operational cycle. Subsequently, sensors deployed on the vessel's propulsion equipment continuously collect operational data within the historical operational cycle. This data is then cleaned and aligned to obtain the historical operational data. In this embodiment, the sensors include at least one of the following: a temperature sensor, a pressure sensor, a vibration sensor, a voltage sensor, and a current sensor. Data cleaning includes removing outliers; data alignment specifically involves unifying the timestamps of different data sets.

[0031] Here, the isolated forest method is used to remove outliers. This involves determining the root node and calculating the outlier score *s* for each data point, then removing data with an outlier score exceeding a preset threshold. The outlier score is calculated as follows: Where h(x) is the path length from the root node to the leaf node containing sample x. Let be the average path length of a sample across multiple isolated trees derived from the root node, and let c(n) be the average path length of n data points, with the following: The average path length H(n-1) of the n-1 data points is calculated as follows: Where γ is the Euler-Marcheroni constant.

[0032] After obtaining historical operating data, it is necessary to analyze the correlation between the collected historical operating data and the output power of the target ship's power system. The output power of the target ship's power system is used as the first historical data, and the historical data with a high correlation to the output power of the target ship's power system is used as the second historical data. For example, the second historical data could be the exhaust gas outlet temperature of the main engine turbocharger, the main engine cylinder combustion pressure, the average cylinder scavenging pressure, the average cylinder scavenging temperature, the air cooler differential pressure, the rotational speed of the centrifugal equipment in the fuel treatment equipment, and the temperature of the fuel heating device in the fuel treatment equipment.

[0033] S2: Determine the data fitting method, fit the first historical data and the second historical data using the data fitting method to obtain multiple initial regression curves, calculate the fitting evaluation parameters of the initial regression curves, and select the current regression curve based on the fitting evaluation parameters; Furthermore, the objective of this stage is to determine the data fitting method, thereby obtaining multiple initial regression curves through fitting, calculating the fitting evaluation parameters of the initial regression curves, and selecting the current regression curve. Specifically, step S2 further includes: S21: Determine the data fitting method including the multinomial regression algorithm, the natural cubic spline regression algorithm, and the kernel ridge regression algorithm; S22: Each data fitting method fits the first historical data and the second historical data respectively to obtain their respective initial regression curves; S23: Calculate the root mean square error, average determination error, and coefficient of determination for each initial regression curve; perform a weighted summation of the root mean square error, average determination error, and coefficient of determination to obtain the fitting evaluation parameters; and select the current regression curve based on the fitting evaluation parameters.

[0034] The specific implementation method for the above steps in this embodiment is as follows: First, the data fitting method needs to be determined. In this embodiment, the data fitting methods include multinomial regression, natural cubic spline regression, and kernel ridge regression. Then, a scatter plot is drawn with the first historical data as the x-axis and the selected second historical data as the y-axis. Each data fitting method is used to fit the scatter plot in turn to obtain the curves obtained by each fitting method, thus obtaining the initial regression curves for each data fitting method.

[0035] Then, the root mean square error (RMSE), mean error of determination (MAE), and coefficient of determination (R²) for each initial regression curve were calculated. 1 The calculation method is as follows: 1-R Where N is the number of sampling points on the initial regression curve. Let be the actual value of the second historical data corresponding to the i-th sampling point on the initial regression curve. Let R be the fitted value of the second historical data corresponding to the i-th sampling point on the initial regression curve, and R be an intermediate determining parameter. The average value of the selected second historical data is used. Then, the root mean square error, average decision error, and coefficient of determination are weighted and summed to obtain the fitting evaluation parameters. The initial regression curve with the smallest fitting evaluation parameters is then used as the current regression curve.

[0036] S3: Obtain the refit trigger parameters, obtain updated data based on the refit trigger parameters, update the current regression curve with the updated data, and obtain the iterative regression curve; Furthermore, the objective of this stage is to obtain updated data based on the refit trigger parameters, thereby updating the current regression curve and obtaining an iterative regression curve. Specifically, step S3 further includes: S31: Detect the equipment maintenance status to obtain the refitting trigger parameter; wherein, after the equipment maintenance is completed, the refitting trigger parameter is set to 1, otherwise it is set to 0; S32: When the refitting trigger parameter is set to 1, the operation data of the target ship equipment after maintenance is obtained as the updated data, and the current regression curve is updated by the updated data to obtain the iterative regression curve; otherwise, the current regression curve is used as the iterative regression curve.

[0037] The specific implementation method for the above steps in this embodiment is as follows: Marine diesel engines use heavy oil as fuel, so they require frequent filter replacement and lubrication. Therefore, the maintenance status of the equipment needs to be checked first. When the equipment maintenance is completed, or after the equipment is replaced or repaired, the refit trigger parameter is set to 1; otherwise, it is set to 0. Then, when the refit trigger parameter is set to 1, the operation data after the maintenance of the target ship equipment is obtained again using the method of obtaining historical operation data in step S1 as the updated data, and the updated data is used to refit, thereby updating the current regression curve and obtaining a new iterative regression curve. Otherwise, the current regression curve is used as the iterative regression curve.

[0038] S4: Obtain the deviation index based on the current regression curve and the iterative regression curve, obtain the deviation warning indication based on the deviation index, acquire the current operating data, and obtain the fault warning through the deviation warning indication, the current operating data, and the iterative regression curve; Furthermore, the objective of this stage is to obtain the deviation index and current operating data, thereby generating a fault warning. Specifically, step S4 further includes: S41: Select benchmark update data, obtain the current curve prediction value corresponding to the benchmark update data on the current regression curve, and obtain the iterative curve prediction value corresponding to the benchmark update data on the iterative regression curve; S42: Obtain the deviation index based on the predicted value of the iterative curve and the predicted value of the current curve, obtain the deviation warning indication based on the deviation index, acquire the current operating data, obtain the fault indication value based on the current operating data and the iterative regression curve, and obtain the fault warning through the deviation warning indication and the fault indication value.

[0039] The specific implementation method for the above steps in this embodiment is as follows: First, a value needs to be selected on the x-axis of the current regression curve and the iterative regression curve as the baseline update data. Then, the value of the y-axis corresponding to the baseline update data is obtained on the current regression curve as the current curve prediction value, and the value of the y-axis corresponding to the baseline update data is obtained on the iterative regression curve as the iterative curve prediction value.

[0040] Next, the deviation index is obtained based on the predicted value of the iterative curve and the current predicted value. Here, it is necessary to calculate the predicted value of the iterative curve. and current curve prediction value Deviation index between : Using the deviation index as the target deviation index, if multiple maintenance and updates have been performed on the equipment, resulting in multiple iterative regression curves, the median of the deviation indices from these curves is taken as the target deviation index. The target deviation index determines the trend of its change. If multiple target deviation indices exhibit a stable trend over a prolonged period—for example, if the target deviation index is consistently positive and continuously increasing—then the marine propulsion system is considered to have experienced performance degradation and deterioration due to continuous operation. In this case, the deviation warning indicator is set to 1. If no stable deviation index is observed, the deviation warning indicator is set to 0. The equipment experiencing performance degradation and deterioration can be identified based on the data source corresponding to the iterative regression curves associated with the deviation warning indicators and the ordinate values ​​of the current regression curves.

[0041] In addition, it is necessary to use the current data corresponding to the value of the vertical axis of the iterative regression curve as the current operating data Y, obtain the current operating data value of the target ship's power equipment during operation and its corresponding power output value during operation, use the power output value as the real-time power value, and obtain the vertical axis value corresponding to the real-time power value on the iterative regression curve. Thus, the actual data drift parameter DI is calculated: If the actual data drift parameter exceeds the pre-determined confidence interval, a fault is considered to be possible, resulting in a fault indication value of 1; otherwise, it is set to 0. Here, multiple second historical data sets can exist, each with a corresponding iterative regression curve, thus generating multiple corresponding fault indication values. Based on the type of current operating data corresponding to the iterative regression curve where the fault indication value is 1, and the value of the actual data drift parameter, the faulty device and the type of fault can be determined using a pre-defined fault knowledge graph. In this way, fault warnings can be obtained through deviation warning indicators and fault indication values. A fault warning is generated when the deviation warning indicator is 1 or when any of the fault indication values ​​is 1. The fault warning includes not only a notification of a fault occurrence but also the type of fault identified above, as well as an indication of the faulty or degraded / deteriorated device.

[0042] S5: Obtain the sludge generation amount, determine the fault handling plan, select the fault handling scheme from the fault handling plan based on the fault warning and sludge generation amount, and control the fuel processing equipment and fuel oil circuit of the power equipment through the fault handling scheme, thereby completing the control of the power equipment.

[0043] Furthermore, the objective of this stage is to determine the contingency plan for handling failures, and then select a failure handling solution from the plan to control the fuel processing equipment and fuel lines. Specifically, step S5 further includes: S51: Determine the sludge monitoring time interval, obtain the amount of sludge generated by the power system of the target ship within the sludge monitoring time interval, and obtain the amount of sludge generated; S52: Determine a fault handling plan including a first fault handling plan and a second fault handling plan, wherein the first fault handling plan controls the fuel processing equipment and the second fault handling plan controls the fuel oil circuit. S53: When the amount of sludge generated exceeds the preset sludge generation threshold and the fault warning indication is faultless, the first fault handling plan shall be adopted first. If the amount of sludge generated in the next sludge monitoring time interval still exceeds the sludge generation threshold, the first fault handling plan and the second fault handling plan shall be adopted simultaneously. When a fault warning indicates that the fuel processing equipment has malfunctioned, the second fault handling plan shall be implemented. When a fault warning indicates that the power equipment has malfunctioned and the amount of sludge generated has not exceeded the preset sludge generation threshold, the first fault handling plan shall be adopted. When the fault warning indicates that a fault still exists, the fuel delivery amount shall be reduced while maintaining the first fault handling plan. When a fault warning indicates that the power equipment has malfunctioned and the amount of sludge generated exceeds the preset sludge generation threshold, both the first fault handling plan and the second fault handling plan will be implemented simultaneously.

[0044] In step S52, the first fault handling plan is to increase the rotation speed of the centrifuge in the fuel processing equipment and increase the temperature of the heating tube. The second fault handling plan is to determine the alternative fuel tank, obtain the alternative fuel in the alternative fuel tank, mix the alternative fuel with the existing fuel in the fuel line, and gradually increase the proportion of the alternative fuel in the fuel delivered to the power equipment.

[0045] The specific implementation method for the above steps in this embodiment is as follows: Marine diesel engines generate a significant amount of sludge during operation because they use heavy oil as fuel. First, a time interval needs to be determined as the sludge monitoring time interval. Then, the amount of sludge generated by the target ship's power system within the sludge monitoring time interval is obtained, thus determining the sludge generation amount.

[0046] With the increasing automation of modern large ships, the number of crew members on board is decreasing, leading to a shortage of manpower. This means that unless a direct failure occurs, minor or potential malfunctions in the ship's power equipment may be difficult to address promptly. Therefore, the power equipment needs to automatically adjust its operating status to prevent these minor or potential malfunctions from escalating into major problems within a short period, thus buying time for maintenance personnel to troubleshoot or resolve the issues. For this reason, it is necessary to develop a fault handling plan that includes a first fault handling plan and a second fault handling plan. The first plan controls the fuel handling equipment, while the second plan controls the fuel oil circuit.

[0047] Specifically, before being fed into large marine diesel engines as fuel, heavy oil, being highly viscous and containing numerous impurities, requires pretreatment by fuel processing equipment. This equipment includes heating devices to liquefy the heavy oil and centrifugal devices to remove contaminants. The heavy oil needs to be heated to a liquid state before centrifugation and filtration before use. The primary contingency plan for the fuel processing equipment is to increase the centrifugal speed and the heating element temperature. Furthermore, the presence of numerous impurities and contaminants in the heavy oil can further exacerbate malfunctions in the large marine diesel engine, leading to continuous performance degradation through piston carbon buildup and the formation of corrosive sulfides. Therefore, as a countermeasure against failure and degradation, it is also necessary to prepare high-purity fuel as alternative fuel and add it to the alternative fuel tank. The second failure handling plan for the fuel line is to identify the alternative fuel tank, obtain the alternative fuel in the alternative fuel tank, mix the alternative fuel with the existing fuel in the fuel line, and gradually increase the proportion of alternative fuel in the fuel delivered to the power equipment.

[0048] Subsequently, when the sludge generation exceeds the preset sludge generation threshold and the fault warning indicator shows no fault, it indicates that the cleanliness of the fuel entering the marine large diesel engine is low. Although no fault occurs at this time, it will lead to an increase in the failure rate of the marine diesel engine and cause engine carbon deposits, resulting in performance degradation. Therefore, the first fault handling plan needs to be implemented to improve the cleanliness of the fuel entering the marine large diesel engine. If the sludge generation still exceeds the sludge generation threshold in the next sludge monitoring time interval, both the first and second fault handling plans will be implemented simultaneously to reduce the probability of fault occurrence.

[0049] When a fault warning indicates that the fuel processing equipment has malfunctioned, the fuel processing equipment's fuel processing capacity will decrease, resulting in a reduction in the fuel purification capacity. In order to ensure the cleanliness of the fuel entering the marine large diesel engine and reduce the load on the fuel processing equipment to avoid direct damage to the fuel processing equipment, a second fault handling plan can be adopted. At the same time, since the backup fuel has a higher cleanliness, the operating parameters of the fuel processing equipment can be appropriately reduced to prevent the fault of the fuel processing equipment from worsening.

[0050] When a fault warning indicates a malfunction in the power equipment, especially a decline or degradation in its performance, one of the main reasons for performance degradation or malfunction in large marine diesel engines is insufficient fuel cleanliness, leading to piston carbon buildup or impurity accumulation. If the sludge generation does not exceed a preset threshold, it indicates that there is no problem with the fuel processing equipment or the fuel entering it. In this case, the first fault handling plan should be implemented to improve the cleanliness of the fuel entering the large marine diesel engine. This can mitigate carbon buildup, detonation, and the formation of corrosive sulfides, effectively curbing the performance degradation of the large marine diesel engine and preventing further deterioration of the fault. Subsequently, the fault warning indication should be continuously monitored. If the fault warning indication persists for a period of time after the first fault handling plan is implemented, it indicates that simply improving fuel cleanliness is no longer sufficient to solve the problem. To prevent further deterioration, while maintaining the first fault handling plan, the fuel delivery rate should be reduced to decrease power output, thereby reducing the burden on the power equipment, preventing further deterioration of the fault, and buying time for manual maintenance. Furthermore, when a fault warning indicates that the performance of the power equipment is deteriorating and declining, and the amount of sludge generated exceeds the preset sludge generation threshold, the piston carbon buildup caused by poor fuel purity will directly lead to the continuous deterioration and decline of the power equipment's performance, and may even cause damage. It is necessary to simultaneously implement both the first and second fault handling plans to slow down the rate of degradation and decline of the power equipment, buying time for manual handling and cleaning. This completes the control of the power equipment.

[0051] The following describes the dynamic baseline-based power equipment operation device provided by the present invention. The dynamic baseline-based power equipment operation device described below and the dynamic baseline-based power equipment operation method described above can be referred to in correspondence.

[0052] Figure 2 A schematic diagram of the structure of a power equipment operation system based on a dynamic baseline is shown, such as... Figure 2 As shown, the method for performing the dynamic baseline-based power equipment operation method described above includes: Historical data module 100: used to identify the target vessel, acquire the historical operating data of the target vessel, and select the first historical data and the second historical data from the historical operating data; Current regression curve module 200: Used to determine the data fitting method, fit the first historical data and the second historical data using the data fitting method to obtain multiple initial regression curves, calculate the fitting evaluation parameters of the initial regression curves, and select the current regression curve based on the fitting evaluation parameters; Iterative Regression Curve Module 300: Used to obtain refit trigger parameters, obtain updated data based on refit trigger parameters, update the current regression curve with the updated data, and obtain the iterative regression curve; Fault warning module 400: used to obtain the deviation index based on the current regression curve and the iterative regression curve, obtain the deviation warning indication based on the deviation index, obtain the current operating data, and obtain fault warning through the deviation warning indication, the current operating data, and the iterative regression curve; Fault handling module 500: It is used to obtain the amount of sludge generated, determine the fault handling plan, select a fault handling scheme from the fault handling plan based on the fault warning and the amount of sludge generated, and control the fuel processing equipment and fuel oil circuit of the power equipment through the fault handling scheme, thereby completing the control of the power equipment.

[0053] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other via the communication bus 840. The processor 810 can call a computer program in the memory 830 to execute a dynamic baseline-based power equipment operation method, which includes: S1: Identify the target vessel, obtain the historical operating data of the target vessel, and select the first historical data and the second historical data from the historical operating data; S2: Determine the data fitting method, fit the first historical data and the second historical data using the data fitting method to obtain multiple initial regression curves, calculate the fitting evaluation parameters of the initial regression curves, and select the current regression curve based on the fitting evaluation parameters; S3: Obtain the refit trigger parameters, obtain updated data based on the refit trigger parameters, update the current regression curve with the updated data, and obtain the iterative regression curve; S4: Obtain the deviation index based on the current regression curve and the iterative regression curve, obtain the deviation warning indication based on the deviation index, acquire the current operating data, and obtain the fault warning through the deviation warning indication, the current operating data, and the iterative regression curve; S5: Obtain the sludge generation amount, determine the fault handling plan, select the fault handling scheme from the fault handling plan based on the fault warning and sludge generation amount, and control the fuel processing equipment and fuel oil circuit of the power equipment through the fault handling scheme, thereby completing the control of the power equipment.

[0054] Furthermore, when the computer program in the aforementioned memory 830 can be implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0055] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the above-described dynamic baseline-based power equipment operation methods, the method comprising: S1: Identify the target vessel, obtain the historical operating data of the target vessel, and select the first historical data and the second historical data from the historical operating data; S2: Determine the data fitting method, fit the first historical data and the second historical data using the data fitting method to obtain multiple initial regression curves, calculate the fitting evaluation parameters of the initial regression curves, and select the current regression curve based on the fitting evaluation parameters; S3: Obtain the refit trigger parameters, obtain updated data based on the refit trigger parameters, update the current regression curve with the updated data, and obtain the iterative regression curve; S4: Obtain the deviation index based on the current regression curve and the iterative regression curve, obtain the deviation warning indication based on the deviation index, acquire the current operating data, and obtain the fault warning through the deviation warning indication, the current operating data, and the iterative regression curve; S5: Obtain the sludge generation amount, determine the fault handling plan, select the fault handling scheme from the fault handling plan based on the fault warning and sludge generation amount, and control the fuel processing equipment and fuel oil circuit of the power equipment through the fault handling scheme, thereby completing the control of the power equipment.

[0056] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0057] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for operating power equipment based on a dynamic baseline, characterized in that, include: S1: Identify the target vessel, obtain its historical operating data, and select the first historical data and the second historical data from the historical operating data; Step S1 further includes: S11: Determine the target vessel and its historical operating cycle, acquire the operating data of the target vessel within the historical operating cycle, and perform data cleaning to obtain the historical operating data; S12: Perform correlation analysis on the historical operating data to obtain data correlation, take the output power of the target ship's power system as the first historical data, and select the second historical data related to the first historical data according to the data correlation; S2: Determine the data fitting method, fit the first historical data and the second historical data using the data fitting method to obtain multiple initial regression curves, calculate the fitting evaluation parameters of the initial regression curves, and select the current regression curve based on the fitting evaluation parameters; S3: Obtain the refit trigger parameters, obtain updated data based on the refit trigger parameters, update the current regression curve with the updated data, and obtain the iterative regression curve; S4: Obtain the deviation index based on the current regression curve and the iterative regression curve, obtain the deviation warning indication based on the deviation index, acquire the current operating data, and obtain the fault warning through the deviation warning indication, the current operating data, and the iterative regression curve; Step S4 further includes: S41: Select benchmark update data, obtain the current curve prediction value corresponding to the benchmark update data on the current regression curve, and obtain the iterative curve prediction value corresponding to the benchmark update data on the iterative regression curve; S42: Obtain the deviation index based on the predicted value of the iterative curve and the predicted value of the current curve, obtain the deviation warning indication based on the deviation index, acquire the current operating data, obtain the fault indication value based on the current operating data and the iterative regression curve, and obtain the fault warning through the deviation warning indication and the fault indication value; S5: Obtain the sludge generation amount, determine the fault handling plan, select the fault handling scheme from the fault handling plan based on the fault warning and sludge generation amount, and control the fuel processing equipment and fuel oil circuit of the power equipment through the fault handling scheme, thereby completing the control of the power equipment.

2. The power equipment operation method based on dynamic baseline according to claim 1, characterized in that, Step S2 further includes: S21: Determine the data fitting method including the multinomial regression algorithm, the natural cubic spline regression algorithm, and the kernel ridge regression algorithm; S22: Each data fitting method fits the first historical data and the second historical data respectively to obtain their respective initial regression curves; S23: Calculate the root mean square error, average determination error, and coefficient of determination for each initial regression curve; perform a weighted summation of the root mean square error, average determination error, and coefficient of determination to obtain the fitting evaluation parameters; and select the current regression curve based on the fitting evaluation parameters.

3. The power equipment operation method based on dynamic baseline according to claim 1, characterized in that, Step S3 further includes: S31: Detect the equipment maintenance status to obtain the refitting trigger parameter; wherein, after the equipment maintenance is completed, the refitting trigger parameter is set to 1, otherwise it is set to 0; S32: When the refitting trigger parameter is set to 1, the operation data of the target ship equipment after maintenance is obtained as the updated data, and the current regression curve is updated by the updated data to obtain the iterative regression curve; otherwise, the current regression curve is used as the iterative regression curve.

4. The power equipment operation method based on dynamic baseline according to claim 1, characterized in that, Step S5 further includes: S51: Determine the sludge monitoring time interval, obtain the amount of sludge generated by the power system of the target ship within the sludge monitoring time interval, and obtain the amount of sludge generated; S52: Determine a fault handling plan including a first fault handling plan and a second fault handling plan, wherein the first fault handling plan controls the fuel processing equipment and the second fault handling plan controls the fuel oil circuit. S53: When the amount of sludge generated exceeds the preset sludge generation threshold and the fault warning indication is faultless, the first fault handling plan shall be adopted first. If the amount of sludge generated in the next sludge monitoring time interval still exceeds the sludge generation threshold, the first fault handling plan and the second fault handling plan shall be adopted simultaneously. When a fault warning indicates that the fuel processing equipment has malfunctioned, the second fault handling plan shall be implemented. When a fault warning indicates that the power equipment has malfunctioned and the amount of sludge generated has not exceeded the preset sludge generation threshold, the first fault handling plan shall be adopted. When the fault warning indicates that a fault still exists, the fuel delivery amount shall be reduced while maintaining the first fault handling plan. When a fault warning indicates that the power equipment has malfunctioned and the amount of sludge generated exceeds the preset sludge generation threshold, both the first fault handling plan and the second fault handling plan will be implemented simultaneously.

5. The power equipment operation method based on dynamic baseline according to claim 4, characterized in that, In step S52, the first fault handling plan is to increase the rotation speed of the centrifuge in the fuel processing equipment and increase the temperature of the heating tube. The second fault handling plan is to determine the alternative fuel tank, obtain the alternative fuel in the alternative fuel tank, mix the alternative fuel with the existing fuel in the fuel line, and gradually increase the proportion of the alternative fuel in the fuel delivered to the power equipment.

6. A dynamic baseline-based power equipment operation system, used to execute the dynamic baseline-based power equipment operation method as described in any one of claims 1 to 5, characterized in that, include: Historical data module: used to identify the target vessel, obtain the target vessel's historical operating data, and select the first historical data and the second historical data from the historical operating data; Current regression curve module: used to determine the data fitting method, fit the first historical data and the second historical data using the data fitting method to obtain multiple initial regression curves, calculate the fitting evaluation parameters of the initial regression curves, and select the current regression curve based on the fitting evaluation parameters; Iterative Regression Curve Module: Used to obtain refit trigger parameters, obtain updated data based on refit trigger parameters, update the current regression curve with the updated data, and obtain the iterative regression curve; Fault warning module: used to obtain the deviation index based on the current regression curve and the iterative regression curve, obtain the deviation warning indication based on the deviation index, obtain the current operating data, and obtain fault warning through the deviation warning indication, the current operating data, and the iterative regression curve; Fault handling module: Used to obtain sludge generation amount, determine fault handling plan, select fault handling scheme from the fault handling plan based on fault warning and sludge generation amount, and control the fuel handling equipment and fuel oil circuit of power equipment through fault handling scheme, thereby completing the control of power equipment.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the power equipment operation method based on dynamic baseline as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the dynamic baseline-based power equipment operation method as described in any one of claims 1 to 5.

Images