Main engine health state determination method and device, ship power equipment and medium

Abstract

The invention discloses a host health state determination method and device, ship power equipment and a medium, and relates to the technical field of ships. The method comprises the steps that working condition characteristic data and host operation data of the ship power equipment are obtained, and the host operation data comprise component operation data corresponding to a plurality of host components; analyzing the working condition characteristic data to obtain the current operation working condition of the ship power equipment; determining health assessment models corresponding to the plurality of host components under the current operation condition; and inputting the component operation data of each host component into the corresponding health assessment model to obtain the health state of each host component. The technical scheme provided by the invention can adapt to various operation conditions, can improve the accuracy of host health assessment, and can effectively guarantee the safety of ship navigation and equipment operation.

Description

Technical Field

[0001] This application relates to the field of marine technology, and in particular to a method, apparatus, marine power equipment and medium for determining the health status of a main engine. Background Technology

[0002] As the core of a ship's power system, the health assessment of its main engine is crucial for navigational safety. Existing technologies are mostly based on assessments under stable main engine load conditions, making it difficult to adapt to dynamic phases such as acceleration and deceleration. Furthermore, they fail to fully consider the influence of external conditions such as fuel quality differences, leading to parameter lags or characteristic deviations, resulting in inaccurate assessment results, missed alarms, or false alarms. Traditional assessments rely on crew experience, periodic inspections, and fixed maintenance schedules, which have limitations such as delayed fault detection, subjective results, low efficiency, and uneconomical maintenance, easily causing secondary damage or wasted resources. With the development of IoT, big data, and AI technologies, main engine health assessment is shifting towards predictive maintenance. However, mainstream data-driven methods, which directly train models using the entire dataset, are prone to insufficient model accuracy, failing to meet the precise assessment needs under complex operating conditions. Therefore, there is an urgent need for a main engine health status determination scheme adaptable to multiple operating conditions to improve the accuracy of main engine health assessments and ensure the safety of ship navigation and equipment operation. Summary of the Invention

[0003] This application provides a method, apparatus, marine power equipment, and medium for determining the health status of a main engine, which can be adapted to various operating conditions, improve the accuracy of main engine health assessment, and effectively ensure the safety of ship navigation and equipment operation.

[0004] Firstly, this application provides a method for determining the health status of a host, the method comprising:

[0005] Acquire the operating condition characteristic data of the ship's power equipment and the main engine operation data, wherein the main engine operation data includes component operation data corresponding to multiple main engine components;

[0006] By analyzing the operating condition characteristic data, the current operating condition of the ship's power equipment can be obtained;

[0007] Determine the health assessment model corresponding to each of the multiple host components under the current operating conditions;

[0008] The component operation data of each host component is input into the corresponding health assessment model to obtain the health status of each host component.

[0009] Furthermore, the step of analyzing the operating condition feature data to obtain the current operating condition of the ship's power equipment includes: acquiring a pre-trained operating condition identification model, which is trained on operating condition datasets under different external conditions for multiple main engine operation stages based on the DBSCAN algorithm; and inputting the operating condition feature data into the operating condition identification model to obtain the current operating condition.

[0010] Furthermore, the ship's power equipment includes multiple operating conditions, with each operating condition corresponding to the operation of a main engine operating phase under a set of external conditions; the main engine operating phase includes at least the ship's motor navigation main engine acceleration phase, ship's motor navigation main engine deceleration phase, main engine program acceleration phase, main engine program deceleration phase, main engine stable operation phase, and main engine shutdown phase; the external conditions include at least one type of fuel, one type of exhaust gas bypass valve opening, one type of turbocharger air inlet temperature, one type of low-temperature cooling water temperature value, and one type of fuel compensation value, and a set of external conditions is a combination of at least one of the external conditions.

[0011] Furthermore, the main unit includes at least a cylinder, piston, oil head, turbocharger, air cooler, friction assembly, and scavenging system.

[0012] Furthermore, before inputting the component operation data of each host component into the corresponding health assessment model to obtain the health status of each host component, the method further includes: determining whether to update all the health assessment models; if the models are updated, then updating all the health assessment models to obtain an updated health assessment model; correspondingly, inputting the component operation data of each host component into the corresponding health assessment model to obtain the health status of each host component includes: inputting the component operation data of each host component into the corresponding updated health assessment model to obtain the health status of each host component.

[0013] Furthermore, determining whether to update all of the health assessment models includes: determining the duration between the current time and the most recent model update time; judging whether the health assessment model meets the initial screening conditions for model update based on the duration; if the initial screening conditions for model update are met, calculating the deviation of the component operation data of each host component from the corresponding data baseline, and obtaining the first health score of the corresponding host component based on the deviation; if the average value of the first health score is lower than a set threshold, determining to update all of the health assessment models.

[0014] Furthermore, determining the deviation of the component operating data of each host component from the corresponding data baseline includes: acquiring historical operating data of each host component; performing data fitting processing on the historical operating data to obtain the data baseline of the corresponding host component; calculating the distance between each data point in the historical operating data and the data baseline; determining the health warning value of the corresponding host component based on the distance; and calculating the deviation of the corresponding host component based on the component operating data of each host component and the corresponding health warning value.

[0015] Secondly, this application provides a host health status determination device, the device comprising:

[0016] The data acquisition module is used to acquire the operating condition characteristic data of the ship's power equipment and the main engine operation data, wherein the main engine operation data includes the component operation data corresponding to multiple main engine components;

[0017] The operating condition determination module is used to analyze the operating condition characteristic data to obtain the current operating condition of the ship's power equipment.

[0018] The model determination module is used to determine the health assessment model corresponding to each of the multiple host components under the current operating conditions.

[0019] The health analysis module is used to input the component operation data of each host component into the corresponding health assessment model to obtain the health status of each host component.

[0020] Thirdly, this application provides a marine propulsion system, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the host health status determination method described in any embodiment of this application.

[0021] Fourthly, this application provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the host health status determination method described in any embodiment of this application.

[0022] To address the shortcomings of existing technologies, this application provides a method for determining the health status of a main engine. This method offers the following advantages: First, it acquires operating condition characteristic data and main engine operating data. Then, it analyzes the current operating condition of the ship's power equipment using multi-dimensional operating condition characteristics. This solves the problem of existing technologies neglecting dynamic stages and external conditions, avoiding missed or false alarms caused by parameter lag or feature deviations. Furthermore, by matching a dedicated health assessment model to each main engine component under the current operating condition, replacing the general model trained with full data, it significantly improves model adaptability and assessment accuracy, meeting the precise assessment needs under complex operating conditions. This application can adapt to various operating conditions, improve the accuracy of main engine health assessment, eliminate reliance on human experience, and overcome the limitations of traditional assessment methods, such as delayed fault detection, subjective results, and low efficiency. This effectively ensures the safety of ship navigation and equipment operation, providing reliable technical support for the implementation of predictive maintenance.

[0023] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the processor of the host health status determination device, or it may be packaged separately from the processor of the host health status determination device; this application does not impose any limitations on this.

[0024] The descriptions of the second, third, and fourth aspects in this application can be referenced to the detailed description of the first aspect; and the beneficial effects described in the second, third, and fourth aspects can be referenced to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0025] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description.

[0026] It is understood that before using the technical solutions disclosed in the various embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1This is a first flowchart illustrating a method for determining the health status of a host provided in an embodiment of this application;

[0029] Figure 2 A schematic diagram illustrating multiple operating conditions provided in the embodiments of this application;

[0030] Figure 3 This is a second flowchart illustrating a method for determining the health status of a host provided in an embodiment of this application;

[0031] Figure 4 This is a schematic diagram of the structure of a host health status determination device provided in an embodiment of this application;

[0032] Figure 5 This is a block diagram of a ship propulsion system used to implement a method for determining the health status of a main engine in an embodiment of this application. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0034] The terms "first," "second," "target," and "original," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in sequences other than those illustrated or described herein. Furthermore, the terms "comprising," "having," and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0035] It should be noted that the information collected in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant countries and regions, necessary confidentiality measures have been taken, and it does not violate public order and good morals. Corresponding operation portals are provided for users to choose to authorize or refuse.

[0036] Figure 1This is a first flowchart illustrating a method for determining the health status of a main engine unit according to an embodiment of this application. This embodiment is applicable to scenarios where the operating data of each main engine component in a ship's power equipment is combined with the current operating condition of the ship's power equipment to determine the health status of each main engine component. The method for determining the health status of a main engine unit provided in this embodiment can be executed by the device for determining the health status of a main engine unit provided in this embodiment. This device can be implemented through software and / or hardware and integrated into the electronic device executing this method. Preferably, the electronic device in this embodiment can be a ship's power equipment.

[0037] See Figure 1 The method in this embodiment includes, but is not limited to, the following steps:

[0038] S110. Obtain the operating condition characteristic data of the ship's power equipment and the main engine operation data.

[0039] The host operating data can be dynamic parameters reflecting the real-time operating status of the host. The host operating data includes component operating data corresponding to multiple host components. Host components include at least cylinders, pistons, oil heads, turbochargers, air coolers, friction components, and scavenging systems. Operating condition characteristic data can be characteristic parameters used to identify the operating status of the host.

[0040] In this embodiment, the data acquisition module in the ship's power equipment collects second-level operating condition characteristic data and main engine operation data through a standard communication protocol. The operating condition characteristic data includes at least the main engine speed, main engine load, main engine fuel inlet temperature, exhaust bypass valve opening, fuel compensation value, and ground speed. The main engine operation data includes at least the cylinder liner cooling water outlet temperature corresponding to the cylinder, the cylinder liner temperature corresponding to the piston, the cylinder combustion pressure corresponding to the oil head, the turbocharger speed corresponding to the turbocharger, the air outlet temperature of the air cooler corresponding to the air cooler, the main bearing lubricating oil temperature corresponding to the friction components, the main engine scavenging air temperature corresponding to the scavenging system, and the main engine hydraulic oil system pressure.

[0041] Optionally, if a ship's power equipment lacks main engine load, the main engine throttle setting can be used instead.

[0042] Optionally, the communication protocol can be Message Queuing Telemetry Transport (MQTT), Modbus Transmission Control Protocol (MODBUS TCP), or Transmission Control Protocol / Internet Protocol (TCP / IP), etc.

[0043] S120. Analyze the operating condition characteristic data to obtain the current operating condition of the ship's power equipment.

[0044] The ship's power equipment includes multiple operating conditions, with each operating condition corresponding to a main engine operating phase under a set of external conditions. The main engine operating phase includes at least the main engine acceleration phase for ship maneuvering, the main engine deceleration phase for ship maneuvering, the main engine programmed acceleration phase, the main engine programmed deceleration phase, the main engine stable operation phase, and the main engine shutdown phase. External conditions include at least one type of fuel, one exhaust gas bypass valve opening degree, one turbocharger air inlet temperature, one cryogenic cooling water temperature value, and one fuel compensation value. A set of external conditions is a combination of at least one of these external conditions.

[0045] like Figure 2 The diagram illustrates multiple operating conditions provided in the embodiments of this application. The diagram shows m operating conditions obtained by arbitrarily combining multiple host operating stages and multiple sets of external conditions. The diagram only illustrates a case where one set of external conditions includes a type of oil, an exhaust gas bypass valve opening, a turbocharger air inlet temperature, a low-temperature cooling water temperature, and a fuel compensation value. Of course, a set of external conditions can also include a combination of at least one of the following: a type of oil, an exhaust gas bypass valve opening, a turbocharger air inlet temperature, a low-temperature cooling water temperature, and a fuel compensation value. Among them, the other 1 shown in the figure includes a parameter group (not shown in the figure) that is any combination of light oil and one of the three exhaust gas bypass valve opening values, one of the three turbocharger air inlet temperature values, one of the three low-temperature coolant temperature values, and one of the three fuel compensation values; the other 2 shown in the figure includes a parameter group (not shown in the figure) that is any combination of heavy oil 1 and one of the three exhaust gas bypass valve opening values, one of the three turbocharger air inlet temperature values, one of the three low-temperature coolant temperature values, and one of the three fuel compensation values; the other 3 shown in the figure includes a parameter group (not shown in the figure) that is any combination of heavy oil 2 and one of the three exhaust gas bypass valve opening values, one of the three turbocharger air inlet temperature values, one of the three low-temperature coolant temperature values, and one of the three fuel compensation values.

[0046] Specifically, the analysis of operating condition characteristic data yields the current operating condition of the ship's power equipment, including: acquiring a pre-trained operating condition recognition model; and inputting the operating condition characteristic data into the operating condition recognition model to obtain the current operating condition.

[0047] The operational condition identification model is trained on a dataset of operational conditions under different external conditions across multiple mainframe operating phases using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. The advantages of using the DBSCAN algorithm are threefold: 1) Classifying ship operational conditions is challenging because it may be difficult to accurately predict the number of typical ship operational conditions, or the actual number of operational conditions may change. The DBSCAN algorithm does not require pre-setting the number of operational conditions; it automatically discovers clusters based on data density, which is more realistic, allowing the algorithm to discover natural groupings within the data. 2) If the data for a certain ship operational condition is not spherical but irregularly shaped (e.g., elongated or L-shaped) in the feature space, the DBSCAN algorithm can better handle the complex, non-spherical distribution of operational condition data in multidimensional space. 3) The distribution of data points corresponding to different ship operational conditions can be very complex, and the DBSCAN algorithm can better capture these irregular patterns.

[0048] The following describes the process of identifying the current operating condition using the operating condition identification model:

[0049] The first step is to process the operating condition characteristic data, including: cleaning out-of-range data according to the range of each signal; supplementing missing data by taking the previous value; calculating the minute-level average value for each signal; calculating the standard deviation of the main engine speed within a preset time period (the preset time period can be configured according to actual conditions); and calculating the change value of the main engine speed per minute. After data processing, the characteristic parameters of the operating condition characteristic data are obtained, including: the standard deviation of the main engine speed within the preset time period, the minute-level rate of change of the main engine speed, the minute-level average value of the main engine load (or throttle scale), the minute-level average value of the main engine fuel inlet temperature, the minute-level average value of the exhaust bypass valve opening, the minute-level average value of the fuel compensation value, and the minute-level average value of the ground speed.

[0050] The second step is to use the DBSCAN algorithm to classify operating conditions. Assume the processed sample data is as follows: Where n is the number of samples per minute, and d is the feature dimension; in this embodiment, d=7. The standard deviation of the main unit's rotational speed is preset over a certain period of time; The rate of change of the main unit's rotational speed in minutes; This is the minute-level average of the main unit load (or throttle setting). This represents the minute-level average of the main engine fuel inlet temperature. This represents the minute-level average opening value of the waste gas bypass valve; This represents the minute-level average of the fuel compensation value. The speed is the average speed over ground in minutes. The distance metric used is the weighted Euclidean distance, expressed as follows: (1):

[0051] (1);

[0052] In the formula, For the i-th sample data, For the j-th sample data, for and The weighted Euclidean distance, For the k-th feature of the i-th sample data, For the k-th feature of the j-th sample data, Let d be the weight vector for the k-th feature dimension, where d is the feature dimension. In this embodiment, d = 7.

[0053] DBSCAN hyperparameter used: neighborhood radius Minimum number of neighborhood points Define the neighborhood as .like ,but As the core point; if and As the core point, but ,but These are boundary points; the remaining points are noise points. Starting from any unvisited core point, recursively process... All core points and boundary points within the neighborhood are grouped into the same cluster, forming the clustering result: Each cluster This corresponds to a set of working condition datasets.

[0054] The silhouette coefficient is used as the clustering quality evaluation index, and the objective function is expressed as formula (2):

[0055] (2);

[0056] In the formula, For sample data The profile coefficient, For sample data The average distance to other samples in the same cluster. For sample data The average distance to the nearest neighbor cluster, For sample data The cluster to which the current sample data belongs, i.e. The cluster set to which it is divided. To remove Other clusters besides these are used to compute sample data. The average distance to the nearest neighbor cluster is given by the constraint expressed in formula (3):

[0057] (3);

[0058] The optimization method for the coefficients is as follows: (1) Initialize parameters: Set the initial value of the weight vector. Set the initial value of the neighborhood radius. Set the maximum number of iterations M and the convergence threshold. (2) Iterative optimization process: For the number of iterations , using parameters and Perform DBSCAN clustering to obtain the cluster set. ; Calculate the profile coefficient Update parameters using optimization algorithms such as Differential Evolution (DE). Determine the convergence condition If the convergence condition is met, the iteration is terminated. (3) Output the optimal parameters and return the optimal weight vector. Optimal neighborhood radius .

[0059] S130. Determine the health assessment model corresponding to each of the multiple host components under the current operating conditions.

[0060] In this model, one host component corresponds to one health assessment model under one operating condition. That is, the health assessment model includes two dimensions: different host component types and different operating condition types. Under each operating condition, the same host component corresponds to a different health assessment model. For example, the turbocharger corresponds to health assessment model 1 under operating condition 1, and health assessment model 2 under operating condition 2.

[0061] In this embodiment, a correlation table, namely the operating condition-component-model correlation table, can be pre-configured to record the correspondence between operating conditions, main engine components, and health assessment models. Based on the identified current operating conditions of the ship's power equipment, the operating condition-component-model correlation table is invoked, and the table is queried according to both the current operating condition and the type of main engine component to obtain the corresponding health assessment model. Following this method, the health assessment model corresponding to each main engine component is obtained.

[0062] For example, in the current operating condition of the ship's main engine acceleration phase, the cylinder corresponds to the cylinder wear assessment model under dynamic load, and the turbocharger corresponds to the variable speed turbocharger efficiency assessment model, rather than the general model under stable operating conditions.

[0063] Optionally, depending on the different operating conditions, a suitable machine learning algorithm can be selected from random forest, extreme gradient boosting (XGBOOST), and support vector regression (SVR) to train the model parameters corresponding to each host component.

[0064] Optionally, model training is performed separately for each host component. The model training process is as follows: the preprocessed dataset is divided into a training set, a validation set, and a test set; the selected model is trained using an appropriate machine learning algorithm on the training set, and the model parameters are continuously adjusted through optimization algorithms (such as gradient descent) so that it can learn the patterns in the data; the model performance is evaluated on the validation set, hyperparameter tuning and model selection are performed to avoid overfitting; the model performance is evaluated, and optimization is performed based on the evaluation results.

[0065] S140. Input the component operation data of each host component into the corresponding health assessment model to obtain the health status of each host component.

[0066] In this embodiment, the host operation data includes component operation data corresponding to multiple host components. The component operation data of each host component is input separately into the corresponding health assessment model, and the health status of the corresponding host component is determined based on the model output. The health status can be expressed as a health score, a health level, or other forms.

[0067] The technical solution provided in this embodiment acquires the operating condition characteristic data and main engine operation data of the ship's power equipment; analyzes the operating condition characteristic data to obtain the current operating condition of the ship's power equipment; determines the corresponding health assessment model for each of the multiple main engine components under the current operating condition; and inputs the component operation data of each main engine component into the corresponding health assessment model to obtain the health status of each main engine component. This application first acquires the operating condition characteristic data and main engine operation data, and combines multi-dimensional operating condition characteristic analysis to determine the current operating condition of the ship's power equipment. This solves the problem of existing technologies ignoring dynamic stages and external conditions, avoiding missed alarms or false alarms caused by parameter lag or characteristic deviations. Furthermore, by matching a dedicated health assessment model to each main engine component under the current operating condition, replacing the general model trained with full data, the model adaptability and assessment accuracy are significantly improved, meeting the precise assessment needs under complex operating conditions. This application can adapt to various operating conditions, improve the accuracy of main engine health assessment, eliminate reliance on human experience, and solve the limitations of traditional assessment methods such as delayed fault detection, subjective results, and low efficiency. It effectively ensures the safety of ship navigation and equipment operation, and provides reliable technical support for the implementation of predictive maintenance.

[0068] The host health status determination method provided in the embodiments of this application is further described below. Figure 3 This is a second flowchart illustrating a method for determining the health status of a host, provided in an embodiment of this application. This embodiment optimizes the above embodiments, specifically by providing a detailed explanation of the update and judgment process for the health assessment model.

[0069] See Figure 3 The method in this embodiment includes, but is not limited to, the following steps:

[0070] S210. Determine the duration between the current time and the most recent model update time.

[0071] Because equipment operating parameters are affected by seasonal temperatures, and equipment performance deteriorates over time, the original health assessment model may no longer be suitable for current operating conditions, potentially leading to false alarms and necessitating a model update. However, manually updating the model is time-consuming and cannot accurately determine whether the model has reached the point where an update is necessary; repeated updates in a short period waste manpower. Therefore, this embodiment sets initial screening conditions for model updates and uses health thresholds to comprehensively determine whether an update of the health assessment model is required.

[0072] In this embodiment, the current time is obtained through the time synchronization module of the ship's power system. The model management database is accessed to query the update log table corresponding to the health assessment model, and the timestamp of the most recent model update is obtained. The duration between the current time and the most recent model update time is calculated.

[0073] It should be noted that each model update applies to all health assessment models. Therefore, the model update timestamp is consistent for each health assessment model.

[0074] S220. Determine whether the health assessment model meets the initial screening conditions for model update based on the duration.

[0075] Among them, the initial screening condition for model update can be a preset judgment condition that triggers model update, which is determined by the time dimension (update duration) and is the initial screening criterion for judging whether the model needs to be retrained.

[0076] In this embodiment, for each host component, based on the duration calculated in step S210, the duration threshold (e.g., whether it exceeds 3 months) of the time dimension in the model update initial screening conditions is read. According to the judgment logic of the model update initial screening conditions, it is determined whether the corresponding health assessment model meets the model update initial screening conditions.

[0077] If the initial screening criteria for model updates are not met (e.g., the time between the current time and the most recent model update time does not exceed 3 months), it indicates that the original health assessment model is still applicable to the current condition of the equipment. In this case, it is determined that not all health assessment models need to be updated, and the original health assessment model will continue to be used to perform health assessments on the corresponding host components. If the initial screening criteria for model updates are met, it is necessary to further determine whether the health assessment model needs to be updated based on the health threshold, i.e., proceed to step S230.

[0078] S230. If the initial screening conditions for model update are met, calculate the degree of deviation between the component operation data of each host component and the corresponding data baseline, and obtain the first health score of the corresponding host component based on the degree of deviation.

[0079] In this embodiment, if the initial screening conditions for model updates are met (e.g., the time between the current time and the most recent model update time exceeds 3 months), it is also necessary to further determine whether the health assessment model needs to be updated by using a health threshold. Therefore, the deviation of the component operation data of each host component from the corresponding data baseline is first calculated. After calculating the deviation, the first health score of the corresponding host component is calculated according to a preset calculation method.

[0080] If the average value of the first health score is not lower than the set threshold, it indicates that the original health assessment model is still applicable to the current condition of the equipment. Therefore, it is determined that no model update is needed for all health assessment models, and the original health assessment model will continue to be used to assess the health of the corresponding host components. If the average value of the first health score is lower than the set threshold, it indicates that the original health assessment model is not applicable to the current condition of the equipment. Therefore, it is determined that all health assessment models will be updated, i.e., step S240 will be executed.

[0081] The reason for setting a health threshold in this implementation is that during equipment use, wear and tear or a decrease in adaptability to operating conditions may occur, leading to suboptimal performance. However, if the equipment is healthy, the original health assessment model may no longer be suitable for the current condition of the equipment. Continuing to use the original health assessment model may result in abnormal health assessment results, i.e., misjudgment. Therefore, setting a health threshold can eliminate this situation and avoid misjudging the health status.

[0082] Specifically, determining the deviation of the component operation data of each host component from the corresponding data baseline includes: acquiring historical operation data of each host component; performing data fitting processing on the historical operation data to obtain the data baseline of the corresponding host component; calculating the distance between each data point in the historical operation data and the data baseline; determining the health warning value of the corresponding host component based on the distance; and calculating the deviation of the corresponding host component based on the component operation data and the corresponding health warning value of each host component.

[0083] In this embodiment, for each main engine component, historical operating data is extracted by the ship's power system data storage module according to the main engine component dimension (e.g., cylinder, turbocharger). This data must cover the normal operating data of the main engine component under all operating conditions (including parameters under different external conditions), while filtering outliers and missing data to ensure data integrity. Data fitting algorithms (e.g., linear regression, multinomial fitting) are used to model the preprocessed historical operating data, generating a data baseline for the main engine component. Distance metric algorithms (e.g., Euclidean distance, Mahalanobis distance) are used to calculate the quantified distance between each data point in the historical data and the corresponding data baseline. This distance directly reflects the degree of deviation of a single historical data point from its normal state. After obtaining the distance for each data point, the maximum value of these distances is calculated, and this maximum value is multiplied by a preset coefficient to obtain the health warning value for the main engine component. The current operating data of the main engine component is obtained, and its distance to the data baseline is calculated. Combined with the preset health warning value, data processing is performed to obtain the quantified degree of deviation.

[0084] Among them, the data baseline can refer to the standard benchmark for the change of host component operating data over time or operating conditions under normal health conditions. The data baseline can be expressed as a trend curve, numerical range or statistical model.

[0085] S240. If the average value of the first health score is lower than the set threshold, then it is determined to update the model for all health assessment models.

[0086] In this embodiment, based on the criterion of whether the first health score is lower than a set threshold, it can be ultimately determined whether to update all health assessment models. For changes in the operating characteristics of host components (such as wear and tear, decreased adaptability to operating conditions), an updated health assessment model is obtained after retraining (incremental training or full retraining). Its parameters and algorithms are more closely aligned with the current actual operating state of the host components, and the assessment accuracy is higher than the original health assessment model.

[0087] This embodiment determines whether to update all health assessment models before inputting the component operation data of each host component into the corresponding health assessment model to obtain the health status of each host component. If the models need updating, then all health assessment models are updated to obtain an updated health assessment model. Correspondingly, inputting the component operation data of each host component into the corresponding health assessment model to obtain the health status of each host component includes: inputting the component operation data of each host component into the corresponding updated health assessment model to obtain the health status of each host component. The health status can be expressed as a health score, a health level, or other forms of expression.

[0088] The technical solution provided in this embodiment determines the duration between the current time and the most recent model update time; based on the duration, it determines whether the health assessment model meets the initial screening conditions for model update; if the initial screening conditions are met, it calculates the deviation of the component operation data of each host component from the corresponding data baseline, and obtains the first health score of the corresponding host component based on the deviation; if the average value of the first health score is lower than a set threshold, it determines that all health assessment models need to be updated. This application sets initial screening conditions for model update and health thresholds to comprehensively determine whether the health assessment model needs to be updated. By first using initial screening conditions for model update that include the model update duration to preliminarily determine whether a model update is needed, and then combining this with health thresholds to further determine whether a model update is needed, it can ensure that the health assessment model is adapted to the current operating characteristics of the host component, thereby improving the accuracy of host health assessment; by directly conducting health status assessment without needing a model update, it can balance efficiency and accuracy, effectively ensuring the safety of ship navigation and equipment operation, and providing reliable technical support for the implementation of predictive maintenance.

[0089] Figure 4 This is a schematic diagram of the structure of a host health status determination device provided in an embodiment of this application, as shown below. Figure 4 As shown, the device 400 may include:

[0090] Data acquisition module 410 is used to acquire the operating condition characteristic data of the ship's power equipment and the main engine operation data, wherein the main engine operation data includes the component operation data corresponding to multiple main engine components;

[0091] The operating condition determination module 420 is used to analyze the operating condition characteristic data to obtain the current operating condition of the ship's power equipment.

[0092] The model determination module 430 is used to determine the health assessment model corresponding to each of the multiple host components under the current operating condition.

[0093] The health analysis module 440 is used to input the component operation data of each host component into the corresponding health assessment model to obtain the health status of each host component.

[0094] In one embodiment, the above-mentioned operating condition determination module 420 can be specifically used to: obtain a pre-trained operating condition recognition model, wherein the operating condition recognition model is trained on operating condition datasets of multiple host operation stages under different external conditions based on the DBSCAN algorithm; and input the operating condition feature data into the operating condition recognition model to obtain the current operating condition.

[0095] In one embodiment, the ship's power equipment includes multiple operating conditions, and each operating condition corresponds to the operation of a main engine operating phase under a set of external conditions; the main engine operating phase includes at least the ship's motor navigation main engine acceleration phase, the ship's motor navigation main engine deceleration phase, the main engine program acceleration phase, the main engine program deceleration phase, the main engine stable operation phase, and the main engine shutdown phase; the external conditions include at least one type of fuel, one type of exhaust gas bypass valve opening, one type of turbocharger air inlet temperature, one type of low-temperature cooling water temperature value, and one type of fuel compensation value, and a set of external conditions is a combination of at least one of the external conditions.

[0096] In one embodiment, the main unit includes at least a cylinder, a piston, an oil head, a turbocharger, an air cooler, a friction assembly, and a scavenging system.

[0097] In one embodiment, the host health status determination device further includes an update judgment module;

[0098] The update judgment module can be used to: determine whether to update all the health assessment models before inputting the component operation data of each host component into the corresponding health assessment model to obtain the health status of each host component; if the model is updated, then update all the health assessment models to obtain an updated health assessment model.

[0099] Accordingly, the aforementioned health analysis module 440 can be specifically used to: input the component operation data of each host component into the corresponding updated health assessment model to obtain the health status of each host component.

[0100] In one embodiment, the update judgment module described above can also be specifically used to: determine the duration between the current time and the most recent model update time; determine whether the health assessment model meets the initial screening conditions for model update based on the duration; if the initial screening conditions for model update are met, calculate the degree of deviation between the component operation data of each host component and the corresponding data baseline, and obtain the first health score of the corresponding host component based on the degree of deviation; if the average value of the first health score is lower than a set threshold, determine to update the model for all the health assessment models.

[0101] In one embodiment, the update judgment module described above can also be specifically used for: acquiring historical operating data of each of the host components; performing data fitting processing on the historical operating data to obtain the data baseline of the corresponding host component; calculating the distance between each data point in the historical operating data and the data baseline; determining the health warning value of the corresponding host component based on the distance; and calculating the deviation degree of the corresponding host component based on the component operating data of each host component and the corresponding health warning value.

[0102] The host health status determination device provided in this embodiment can be applied to the host health status determination method provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0103] Figure 5 This is a block diagram of a marine propulsion system used to implement a host health status determination method according to embodiments of this application. The marine propulsion system 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The marine propulsion system can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0104] like Figure 5 As shown, the marine propulsion system 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the marine propulsion system 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0105] Multiple components in the marine propulsion system 10 are connected to the input / output (I / O) interface 15, including: an input unit 16, such as a keyboard, mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, optical disk, etc.; and a communication unit 19, such as a network card, modem, wireless transceiver, etc. The communication unit 19 allows the marine propulsion system 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0106] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as host health status determination methods.

[0107] In some embodiments, the host health status determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the marine propulsion system 10 via read-only memory (ROM) 12 and / or communication unit 19. When the computer program is loaded into random access memory (RAM) 13 and executed by processor 11, one or more steps of the host health status determination method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the host health status determination method by any other suitable means (e.g., by means of firmware).

[0108] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0109] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0110] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0111] To provide interaction with the user, the systems and techniques described herein can be implemented on a marine propulsion system having: a display device (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the marine propulsion system. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0112] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0113] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to address the shortcomings of traditional physical hosts and virtual private servers, such as high management difficulty and weak business scalability.

[0114] Note that the above are merely preferred embodiments and technical principles applied in this application. Those skilled in the art will understand that this application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of this application. For example, those skilled in the art can use the various forms of processes shown above to reorder, add, or delete steps; the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solution of this application can be achieved, and no limitations are imposed herein.

[0115] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method of host health status determination, the method comprising: The method comprises: obtaining working condition characteristic data of a ship power equipment and main engine operation data, wherein the main engine operation data comprises component operation data corresponding to a plurality of main engine components; analyzing the working condition characteristic data to obtain a current operation working condition of the ship power equipment; determining a health assessment model corresponding to each of the plurality of main engine components under the current operation working condition; inputting the component operation data of each main engine component into the corresponding health assessment model to obtain a health state of each main engine component.

2. The method of claim 1, wherein, The analysis of the working condition characteristic data to obtain the current operation working condition of the ship power equipment comprises: obtaining a pre-trained working condition recognition model, wherein the working condition recognition model is trained based on a density-based DBSCAN algorithm with noise application space clustering on a working condition data set of a plurality of main engine operation stages under different external conditions; inputting the working condition characteristic data into the working condition recognition model to obtain the current operation working condition.

3. The method of claim 1, wherein, The ship power equipment comprises a plurality of operation working conditions, and a single operation working condition corresponds to an operation condition of a main engine operation stage under a set of external conditions; The main engine operation stage at least comprises a ship maneuvering navigation main engine acceleration stage, a ship maneuvering navigation main engine deceleration stage, a main engine program acceleration stage, a main engine program deceleration stage, a main engine stable operation stage and a main engine shutdown stage; The external conditions at least comprise one kind of oil, one kind of exhaust gas bypass valve opening, one kind of supercharger air inlet temperature, one kind of low-temperature cooling water temperature value and one kind of fuel compensation value, and a set of external conditions is a combination of at least one of the external conditions.

4. The method of claim 1, wherein, The main engine components at least comprise a cylinder, a piston, an oil head, a supercharger, an air cooler, a friction assembly and a scavenging system.

5. The method of claim 1, wherein, Before the inputting of the component operation data of each main engine component into the corresponding health assessment model to obtain the health state of each main engine component, the method further comprises: determining whether to perform model updating on all the health assessment models; if model updating is required, performing model updating on all the health assessment models to obtain updated health assessment models; correspondingly, the inputting of the component operation data of each main engine component into the corresponding health assessment model to obtain the health state of each main engine component comprises: inputting the component operation data of each main engine component into the corresponding updated health assessment model to obtain the health state of each main engine component.

6. The method of claim 5, wherein, The determination of whether to perform model updating on all the health assessment models comprises: determining a time length between a current time and a last model updating time; judging whether the health assessment model satisfies a model updating preliminary screening condition based on the time length; if the model updating preliminary screening condition is satisfied, calculating a deviation degree of the component operation data of each main engine component from a corresponding data baseline, and obtaining a first health score of the corresponding main engine component based on the deviation degree; if an average value of the first health scores is lower than a set threshold, determining to perform model updating on all the health assessment models.

7. The method of claim 6, wherein, The determination of the deviation degree of the component operation data of each main engine component from the corresponding data baseline comprises: acquire historical operation data of each of the main components; perform data fitting processing on the historical operation data to obtain a data baseline of the corresponding main component; calculate a distance between each data point in the historical operation data and the data baseline; determine a health early warning value of the corresponding main component based on the distance; calculate a deviation degree of the corresponding main component based on the component operation data of each main component and the corresponding health early warning value.

8. A host health status determination apparatus, characterized by comprising: The device comprises: a data acquisition module configured to acquire working condition characteristic data and main engine operation data of a marine power plant, wherein the main engine operation data comprises component operation data corresponding to a plurality of main components; a working condition determination module configured to analyze the working condition characteristic data to obtain a current operation working condition of the marine power plant; a model determination module configured to determine a health assessment model corresponding to each of the plurality of main components under the current operation working condition; a health analysis module configured to input the component operation data of each main component into the corresponding health assessment model to obtain a health state of each main component.

9. A marine power plant, characterized by The marine power plant comprises: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the main engine health state determination method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to implement the main engine health state determination method according to any one of claims 1 to 7 when executed.

Images