Method, apparatus, medium, and system for monitoring an oil filter

Abstract

The application provides a monitoring method, device, medium and system of an engine oil filter, the method comprising: obtaining engine oil filter data, the engine oil filter data comprising engine oil filter pressure data, historical accumulation data and preset limit value data; selecting a corresponding sliding window according to a cumulative use duration to perform data extraction and preprocessing on the engine oil filter data, and generating granularity data; performing an information granulation operation on the granularity data and determining an upper boundary and a lower boundary of an information granule, calculating the similarity between each information granule according to the upper boundary and the lower boundary of each information granule, and generating an abnormal score for each information granule based on the similarity; and determining whether warning information of a corresponding level needs to be generated according to the size of the abnormal score. The application solves the problem that the existing scheme for the engine oil filter of a diesel engine is based on fixed period implementation of planned or preventive maintenance, thereby causing the problem of untimely engine oil filter maintenance.

Description

Technical Field

[0001] This application relates to the field of diesel engine technology, and more specifically, to a method for monitoring an oil filter, a device for monitoring an oil filter, a computer-readable storage medium, and a system for monitoring an oil filter. Background Technology

[0002] For diesel engine oil filters, traditional maintenance solutions are planned or preventative maintenance based on fixed cycles (such as 500 hours). This is out of touch with the actual deterioration of the engine, the operating environment, and the individual differences of parts, resulting in untimely or excessive maintenance. It also lacks intelligent and customized maintenance. Summary of the Invention

[0003] The main objective of this application is to provide a method for monitoring an oil filter, a device for monitoring an oil filter, a computer-readable storage medium, and a system for monitoring an oil filter, so as to at least solve the problem that existing solutions for diesel engine oil filters are based on planned or preventative maintenance performed at fixed intervals, resulting in untimely maintenance of the oil filter.

[0004] To achieve the above objectives, according to one aspect of this application, a method for monitoring an oil filter is provided. The method includes: acquiring oil filter data, the oil filter data including oil filter pressure data, historical accumulated data, and preset limit data; selecting a corresponding sliding window based on the accumulated usage time to extract and preprocess the oil filter data, generating granular data; performing information granulation on the granular data and determining the upper and lower boundaries of the information particles, calculating the similarity between each information particle based on the upper and lower boundaries, and generating an anomaly score for each information particle based on the similarity; and determining whether to generate a corresponding level of warning information based on the magnitude of the anomaly score.

[0005] Optionally, the oil filter data is extracted and preprocessed using a corresponding sliding window based on the cumulative usage time to generate granular data. This includes: when the cumulative usage time is less than a first duration threshold, selecting an hourly sliding window to extract and preprocess the oil filter data to generate the granular data; when the cumulative usage time is greater than or equal to the first duration threshold and less than a second duration threshold, selecting a minute-level sliding window to extract and preprocess the oil filter data to generate the granular data; and when the cumulative usage time is greater than or equal to the second duration threshold, selecting a second-level sliding window to extract and preprocess the oil filter data to generate the granular data.

[0006] Optionally, the upper boundary of the information granule is determined, including:

[0007] according to ,

[0008] Determine the fitness of a portion of the information particles in the granular data, where card represents the number of data particles belonging to the corresponding sliding window. Here, m is a preset coefficient, and m is the mean of the granularity data. Let b be the value of the i-th data in the granularity data, and let b be the boundary value of the granularity data. For the fitness, x max The maximum value of the granularity data;

[0009] The value of the data corresponding to the maximum value of the fitness is determined as the upper boundary.

[0010] Optionally, calculating the similarity between the information particles based on their upper and lower boundaries includes:

[0011] according to Determine the similarity between each of the information particles, wherein A i Let A be the upper and lower boundaries of the information grain of the i-th corresponding sliding window. j S represents the upper and lower boundaries of the information granules of the j-th corresponding sliding window. ij The similarity is given.

[0012] Optionally, an anomaly score is generated for each information particle based on the similarity, including:

[0013] according to Determine the abnormal score;

[0014] Where N is the number of information particles. Let be the anomaly score of the information granules in the i-th corresponding sliding window.

[0015] Optionally, determining whether to generate a warning message of the corresponding level based on the magnitude of the abnormal score includes: determining that a warning message of the corresponding level needs to be generated when the abnormal score is greater than or equal to a score threshold; and determining that a warning message of the corresponding level does not need to be generated when the abnormal score is less than a score threshold.

[0016] Optionally, after determining that it is not necessary to generate warning information of the corresponding level, the method further includes: adjusting the sliding window based on the cumulative usage time and regenerating the granular data; regenerating each information granule to generate the anomaly score until it is determined that it is necessary to generate warning information of the corresponding level.

[0017] According to another aspect of this application, an oil filter monitoring device is provided, the device comprising: an acquisition unit for acquiring oil filter data, the oil filter data including oil filter pressure data, historical accumulated data, and preset limit data; a first processing unit for selecting a corresponding sliding window based on the accumulated usage time to extract and preprocess the oil filter data, generating granular data; a second processing unit for performing information granulation on the granular data and determining the upper and lower boundaries of the information particles, calculating the similarity between each information particle based on the upper and lower boundaries of each information particle, and generating an anomaly score for each information particle based on the similarity; and a third processing unit for determining whether to generate a corresponding level of warning information based on the magnitude of the anomaly score.

[0018] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform any of the methods described.

[0019] According to another aspect of this application, an oil filter monitoring system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any one of the methods described.

[0020] Applying the technical solution of this application, the size of the sliding window is dynamically adjusted according to the cumulative usage time of the oil filter, extracting data at the hourly, minutely, and even secondly granular levels. This adaptability can more accurately capture the state changes of the oil filter at different operating stages, avoiding the limitations of fixed cycles that cannot adapt to rapid or slow deterioration. The extracted granular data is then granulated to construct hourly, minutely, and secondly information granules. This process not only reduces the amount of data and improves processing efficiency but also effectively identifies representative and distinguishable data features by determining the upper and lower boundaries of the information granules through reasonable granularity principles, providing a solid foundation for subsequent anomaly detection. The similarity between information granules is calculated using a formula to assess the degree of anomaly in each granule and assign a corresponding anomaly score. This method considers the time-series characteristics of the data, identifying trends that gradually deviate from the normal range over time, rather than just static threshold comparisons, thus better reflecting the real-time health status of the filter. Based on the anomaly score, this system sets up a three-level early warning mechanism (reminder, attention, and warning), corresponding to mild, moderate, and severe anomalies, respectively. This tiered early warning system not only promptly notifies users of potential problems, but also provides different levels of attention and handling suggestions based on the severity of the problem, avoiding over-maintenance or neglect of maintenance. This solves the problem of untimely oil filter maintenance in existing diesel engine solutions, which rely on planned or preventative maintenance based on fixed cycles. Attached Figure Description

[0021] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0022] Figure 1 A schematic flowchart of a method for monitoring an oil filter according to an embodiment of this application is shown;

[0023] Figure 2 A structural block diagram of a monitoring device for an oil filter according to an embodiment of this application is shown. Detailed Implementation

[0024] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first," "second," etc., 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 for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover 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.

[0027] As described in the background section, traditional maintenance solutions for diesel engine oil filters are planned or preventative maintenance based on fixed cycles (e.g., 500 hours). This is disconnected from the actual deterioration state of the engine, operating environment, and individual differences in components, leading to untimely or excessive maintenance. Furthermore, there is a lack of intelligent and customized maintenance. To address the problem of untimely oil filter maintenance due to the fixed-cycle planned or preventative maintenance in existing solutions, embodiments of this application provide an oil filter monitoring method, an oil filter monitoring device, a computer-readable storage medium, and an oil filter monitoring system.

[0028] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0029] This embodiment provides a method for monitoring an oil filter. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] Figure 1 This is a flowchart of a method for monitoring an oil filter according to an embodiment of this application. Figure 1 As shown, the method includes the following steps:

[0031] Step S101: Obtain oil filter data, which includes oil filter pressure data, historical accumulated data, and preset limit data.

[0032] Step S102: Select the corresponding sliding window based on the cumulative usage time to extract and preprocess the oil filter data to generate granular data.

[0033] Step S103: Perform information granulation operation on the above granular data and determine the upper and lower boundaries of the information particles. Calculate the similarity between each information particle based on the upper and lower boundaries of each information particle, and generate an anomaly score for each information particle based on the similarity.

[0034] Step S104: Determine whether to generate a warning message of the corresponding level based on the magnitude of the above-mentioned abnormal score.

[0035] Data Collection and Preparation: Collect oil filter pressure data during engine operation. This data may come from the vehicle engine's real-time monitoring system or data recorded while the engine is running under laboratory conditions. Prepare historical laboratory data for the oil filter, including performance parameters under different operating conditions, such as pressure variations and flow rates. Design and determine the operating limits for the oil filter; these limits are used to determine whether the filter is functioning properly.

[0036] Conditional judgment and window selection: Determine the current time stage (hours, minutes, seconds) of the oil filter based on its cumulative usage time.

[0037] Choose an appropriate time window for data extraction. For example, if the cumulative usage time is less than a certain threshold, you may choose an hourly window, such as a sliding window of 1 hour, 5 hours, or 10 hours.

[0038] Data Extraction and Preprocessing: Non-overlapping extraction is performed on real-time or historically accumulated oil filter data using a selected sliding window. Data preprocessing is then carried out to ensure data quality and integrity, removing erroneous rows and garbled characters. This may include data cleaning, missing value imputation, and outlier detection.

[0039] Generating granular data: After data extraction and preprocessing, the data is divided into small units that correspond to the time granularity. These small units are called "granular data". Each set of granular data should be a clean set of preprocessed data to facilitate subsequent information granulation operations.

[0040] Information granulation: Applying appropriate granularity principles to each set of granular data, transforming it into time-information granules, minute-information granules, or second-information granules. This step involves further data abstraction and feature extraction. Statistical methods, such as mean, standard deviation, and maximum value, may be used to define the boundaries of each information granule to reflect changes in the oil filter's condition at different time scales.

[0041] In the above steps, the size of the sliding window is dynamically adjusted based on the cumulative usage time of the oil filter, extracting data at the hourly, minutely, and even secondly granular levels. This adaptability allows for more accurate capture of the oil filter's state changes at different operating stages, avoiding the limitations of fixed cycles that cannot adapt to rapid or slow deterioration. The extracted granular data is then granulated to construct hourly, minutely, and secondly information granules. This process not only reduces data volume and improves processing efficiency but also effectively identifies representative and discriminative data features by determining the upper and lower boundaries of the information granules based on reasonable granularity principles, providing a solid foundation for subsequent anomaly detection. The similarity between information granules is calculated using a formula to assess the degree of anomaly in each granule and assign a corresponding anomaly score. This method considers the time-series characteristics of the data, identifying trends that gradually deviate from the normal range over time, rather than just static threshold comparisons, thus better reflecting the real-time health status of the filter. Based on the anomaly score, the system sets up a three-level early warning mechanism (reminder, attention, warning), corresponding to mild, moderate, and severe anomalies, respectively. This tiered early warning system not only promptly notifies users of potential problems, but also provides different levels of attention and handling suggestions based on the severity of the problem, avoiding over-maintenance or neglect of maintenance. This solves the problem of untimely oil filter maintenance in existing diesel engine solutions, which rely on planned or preventative maintenance based on fixed cycles.

[0042] In one specific embodiment of this application, the oil filter data is extracted and preprocessed using a corresponding sliding window based on the cumulative usage time to generate granular data. This includes: when the cumulative usage time is less than a first duration threshold, selecting an hourly sliding window to extract and preprocess the oil filter data to generate the granular data; when the cumulative usage time is greater than or equal to the first duration threshold and less than a second duration threshold, selecting a minute-level sliding window to extract and preprocess the oil filter data to generate the granular data; and when the cumulative usage time is greater than or equal to the second duration threshold, selecting a second-level sliding window to extract and preprocess the oil filter data to generate the granular data.

[0043] Specifically, as the cumulative usage time of an oil filter increases, its condition may change more frequently and subtly. Using a tiered sliding window from hours to minutes to seconds ensures that a coarser granularity is used in the early stages of filter deterioration, reducing computational resource consumption, while a finer granularity is used in the later stages of rapid condition changes, improving detection sensitivity and accuracy. This method automatically adjusts the monitoring granularity according to the filter's usage status, eliminating the need for frequent human intervention. The system can adaptively select the most appropriate monitoring strategy at different times, reducing maintenance costs and manpower requirements. In the early stages of filter use, because its condition is relatively stable, using an hourly sliding window reduces data processing and saves computational resources. As usage time increases, gradually decreasing the window granularity allows for timely detection of potential abnormal changes, avoiding resource waste. Hourly windows are suitable for long-term health monitoring, providing initial usage status feedback; minute-level windows are more suitable for monitoring mid-term condition changes, providing more timely information; and second-level windows can capture the moment when the filter is about to fail or has already failed, achieving the most timely early warning. This tiered mechanism can allocate alarm resources more rationally, avoiding problems such as excessive or untimely warnings.

[0044] In one specific embodiment of this application, determining the upper boundary of the information granule includes:

[0045] according to ,

[0046] Determine the fitness of a portion of the aforementioned information particles in the granular data, where card represents the number of data particles belonging to the corresponding sliding window. Here, m is the preset coefficient, and m is the mean of the above granularity data. Let be the value of the i-th data point in the above granularity data, and b be the boundary value of the above granularity data. For the above fitness, x max This represents the maximum value of the granularity data mentioned above.

[0047] The value of the data corresponding to the maximum fitness value is determined as the upper boundary.

[0048] The preset coefficient range is (0, 1).

[0049] The default value can be 1 / 2.

[0050] Similarly, according to Determine the lower boundary.

[0051] in, and Similarly, it is also a preset coefficient. The same applies to a and b, where b is one boundary value of the aforementioned granularity data, and a is another boundary value of the aforementioned granularity data, x. minJ is the minimum value of the above granularity data. opt2 To determine the fitness during the lower boundary process, the value of the data corresponding to the maximum fitness value is selected as the lower boundary.

[0052] Specifically, determining fitness involves an optimization process: finding information granules that cover a sufficient number of data points while maintaining high performance. This reduces data complexity while preserving information integrity. Choosing the data point with the highest fitness as the upper boundary means that this boundary can encompass all relevant data to the greatest extent possible while minimizing interference from irrelevant data, thereby improving the accuracy and effectiveness of the information granules. Information granules with high fitness typically mean they can keenly capture data trends and anomalies. Applying such an upper boundary to a monitoring system makes the system more sensitive to changes in filter status and issues timely warnings. By adaptively selecting the upper boundary, monitoring strategies can be dynamically adjusted based on the actual working conditions and operating environment of the filter, avoiding over-maintenance or under-maintenance, making maintenance decisions more scientific and reasonable, and improving equipment availability and efficiency. Automated boundary determination reduces the need for manual intervention, saving time and manpower costs, and also allows for more efficient use of monitoring system resources because the system focuses more on the data ranges that truly require attention.

[0053] In one specific embodiment of this application, calculating the similarity between the aforementioned information particles based on their upper and lower boundaries includes:

[0054] according to Determine the similarity between each of the aforementioned information particles, where A i Let A be the upper and lower boundaries of the aforementioned information granules for the i-th corresponding sliding window. j S represents the upper and lower boundaries of the aforementioned information granules for the j-th corresponding sliding window. ij The similarity is as described above.

[0055] By calculating boundary values, the range of information granules can be defined more accurately, thereby reducing false alarms and missed alarms during monitoring and early warning, and improving monitoring accuracy. The upper and lower boundaries are determined based on the statistical characteristics of the granular data. This dynamic boundary setting can adapt to data changes under different operating environments and conditions, making the monitoring system more intelligent and flexible. Information granulation operations under the principle of reasonable granularity can effectively compress raw data, reduce the burden of data processing and storage, and facilitate data management and subsequent analysis. Granularity verification calculations using upper and lower boundaries can quickly identify anomalies in the data, trigger early warning mechanisms in a timely manner, and improve the response speed and efficiency of anomaly detection. By constructing information granules at different levels, a more detailed hierarchical basis can be provided for the maintenance strategy of oil filters, making maintenance reminders more personalized and precise, reducing unnecessary maintenance actions, and avoiding failures caused by untimely maintenance.

[0056] In one specific embodiment of this application, an anomaly score is generated for each information particle based on the aforementioned similarity, including:

[0057] according to Determine the above abnormal scores;

[0058] Where N is the number of the aforementioned information particles. Let be the anomaly score of the aforementioned information granules for the i-th corresponding sliding window.

[0059] Specifically, this method enables multi-level, refined monitoring of the oil filter's condition based on information granules at different time scales (hours, minutes, seconds). This means the system can issue an alert when filter performance begins to decline but hasn't reached a critical level, helping to take early action and avoid sudden failures. Since the construction of information granules and the calculation of anomaly scores are based on the filter's actual operating time and state changes, this method can adaptively adjust the sensitivity and frequency of monitoring. For example, in the initial operating phase, only hourly monitoring may be needed; while as the filter approaches the end of its lifespan, more frequent second-level monitoring may be required to capture rapidly changing anomalies. The anomaly scores calculated through granular testing, combined with pre-set thresholds, can more accurately identify truly concerning anomalies, avoiding false alarms or missed alarms that may occur with traditional fixed-threshold warnings. This anomaly scoring mechanism based on similarity calculation better reflects the degree of deviation between the filter's current state and its normal state.

[0060] In one specific embodiment of this application, determining whether to generate a warning message of a corresponding level based on the magnitude of the abnormal score includes: determining that a warning message of a corresponding level needs to be generated when the abnormal score is greater than or equal to a score threshold; and determining that a warning message of a corresponding level does not need to be generated when the abnormal score is less than a score threshold.

[0061] By monitoring real-time pressure changes and dynamic updates of the oil filter's anomaly score, an early warning can be triggered immediately when an anomaly reaches a preset severity level. This enables early detection and preventative maintenance of potential faults, reducing the occurrence of sudden failures and improving equipment reliability and safety. Because warning information is tiered (alert, attention, alert), the system can automatically adjust the urgency level of the alert based on the severity of the anomaly. This allows users to respond more effectively to warnings at different levels, prioritizing high-risk issues and avoiding wasting resources on low-priority events. Setting a score threshold can filter out minor fluctuations or transient anomalies, issuing warnings only when the anomaly persists and reaches a certain level. This significantly reduces false alarm rates, minimizes unnecessary inspections and maintenance, and saves costs.

[0062] Conversely, when the aforementioned anomaly scores do not reach the score threshold, determining that no corresponding level of warning information needs to be generated demonstrates another advantage of the system: for minor anomalies that do not reach the threshold, the system will not generate warning information, avoiding excessive user anxiety and unnecessary actions, while also reducing unnecessary maintenance costs. Generating warning information only when truly needed ensures the effective use of system resources, reduces the distraction of users from invalid alarms, allows users to focus on solving real problems, and improves overall work efficiency. The score threshold setting is based on extensive data analysis and practical verification, ensuring the accuracy and reliability of warnings and avoiding misjudgments caused by data fluctuations or noise.

[0063] In one specific embodiment of this application, after determining that it is not necessary to generate warning information of the corresponding level, the above method further includes: adjusting the sliding window based on the cumulative usage time and regenerating granular data; regenerating each information granule to generate the above abnormal score, until it is determined that it is necessary to generate warning information of the corresponding level.

[0064] As the cumulative usage time of the oil filter increases, the monitoring granularity of the system gradually refines, transitioning from hourly to minutely and even secondly. This adaptive monitoring strategy ensures that the monitoring system can capture more subtle changes at critical moments in the filter's condition, thereby improving the accuracy and timeliness of early warnings. In the initial stages of use, because the filter's condition is relatively stable, a larger time window (e.g., hourly) is used for data extraction and processing, reducing unnecessary computational load and storage requirements. However, as the equipment operates for longer periods and the potential risk of failure increases, the system automatically adjusts to a finer time window (e.g., secondly). This ensures the effectiveness of monitoring while avoiding excessive consumption of computational resources in the early stages. Through continuous iteration of granular data and anomaly score calculations, the system can continuously assess the filter's health status. Once any level of anomaly score exceeds a predetermined threshold, corresponding early warning information (reminder, attention, or alert) is immediately triggered, allowing maintenance personnel to take action before a failure occurs, extending the filter's lifespan and reducing maintenance costs.

[0065] After determining that the corresponding level of early warning information needs to be generated, you can also adjust the sliding window and generate granular data again.

[0066] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0067] This application also provides an oil filter monitoring device. It should be noted that the oil filter monitoring device of this application can be used to execute the oil filter monitoring method provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0068] The following describes the monitoring device for the oil filter provided in the embodiments of this application.

[0069] Figure 2 This is a schematic diagram of a monitoring device for an oil filter according to an embodiment of this application. Figure 2As shown, the device includes: an acquisition unit 21 for acquiring oil filter data, the oil filter data including oil filter pressure data, historical accumulated data, and preset limit data; a first processing unit 22 for selecting a corresponding sliding window based on the accumulated usage time to extract and preprocess the oil filter data, generating granular data; a second processing unit 23 for performing information granulation on the granular data and determining the upper and lower boundaries of the information particles, calculating the similarity between each information particle based on the upper and lower boundaries of each information particle, and generating an anomaly score for each information particle based on the similarity; and a third processing unit 24 for determining whether to generate a corresponding level of warning information based on the magnitude of the anomaly score.

[0070] In the aforementioned device, the size of the sliding window is dynamically adjusted based on the cumulative usage time of the oil filter, extracting data at the hourly, minutely, and even secondly granular levels. This adaptability allows for more accurate capture of the oil filter's state changes at different operating stages, avoiding the limitations of fixed cycles that cannot adapt to rapid or slow deterioration. The extracted granular data undergoes information granulation, constructing hourly, minutely, and secondly information granules. This process not only reduces data volume and improves processing efficiency but also effectively identifies representative and discriminative data features by determining the upper and lower boundaries of the information granules through reasonable granularity principles, providing a solid foundation for subsequent anomaly detection. The similarity between information granules is calculated using formulas to assess the degree of anomaly in each granule and assign a corresponding anomaly score. This method considers the time-series characteristics of the data, identifying trends that gradually deviate from the normal range over time, rather than just static threshold comparisons, thus better reflecting the real-time health status of the filter. Based on the anomaly score, the system sets up a three-level early warning mechanism (reminder, attention, and warning), corresponding to mild, moderate, and severe anomalies, respectively. This tiered early warning system not only promptly notifies users of potential problems, but also provides different levels of attention and handling suggestions based on the severity of the problem, avoiding over-maintenance or neglect of maintenance. This solves the problem of untimely oil filter maintenance in existing diesel engine solutions, which rely on planned or preventative maintenance based on fixed cycles.

[0071] In one specific embodiment of this application, the first processing unit includes: a first processing module configured to extract and preprocess the oil filter data using an hourly sliding window to generate the granular data when the cumulative usage time is less than a first duration threshold; a second processing module configured to extract and preprocess the oil filter data using a minute-level sliding window to generate the granular data when the cumulative usage time is greater than or equal to the first duration threshold and less than a second duration threshold; and a third processing module configured to extract and preprocess the oil filter data using a second-level sliding window to generate the granular data when the cumulative usage time is greater than or equal to the second duration threshold.

[0072] In one specific embodiment of this application, the second processing unit includes:

[0073] The first determining module is used to determine based on ,

[0074] Determine the fitness of a portion of the aforementioned information particles in the granular data, where card represents the number of data particles belonging to the corresponding sliding window. Here, m is the preset coefficient, and m is the mean of the above granularity data. Let be the value of the i-th data point in the above granularity data, and b be the boundary value of the above granularity data. For the above fitness, x max This represents the maximum value of the granularity data mentioned above.

[0075] The second determining module is used to determine the value of the data corresponding to the maximum value of the fitness as the upper boundary.

[0076] In one specific embodiment of this application, the second processing unit includes:

[0077] The third determining module is used to determine based on Determine the similarity between each of the aforementioned information particles, where A i Let A be the upper and lower boundaries of the aforementioned information granules for the i-th corresponding sliding window. j S represents the upper and lower boundaries of the aforementioned information granules for the j-th corresponding sliding window. ij The similarity is as described above.

[0078] In one specific embodiment of this application, the second processing unit includes:

[0079] The fourth determining module is used to determine based on Determine the above abnormal scores;

[0080] Where N is the number of the aforementioned information particles. Let be the anomaly score of the aforementioned information granules for the i-th corresponding sliding window.

[0081] In one specific embodiment of this application, the third processing unit includes: a fifth determining module for determining that a corresponding level of warning information needs to be generated when the abnormal score is greater than or equal to a score threshold; and a sixth determining module for determining that a corresponding level of warning information does not need to be generated when the abnormal score is less than a score threshold.

[0082] In one specific embodiment of this application, the oil filter monitoring device further includes: a fourth processing unit for adjusting the sliding window and regenerating granular data based on the cumulative usage time after determining that no corresponding level of warning information needs to be generated; and a fifth processing unit for regenerating each information granule to generate the above-mentioned abnormal score until it is determined that a corresponding level of warning information needs to be generated.

[0083] The aforementioned oil filter monitoring device includes a processor and a memory. The acquisition unit, first processing unit, second processing unit, and third processing unit are all stored as program units in the memory. The processor executes these program units stored in the memory to achieve the corresponding functions. All of the above modules are located in the same processor; alternatively, the modules may be located in different processors in any combination.

[0084] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured. By adjusting kernel parameters, the problem of untimely oil filter maintenance in existing diesel engine solutions—which rely on planned or preventative maintenance based on fixed cycles—can be addressed.

[0085] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0086] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the oil filter monitoring method.

[0087] This invention provides a processor for running a program, wherein the program executes the oil filter monitoring method.

[0088] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps: acquiring oil filter data, including oil filter pressure data, historical accumulated data, and preset limit data; extracting and preprocessing the oil filter data using a corresponding sliding window based on the accumulated usage time to generate granular data; performing information granulation on the granular data and determining the upper and lower boundaries of the information particles; calculating the similarity between each information particle based on its upper and lower boundaries; and generating an anomaly score for each information particle based on the similarity score; and determining whether to generate a corresponding level of warning information based on the magnitude of the anomaly score. The device described herein can be a server, PC, PAD, mobile phone, etc.

[0089] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps: acquiring oil filter data, the oil filter data including oil filter pressure data, historical accumulated data, and preset limit data; selecting a corresponding sliding window based on the accumulated usage time to extract and preprocess the oil filter data, generating granular data; performing information granulation operations on the granular data and determining the upper and lower boundaries of the information particles, calculating the similarity between each information particle based on the upper and lower boundaries of each information particle, and generating an anomaly score for each information particle based on the similarity; and determining whether to generate a warning message of the corresponding level based on the magnitude of the anomaly score.

[0090] This application also provides an oil filter monitoring system, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for performing any of the above-described methods.

[0091] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0092] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0094] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0095] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0096] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0097] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0098] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0099] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0100] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0101] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for monitoring an oil filter, characterized in that, include: Obtain oil filter data, which includes oil filter pressure data, historical accumulated data, and preset limit data; Based on the cumulative usage time, the corresponding sliding window is selected to extract and preprocess the oil filter data to generate granular data. The granular data is granulated to determine the upper and lower boundaries of the information particles. The similarity between the information particles is calculated based on the upper and lower boundaries of each information particle. An anomaly score is generated for each information particle based on the similarity. Determine whether a corresponding level of early warning information needs to be generated based on the magnitude of the abnormal score; Based on the cumulative usage time, a corresponding sliding window is selected to extract and preprocess the oil filter data to generate granular data. This includes: when the cumulative usage time is less than a first duration threshold, selecting an hourly sliding window to extract and preprocess the oil filter data to generate the granular data; when the cumulative usage time is greater than or equal to the first duration threshold and less than a second duration threshold, selecting a minute-level sliding window to extract and preprocess the oil filter data to generate the granular data; and when the cumulative usage time is greater than or equal to the second duration threshold, selecting a second-level sliding window to extract and preprocess the oil filter data to generate the granular data. Determine the upper boundary of the information granule, including: according to , Determine the fitness of a portion of the information particles in the granular data, where card represents the number of data particles belonging to the corresponding sliding window. Here, m is a preset coefficient, and m is the mean of the granularity data. Let b be the value of the i-th data in the granularity data, and let b be the boundary value of the granularity data. For the fitness, x max The maximum value of the granularity data; The value of the data corresponding to the maximum value of the fitness is determined as the upper boundary; Calculating the similarity between each information particle based on its upper and lower boundaries includes: according to The similarity between each information particle is determined, where Ai is the upper and lower boundaries of the information particle of the i-th corresponding sliding window, Aj is the upper and lower boundaries of the information particle of the j-th corresponding sliding window, and Sij is the similarity. An anomaly score is generated for each information particle based on the similarity, including: according to Determine the abnormal score; Where N is the number of information particles. The anomaly score of the information granules corresponding to the i-th sliding window; Determining whether to generate a corresponding level of early warning information based on the magnitude of the abnormal score includes: If the abnormal score is greater than or equal to the score threshold, it is determined that a warning message of the corresponding level needs to be generated; If the abnormal score is less than the score threshold, it is determined that no warning information of the corresponding level needs to be generated.

2. The method according to claim 1, characterized in that, After determining that it is unnecessary to generate warning information of a corresponding level, the method further includes: Adjust the sliding window based on the cumulative usage time and generate granular data again; The anomaly score is regenerated for each information particle until it is determined that a warning message of the corresponding level needs to be generated.

3. A monitoring device for an oil filter, characterized in that, The monitoring device monitors the oil filter using the method described in claim 1 or 2, and the monitoring device comprises: The acquisition unit is used to acquire oil filter data, which includes oil filter pressure data, historical accumulated data, and preset limit data. The first processing unit is used to select the corresponding sliding window based on the cumulative usage time to extract and preprocess the oil filter data, and generate granular data. The second processing unit is used to perform information granulation operation on the granular data and determine the upper and lower boundaries of the information particles, calculate the similarity between each information particle according to the upper and lower boundaries of each information particle, and generate an anomaly score for each information particle based on the similarity. The third processing unit is used to determine whether to generate a warning message of the corresponding level based on the magnitude of the abnormal score.

4. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method of claim 1 or 2.

5. A monitoring system for an oil filter, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing the method of claim 1 or 2.

Images