A method, system, device and medium for early warning of air filter blockage of a fuel cell system

Abstract

The present application relates to the technical field of fuel cell, and particularly relates to a fuel cell system air filter blockage early warning method, system, equipment and medium, comprising the following steps: collecting geographical position information and air filter inside pressure data in a target area in real time when a vehicle is running; constructing an atmospheric pressure estimation model by using a clustering algorithm; calculating current atmospheric pressure by using the atmospheric pressure estimation model according to the geographical position information, to obtain air filter outside atmospheric pressure data; comparing the air filter outside atmospheric pressure data with the air filter inside pressure data, to obtain air filter two-side pressure difference; and detecting the air filter according to the air filter two-side pressure difference and a pre-determined adaptive early warning threshold, to generate an air filter blockage early warning signal. The present application realizes accurate early warning of the air filter blockage state by collecting geographical position and air filter inside pressure data in real time, combining the atmospheric pressure estimation model and the adaptive early warning threshold.

Description

Technical Field

[0001] This invention relates to the field of fuel cell technology, and in particular to a method, system, device and medium for early warning of air filter blockage in a fuel cell system. Background Technology

[0002] As a crucial component of the new energy field, the performance stability of fuel cell systems is closely related to the cleanliness of the air filter. Air filter blockage not only affects the system's intake efficiency but also leads to overheating, thereby impacting overall performance and lifespan. Currently, existing technologies typically determine air filter blockage by detecting the pressure difference across the air filter, air quality, or changes in system parameters. However, these methods have significant limitations. For instance, existing technologies use pressure sensors installed on both sides of the air filter to monitor the pressure difference and determine blockage. However, in practical applications, if sensors are only installed on the inside of the air filter, the atmospheric pressure on the outside cannot be accurately obtained, leading to inaccurate pressure difference calculations. Furthermore, adding external sensors significantly increases system costs.

[0003] Secondly, existing technologies utilize gas sensors to detect changes in air quality before and after air filtration, and assess the adsorption capacity and lifespan of the air filter by calculating the pollutant mass before and after filtration. However, this method is limited by the accuracy and durability of gas sensors and is costly, thus restricting its widespread application. In addition, existing technologies also determine the filter element clogging status by monitoring changes in a combination of system parameters such as back pressure valve opening, fuel cell flow resistance, and fuel cell power. However, this method requires coupling multiple system parameters, increasing computational complexity and power consumption. Furthermore, parameter changes under different operating conditions interfere with each other, affecting the accuracy of the judgment.

[0004] In summary, existing technologies have many problems in air filter blockage early warning, and there is an urgent need to provide a more accurate, reliable and efficient early warning method to solve this technical problem. Summary of the Invention

[0005] To address the above technical problems, this invention provides a method, system, device, and medium for early warning of air filter blockage in a fuel cell system.

[0006] In a first aspect, the present invention provides a method for early warning of air filter blockage in a fuel cell system, the method comprising the following steps:

[0007] The system collects real-time geographic location information and air filter inner pressure data within the target area during vehicle operation; wherein, the geographic location information includes latitude and longitude data and altitude data;

[0008] An atmospheric pressure estimation model is constructed using a clustering algorithm. Based on the geographical location information, the current atmospheric pressure is calculated using the atmospheric pressure estimation model to obtain atmospheric pressure data outside the air filter.

[0009] The atmospheric pressure data on the outside of the air filter is compared with the pressure data on the inside of the air filter to obtain the pressure difference on both sides of the air filter.

[0010] The air filter is detected based on the pressure difference across the air filter and a pre-determined adaptive warning threshold, generating an air filter blockage warning signal.

[0011] In a further implementation, the step of constructing an atmospheric pressure estimation model using a clustering algorithm includes:

[0012] The system collects historical geographical location information of the target area traversed by the vehicle during its historical operation, as well as ambient atmospheric pressure data collected by sensors inside the air filter when the air compressor stops working; wherein, the historical geographical location information includes historical latitude and longitude data and historical altitude data.

[0013] With the optimization objective of minimizing the Euclidean distance between each historical geographic location point and the center point of its respective cluster, a clustering algorithm is used to divide the historical geographic location information within the target area into different clusters;

[0014] By using a regression algorithm to fit all historical altitude data within each cluster with ambient atmospheric pressure data, an atmospheric pressure estimation model is obtained.

[0015] In a further implementation, the optimization objective function of the clustering algorithm is specifically:

[0016]

[0017] In the formula, D ij Let be the Euclidean distance between the j-th historical geographic location and the center of its cluster; i is the cluster index; n is the number of clusters; m is the number of historical geographic locations in the i-th cluster; d ij Let be the true distance between the j-th historical geographical location and the center point of its cluster; This is the preset real distance threshold.

[0018] In a further embodiment, the Euclidean distance is calculated using the following formula:

[0019]

[0020] In the formula, D ij Long is the Euclidean distance between the j-th historical geographic location and the center of its cluster; i The normalized longitude data for the center point of the i-th cluster; Long ′ j Here is the normalized historical longitude data for the j-th historical geographical location; Lati The normalized dimension data for the center point of the i-th cluster; Lat ′ j H represents the normalized historical latitude data for the j-th historical geographical location; i H represents the normalized elevation data of the center point of the i-th cluster; ′ j This represents the normalized historical elevation data for the j-th historical geographical location.

[0021] In a further implementation, the step of calculating the current atmospheric pressure using the atmospheric pressure estimation model based on the geographical location information to obtain the atmospheric pressure data outside the air filter includes:

[0022] The target cluster is obtained by finding the corresponding cluster based on the geographical location information.

[0023] The atmospheric pressure is calculated using the atmospheric pressure estimation model of the target cluster, and the atmospheric pressure data outside the air filter is obtained.

[0024] In a further embodiment, the step of detecting the air filter based on the pressure difference across the air filter and a pre-determined adaptive warning threshold to generate an air filter blockage warning signal includes:

[0025] The pressure difference across the air filter is compared with a predetermined adaptive warning threshold. If the pressure difference across the air filter exceeds the adaptive warning threshold within a preset air filter detection period, the air filter is determined to be clogged, and an air filter clog warning signal is generated.

[0026] In a further implementation, the process of determining the adaptive early warning threshold includes:

[0027] Airflow and pressure difference data were collected under both normal and clogged air filter conditions.

[0028] Based on the airflow and pressure difference sample data, fit the airflow-pressure difference characteristic curves for the normal state and the air filter blockage state, respectively.

[0029] Obtain the distinguishing boundary of the air flow-pressure difference characteristic curve, and determine the adaptive warning threshold based on the distinguishing boundary.

[0030] In a second aspect, the present invention provides a fuel cell system air filter blockage early warning system, the system comprising:

[0031] The data acquisition module is used to collect real-time geographic location information and air filter inner pressure data within the target area during vehicle operation; wherein, the geographic location information includes latitude and longitude data and altitude data;

[0032] The pressure estimation module is used to construct an atmospheric pressure estimation model using a clustering algorithm, and calculate the current atmospheric pressure based on the geographical location information using the atmospheric pressure estimation model to obtain atmospheric pressure data outside the air filter.

[0033] The pressure analysis module is used to compare the atmospheric pressure data outside the air filter with the pressure data inside the air filter to obtain the pressure difference between the two sides of the air filter.

[0034] The blockage warning module is used to detect the air filter based on the pressure difference across the air filter and a pre-determined adaptive warning threshold, and generate an air filter blockage warning signal.

[0035] Thirdly, the present invention also provides a computer device, including a processor and a memory, the processor being connected to the memory, the memory being used to store a computer program, and the processor being used to execute the computer program stored in the memory, so that the computer device performs the steps of implementing the above-described method.

[0036] Fourthly, the present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0037] This invention provides a method, system, device, and medium for early warning of air filter blockage in a fuel cell system. The method involves real-time acquisition of geographical location information and air filter inner pressure data within a target area during vehicle operation; constructing an atmospheric pressure estimation model using a clustering algorithm; calculating the current atmospheric pressure based on the geographical location information using the atmospheric pressure estimation model to obtain atmospheric pressure data outside the air filter; comparing the atmospheric pressure data outside the air filter with the pressure data inside the air filter to obtain the pressure difference between the two sides of the air filter; and detecting the air filter based on the pressure difference and a pre-determined adaptive warning threshold to generate an air filter blockage warning signal. Compared with existing technologies, this method achieves accurate early warning of air filter blockage by real-time acquisition of geographical location and air filter inner pressure data, combined with an atmospheric pressure estimation model and an adaptive warning threshold, avoiding warning errors caused by inaccurate atmospheric pressure acquisition or complex system parameter coupling in existing technologies. Attached Figure Description

[0038] Figure 1 This is a schematic diagram of the air filter blockage early warning method for a fuel cell system provided in an embodiment of the present invention;

[0039] Figure 2 This is a schematic diagram of the flow rate-pressure difference relationship provided in an embodiment of the present invention;

[0040] Figure 3This is a block diagram of the fuel cell system air filter blockage early warning system provided in an embodiment of the present invention;

[0041] Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0042] The embodiments of the present invention are described in detail below with reference to the accompanying drawings. The embodiments are given for illustrative purposes only and should not be construed as limiting the present invention. The accompanying drawings are for reference and illustration only and do not constitute a limitation on the scope of patent protection of the present invention, because many changes can be made to the present invention without departing from the spirit and scope of the present invention.

[0043] refer to Figure 1 This invention provides a method for early warning of air filter blockage in a fuel cell system, such as... Figure 1 As shown, the method includes the following steps:

[0044] S1. Real-time acquisition of geographical location information and air filter inner pressure data within the target area during vehicle operation; wherein, the geographical location information includes latitude and longitude data and altitude data.

[0045] Specifically, in this embodiment, the latitude, longitude, and altitude data of all vehicles within the target area during operation are collected by the vehicle-mounted communication terminal Tbox to form geographical location information. The latitude, longitude, and altitude data are collected in real time by the vehicle-mounted communication terminal Tbox and uploaded to the cloud platform. The latitude, longitude, and altitude data are normalized to ensure that the data are on the same scale, which is beneficial to the accuracy of subsequent clustering algorithms.

[0046] S2. Construct an atmospheric pressure estimation model using a clustering algorithm. Based on the geographical location information, calculate the current atmospheric pressure using the atmospheric pressure estimation model to obtain atmospheric pressure data outside the air filter.

[0047] In this embodiment, the step of constructing an atmospheric pressure estimation model using a clustering algorithm includes:

[0048] The system collects historical geographical location information of the target area traversed by the vehicle during its historical operation, as well as ambient atmospheric pressure data collected by sensors inside the air filter when the air compressor stops working; wherein, the historical geographical location information includes historical latitude and longitude data and historical altitude data.

[0049] With the optimization objective of minimizing the Euclidean distance between each historical geographic location point and the center point of its respective cluster, a clustering algorithm is used to divide the historical geographic location information within the target area into different clusters;

[0050] By using a regression algorithm to fit all historical altitude data within each cluster with ambient atmospheric pressure data, an atmospheric pressure estimation model is obtained.

[0051] Specifically, this embodiment uses the vehicle's onboard communication terminal (Tbox) to collect historical latitude and longitude data of the target area traversed by the vehicle during its historical operation. Simultaneously, it utilizes a Geographic Information System (GIS) database to query and record corresponding historical altitude data based on the latitude and longitude information. This historical latitude and longitude data and historical altitude data are integrated into historical geographic location information. Furthermore, even when the air compressor is not operating, ambient atmospheric pressure data is collected in real-time via a pressure sensor inside the air filter to ensure the data is unaffected by the air compressor's operating status. The collected historical geographic location information and ambient atmospheric pressure data are cleaned and formatted to ensure data validity and consistency. Then, clustering algorithms such as K-means, DBSCAN, or hierarchical clustering can be selected to divide the historical geographic location information within the target area into different clusters. For ease of understanding, this embodiment uses the K-means algorithm as an example. In detail, for the K-means algorithm, this embodiment sets the number of clusters to n, initializes n cluster centers, and iteratively calculates the Euclidean distance between each historical geographical location point and the cluster center of its respective cluster according to the optimization objective function of the clustering algorithm. The point is then assigned to the nearest cluster. The Euclidean distances from all historical geographical locations to their respective cluster centers are summed to obtain the total distance sum. Through the iterative process of the K-means algorithm, this total distance sum is continuously reduced until the optimization objective is reached, ultimately resulting in n clusters. Each cluster contains a set of historical geographical locations. In this embodiment, the minimax normalization algorithm is used to normalize the latitude, longitude, and altitude data of the historical geographical locations and the cluster centers, normalizing the data to the [0, 1] interval to ensure that the data are on the same scale. Specifically, the optimization objective function of the clustering algorithm is:

[0052]

[0053]

[0054] In the formula, D ij Let be the Euclidean distance between the j-th historical geographic location and the center of its cluster; i is the cluster index; n is the number of clusters; m is the number of historical geographic locations in the i-th cluster; d ij This represents the true distance (great circle distance) between the j-th historical geographical location and the center of its cluster. The threshold value is the preset true distance threshold, and "Subject to" represents the constraint condition. Since the true distance between the j-th historical geographical location and the center point of its cluster exceeds a certain range, the temperature and humidity variations within a cluster are significant, resulting in an unsatisfactory atmospheric pressure estimation model. Therefore, those skilled in the art can adjust the true distance threshold according to the specific implementation. For example, the threshold value can be adjusted... Set to 10km, constraining the range of each cluster to no more than 10km; Long i The normalized longitude data for the center point of the i-th cluster; Long ′ j Here is the normalized historical longitude data for the j-th historical geographical location; Lat i The normalized dimension data for the center point of the i-th cluster; Lat ′ j H represents the normalized historical latitude data for the j-th historical geographical location; i H represents the normalized elevation data of the center point of the i-th cluster; ′ j This represents the normalized historical elevation data for the j-th historical geographical location.

[0055] Next, for each cluster, the altitude data within it is extracted as feature values, and the ambient atmospheric pressure data is used as target values. A regression algorithm is then used to fit all historical altitude data and ambient atmospheric pressure data within each cluster to obtain a corresponding atmospheric pressure estimation model for each cluster. In this embodiment, for each cluster, P = a*(1-b*H) can be used. c The atmospheric pressure formula is fitted, with the altitude H and corresponding ambient atmospheric pressure data P of all data in the cluster as inputs, and the fitting parameters a, b, and c in the atmospheric pressure formula of the cluster as outputs. If a cluster does not have historical data, the fitting process for that cluster is skipped. This atmospheric pressure estimation model can predict the atmospheric pressure value in the target area based on the geographical location information of the vehicle. The finalized model can be deployed on the vehicle to collect the vehicle's geographical location information in real time and use the model to estimate the ambient atmospheric pressure. In this embodiment, the step of calculating the current atmospheric pressure based on the geographical location information using the atmospheric pressure estimation model to obtain the atmospheric pressure data outside the air filter includes:

[0056] The target cluster is obtained by finding the corresponding cluster based on the geographical location information.

[0057] The atmospheric pressure is calculated using the atmospheric pressure estimation model of the target cluster, and the atmospheric pressure data outside the air filter is obtained.

[0058] This embodiment can find the cluster to which the location belongs based on the real-time acquired geographic location information (latitude, longitude, and altitude) in the pre-trained clustering results. The pre-trained clustering results include the coordinates of the center point of each cluster and the boundary information of the cluster. This embodiment can use methods such as nearest neighbor search or spatial indexing to quickly find the cluster to which the real-time geographic location information belongs. If the geographic location information is near the boundary of multiple clusters, a decision can be made based on factors such as distance and area overlap to select the most suitable cluster. The atmospheric pressure estimation model corresponding to the found cluster is obtained, and the real-time acquired geographic location information is input into the atmospheric pressure estimation model of the target cluster to calculate the current atmospheric pressure value, thus obtaining the atmospheric pressure data outside the air filter. If the cluster to which the location belongs is not found, the great circle distance from the current geographic location information to the center of all known clusters is calculated, the nearest cluster containing the atmospheric pressure estimation model is found, and the atmospheric pressure is calculated using the atmospheric pressure estimation model of that cluster as the atmospheric pressure value outside the air filter.

[0059] S3. Compare the atmospheric pressure data on the outside of the air filter with the pressure data on the inside of the air filter to obtain the pressure difference between the two sides of the air filter.

[0060] S4. The air filter is detected based on the pressure difference across the air filter and a pre-determined adaptive warning threshold, and an air filter blockage warning signal is generated.

[0061] Specifically, in this embodiment, the pressure data Pin on the inside of the air filter is subtracted from the atmospheric pressure data Pout on the outside of the air filter to calculate the pressure difference ΔP between the two sides of the air filter, where ΔP = Pin - Pout. Since the pressure on the outside of the air filter (atmospheric side) is usually greater than or equal to the pressure on the inside of the air filter (intake side) when the air compressor is working, ΔP is usually a negative number. Then, this embodiment compares the pressure difference between the two sides of the air filter with a pre-determined adaptive warning threshold. When the pressure difference between the two sides of the air filter exceeds the adaptive warning threshold within a preset air filter detection period, the air filter is determined to be blocked, and an air filter blockage warning signal is generated. The process of determining the adaptive warning threshold includes:

[0062] Airflow and pressure difference data were collected under both normal and clogged air filter conditions.

[0063] Based on the airflow and pressure difference sample data, fit the airflow-pressure difference characteristic curves for the normal state and the air filter blockage state, respectively.

[0064] Obtain the distinguishing boundary of the air flow-pressure difference characteristic curve, and determine the adaptive warning threshold based on the distinguishing boundary.

[0065] With the vehicle running normally and the air filter not clogged, pressure difference data across the air filter was collected under different airflow rates. Based on the collected sample data, airflow-pressure difference characteristic curves were fitted for both the normal and clogged states of the air filter. A quadratic mathematical model can be used for fitting, i.e., P = a * Q. 2 +b*n+c, where Q is the airflow rate, and a, b, and c are fitting coefficients. On the two fitted characteristic curves, find the boundary point or boundary line that can distinguish between the normal and clogged states of the air filter. For example, in this embodiment, the boundary point or boundary line that can distinguish between the normal and clogged states of the air filter can be found by calculating the minimum distance and maximum difference between the two curves. Based on the distinguishing boundary, determine one or more adaptive warning thresholds. These adaptive warning thresholds should accurately reflect the transition of the air filter from a normal state to a clogged state. During vehicle operation, real-time data on the pressure difference across the air filter is collected, and the actual measured... The measured pressure difference is compared with a preset adaptive warning threshold. If the actual measured pressure difference continuously exceeds the adaptive warning threshold within a preset air filter detection period (e.g., t≥5 seconds), the air filter is determined to be clogged. When the air filter is determined to be clogged, the system generates an air filter clog warning signal to prompt the driver to check and replace the air filter in time. This signal can be conveyed to the driver through instrument panel display, audible alarm, etc. In summary, this embodiment can accurately and timely detect air filter clog by real-time monitoring of the pressure difference on both sides of the air filter and combining it with the adaptive warning threshold, thereby improving the vehicle's operational safety and reliability.

[0066] To illustrate the process of obtaining the adaptive warning threshold, this embodiment uses several vehicles marked as having clogged air filters as examples. This embodiment extracts the operating data of these vehicles for the five days immediately after air filter replacement from the vehicle operation database, serving as the dataset for the normal state. Simultaneously, this embodiment also obtains data for each vehicle for the five days prior to maintenance, serving as the dataset for the clogged state. To ensure data accuracy, this embodiment requires that the maximum flow rate in each day's data must exceed a preset gas flow rate threshold. For both the normal and clogged state datasets, this embodiment establishes univariate quadratic models. In the normal state model, the pressure difference (ΔP) is the dependent variable, the air flow rate (Q) is the independent variable, and a, b, and c are the model parameters. Similarly, in the clogged state model, this embodiment uses the same variable but a different parameter a. ′ b ′ c ′Next, this embodiment uses the least squares method to fit the parameters of the two models based on the collected data, and determines the distinguishing boundary between the normal state and the blockage state, i.e., the warning threshold. This embodiment considers that in the low airflow range, the normal state curve and the blockage state curve are close together and are more affected by pressure disturbances. If the boundary is set too close to the normal state curve, it will lead to false warnings. In the high airflow range, the fuel cell system is more sensitive to air supply, so early detection of blockage information is crucial. If the boundary is set too close to the blockage state curve, it will cause missed warnings. To solve this problem, this embodiment designs an adaptive boundary feature curve associated with airflow and the normal / blockage state curves. This curve is closer to the blockage state curve in the low airflow range and closer to the normal state curve in the high airflow range. By smoothly and adaptively adjusting the parameters, the accuracy of the warning threshold is ensured. The specific formula is as follows:

[0067]

[0068] In the formula, a(Q), b(Q), and c(Q) are the coefficients of the warning threshold curve when the flow rate is Q; w0 is the weight of the low flow rate range; w1 is the weight of the high flow rate range, where w0 and w1 are both greater than or equal to 0 and less than or equal to 1, and w0 ≥ w1; Q max Q represents the maximum air velocity of this type of air compressor; Q is the current air flow rate.

[0069] In practical applications, this embodiment can calculate the warning threshold in real time based on any air flow rate, such as... Figure 2 As shown, by plotting the fitting curves for the blocked sample, the fitting curves for the normal sample, and the warning threshold curve (taking a flow rate of 200g / s as an example), the relationship between them can be seen intuitively.

[0070] This invention provides a method for early warning of air filter blockage in a fuel cell system. The method involves real-time acquisition of geographical location information and air filter inner pressure data within a target area during vehicle operation; constructing an atmospheric pressure estimation model using a clustering algorithm; calculating the current atmospheric pressure based on the geographical location information using the atmospheric pressure estimation model to obtain atmospheric pressure data outside the air filter; comparing the atmospheric pressure data outside the air filter with the pressure data inside the air filter to obtain the pressure difference between the two sides of the air filter; and detecting the air filter based on the pressure difference and a pre-determined adaptive warning threshold to generate an air filter blockage warning signal. Compared with existing technologies, this method achieves accurate early warning of air filter blockage by real-time acquisition of geographical location and air filter inner pressure data, combined with an atmospheric pressure estimation model and an adaptive warning threshold.

[0071] It should be noted that the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0072] In one embodiment, such as Figure 3 As shown, this embodiment of the invention provides a fuel cell system air filter clogging early warning system, the system comprising:

[0073] The data acquisition module 101 is used to collect geographical location information and air filter inner pressure data in the target area during vehicle operation in real time; wherein, the geographical location information includes latitude and longitude data and altitude data;

[0074] The pressure estimation module 102 is used to construct an atmospheric pressure estimation model using a clustering algorithm, calculate the current atmospheric pressure based on the geographical location information using the atmospheric pressure estimation model, and obtain atmospheric pressure data outside the air filter.

[0075] Pressure analysis module 103 is used to compare the atmospheric pressure data outside the air filter with the pressure data inside the air filter to obtain the pressure difference between the two sides of the air filter;

[0076] The blockage warning module 104 is used to detect the air filter based on the pressure difference across the air filter and a pre-determined adaptive warning threshold, and generate an air filter blockage warning signal.

[0077] For specific limitations regarding a fuel cell system air filter clogging early warning system, please refer to the above-described limitations regarding a fuel cell system air filter clogging early warning method, which will not be repeated here. Those skilled in the art will recognize that the various modules and steps described in conjunction with the embodiments disclosed in this application can be implemented in hardware, software, or a combination of both. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0078] This invention provides a fuel cell system air filter clogging early warning system. The system uses a data acquisition module to collect real-time geographical location information and air filter inner pressure data within the target area during vehicle operation. A pressure estimation module uses a clustering algorithm to construct an atmospheric pressure estimation model. Based on the geographical location information, it calculates the current atmospheric pressure using the atmospheric pressure estimation model to obtain the atmospheric pressure data outside the air filter. A pressure analysis module compares the atmospheric pressure data outside the air filter with the pressure data inside the air filter to obtain the pressure difference between the two sides of the air filter. A clogging early warning module detects the air filter based on the pressure difference and a pre-determined adaptive early warning threshold, generating an air filter clogging early warning signal. Compared with existing technologies, this system achieves accurate early warning of air filter clogging status by collecting real-time geographical location and air filter inner pressure data, combined with an atmospheric pressure estimation model and an adaptive early warning threshold.

[0079] Figure 4 This invention provides a computer device including a memory, a processor, and a transceiver, which are connected to each other via a bus. The memory is used to store a set of computer program instructions and data, and can transmit the stored data to the processor. The processor can execute the program instructions stored in the memory to perform the steps of the above method.

[0080] The memory may include volatile memory or non-volatile memory, or both; the processor may be a central processing unit, a microprocessor, an application-specific integrated circuit, a programmable logic device, or a combination thereof. By way of example, but not limitation, the programmable logic device described above may be a complex programmable logic device, a field-programmable gate array, a general-purpose array logic, or any combination thereof.

[0081] In addition, memory can be a physically independent unit or integrated with the processor.

[0082] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have the same component arrangement.

[0083] In one embodiment, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0084] This invention provides a method, system, device, and medium for early warning of air filter blockage in a fuel cell system. The method for early warning of air filter blockage in a fuel cell system ensures the timeliness and accuracy of the data by collecting geographical location information and internal pressure data of the air filter in real time. At the same time, it dynamically calculates atmospheric pressure using an atmospheric pressure estimation model based on geographical location information, avoiding errors caused by changes in atmospheric pressure in traditional methods, and realizing accurate monitoring and early warning of air filter blockage.

[0085] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., SSD), etc.

[0086] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed, it can include the processes of the embodiments of the above methods.

[0087] The embodiments described above are merely preferred embodiments of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various improvements and substitutions without departing from the technical principles of this invention, and these improvements and substitutions should also be considered within the scope of protection of this application. Therefore, the scope of protection of this patent application should be determined by the scope of the claims.

Claims

1. A method for early warning of air filter blockage in a fuel cell system, characterized in that, Includes the following steps: The system collects real-time geographic location information and air filter inner pressure data within the target area during vehicle operation; wherein, the geographic location information includes latitude and longitude data and altitude data; An atmospheric pressure estimation model is constructed using a clustering algorithm. Based on the geographical location information, the current atmospheric pressure is calculated using the atmospheric pressure estimation model to obtain atmospheric pressure data outside the air filter. The atmospheric pressure data on the outside of the air filter is compared with the pressure data on the inside of the air filter to obtain the pressure difference on both sides of the air filter. The air filter is detected based on the pressure difference across the air filter and a pre-determined adaptive warning threshold, and an air filter blockage warning signal is generated. The steps for constructing an atmospheric pressure estimation model using a clustering algorithm include: The system collects historical geographical location information of the target area traversed by the vehicle during its historical operation, as well as ambient atmospheric pressure data collected by sensors inside the air filter when the air compressor stops working; wherein, the historical geographical location information includes historical latitude and longitude data and historical altitude data. With the optimization objective of minimizing the Euclidean distance between each historical geographic location point and the center point of its respective cluster, a clustering algorithm is used to divide the historical geographic location information within the target area into different clusters; By using a regression algorithm to fit all historical altitude data within each cluster with ambient atmospheric pressure data, an atmospheric pressure estimation model is obtained. The step of calculating the current atmospheric pressure using the atmospheric pressure estimation model based on the geographical location information to obtain the atmospheric pressure data outside the air filter includes: The target cluster is obtained by finding the corresponding cluster based on the geographical location information. The atmospheric pressure is calculated using the atmospheric pressure estimation model of the target cluster, and the atmospheric pressure data outside the air filter is obtained.

2. The method for early warning of air filter blockage in a fuel cell system as described in claim 1, characterized in that, The specific optimization objective function of the clustering algorithm is as follows: In the formula, Let be the Euclidean distance between the j-th historical geographic location and the center of its cluster; i is the cluster index; n is the number of clusters; m is the number of historical geographic locations in the i-th cluster. Let be the true distance between the j-th historical geographical location and the center point of its cluster; This is the preset real distance threshold.

3. The method for early warning of air filter blockage in a fuel cell system as described in claim 2, characterized in that, The formula for calculating the Euclidean distance is: In the formula, Let be the Euclidean distance between the j-th historical geographical location and the center of its cluster; The normalized longitude data for the center point of the i-th cluster; For the j-th historical geographical location point, the normalized historical longitude data is provided. The normalized dimension data for the center point of the i-th cluster; For the j-th historical geographical location point, the normalized historical latitude data is provided. The normalized elevation data for the center point of the i-th cluster; This represents the normalized historical elevation data for the j-th historical geographical location.

4. The method for early warning of air filter blockage in a fuel cell system as described in claim 1, characterized in that, The step of detecting the air filter based on the pressure difference across the air filter and a pre-determined adaptive warning threshold to generate an air filter blockage warning signal includes: The pressure difference across the air filter is compared with a predetermined adaptive warning threshold. If the pressure difference across the air filter exceeds the adaptive warning threshold within a preset air filter detection period, the air filter is determined to be clogged, and an air filter clog warning signal is generated.

5. The method for early warning of air filter blockage in a fuel cell system as described in claim 1, characterized in that, The process of determining the adaptive early warning threshold includes: Airflow and pressure difference data were collected under both normal and clogged air filter conditions. Based on the airflow and pressure difference sample data, fit the airflow-pressure difference characteristic curves for the normal state and the air filter blockage state, respectively. Obtain the distinguishing boundary of the air flow-pressure difference characteristic curve, and determine the adaptive warning threshold based on the distinguishing boundary.

6. A pre-warning system for air filter blockage in a fuel cell system, characterized in that, The fuel cell system air filter clogging early warning method according to any one of claims 1 to 5, wherein the system comprises: The data acquisition module is used to collect real-time geographic location information and air filter inner pressure data within the target area during vehicle operation; wherein, the geographic location information includes latitude and longitude data and altitude data; The pressure estimation module is used to construct an atmospheric pressure estimation model using a clustering algorithm, and calculate the current atmospheric pressure based on the geographical location information using the atmospheric pressure estimation model to obtain atmospheric pressure data outside the air filter. The pressure analysis module is used to compare the atmospheric pressure data outside the air filter with the pressure data inside the air filter to obtain the pressure difference between the two sides of the air filter. The blockage warning module is used to detect the air filter based on the pressure difference across the air filter and a pre-determined adaptive warning threshold, and generate an air filter blockage warning signal.

7. A computer device, characterized in that: The device includes a processor and a memory, the processor being connected to the memory for storing computer programs, and the processor for executing the computer programs stored in the memory to cause the computer device to perform the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that, when executed, implements the method as described in any one of claims 1 to 5.

Images