A method and system for predicting the remaining life of a vehicle filter element

Abstract

The present invention provides a method and system for predicting the remaining life of a vehicle filter element, the method comprising: determining the effective flow resistance value at the vehicle filter in the current mileage section as the current effective flow resistance value; updating the effective flow resistance value sequence according to the current effective flow resistance value; the effective flow resistance value sequence includes multiple effective flow resistance values; using a linear regression algorithm, processing the multiple effective flow resistance values ​​in the updated effective flow resistance value sequence to obtain a linear regression equation; determining the remaining life of the vehicle filter element according to the linear regression equation. The present invention can determine the remaining life of the vehicle filter element by constructing and updating the effective flow resistance value sequence in combination with a linear regression algorithm, thereby improving the accuracy and automation of determining the opportunity to replace the vehicle filter element.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle filters, and in particular to a method and system for predicting the remaining life of a vehicle filter element. Background Art

[0002] The vehicle filter is an important component to reduce the wear of the automobile engine. The filter element of the vehicle filter needs to be replaced in time to ensure the normal operation of the automobile engine. At present, there are two ways to judge the opportunity to replace the vehicle filter element. One is to maintain the filter element after using it for a fixed mileage or a fixed time according to the vehicle maintenance instructions. This method has the following disadvantages: if the vehicle is in good condition, the filter element still performs well after using it for a fixed mileage or a fixed time, and the filter element is replaced when it reaches its service life, resulting in a waste of resources. If the vehicle is in very poor condition, the filter element may be clogged before it is used for a fixed mileage or a fixed time. Failure to replace the filter element in time will cause poor engine air intake, increase engine fuel consumption, and damage the engine.

[0003] Another method is to set a pressure alarm switch to detect whether the maximum flow resistance at the filter element has reached the flow resistance threshold value, and determine whether to replace the filter element. The flow resistance value of the filter element represents the service life of the filter element. During the driving process of the vehicle, the flow resistance value of the filter element is affected by the medium flow rate and presents a wave-like change. The flow rate of the medium is affected by the load state of the engine, and the load state of the engine is affected by many factors such as the driver's driving habits, vehicle load, and vehicle running posture. The pressure alarm switch uses a certain state at a certain moment to measure the flow resistance of the entire filter element, resulting in inaccurate opportunity judgment. For example, when the driver steps on the accelerator, the engine load increases, the flow resistance value of the filter element increases, and is higher than the flow resistance threshold value. At this time, the filter element performance is intact, but the pressure alarm switch generates a false alarm.

[0004] Therefore, there is an urgent need for a technology that accurately determines the opportunity to replace the vehicle filter element. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for predicting the remaining life of a vehicle filter element, which can improve the accuracy and automation of determining the opportunity to replace the vehicle filter element.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] A method for predicting the remaining life of a vehicle filter element, comprising:

[0008] Determine the effective flow resistance value at the vehicle filter within the current mileage segment as the current effective flow resistance value;

[0009] Update the effective flow resistance value sequence according to the current effective flow resistance value; the effective flow resistance value sequence includes multiple effective flow resistance values;

[0010] Using a linear regression algorithm, multiple effective flow resistance values ​​in the updated effective flow resistance value sequence are processed to obtain a linear regression equation;

[0011] According to the linear regression equation, the remaining life of the vehicle filter element is determined.

[0012] Optional,

[0013] The lengths of the mileage segments corresponding to the multiple effective flow resistance values ​​in the effective flow resistance value sequence are all equal;

[0014] In the effective flow resistance value sequence, except for the first effective flow resistance value, the starting point of the mileage segment corresponding to any effective flow resistance value is the end point of the mileage segment corresponding to the previous effective flow resistance value;

[0015] Except for the last effective flow resistance value in the effective flow resistance value sequence, the end point of a mileage segment corresponding to any effective flow resistance value is the starting point of a mileage segment corresponding to the next effective flow resistance value.

[0016] Optionally, determining the effective flow resistance value at the vehicle filter in the current mileage segment as the current effective flow resistance value specifically includes:

[0017] Acquiring a real-time flow resistance value at the vehicle filter at a preset frequency until the mileage of the vehicle reaches the length of the current mileage segment;

[0018] dividing the plurality of real-time flow resistance values ​​into a plurality of real-time flow resistance value sequences;

[0019] Determine the theoretical flow resistance value corresponding to each real-time flow resistance value sequence;

[0020] Using a K-means algorithm to cluster the plurality of theoretical flow resistance values ​​to obtain a plurality of cluster centers;

[0021] The maximum effective flow resistance value corresponding to the multiple cluster centers is determined as the effective flow resistance value at the vehicle filter in the current mileage segment.

[0022] Optionally, determining the theoretical flow resistance value corresponding to each real-time flow resistance value sequence specifically includes:

[0023] Determine any real-time flow resistance value sequence as the current real-time flow resistance value sequence;

[0024] Deleting the maximum value and the minimum value in the current real-time flow resistance value sequence to obtain an updated current real-time flow resistance value sequence;

[0025] Determine the average value of multiple real-time flow resistances in the updated current real-time flow resistance sequence, which is the theoretical flow resistance corresponding to the updated current real-time flow resistance sequence.

[0026] Optionally, clustering the multiple theoretical flow resistances using the K-means algorithm to obtain multiple cluster centers, specifically including:

[0027] Determine that the types of theoretical flow resistances with equal values are the same;

[0028] Determine the quantity of theoretical flow resistances corresponding to each type among the multiple theoretical flow resistances;

[0029] Construct two-dimensional flow resistance data with different types of theoretical flow resistances as the ordinate and the quantity of theoretical flow resistances included in the corresponding type of the ordinate as the abscissa;

[0030] Take the two-dimensional flow resistance data with the largest abscissa as the first cluster center;

[0031] Take the two-dimensional flow resistance data with the largest ordinate as the second cluster center;

[0032] Let the iteration number n = 1;

[0033] Determine any two-dimensional flow resistance data as the current two-dimensional flow resistance data;

[0034] Calculate the distance between the current two-dimensional flow resistance data and the first cluster center as the first distance;

[0035] Calculate the distance between the current two-dimensional flow resistance data and the second cluster center as the second distance;

[0036] Add the current two-dimensional flow resistance data to the cluster corresponding to the smaller value among the first distance and the second distance, update the current two-dimensional flow resistance data, and return to the step "Calculate the distance between the current two-dimensional flow resistance data and the first cluster center as the first distance" until all two-dimensional flow resistance data are traversed to obtain the first cluster and the second cluster;

[0037] Take the average value of the multiple two-dimensional flow resistance data in the first cluster as the updated first cluster center;

[0038] Take the average value of the multiple two-dimensional flow resistance data in the second cluster as the updated second cluster center;

[0039] Increase the value of the iteration number n by 1 and return to the step "Determine any two-dimensional flow resistance data as the current two-dimensional flow resistance data" until the first cluster center in this iteration is equal to the first cluster center in the previous iteration, and the second cluster center in this iteration is equal to the second cluster center in the previous iteration, to obtain the multiple cluster centers.

[0040] Optionally, updating the effective flow resistance value sequence according to the current effective flow resistance value specifically includes:

[0041] Add the current effective flow resistance value as the last element of the effective flow resistance value sequence to the effective flow resistance value sequence to obtain an updated effective flow resistance value sequence;

[0042] Determine whether the number of effective flow resistance values ​​in the effective flow resistance value sequence updated once is greater than the number of standard elements in the effective flow resistance value sequence, and obtain a first determination result;

[0043] If the first judgment result is no, the current mileage segment is updated and the process returns to the step of "determining the effective flow resistance value at the vehicle filter within the current mileage segment as the current effective flow resistance value";

[0044] If the first judgment result is yes, the first element in the updated effective flow resistance value sequence is deleted to obtain an updated effective flow resistance value sequence.

[0045] Optionally, the use of a linear regression algorithm to process multiple effective flow resistance values ​​in the updated effective flow resistance value sequence to obtain a linear regression equation specifically includes:

[0046] Construct the initial linear regression equation y=ax+b;

[0047] According to the multiple effective flow resistance values ​​in the updated effective flow resistance value sequence, using the formula and Determine the coefficients of the initial linear regression equation to obtain the linear regression equation;

[0048] Where a and b are the coefficients of the initial linear regression equation; N is the number of standard elements in the effective flow resistance value sequence, x i is the serial number of the effective flow resistance value in the updated effective flow resistance value sequence; y i is the i-th effective flow resistance value in the updated effective flow resistance value sequence.

[0049] Optionally, determining the remaining life of the vehicle filter element according to the linear regression equation specifically includes:

[0050] Substituting the number of standard elements of the effective flow resistance value sequence as an independent variable into the linear regression equation, the dependent variable is obtained as the total effective flow resistance value of the updated effective flow resistance value sequence;

[0051] Determine whether the total effective flow resistance value is less than a first total effective flow resistance value threshold value, and obtain a second determination result;

[0052] If the second judgment result is no, it is determined that the remaining life of the filter element is 0, and a first warning signal is issued; the first warning signal is used to prompt the driver to replace the filter element;

[0053] If the second judgment result is yes, then according to the total effective flow resistance, the formula Determine the remaining filter life;

[0054] Among them, A A , A 1 , A 2 They respectively represent the remaining life of the filter element, the total effective flow resistance and the first total effective flow resistance threshold.

[0055] Optionally, according to the total effective flow resistance, using the formula After determining the remaining filter life, also include:

[0056] Determine whether the total effective flow resistance value is less than a second total effective flow resistance value threshold value, and obtain a third determination result; the second total effective flow resistance value threshold value is less than the first total effective flow resistance value threshold value;

[0057] If the third judgment result is no, a second warning signal is issued; the second warning signal is used to remind the driver that the remaining life of the filter element is insufficient;

[0058] If the third judgment result is yes, the current mileage segment is updated and the process returns to the step of “determining the effective flow resistance value at the vehicle filter within the current mileage segment as the current effective flow resistance value”.

[0059] A prediction system for the remaining life of a vehicle filter element, comprising:

[0060] A current effective flow resistance value determination module, used to determine the effective flow resistance value at the vehicle filter within the current mileage section as the current effective flow resistance value;

[0061] An effective flow resistance value sequence updating module, used for updating an effective flow resistance value sequence according to a current effective flow resistance value; the effective flow resistance value sequence includes a plurality of effective flow resistance values;

[0062] A linear regression equation determination module is used to process multiple effective flow resistance values ​​in the updated effective flow resistance value sequence using a linear regression algorithm to obtain a linear regression equation;

[0063] The remaining life determination module is used to determine the remaining life of the vehicle filter element according to the linear regression equation.

[0064] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0065] The present invention provides a method and system for predicting the remaining life of a vehicle filter element, the method comprising: determining the effective flow resistance value at the vehicle filter within the current mileage section as the current effective flow resistance value; updating the effective flow resistance value sequence according to the current effective flow resistance value; the effective flow resistance value sequence includes multiple effective flow resistance values; using a linear regression algorithm, processing the multiple effective flow resistance values ​​in the updated effective flow resistance value sequence to obtain a linear regression equation; determining the remaining life of the vehicle filter element according to the linear regression equation. The present invention can determine the remaining life of the vehicle filter element by constructing and updating the effective flow resistance value sequence in combination with a linear regression algorithm, thereby improving the accuracy and automation of determining the opportunity to replace the vehicle filter element. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0067] Figure 1 The flowchart of the method for predicting the remaining life of the vehicle filter element in the embodiment of the present invention is shown in FIG. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0069] The purpose of the present invention is to provide a method and system for predicting the remaining life of a vehicle filter element, which can improve the accuracy and automation of determining the opportunity to replace the vehicle filter element.

[0070] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0071] Example

[0072] like Figure 1 The present invention provides a method for predicting the remaining life of a vehicle filter element, comprising:

[0073] Step 101: determining an effective flow resistance value at a vehicle filter within a current mileage segment as a current effective flow resistance value;

[0074] Step 102: Update the effective flow resistance sequence according to the current effective flow resistance value; the effective flow resistance sequence includes multiple effective flow resistance values; the lengths of the mileage segments corresponding to the multiple effective flow resistance values in the effective flow resistance sequence are equal;

[0075] Except for the first effective flow resistance value in the effective flow resistance sequence, the starting point of the mileage segment corresponding to any effective flow resistance value is the ending point of the mileage segment corresponding to the previous effective flow resistance value;

[0076] Except for the last effective flow resistance value in the effective flow resistance sequence, the ending point of the mileage segment corresponding to any effective flow resistance value is the starting point of the mileage segment corresponding to the next effective flow resistance value.

[0077] Step 103: Use the linear regression algorithm to process the multiple effective flow resistance values in the updated effective flow resistance sequence to obtain a linear regression equation;

[0078] Step 104: Determine the remaining life of the vehicle-mounted filter element according to the linear regression equation.

[0079] Step 101 specifically includes:

[0080] Obtain the real-time flow resistance value at the vehicle-mounted filter at a preset frequency until the mileage traveled by the vehicle reaches the length of the current mileage segment;

[0081] Divide the multiple real-time flow resistance values into multiple real-time flow resistance sequences;

[0082] Determine the theoretical flow resistance value corresponding to each real-time flow resistance sequence;

[0083] Use the K-means algorithm to perform clustering processing on the multiple theoretical flow resistance values to obtain multiple cluster centers;

[0084] Determine that the maximum effective flow resistance value corresponding to the multiple cluster centers is the effective flow resistance value at the vehicle-mounted filter within the current mileage segment.

[0085] Determine the theoretical flow resistance value corresponding to each real-time flow resistance sequence, specifically including:

[0086] Determine any real-time flow resistance sequence as the current real-time flow resistance sequence;

[0087] Delete the maximum and minimum values in the current real-time flow resistance sequence to obtain the updated current real-time flow resistance sequence;

[0088] Determine the average value of the multiple real-time flow resistance values in the updated current real-time flow resistance sequence as the theoretical flow resistance value corresponding to the updated current real-time flow resistance sequence.

[0089] Among them, using the K-means algorithm to perform clustering processing on the multiple theoretical flow resistance values to obtain multiple cluster centers specifically includes:

[0090] The types of theoretical flow resistance values ​​with equal values ​​are determined to be the same;

[0091] Determining the number of theoretical flow resistance values ​​corresponding to each type of the plurality of theoretical flow resistance values;

[0092] The theoretical flow resistance values ​​of different types are used as the ordinate, and the number of theoretical flow resistance values ​​contained in the type corresponding to the ordinate is used as the abscissa to construct two-dimensional flow resistance data;

[0093] The two-dimensional flow resistance data with the largest horizontal coordinate is taken as the first cluster center;

[0094] The two-dimensional flow resistance data with the largest ordinate is used as the second cluster center;

[0095] Let the number of iterations n = 1;

[0096] Determine any two-dimensional flow resistance data as current two-dimensional flow resistance data;

[0097] Calculate the distance between the current two-dimensional flow resistance data and the first cluster center as the first distance;

[0098] Calculate the distance between the current two-dimensional flow resistance data and the second cluster center as the second distance;

[0099] Add the current two-dimensional flow resistance data to the cluster corresponding to the smaller value of the first distance and the second distance, update the current two-dimensional flow resistance data and return to the step of "calculating the distance between the current two-dimensional flow resistance data and the first cluster center as the first distance", until all the two-dimensional flow resistance data are traversed to obtain the first cluster and the second cluster;

[0100] The average value of the plurality of two-dimensional flow resistance data in the first cluster is used as the updated first cluster center;

[0101] The average value of the plurality of two-dimensional flow resistance data in the second cluster is used as the updated second cluster center;

[0102] Increase the value of the iteration number n by 1 and return to the step "determine any two-dimensional flow resistance data as the current two-dimensional flow resistance data" until the first cluster center in this iteration is equal to the first cluster center in the previous iteration, and the second cluster center in this iteration is equal to the second cluster center in the previous iteration, and multiple cluster centers are obtained.

[0103] Step 102 specifically includes:

[0104] Add the current effective flow resistance value as the last element of the effective flow resistance value sequence to the effective flow resistance value sequence to obtain an updated effective flow resistance value sequence;

[0105] Determine whether the number of effective flow resistance values ​​in the effective flow resistance value sequence updated once is greater than the number of standard elements in the effective flow resistance value sequence, and obtain a first determination result;

[0106] If the first judgment result is no, the current mileage segment is updated and the process returns to the step of "determining the effective flow resistance value at the vehicle filter within the current mileage segment as the current effective flow resistance value";

[0107] If the first judgment result is yes, the first element in the updated effective flow resistance value sequence is deleted to obtain an updated effective flow resistance value sequence.

[0108] Step 103 specifically includes:

[0109] Construct the initial linear regression equation y=ax+b;

[0110] According to the multiple effective flow resistance values ​​in the updated effective flow resistance value sequence, using the formula and Determine the coefficients of the initial linear regression equation to obtain the linear regression equation;

[0111] Where a and b are the coefficients of the initial linear regression equation; N is the number of standard elements in the effective flow resistance value sequence, x i is the serial number of the effective flow resistance value in the updated effective flow resistance value sequence; y i is the i-th effective flow resistance value in the updated effective flow resistance value sequence.

[0112] Step 104 specifically includes:

[0113] The number of standard elements in the effective flow resistance value sequence is used as an independent variable and substituted into the linear regression equation to obtain the total effective flow resistance value as the dependent variable of the updated effective flow resistance value sequence;

[0114] Determine whether the total effective flow resistance value is less than a first total effective flow resistance value threshold value, and obtain a second determination result;

[0115] If the second judgment result is no, it is determined that the remaining life of the filter element is 0, and a first warning signal is issued; the first warning signal is used to prompt the driver to replace the filter element;

[0116] If the second judgment result is yes, then according to the total effective flow resistance, use the formula Determine the remaining filter life;

[0117] Among them, A A , A 1 , A 2 They respectively represent the remaining life of the filter element, the total effective flow resistance and the first total effective flow resistance threshold.

[0118] According to the total effective flow resistance, using the formula After determining the remaining filter life, also include:

[0119] Determine whether the total effective flow resistance value is less than a second total effective flow resistance value threshold value, and obtain a third determination result; the second total effective flow resistance value threshold value is less than the first total effective flow resistance value threshold value;

[0120] If the third judgment result is no, a second warning signal is issued; the second warning signal is used to remind the driver that the remaining life of the filter element is insufficient;

[0121] If the third judgment result is yes, the current mileage segment is updated and the process returns to the step of “determining the effective flow resistance value at the vehicle filter within the current mileage segment as the current effective flow resistance value”.

[0122] The present invention provides a prediction algorithm for the remaining life of a vehicle filter element, which is run on an intelligent filtering system, which includes a traditional filtering system, a pressure sensor installed on the filtering system, and an intelligent controller with functions such as filter element mileage or usage time statistics, digital calculation, information storage, and CAN communication. The life prediction algorithm is divided into three parts: life data statistics, life data processing, and life prediction result display.

[0123] 1. Life expectancy statistics

[0124] An array is created in the system. The subscript value of the array represents 10 times of each flow resistance value. For example, if the real-time flow resistance value is 3.5 kPa, Flow

[35] is used instead. The system here refers to the intelligent controller embedded software system. The subscript of the array is the flow resistance value. For the air filter, the array has 100 members, and the fuel filter has 120 members. The array is used to represent the number of times each flow resistance value appears.

[0125] The controller reads the flow resistance value of the filter 12 times continuously every 5 seconds, with an interval of 10ms each time. The CAN signal sent by the pressure detection device can be obtained from the CAN line, or it can be directly read from the pressure sensor installed on the smart filter; in order to obtain a more accurate data, it is necessary to process these 12 data (i.e., the real-time flow resistance value sequence), and the processing method is as follows: remove a maximum value, then remove a minimum value, and then calculate the average value of the remaining 10 values, and finally use the average value to retain 1 decimal place as the valid data collected this time (i.e., the theoretical flow resistance value corresponding to the real-time flow resistance value sequence); Specifically, each data is a separate value, and the program will obtain the maximum and minimum values ​​through 2 rounds of comparison, and the data obtained is a value: the method for obtaining the maximum and minimum values ​​is as follows: take the maximum value, assign 0 to the variable max, and then compare each data with max. If the data is larger than the value in max, assign the current data to max. After all comparisons are completed, the value in max is the maximum value; take the minimum value, assign 9999 to the variable min, and then compare each data with mim. If the data is smaller than the value in min, assign the current data to min. After all comparisons are completed, the value in min is the minimum value.

[0126] After obtaining the effective value (theoretical flow resistance value) collected this time, add 1 to the array content representing this effective value. In other words, count the number of occurrences of each flow resistance, and save the number of occurrences in the array representing the flow resistance. For example, Flow

[35] =10 means that 3.5kPa appears 10 times, 3.5kPa appears once, and the content in Flow

[35] is increased by 1. Adding 1 means the value of the member in the array is increased by 1. When the value in Flow

[35] is increased by 1, it is 11.

[0127] 2. Lifespan Data Processing

[0128] The array data obtained from the life data statistics needs to be processed every 50 km the vehicle travels.

[0129] 1. Every time the vehicle travels 50 km, the system will perform a two-dimensional K-means calculation on the data of multiple theoretical flow resistance values. Because the larger flow resistance value needs to be paid attention to during the use of the filter element, the larger cluster center is selected as the effective flow resistance value of this 50 km.

[0130] Specifically, the K-means algorithm is as follows:

[0131] (1) Select two initialized samples as the initial cluster centers; one cluster center is the non-zero array with the largest subscript, and the other is the array member with the largest subscript value.

[0132] (2) For each sample in the data set, calculate its distance to the two cluster centers respectively, and classify it into the class corresponding to the cluster center with the smallest distance. The x-axis represents the flow resistance value, which is the array subscript, and the y-axis represents the number of occurrences of the flow resistance; point A (x1, y1), point B (x2, y2), the distance from point A to point B is:

[0133] (3) Recalculate the cluster center of each cluster, that is, the centroid of all samples belonging to the cluster; the centroid of the sample is the average value of the sample. Here is two-dimensional data, each data has an X-axis and a Y-axis. The X-axis represents the number of times the data appears, and the Y-axis represents the specific value of the data. For example, the point (563, 4.5) means that 4.5 kpa appears 563 times.

[0134] Repeat steps (2)-(3) above until the results of two consecutive calculations are equal, and obtain two cluster centers. Select the larger cluster center as the value of the effective flow resistance.

[0135] 2. When the vehicle has collected 500km (10 clusters) of data, the linear regression method is used to calculate it, and the last point of the calculation result after the linear regression is used as the final effective flow resistance (i.e. the total effective flow resistance). The result obtained by using linear regression is smoother than the result obtained in step 1; every time the vehicle travels 50km, the initial data will be replaced and recalculated after supplementing with new data, which is similar to the circular recording of the driving recorder; for example: in chronological order, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 data are collected in sequence, of which 1 is the earliest collected data and 10 is the latest collected data. When there is new data 11, the control program will replace the data with 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, a total of 10 data. This is to replace the earliest data with the latest data, but the order of the data must still be maintained.

[0136] The linear regression algorithm is as follows:

[0137] Assume that there are N known points (the 10 largest cluster centers obtained after 10 clusterings), and let the equation of this line be: y = a x + b. After calculating a and b, y = ax + b will be completed. Then take x as 10, and the y obtained is the last point. The actual calculation of the remaining life percentage uses this data.

[0138] The calculation formulas for a and b are as follows:

[0139]

[0140]

[0141] 3. If the calculation result of step 2 is less than the second effective total flow resistance threshold (80% of the first effective total flow resistance threshold, the first effective total flow resistance threshold is the flow resistance value at the end of the filter element's life, for example, the air filter is 6.2kpa, for the same engine, the final flow resistance (the first effective total flow resistance threshold) is fixed. This data will be given by the host designer at the beginning of product development), the system will send a message to the CAN bus that the filter element life is less than 80%. If the result is greater than the second effective total flow resistance threshold and less than the first effective total flow resistance threshold, the system will send a message to remind you to prepare the filter element in advance. If the result exceeds the first effective total flow resistance threshold, the system will send a message to replace the filter element in time.

[0142] 3. Lifespan prediction results show

[0143] In order to prevent huge fluctuations in the displayed remaining life data, the program will update the remaining life result every 10km, and the updated content is one-fifth of the difference between the current displayed content and the calculated content. One-fifth, assuming that the last calculated result is Akm, and the result of this calculation is Bkm, then the update from Akm to Bkm is completed in 5 times, and each time |(AB)| / 5 is displayed. In actual situations, there is such a situation: the vehicle is fully loaded a moment ago, and the cargo is unloaded the next moment. Such a gap will cause changes in the engine output power, reduce the flow rate through the filter element medium, and cause a sharp increase in the remaining life. In order to reduce the impact of information on users, a multiple update solution is used. It is expected that the result of the last calculation will be updated every 50km.

[0144] 4. There are three ways to express the remaining life:

[0145] (1) The remaining life of the filter element is expressed in percentage. This is similar to the percentage of remaining battery power displayed on computers and mobile phones. The calculation method is as follows:

[0146] (2) The remaining mileage that the filter element can travel. This is calculated using the percentage of the remaining life of the filter element. For road vehicles, this method can be used:

[0147] (3) Or the remaining time the filter can run. This is calculated using the percentage of remaining use of the filter. For non-road vehicles, this method can be used:

[0148] In addition, the present invention also provides a system for predicting the remaining life of a vehicle filter element, comprising:

[0149] A current effective flow resistance value determination module, used to determine the effective flow resistance value at the vehicle filter within the current mileage section as the current effective flow resistance value;

[0150] An effective flow resistance value sequence updating module is used to update the effective flow resistance value sequence according to the current effective flow resistance value; the effective flow resistance value sequence includes multiple effective flow resistance values;

[0151] A linear regression equation determination module is used to process multiple effective flow resistance values ​​in the updated effective flow resistance value sequence using a linear regression algorithm to obtain a linear regression equation;

[0152] The remaining life determination module is used to determine the remaining life of the vehicle filter element according to a linear regression equation.

[0153] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0154] This article uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the method and core ideas of the present invention. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for predicting the remaining life of a vehicle filter element. It is characterized in that The method comprises: Determine the effective flow resistance value at the vehicle filter within the current mileage segment as the current effective flow resistance value; Update the effective flow resistance value sequence according to the current effective flow resistance value; the effective flow resistance value sequence includes multiple effective flow resistance values; Using a linear regression algorithm, multiple effective flow resistance values ​​in the updated effective flow resistance value sequence are processed to obtain a linear regression equation; Determining the remaining life of the vehicle filter element according to the linear regression equation; Determining the remaining life of the vehicle filter element according to the linear regression equation specifically includes: Substituting the number of standard elements of the effective flow resistance value sequence as an independent variable into the linear regression equation, the dependent variable is obtained as the total effective flow resistance value of the updated effective flow resistance value sequence; Determine whether the total effective flow resistance value is less than a first total effective flow resistance value threshold value, and obtain a second determination result; If the second judgment result is no, it is determined that the remaining life of the filter element is 0, and a first warning signal is issued; the first warning signal is used to prompt the driver to replace the filter element; If the second judgment result is yes, then according to the total effective flow resistance, the formula Determine the remaining filter life; Among them, A A , A 1 , A 2 They respectively represent the remaining life of the filter element, the total effective flow resistance and the first total effective flow resistance threshold.

2. The method for predicting the remaining life of a vehicle filter element according to claim 1, It is characterized in that The lengths of the mileage segments corresponding to the multiple effective flow resistance values ​​in the effective flow resistance value sequence are all equal; In the effective flow resistance value sequence, except for the first effective flow resistance value, the starting point of the mileage segment corresponding to any effective flow resistance value is the end point of the mileage segment corresponding to the previous effective flow resistance value; Except for the last effective flow resistance value in the effective flow resistance value sequence, the end point of a mileage segment corresponding to any effective flow resistance value is the starting point of a mileage segment corresponding to the next effective flow resistance value.

3. The method for predicting the remaining life of a vehicle filter element according to claim 1, It is characterized in that The determining of the effective flow resistance value at the vehicle filter within the current mileage segment is the current effective flow resistance value, specifically comprising: Acquiring a real-time flow resistance value at the vehicle filter at a preset frequency until the mileage of the vehicle reaches the length of the current mileage segment; dividing the plurality of real-time flow resistance values ​​into a plurality of real-time flow resistance value sequences; Determine the theoretical flow resistance value corresponding to each real-time flow resistance value sequence; Using a K-means algorithm to cluster the plurality of theoretical flow resistance values ​​to obtain a plurality of cluster centers; The maximum effective flow resistance value corresponding to the multiple cluster centers is determined as the effective flow resistance value at the vehicle filter in the current mileage segment.

4. The method for predicting the remaining life of a vehicle filter element according to claim 3, It is characterized in that Determining the theoretical flow resistance value corresponding to each real-time flow resistance value sequence specifically includes: Determine any real-time flow resistance value sequence as the current real-time flow resistance value sequence; Deleting the maximum value and the minimum value in the current real-time flow resistance value sequence to obtain an updated current real-time flow resistance value sequence; An average value of a plurality of real-time flow resistance values ​​in the updated current real-time flow resistance value sequence is determined as a theoretical flow resistance value corresponding to the updated current real-time flow resistance value sequence.

5. The method for predicting the remaining life of a vehicle filter element according to claim 3, It is characterized in that The method of clustering the plurality of theoretical flow resistance values ​​using the K-means algorithm to obtain a plurality of cluster centers specifically includes: The types of theoretical flow resistance values ​​with equal values ​​are determined to be the same; Determine the number of theoretical flow resistance values ​​corresponding to each type of the plurality of theoretical flow resistance values; The theoretical flow resistance values ​​of different types are used as the ordinate, and the number of theoretical flow resistance values ​​contained in the type corresponding to the ordinate is used as the abscissa to construct two-dimensional flow resistance data; The two-dimensional flow resistance data with the largest horizontal coordinate is taken as the first cluster center; The two-dimensional flow resistance data with the largest ordinate is used as the second cluster center; Let the number of iterations n = 1; Determine any two-dimensional flow resistance data as current two-dimensional flow resistance data; Calculate the distance between the current two-dimensional flow resistance data and the first cluster center as the first distance; Calculate the distance between the current two-dimensional flow resistance data and the second cluster center as the second distance; Add the current two-dimensional flow resistance data to the cluster corresponding to the smaller value of the first distance and the second distance, update the current two-dimensional flow resistance data and return to the step of "calculating the distance between the current two-dimensional flow resistance data and the first cluster center as the first distance", until all the two-dimensional flow resistance data are traversed to obtain the first cluster and the second cluster; The average value of the plurality of two-dimensional flow resistance data in the first cluster is used as the updated first cluster center; The average value of the plurality of two-dimensional flow resistance data in the second cluster is used as the updated second cluster center; Increase the value of the iteration number n by 1 and return to step "determine any two-dimensional flow resistance data as the current two-dimensional flow resistance data" until the first cluster center in this iteration is equal to the first cluster center in the previous iteration, and the second cluster center in this iteration is equal to the second cluster center in the previous iteration, and multiple cluster centers are obtained.

6. The method for predicting the remaining life of a vehicle filter element according to claim 5, It is characterized in that The updating of the effective flow resistance value sequence according to the current effective flow resistance value specifically includes: Add the current effective flow resistance value as the last element of the effective flow resistance value sequence to the effective flow resistance value sequence to obtain an updated effective flow resistance value sequence; Determine whether the number of effective flow resistance values ​​in the effective flow resistance value sequence updated once is greater than the number of standard elements in the effective flow resistance value sequence, and obtain a first determination result; If the first judgment result is no, the current mileage segment is updated and the process returns to step "determining the effective flow resistance value at the vehicle filter within the current mileage segment as the current effective flow resistance value"; If the first judgment result is yes, the first element in the updated effective flow resistance value sequence is deleted to obtain an updated effective flow resistance value sequence.

7. The method for predicting the remaining life of a vehicle filter element according to claim 1, It is characterized in that The linear regression algorithm is used to process multiple effective flow resistance values ​​in the updated effective flow resistance value sequence to obtain a linear regression equation, which specifically includes: Construct the initial linear regression equation y=ax+b; According to the multiple effective flow resistance values ​​in the updated effective flow resistance value sequence, using the formula and Determine the coefficients of the initial linear regression equation to obtain the linear regression equation; Where a and b are the coefficients of the initial linear regression equation; N is the number of standard elements in the effective flow resistance value sequence, x i is the serial number of the effective flow resistance value in the updated effective flow resistance value sequence; y i is the i-th effective flow resistance value in the updated effective flow resistance value sequence.

8. The method for predicting the remaining life of a vehicle filter element according to claim 1, It is characterized in that According to the total effective flow resistance, using the formula After determining the remaining filter life, also include: Determine whether the total effective flow resistance value is less than a second total effective flow resistance value threshold value, and obtain a third determination result; the second total effective flow resistance value threshold value is less than the first total effective flow resistance value threshold value; If the third judgment result is no, a second warning signal is issued; the second warning signal is used to remind the driver that the remaining life of the filter element is insufficient; If the third judgment result is yes, the current mileage segment is updated and the process returns to step "determining that the effective flow resistance value at the vehicle filter within the current mileage segment is the current effective flow resistance value".

9. A prediction system for the remaining life of a vehicle filter element. It is characterized in that The system comprises: A current effective flow resistance value determination module, used to determine the effective flow resistance value at the vehicle filter within the current mileage section as the current effective flow resistance value; An effective flow resistance value sequence updating module, used for updating an effective flow resistance value sequence according to a current effective flow resistance value; the effective flow resistance value sequence includes a plurality of effective flow resistance values; A linear regression equation determination module is used to process multiple effective flow resistance values ​​in the updated effective flow resistance value sequence using a linear regression algorithm to obtain a linear regression equation; The remaining life determination module is used to determine the remaining life of the vehicle filter element according to the linear regression equation; the remaining life determination module is also used to take the number of standard elements of the effective flow resistance value sequence as an independent variable, bring it into the linear regression equation, and obtain the total effective flow resistance value of the effective flow resistance value sequence after the dependent variable is updated; judge whether the total effective flow resistance value is less than the first total effective flow resistance value threshold value, and obtain a second judgment result; if the second judgment result is no, determine that the remaining life of the filter element is 0, and issue a first warning signal; the first warning signal is used to prompt the driver to replace the filter element; if the second judgment result is yes, according to the total effective flow resistance value, use the formula Determine the remaining life of the filter element; where A A , A 1 , A 2 They respectively represent the remaining life of the filter element, the total effective flow resistance and the first total effective flow resistance threshold.

Images