Typical operation feature extraction method for dual-parameter control of diesel engine

Abstract

The invention provides a typical operation feature extraction method for dual-parameter control of a diesel engine, and the method comprises the following steps: S1, determining bench operation control parameters according to vehicle-mounted test data of the diesel engine, and carrying out the standardization processing; s2, constructing parameters for describing typical feature extraction, and dividing a distribution statistical interval; s3, calculating the proportion of each interval according to the parameters and intervals constructed in the previous step; s4, determining the rack circulation time, the verification time of each scene and the corresponding sample length; s5, in each scene, sequentially selecting corresponding sample length data according to a collection sequence for verification; and S6, forming a bench operation test cycle. According to the invention, the typical working condition of the diesel engine running along with the vehicle can be obtained, so that the behavior after loading is simulated on the rack, the problem that the rack verification is inconsistent with the actual application is solved, the means of the diesel engine rack verification is supplemented, and the development quality and reliability of the product are more effectively improved.

Description

Technical Field

[0001] The invention belongs to the field of diesel engine bench testing, and in particular relates to a typical operating feature extraction method for dual-parameter control of a diesel engine. Background Art

[0002] Diesel engines are typically tested and verified before leaving the factory according to the test contents specified in relevant standards. To determine the diesel engine's operational suitability, reliability, stability, and environmental emissions, on-vehicle testing and verification are often required after installation in a complete vehicle. If all test indicators during on-vehicle testing meet design requirements, the diesel engine enters mass production and vehicle installation. However, due to inconsistent test conditions, inconsistent focus between test bench and on-vehicle testing, and the non-reproducibility of test bench conditions during road operation, various problems often emerge during on-road testing and verification, such as excessive emissions, component damage, unsatisfactory response, and abnormal vibration. These problems often require the diesel engine to be returned to the design company for redesign, improvement, and retesting. Resolving these issues often requires multiple iterations and repetitions. Sometimes, due to the non-reproducibility of test bench methods, some issues cannot be fundamentally resolved after several rounds of repetition. Ultimately, depending on the severity of the impact, they are incorporated into the design improvements of the next generation of products.

[0003] An effective solution to these aforementioned issues is to convert the data collected during the diesel engine installation and driving verification process into bench operating conditions and conduct bench testing and verification. However, the amount of data collected during diesel engine installation and driving is large and non-repetitive. Randomly extracting a section for bench testing and verification is incomplete, meaningless, and ineffective. To address this issue, a method for extracting typical operating characteristics of diesel engine dual-parameter control is proposed. This method obtains operating characteristics that represent the entire diesel engine installation and driving process. These characteristics are then used in diesel engine bench testing and verification, improving the effectiveness of bench verification, reducing iterations during the development process, shortening the development cycle, and ultimately improving product quality. Summary of the Invention

[0004] In view of this, the present invention aims to propose a typical operating feature extraction method for dual-parameter control of a diesel engine, so as to extract the characteristics of the data collected during on-board testing of the diesel engine, calculate the proportion, set the quasi-cycle, and verify the compliance, so as to finally form a test cycle for the diesel engine bench simulation operation.

[0005] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0006] A typical operating feature extraction method for dual-parameter control of a diesel engine includes the following steps:

[0007] S1. Determine control parameters: Determine bench operation control parameters based on diesel engine vehicle test data and standardize them;

[0008] Determine the parameters of diesel engine test bench operation control, such as speed n and torque T, and use the standardized formula: Convert to a number between 0 and 100%;

[0009] S2. Construct parameters; construct parameters for extracting typical features and divide the distribution statistical intervals; based on the bench operation test parameters speed n and torque T determined in the previous step, construct single descriptive parameters speed change △n, torque change △T and group descriptive parameters (speed n, torque T), (speed n, torque change △T), (torque T, speed change △n), a total of 5 groups of parameters, calculate all data collected during vehicle operation according to these parameters, and divide the statistical intervals;

[0010] S3. Calculate the proportion: According to the parameters and intervals constructed in the previous step, calculate the proportion of each interval;

[0011] Count all the data items a collected when the diesel engine is running on the vehicle and the number of data items b that fall within the corresponding interval, and calculate the proportion using the formula a / b×100;

[0012] S4. Determine the various parameters of the test bench; determine the test bench cycle time, each scenario verification time, and the corresponding sample length;

[0013] Compress the data of each scene in proportion and determine the number of samples for each scene as X1, X2, X3, ..., and calculate the verification time of each scene as X1 / f, X2 / f, X3 / f, ... according to the acquisition frequency f. The cycle time is the sum of the verification time of each scene.

[0014] S5. Data verification: In each scenario, select the corresponding sample length data in the order of collection for verification;

[0015] In each scenario, select the data with the sample length determined in step 4 as the candidate loop and perform the following operations: for each set of parameters in S2, calculate the expected number of occurrences G, which is the product of the sample length and the proportion, according to the proportion determined in S3; count the number of distributions Q in each interval determined in step 2; calculate the checksum (GQ) for each interval 2 / Q, and sum all intervals under each set of parameters;

[0016] S6. Form a cycle; form a bench operation test cycle; in each scenario, select the candidate cycle with the smallest sum of the checksum values ​​as the quasi-cycle, and combine the quasi-cycles of all scenarios in time to form the final bench operation test cycle.

[0017] Furthermore, in step S2, when the interval is a non-changing parameter, the interval is 10% or 20%; when it is a changing parameter, the interval is 5% or 10%.

[0018] Furthermore, in step S4, the compression ratio of each scene data is greater than 5:1, and the number of samples of each scene after final compression is an integer.

[0019] Furthermore, in step S5, the selected candidate cycle data are intercepted according to the data sequence correspondence, and the original sequence and corresponding features are retained after interception.

[0020] Compared with the prior art, the typical operating feature extraction method for dual-parameter control of a diesel engine described in the present invention has the following advantages:

[0021] The method for extracting typical operating characteristics of dual-parameter control of a diesel engine described in the present invention can obtain typical operating conditions of a diesel engine running on a vehicle, thereby simulating the behavior after being installed on the vehicle on a test bench, solving the problem of inconsistency between test bench verification and actual application, supplementing the means of diesel engine test bench verification, and enabling diesel engine test bench verification to be advanced to the test bench. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings, which constitute part of the present invention, are provided to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are provided to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0023] Figure 1 This is a flow chart of a typical operating feature extraction method for dual-parameter control of a diesel engine according to an embodiment of the present invention;

[0024] Figure 2 This is a schematic diagram of a candidate test cycle captured in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other.

[0026] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, features defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0027] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0028] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0029] A typical operating feature extraction method for dual-parameter control of a diesel engine includes the following steps:

[0030] S1. Determine control parameters: Determine bench operation control parameters based on diesel engine vehicle test data and standardize them;

[0031] Determine the parameters of diesel engine test bench operation control, such as speed n and torque T, and use the standardized formula: Convert them into numbers between 0 and 100%, keep the original order and correspondence, and organize them into a table;

[0032] S2. Construct parameters; construct parameters for extracting typical features and divide the distribution statistical intervals; based on the test bench operation parameters speed n and torque T determined in the previous step, construct parameters for describing typical features, including single description parameters speed change △n, torque change △T and group description parameters (speed n, torque T), (speed n, torque change △T), (torque T, speed change △n), where the change value is shown in Table 1 below, which is the difference between the latter number and the previous number, and the change value is 0 for the starting number;

[0033] Time(s) Standard speed (%) Standard torque (%) Speed ​​change (%) Torque change (%) 1 74 82 0 0 2 77 79 3 -3 3 76 78 -1 -1 4 76 81 0 3 5 77 75 1 -6 6 80 82 3 7 7 79 78 -1 -4 8 76 75 -3 -3 9 77 80 1 5 … … … … …

[0034] Table 1. Data normalization and calculation of change values

[0035] For each group of parameters, the interval is divided. The part containing the speed n and torque T is divided at intervals of 10% or 20%. The total interval should be [0, 100%]. The part containing the speed change △n and torque change △T is divided at intervals of 5% or 10%. The total interval can cover all data and should include negative values. The upper and lower limits are integer multiples of the interval.

[0036] S3. Calculate the proportion: According to the parameters and intervals constructed in the previous step, calculate the proportion of each interval;

[0037] The number of all data items a collected during the operation of the diesel engine on the vehicle was counted. The number of data items b corresponding to each parameter group was further counted, as shown in Table 2 below. The proportion was calculated using the formula a / b×100, and the distribution characteristics of the total sample were formed by sorting the parameters according to each group. There are 5 groups of characteristics in total.

[0038]

[0039] Table 2. The proportion of total sample data in each interval

[0040] S4. Determine the various parameters of the test bench; determine the test bench cycle time, each scenario verification time, and the corresponding sample length;

[0041] Based on the number of data items a collected during on-board operation of the diesel engine, the sample length for the bench test cycle is determined by compressing them at a ratio of no less than 5:1. For different scenarios (such as urban driving and rural driving), the sample lengths are determined to be X1, X2, X3, ..., in sequence, compressed at the same ratio. Furthermore, based on the acquisition frequency f used in the test, the verification time for each scenario is calculated as X1 / f, X2 / f, X3 / f, ..., and the total bench cycle time is X1 / f + X2 / f + X3 / f + ...;

[0042] S5. Data verification: In each scenario, select the corresponding sample length data in the order of collection for verification;

[0043] In each scene, press Figure 2 Select the data with the sample length determined in the previous step as the candidate cycle and perform the checksum calculation shown in Table 3 below: For each set of parameters determined in the second step, calculate the expected number of occurrences G, which is the product of the sample length and the proportion, based on the proportion in the third step; count the number of candidate cycles distributed in each interval according to the interval determined in the second step; and calculate the checksum value (GQ) for each interval. 2 / Q, and sum the checksum values ​​of all intervals under each set of parameters;

[0044] Speed ​​range Torque range Statistics Expected number 0-20 0-20 36 45.0 0-20 20-40 11 23.9 0-20 40-60 12 15.4 0-20 60-80 10 6.5 0-20 80-100 1 1.2 20-40 0-20 1 7.9 20-40 20-40 5 5.8 20-40 40-60 17 16.6 20-40 60-80 17 15.8 20-40 80-100 3 13.3 40-60 0-20 2 1.1 40-60 20-40 0 1.8 40-60 40-60 20 15.0 40-60 60-80 48 63.4 40-60 80-100 11 9.2 60-80 0-20 0 0.1 60-80 20-40 4 3.3 60-80 40-60 31 19.9 60-80 60-80 103 68.6 60-80 80-100 18 17.1 80-100 0-20 0 0.0 80-100 20-40 0 0.0 80-100 40-60 4 4.3 80-100 60-80 6 4.6 80-100 80-100 0 0.0

[0045] Table 3. Distribution of candidate test cycles calculated for grouped parameters (speed n, torque T) in all intervals

[0046] Repeat the above steps until all the sample data are calculated to form a set of candidate cycles (total number of scene sample data s / candidate cycle length X);

[0047] S6. Form a cycle; form a bench operation test cycle; in each scenario, select the candidate cycle with the smallest sum of the checksum values ​​as the quasi-cycle, and combine the quasi-cycles of all scenarios in time to form the final bench operation test cycle.

[0048] Preferably, in step S2, when the interval is divided into non-changing parameters, the interval is 10% or 20%; when the parameters are changed, the interval is 5% or 10%.

[0049] Preferably, in step S4, the compression ratio of each scene data is greater than 5:1, and the number of samples of each scene after final compression is an integer.

[0050] Preferably, in step S5, the selected candidate cycle data are intercepted according to the data sequence correspondence, and the original sequence and corresponding features are retained after interception.

[0051] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A typical operating feature extraction method for dual-parameter control of a diesel engine, characterized in that The steps include: S1. Determine control parameters: Determine bench operation control parameters based on diesel engine vehicle test data and standardize them; Determine the parameters of diesel engine test bench operation control, such as speed n and torque T, and use the standardized formula: Convert to a number between 0 and 100%; S2. Construct parameters; construct parameters for extracting typical features and divide the distribution statistical intervals; based on the bench operation test parameters speed n and torque T determined in the previous step, construct single descriptive parameters speed change △n, torque change △T and group descriptive parameters (speed n, torque T), (speed n, torque change △T), (torque T, speed change △n), a total of 5 groups of parameters, calculate all data collected during vehicle operation according to these parameters, and divide the statistical intervals; S3. Calculate the proportion: According to the parameters and intervals constructed in the previous step, calculate the proportion of each interval; Count all the data items a collected when the diesel engine is running on the vehicle and the number of data items b that fall within the corresponding interval, and calculate the proportion using the formula a / b×100; S4, determine the parameters of the test bench; Determine the bench cycle time and verification time for each scenario and the corresponding sample length; Compress the data of each scene in proportion and determine the number of samples for each scene as X1, X2, X3, ..., and calculate the verification time of each scene as X1 / f, X2 / f, X3 / f, ... according to the acquisition frequency f. The cycle time is the sum of the verification time of each scene. S5. Data verification: In each scenario, select the corresponding sample length data in the order of collection for verification; In each scenario, select the data with the sample length determined in step 4 as the candidate loop and perform the following operations: for each set of parameters in S2, calculate the expected number of occurrences G, which is the product of the sample length and the proportion, according to the proportion determined in S3; count the number of distributions Q in each interval determined in step 2; calculate the checksum (GQ) for each interval 2 / Q, and sum all intervals under each set of parameters; S6, forming a cycle; A bench operation test cycle is formed; in each scenario, the candidate cycle with the smallest sum of checksum values ​​is selected as the quasi-cycle, and the quasi-cycles of all scenarios are combined in time to form the final bench operation test cycle.

2. The method for extracting typical operating characteristics of a diesel engine dual-parameter control according to claim 1, characterized in that: In step S2, when the interval is a non-changing parameter, the interval is 10% or 20%; when it is a changing parameter, the interval is 5% or 10%.

3. The method for extracting typical operating characteristics of a diesel engine dual-parameter control according to claim 1, characterized in that: In step S4, the compression ratio of each scene data is greater than 5:1, and the number of samples of each scene after final compression is an integer.

4. The method for extracting typical operating characteristics of a diesel engine dual-parameter control according to claim 1, characterized in that: In step S5, the selected candidate cycle data are intercepted according to the data sequence correspondence, and the original sequence and corresponding features are retained after interception.

Images