A processing method and device for engine performance calibration

Abstract

The present application discloses a processing method and device for engine performance calibration, the method comprising: obtaining operating parameters of the engine, the operating parameters comprising at least a plurality of operating condition parameters; obtaining a current operating condition profile of the engine according to the operating parameters; obtaining a target data version corresponding to the current operating condition profile using a calibration function model, the target data version comprising support parameters corresponding to a control strategy of the engine; wherein the calibration function model represents: a functional relationship between the performance index of the engine and the support parameters of the controller of the engine and the operating condition profile of the engine; sending the target data version to the controller of the engine, and the controller executing the control strategy according to the support parameters in the target data version, so that the performance index of the engine meets the optimization conditions.

Description

Technical Field

[0001] The present application relates to the field of engine technology, and in particular to a method and device for processing engine performance calibration. Background Art

[0002] At present, in order to ensure that the engine can achieve optimal performance indicators regardless of the operating conditions, engineers usually pre-calibrate the controller support parameters under various operating conditions.

[0003] However, in actual engine applications, operating conditions are ever-changing. Even if engineers have pre-calibrated multiple versions of support parameters, there may still be certain operating conditions under which the engine performance indicators cannot be optimized. Summary of the invention

[0004] In view of the above problems, the present application provides a method and device for processing engine performance calibration to achieve the purpose of calibrating supporting parameters so that the engine performance indicators can reach the optimal level. The specific scheme is as follows:

[0005] A first aspect of the present application provides a method for processing engine performance calibration, the method comprising:

[0006] Obtaining operating parameters of the engine, wherein the operating parameters include at least a plurality of operating condition parameters;

[0007] According to the operating parameters, a current operating condition profile of the engine is obtained;

[0008] Using a calibration function model, obtaining a target data version corresponding to the current operating condition portrait, wherein the target data version includes support parameters corresponding to the control strategy of the engine;

[0009] The calibration function model represents: a functional relationship between the performance index of the engine and the supporting parameters of the controller of the engine and the operating condition profile of the engine;

[0010] The target data version is sent to the controller of the engine, and the controller executes the control strategy according to the supporting parameters in the target data version, so that the performance index of the engine meets the optimization condition.

[0011] In a possible implementation, obtaining a target data version corresponding to the current operating condition portrait by using a calibration function model includes:

[0012] Inputting the operating condition parameters in the current operating condition portrait into the calibration function model;

[0013] adjusting support parameters in the calibration function model;

[0014] The supporting parameters that make the performance indicators of the engine output by the calibration function model meet the optimization conditions are determined as the target data version corresponding to the current operating condition portrait.

[0015] In a possible implementation, before obtaining the target data version corresponding to the current operating condition portrait by using the calibration function model, the method further includes:

[0016] In the data version library, searching whether there is an optimized data version that matches the current working condition profile;

[0017] The data version library contains at least one optimized data version, and the optimized data version corresponds to a typical operating condition portrait; the supporting parameters in the optimized data version enable the performance index of the engine under the typical operating condition portrait to meet the optimization condition when the controller of the engine executes the control strategy;

[0018] If an optimized data version matching the current operating condition portrait is found in the data version library, the found optimized data version is determined as the target data version corresponding to the current operating condition portrait;

[0019] If the optimized data version matching the current operating condition portrait is not found in the data version library, the calibration function model is executed to obtain the target data version corresponding to the current operating condition portrait.

[0020] In a possible implementation, searching in the data version library whether there is an optimized data version matching the current working condition profile includes:

[0021] Using a working condition clustering analysis algorithm, obtaining a current working condition type corresponding to the current working condition portrait;

[0022] Comparing the current working condition type with the working condition type of the typical working condition portrait;

[0023] If there is a typical working condition portrait in the data version library whose working condition type is consistent with the current working condition type, a first search result is obtained; the first search result indicates that: in the data version library, the optimized data version corresponding to the typical working condition portrait whose working condition type is consistent with the current working condition type is the optimized data version found to match the current working condition portrait;

[0024] If there is no typical working condition portrait of a working condition type consistent with the current working condition type in the data version library, a second search result is obtained, and the second search result indicates that no optimized data version matching the current working condition portrait is found in the data version library.

[0025] In a possible implementation, searching in the data version library whether there is an optimized data version matching the current working condition profile includes:

[0026] Comparing the current working condition portrait with the typical working condition portrait in the data version library;

[0027] If there is a typical working condition portrait in the data version library that satisfies the working condition similarity condition with the current working condition portrait, a first search result is obtained; the first search result indicates that: in the data version library, the optimized data version corresponding to the typical working condition portrait that satisfies the working condition similarity condition with the current working condition portrait is the optimized data version found to match the current working condition portrait;

[0028] If there is no typical operating condition portrait in the data version library that satisfies the operating condition similarity condition with the current operating condition portrait, a second search result is obtained, and the second search result indicates that no optimized data version matching the current operating condition portrait is found in the data version library.

[0029] In a possible implementation, after determining the support parameters that make the performance index of the engine output by the calibration function model meet the optimization condition as the target data version corresponding to the current operating condition profile, the method further includes:

[0030] The target data version corresponding to the current working condition portrait is added to the data version library as an optimized data version.

[0031] In a possible implementation, before sending the target data version to the controller of the engine, the method further includes:

[0032] determining whether the target data version is consistent with a current data version used by a controller of the engine;

[0033] If the target data version is inconsistent with the current data version, sending the target data version to the controller of the engine is performed.

[0034] In a possible implementation, obtaining the operating parameters of the engine includes:

[0035] A plurality of sensors deployed on the engine are used to collect a plurality of operating parameters of the engine to obtain operating parameters of the engine.

[0036] In a possible implementation, the calibration function model is represented by a first function model, the first function model is composed of a plurality of second function models, and each of the second function models is respectively composed of a plurality of third function models;

[0037] Wherein, the first function model represents: the functional relationship between the overall performance index of the engine and a plurality of component performance indexes;

[0038] Each of the second function models corresponds to one of the component performance indicators; the second function model represents: the functional relationship between the component performance indicator and a plurality of subdivision indicators;

[0039] Each of the third function models corresponds to one of the subdivision indicators; the third function model represents: the functional relationship between the subdivision indicator and the supporting parameter and the operating condition parameter in the operating condition portrait of the engine.

[0040] A second aspect of the present application provides a processing device for engine performance calibration, the device comprising:

[0041] A parameter obtaining unit, used to obtain operating parameters of the engine, wherein the operating parameters at least include a plurality of operating condition parameters;

[0042] A portrait obtaining unit, used for obtaining a current operating condition portrait of the engine according to the operating parameters;

[0043] A data acquisition unit, used to obtain a target data version corresponding to the current operating condition portrait by using a calibration function model, wherein the target data version includes support parameters corresponding to the control strategy of the engine;

[0044] The calibration function model represents: a functional relationship between the performance index of the engine and the supporting parameters of the controller of the engine and the operating condition profile of the engine;

[0045] The data sending unit is used to send the target data version to the controller of the engine, and the controller executes the control strategy according to the supporting parameters in the target data version, so that the performance index of the engine meets the optimization condition. In a possible implementation,

[0046] A third aspect of the present application provides a computer program product, comprising computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the processing method for engine performance calibration of the above-mentioned first aspect or any implementation of the first aspect.

[0047] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0048] The memory is used to store computer programs;

[0049] The processor is used to execute the computer program so that the electronic device can implement the processing method for engine performance calibration of the above-mentioned first aspect or any implementation manner of the first aspect.

[0050] A fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can perform a processing method for engine performance calibration according to the first aspect or any implementation of the first aspect.

[0051] By means of the above technical scheme, in a processing method and device for engine performance calibration provided by the present application, after obtaining the operating parameters of the engine including multiple operating parameters, the current operating condition profile of the engine is first obtained according to the operating parameters, and then the calibration function model is used to obtain the target data version corresponding to the current operating condition profile including the support parameters corresponding to the control strategy. Since the calibration function model represents: the functional relationship between the performance index of the engine and the support parameters of the engine controller and the operating condition profile of the engine, after sending the target data version to the control of the engine, the controller executes the control strategy according to the support parameters in the target data version, thereby making the performance index of the engine meet the optimization conditions. It can be seen that in the present application, no matter what operating state the current operating condition profile of the engine is, the calibration function model can be used to calibrate the support parameters, so that when the engine controller executes the control strategy according to the calibrated support parameters, the performance index of the engine can be optimized, thereby achieving the purpose of calibrating the performance index of the engine to the optimal state. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 A flowchart of a method for processing engine performance calibration provided in an embodiment of the present application;

[0054] Figure 2 A partial flow chart of a method for processing engine performance calibration provided in an embodiment of the present application;

[0055] Figure 3 Another flow chart of a method for processing engine performance calibration provided in an embodiment of the present application;

[0056] Figure 4Another partial flow chart of a method for processing engine performance calibration provided in an embodiment of the present application;

[0057] Figure 5 A flowchart of another part of a method for processing engine performance calibration provided in an embodiment of the present application;

[0058] Figure 6 Another partial flow chart of a method for processing engine performance calibration provided in an embodiment of the present application;

[0059] Figure 7 Another flow chart of a method for processing engine performance calibration provided in an embodiment of the present application;

[0060] Figure 8 A schematic diagram of the structure of a processing device for engine performance calibration provided in an embodiment of the present application;

[0061] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0062] Fig.10 For engine product development, the performance parameter example diagrams of each system are calibrated based on the R&D mechanism (experience) and static operating condition input;

[0063] Fig.11 This is a diagram of the optimization model architecture for calibration of engine performance parameter indicators based on working condition adaptation in this application;

[0064] Fig.12 This is a functional flow chart of data collection and working condition clustering in this application. DETAILED DESCRIPTION

[0065] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0066] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0067] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0068] The present application can be applied in the field of engines. Taking diesel engines as an example, multiple application scenarios of the products will be introduced below.

[0069] Reference Figure 1 , is a flow chart of a method for processing engine performance calibration provided in an embodiment of the present application, which can be applied to an electronic device capable of data processing, which can be a local device connected to the engine or a cloud device connected to the engine. The technical solution in this embodiment is mainly used to optimize the performance indicators of the engine.

[0070] Specifically, the method in this embodiment may include the following steps:

[0071] Step 101: Obtain operating parameters of the engine.

[0072] Among them, the operating parameters include at least multiple operating parameters, such as rotation speed, torque, vehicle speed, altitude, temperature, load, acceleration, idle speed, etc.

[0073] In one implementation, in step 101 , multiple sensors deployed on the engine may be used to collect multiple operating parameters of the engine to obtain the operating parameters of the engine.

[0074] For example, a data connection is established between the electronic device in this embodiment and the sensor deployed on the engine. After the sensor collects the operating parameters, the operating parameters are sent to the electronic device in this embodiment through the data connection, thereby obtaining operating parameters including these operating parameters on the electronic device.

[0075] It should be noted that the operating parameters may also include non-operating parameters, which refer to parameters that will not change after the engine leaves the factory.

[0076] It should be noted that this embodiment can be executed when the operating parameters of the engine change, that is, this embodiment continuously detects whether the operating parameters of the engine have changed. If it is monitored that the operating parameters of the engine have changed, then step 101 and subsequent steps are executed.

[0077] Step 102: Obtain a current operating condition profile of the engine according to the operating parameters.

[0078] Specifically, in step 102, the operating parameters can be first filtered for data standardization by using rules such as data correlation and range limits to remove abnormal data; then, the operating parameters are segmented according to the selected data processing method (such as driving cycle mode, mileage, operating time, etc.), so that corresponding parameter features are extracted from the segmented operating parameters, such as temperature, altitude, humidity, speed, torque, load, etc., and then the current working condition profile of the engine is constructed based on these parameter features. The current working condition profile of the engine can be represented by the extracted parameter features, as shown in Table 1.

[0079] Table 1 Current working condition portrait

[0080]

[0081] Step 103: Use the calibration function model to obtain the target data version corresponding to the current working condition profile.

[0082] The target data version includes the supporting parameters corresponding to the control strategy of the engine. The supporting parameters refer to the parameters required by the engine controller to execute the control strategy. The control strategy refers to the strategy used by the controller to control the engine, for example, when the speed reaches a certain value, the strategy of the controller to control a certain operating parameter of the engine.

[0083] Specifically, the calibration function model characterizes: the functional relationship between the performance indicators of the engine and the supporting parameters of the engine controller and the operating condition profile of the engine.

[0084] In one implementation, the calibration function model can be represented by a first function model, the first function model is composed of a plurality of second function models, and each second function model is respectively composed of a plurality of third function models.

[0085] Firstly, the first functional model characterizes: the functional relationship between the overall performance index of the engine and multiple component performance indexes.

[0086] There may be multiple component performance indicators, each corresponding to the corresponding performance type of the engine. For example, the component performance indicators may include economic indicators e, dynamic indicators p, environmental indicators en, reliability indicators r, durability indicators d, etc. The component performance indicators may be identified and weightedly extracted based on the collected engine performance indicator parameters by methods such as principal component analysis, factor analysis, and fuzzy comprehensive evaluation.

[0087] Specifically, the first function model can be expressed by the following formula (1):

[0088] (1)

[0089] Among them, Z is the overall performance index. Z shows a Weibull exponential decay curve as time (or kilometers) is consumed. The optimal value range of Z (that is, the value range corresponding to the optimization condition) can be the 95% quantile interval. eco t Indicates economic indicators, pow t Indicates dynamic index, env t Represents environmental indicators, rea t Represents the reliability index, dur t represents the durability index, ε represents other influencing factors, and formula (2) is the optimized value range corresponding to each component performance index, that is, the value range corresponding to the optimization condition, such as the value range from e1 to e2, the value range from p1 to p2, the value range from en1 to en2, the value range from r1 to r2, and the value range from d1 to d2:

[0090] st. (2)

[0091] Secondly, each second function model corresponds to a component performance index and multiple detailed indicators corresponding to the component performance index. For example, the economic index, dynamic index, environmental index, reliability index, and durability index each correspond to a second function model. The second function model represents: the functional relationship between the component performance index and multiple detailed indicators.

[0092] There can be multiple detailed indicators. For example, the economic indicator can contain multiple sub-indicators, which can be expressed as 1t ,e 2t ,...,e nt Indicates; dynamic indicators can include multiple sub-indicators, which can be expressed as p 1t ,p 2t ,...,p nt Indicates that environmental indicators can contain multiple sub-indicators, which can be expressed as 1t ,en 2t ,...,ennt Indicates that the reliability index can contain multiple sub-indicators, which can be expressed as r 1t ,r 2t ,...,r nt Indicates that the durability index can contain multiple sub-indicators, which can be expressed as d 1t ,d 2t ,...,d nt The extraction of detailed indicators of each component performance index can be achieved through regression model, principal component, factor analysis, fuzzy comprehensive evaluation, hierarchical analysis method and other methods.

[0093] Specifically, each second function model can be expressed by formula (3) to formula (7):

[0094] ) (3)

[0095] ) (4)

[0096] ) (5)

[0097] ) (6)

[0098] ) (7)

[0099] Finally, each third function model corresponds to a detail index and a plurality of operating parameters corresponding to the detail index. For example, each detail index corresponds to operating parameters x1 to x2. n The third function model characterization: the functional relationship between the detail indicators and the supporting parameters and the operating parameters in the engine operating profile.

[0100] Specifically, each third function model can be expressed by formula (8):

[0101] (8)

[0102] Among them, Opt represents the optimization value range corresponding to the corresponding detail index, that is, the value range corresponding to the optimization condition.

[0103] Step 104: Send the target data version to the controller of the engine.

[0104] The controller executes the control strategy according to the supporting parameters in the target data version so that the performance indicators of the engine meet the optimization conditions.

[0105] Specifically, in step 104, the target data version can be sent to the engine controller via OTA (Over The Air), so that when the controller executes the control strategy according to the supporting parameters in the target data version, the performance indicators of the engine can meet the optimization conditions, specifically: the overall performance indicators of the engine are in the 95th percentile interval, the component performance indicators of the engine are each in the corresponding optimization value range, and the detailed indicators of the engine are each in the corresponding optimization value range.

[0106] By means of the above technical scheme, in a processing method for engine performance calibration provided by an embodiment of the present application, after obtaining the operating parameters of the engine including multiple operating parameters, the current operating condition profile of the engine is first obtained according to the operating parameters, and then the calibration function model is used to obtain the target data version corresponding to the current operating condition profile including the support parameters corresponding to the control strategy. Since the calibration function model represents: the functional relationship between the performance index of the engine and the support parameters of the engine controller and the operating condition profile of the engine, after sending the target data version to the control of the engine, the controller executes the control strategy according to the support parameters in the target data version, thereby making the performance index of the engine meet the optimization conditions. It can be seen that in this embodiment, no matter what operating state the current operating condition profile of the engine is, the calibration function model can be used to calibrate the support parameters, so that when the engine controller executes the control strategy according to the calibrated support parameters, the performance index of the engine can be optimized, thereby achieving the purpose of calibrating the performance index of the engine to the optimal state.

[0107] In one implementation, when the calibration function model is used to obtain the target data version corresponding to the current working condition profile in step 103, it can be implemented in the following manner: Figure 2 As shown in:

[0108] Step 201: Input the operating condition parameters in the current operating condition portrait into the calibration function model.

[0109] For example, the operating parameters in the current operating condition profile, such as speed, torque, altitude, etc., are input into formula (8).

[0110] Step 202: Adjust the support parameters in the calibration function model.

[0111] Specifically, in step 202, one or more supporting parameters in the calibration function model may be adjusted multiple times until the performance index of the engine meets the optimization condition.

[0112] For example, in step 202, the support parameters in formula (8) are adjusted, so that the output value of each third function model in formula (8) can be adjusted until the output value of the third function model satisfies Opt, the output value of the second function model satisfies the value range in formula (2), and the output value of the first function model, i.e., Z, is in the 95% quantile interval.

[0113] Step 203: Determine the support parameters that make the engine performance indicators output by the calibration function model meet the optimization conditions as the target data version corresponding to the current working condition profile.

[0114] For example, after adjusting the support parameters in formula (8) multiple times until the output value of the third function model satisfies Opt, the output value of the second function model satisfies the value range in formula (2), and the output value of the first function model, i.e., Z, is in the 95% percentile interval, the adjusted support parameters are determined as the target data version.

[0115] Based on the above implementation, before step 103, the method in this embodiment may further include the following steps: Figure 3 As shown in:

[0116] Step 105: Search the data version library for an optimized data version that matches the current operating condition portrait. If an optimized data version that matches the current operating condition portrait is found in the data version library, execute step 106. If no optimized data version that matches the current operating condition portrait is found in the data version library, execute step 103.

[0117] Among them, the data version library contains at least one optimized data version, and the optimized data version corresponds to a typical operating condition portrait; the supporting parameters in the optimized data version make the performance indicators of the engine under the typical operating condition portrait meet the optimization conditions when the engine controller executes the control strategy.

[0118] Step 106: Determine the found optimized data version as the target data version corresponding to the current working condition profile.

[0119] That is to say, in this embodiment, a data version library is pre-deployed, and the data version library stores optimized data versions that can make the performance indicators of the engine under the corresponding typical working condition portrait meet the optimization conditions, as shown in Table 2. In this way, after obtaining the current working condition portrait of the engine, the calibration function model may not be applied first, but first search in the data version library to see whether there is a matching optimized data version. If no matching optimized data version is found, step 103 is executed. This can reduce the amount of data processing to improve efficiency.

[0120] Table 2 Optimized data version

[0121]

[0122] In a specific implementation, step 104 can be implemented in the following manner: Figure 4 As shown in:

[0123] Step 401: using the working condition clustering analysis algorithm, obtain the current working condition type corresponding to the current working condition portrait.

[0124] Among them, the working condition clustering analysis algorithm can adopt clustering algorithms such as Markov chain, decision tree, etc. The working condition clustering analysis algorithm can cluster the working condition profile of the engine into multiple working condition types, such as the working condition types in Table 3. There is at least one working condition parameter different between different working condition types, specifically, at least one working condition parameter is in a different parameter range.

[0125] Table 3 Working condition types

[0126]

[0127] Specifically, each operating condition parameter in the operating condition type identified by the operating condition clustering analysis algorithm is within a corresponding parameter range.

[0128] Step 402: Compare the current working condition type with the working condition type of the typical working condition portrait; if there is a working condition type of the typical working condition portrait in the data version library that is consistent with the current working condition type, execute step 403; if there is no working condition type of the typical working condition portrait in the data version library that is consistent with the current working condition type, execute step 404.

[0129] Specifically, in step 402, the parameter range of each operating condition parameter in the current operating condition type can be compared with the parameter range of the corresponding operating condition parameter in the operating condition type of the typical operating condition portrait. If the parameter range of each identical operating condition parameter between the current operating condition type and the operating condition type of a typical operating condition portrait is the same, then the current operating condition type is consistent with the operating condition type of the typical operating condition portrait, and step 403 is executed at this time; if the parameter range of one or more identical operating condition parameters between the current operating condition type and the operating types of all typical operating condition portraits is different, then the current operating condition type is different from the operating condition types of all typical operating condition portraits, and step 404 is executed at this time.

[0130] Step 403: Obtain a first search result.

[0131] Among them, the first search result represents: in the data version library, the optimized data version corresponding to the typical working condition portrait whose working condition type is consistent with the current working condition type is the optimized data version found that matches the current working condition portrait.

[0132] Step 404: Obtain a second search result.

[0133] Among them, the second search result represents: no optimized data version matching the current working condition profile is found in the data version library.

[0134] In another specific implementation, step 104 can be implemented in the following manner: Figure 5 As shown in:

[0135] Step 501: Compare the current working condition portrait with the typical working condition portrait in the data version library; if there is a typical working condition portrait in the data version library that satisfies the working condition similarity condition with the current working condition portrait, execute step 502; if there is no typical working condition portrait in the data version library that satisfies the working condition similarity condition with the current working condition portrait, execute step 503.

[0136] The operating condition similarity condition may be that the parameter range of each identical operating condition parameter between the typical operating condition portrait and the current operating condition portrait is consistent.

[0137] In one implementation, in step 501, the parameter difference between each identical operating condition parameter between the current operating condition portrait and each typical operating condition portrait can be judged. If the parameter difference between one or more operating condition parameters exceeds the difference threshold, then the current operating condition portrait and the corresponding typical operating condition portrait do not meet the operating condition similarity condition; if the parameter difference between all operating condition parameters does not exceed the difference threshold, then the current operating condition portrait and the typical operating condition portrait meet the operating condition similarity condition.

[0138] In another implementation, in step 501, it can be determined whether the parameter ranges of each identical operating condition parameter between the current operating condition portrait and each typical operating condition portrait are the same. If the parameter ranges of each operating condition parameter are the same, then the current operating condition portrait and the typical operating condition portrait satisfy the operating condition similarity condition; if the parameter ranges of one or more operating condition parameters are different, then the current operating condition portrait and the corresponding typical operating condition portrait do not satisfy the operating condition similarity condition.

[0139] Step 502: Obtain a first search result.

[0140] Among them, the first search result represents: in the data version library, the optimized data version corresponding to the typical working condition portrait that meets the working condition similarity condition with the current working condition portrait is the optimized data version found to match the current working condition portrait.

[0141] Step 503: Obtain a second search result.

[0142] Among them, the second search result represents: no optimized data version matching the current working condition profile is found in the data version library.

[0143] Based on the above implementation scheme, after step 203, the method in this embodiment may further include the following processing, such as Figure 6 As shown in:

[0144] Step 204: Add the target data version corresponding to the current working condition profile as the optimized data version to the data version library.

[0145] Therefore, after each target data version is calibrated, it is added to the data version library. In subsequent processing, when the operating parameters of the engine change again, after obtaining the new operating parameters and the corresponding new operating condition portrait, first search in the data version library to see whether there is an optimized data version that matches the new operating condition portrait. If not, then use the calibration function model to obtain the target data version corresponding to the current operating condition portrait. If so, then the found optimized data version is determined as the new target data version. After the new target data version is transmitted to the engine controller, the controller executes the control strategy according to the supporting parameters in the new target data version, so that the performance indicators of the engine under the new operating parameters still meet the optimization conditions, thereby ensuring that the engine is continuously in the state of optimal performance indicators.

[0146] In another implementation, the optimized data version in the data version library can also be preset by the user. For example, the support data manually calibrated by the engineer before the engine leaves the factory is added to the data version library as the optimized data version.

[0147] In one implementation, before step 104, the method in this embodiment may further include the following processing: Figure 7 As shown in:

[0148] Step 105: Determine whether the target data version is consistent with the current data version used by the engine controller. If the target data version is inconsistent with the current data version, then execute step 104. At this time, the engine controller uses the support parameters in the received target data version to execute the control strategy. If the target data version is consistent with the current data version, then end the current process, that is, do not execute step 104. At this time, the engine controller continues to use the support parameters in the original data version to execute the control strategy.

[0149] A method for processing engine performance calibration provided in an embodiment of the present application is introduced above, and a device for executing the above-mentioned method for processing engine performance calibration will be introduced below.

[0150] See also Figure 8, is a schematic diagram of the structure of a processing device for engine performance calibration provided in an embodiment of the present application. The device can be deployed in an electronic device capable of data processing, and the electronic device can be a local device connected to the engine, or a cloud device connected to the engine. The technical solution in this embodiment is mainly used to optimize the performance indicators of the engine.

[0151] Specifically, the device in this embodiment may include the following units:

[0152] The parameter obtaining unit 801 is used to obtain the operating parameters of the engine, wherein the operating parameters at least include multiple operating condition parameters;

[0153] A portrait obtaining unit 802 is used to obtain a current operating condition portrait of the engine according to the operating parameters;

[0154] A data acquisition unit 803 is used to obtain a target data version corresponding to the current operating condition profile by using a calibration function model, wherein the target data version includes support parameters corresponding to the control strategy of the engine;

[0155] The calibration function model represents: a functional relationship between the performance index of the engine and the supporting parameters of the controller of the engine and the operating condition profile of the engine;

[0156] The data sending unit 804 is used to send the target data version to the controller of the engine, and the controller executes the control strategy according to the supporting parameters in the target data version, so that the performance index of the engine meets the optimization condition.

[0157] By means of the above technical scheme, in a processing device for engine performance calibration provided by an embodiment of the present application, after obtaining the operating parameters of the engine including multiple operating parameters, the current operating condition profile of the engine is first obtained according to the operating parameters, and then the calibration function model is used to obtain the target data version corresponding to the current operating condition profile including the support parameters corresponding to the control strategy. Since the calibration function model represents: the functional relationship between the performance index of the engine and the support parameters of the engine controller and the operating condition profile of the engine, after sending the target data version to the control of the engine, the controller executes the control strategy according to the support parameters in the target data version, thereby making the performance index of the engine meet the optimization conditions. It can be seen that in this embodiment, no matter what operating state the current operating condition profile of the engine is, the calibration function model can be used to calibrate the support parameters, so that when the engine controller executes the control strategy according to the calibrated support parameters, the performance index of the engine can be optimized, thereby achieving the purpose of calibrating the performance index of the engine to the optimal state.

[0158] The present application also provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0159] The memory is used to store computer programs;

[0160] The processor is used to execute the computer program so that the electronic device can implement the processing method for engine performance calibration of the above-mentioned first aspect or any implementation manner of the first aspect.

[0161] refer to Fig. 9 As shown, it shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiment of the present application. The electronic device in the embodiment of the present application may include but is not limited to fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Fig. 9 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0162] like Fig. 9 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 to a random access memory (RAM) 903. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 903. The processing device 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0163] Typically, the following devices may be connected to the I / O interface 905: an input device 906 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 908 including, for example, a memory card, a hard disk, etc.; and a communication device 909. The communication device 909 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Fig. 9 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0164] Also provided in an embodiment of the present application is a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the engine performance calibration processing methods provided in the embodiments of the present application.

[0165] A computer storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When one or more computer programs are executed by an electronic device, the electronic device can implement any engine performance calibration processing method provided in the embodiment of the present application.

[0166] The following takes a diesel engine as an example to explain the technical solution of the present application in detail:

[0167] At present, the input operating conditions for the performance parameter calibration of each system department of the engine are mainly based on the accumulation of R&D experience (existing map). Test calibration is carried out on the test bench to meet the index requirements of the development task number design. However, the laboratory operating conditions can never replace the actual operating conditions of the user's vehicle, which makes the early failure rate of new products very high. However, in the actual repair and maintenance process, it is found that most of the faults are false alarms.

[0168] In the production and calibration of engines, existing road spectrum data is generally used to determine the current operating conditions of the engine and adapt the corresponding control strategy. However, due to the limited road spectrum data and the resource limitations of the controller ECU (Electronic Control Unit), it is impossible to finely calibrate and switch strategies for all road conditions and control situations. Therefore, the current application strategy is a limited control strategy based on limited data, and various performance indicators of the engine cannot be brought into optimal condition.

[0169] With the development of connected technology, the frequency and number of engine configuration parameters can be collected and configured, but how to extract typical operating conditions based on massive data and store them in the product life cycle operating condition library to form an engine operating condition portrait, so that each system component of the engine can adaptively optimize and make judgment strategies under dynamic operating conditions, and send them to the engine ECU through OTA technology to continuously improve engine performance, is a technical problem that R&D engineers urgently need to overcome.

[0170] Traditional engine product development is mostly based on R&D mechanisms (experience) and static operating condition input to calibrate the performance parameters of each system, such as Fig.10 The inputs include: operating condition input (i.e. operating condition parameters) and initial performance parameters (such as ignition strategy, etc.).

[0171] Based on the initial input, R&D engineers calibrate the relevant parameters of the engine and each system, such as maintenance specifications (such as the first maintenance of 3000km or 30 days, whichever comes first), fault code strategies (such as sensor short circuit alarm), control strategies (such as water temperature over-alert), mechanical failure modes (such as insufficient power) and other parameters. After the performance development test phase is completed, the engine product needs to undergo durability testing. The data version of the engine product that passes the threshold control is unified and finalized. The finalized data is the data strategy V1 of the product (that is, the data version containing supporting parameters). After the data is placed in the engine electronic control unit, it enters the market for verification. If the market verification phase identifies that some control strategies need to be updated, the data strategy V2 that needs to be updated is determined after re-testing and calibration. Engine performance optimization and improvement depends on accurate operating condition characteristics and the robustness of calibrated performance parameter indicators. However, in the entire process, the typical operating condition data accumulated or identified in the early stage of product development cannot fully represent the user's actual operating conditions, and the new operating condition extraction from offline analysis cannot be quickly fed back to the product performance parameter calibration update link, resulting in poor performance, which leads to a high early failure rate of new products, low reliability level, and many false alarms. Due to the problem of low reliability of new products, R&D engineers began to use OTA technology to explore the technology of remotely clearing fault codes and remotely flashing data, but failed to combine with the user's typical operating condition characteristics to generate a new data version suitable for the user's operating conditions. It can only solve the temporary fault symptoms of the user's vehicle, but cannot solve the root cause of the fault. The main shortcomings of the existing technology are summarized as follows:

[0172] (1) The typical operating condition database accumulated by R&D engineers and the operating condition database collected in outdoor extreme environments are always limited. These operating condition data cannot represent the actual operating conditions of the user's vehicle, and the typical operating condition database has its own incompleteness.

[0173] (2) Although operating condition data can be collected and analyzed manually, the engine performance index calibration test based on the extracted operating condition data in the bench test laboratory consumes a lot of fuel and takes a long time. The data version generated that matches the user's actual operating conditions is not timely enough.

[0174] (3) Existing Internet-connected technology is already mature. R&D engineers can extract typical operating conditions based on the mechanism and calibrate engine performance parameters through bench tests. However, they are unable to directly calibrate engine performance parameters through the remote cloud.

[0175] (4) Existing working condition extraction technologies mostly use unsupervised clustering to analyze the collected road spectrum data. The parameters analyzed are mainly vehicle speed, rotational speed, torque, etc. However, there is a lack of quantitative evaluation and parameter selection mechanism to determine which parameters have the most significant impact on engine reliability. Variables with significant coefficients should be selected from the parameters (that can be collected and have been collected) that affect the relevant dimensional indicators of the engine product development task book by stepwise regression.

[0176] (5) Due to the low reliability and high fault code of new engine products (mostly at the fault code alarm level), Internet of Things technology has gradually been used for remote fault code clearing or remote refresh in the cloud. The relevant data version update has only remained at the fault code strategy. It has not been able to form new engine performance parameter indicators based on the new typical operating condition data and the performance parameters of the two major mechanisms and six major systems of the engine. It has not formed a new controller data version [V2~Vn] that can be matched based on the operating condition characteristics. The engine performance index calibration technology based on typical operating condition characteristics has not yet formed a closed loop with remote calibration, remote flashing and other technologies, and the adaptive engine performance index parameter optimization function based on the engine operating condition portrait has not been realized.

[0177] In view of this, the present application proposes an engine virtual calibration model based on working condition adaptation (i.e., the calibration function model mentioned above), a vehicle working condition image clustering model, and an engine performance parameter calibration self-learning optimization method and application device based on working condition image classification. Fig.11 As shown in , it is the architecture diagram of the engine performance parameter index calibration optimization model based on working condition adaptation in this application.

[0178] Traditional engine performance parameter calibration methods mostly rely on static operating condition inputs. Whether the R&D engineers use predefined operating conditions inferred from theories or collect operating condition data from extreme environments such as high temperature, severe cold, and plateaus, the predefined operating condition data cannot reflect the actual operating conditions of the user's vehicle. The data pre-set to the engine controller cannot well guarantee the vehicle's power, economy, environment, and reliability. This application, from the perspective of operating condition adaptation, has developed a method and device for calibrating engine performance parameter indicators that can be optimized according to the actual vehicle operating conditions. Fig.11 As shown in Figure 2, the method for optimizing the calibration of engine performance parameters based on real working conditions can be divided into two stages: the first stage is the offline manual optimization stage. Fig.11 As shown in the left part of the figure; the second stage is the cloud self-learning optimization stage, as shown in Fig.11 The right part shows:

[0179] First, in the cloud, the predefined engine operating condition library is imported into the typical engine operating condition library, and the engine operating condition manually updated in the offline manual optimization stage on the left is also imported into the typical engine operating condition library. Based on this, the support parameters are calibrated for the typical operating condition portrait in the typical operating condition library using the automatic virtual calibration model (i.e., the calibration function model mentioned above) to obtain the controller data (i.e., the target data version) based on the local (engine) optimization, and then the controller data based on the local optimization is transmitted to the engine controller via OTA to update the data of the support parameters; and as the engine runs after leaving the factory, the engine operating condition parameters can be detected by sensors to realize data collection, and the data features can be extracted in the cloud to construct the vehicle engine operating condition portrait (i.e., the current operating condition portrait), and then, the cloud-based clustering algorithm is used for automatic clustering. If the clustering results are The working condition type is an existing classification, that is, in the data version library based on the working condition portrait, there is a data version corresponding to the typical working condition portrait whose working condition type matches the current working condition portrait. The data version of the working condition type corresponding to the clustering result is extracted, and the extracted controller data (that is, the data version containing the supporting parameters) is first compared with the current data version used by the engine controller. If the comparison is inconsistent, the extracted controller data is used as the controller data based on local optimization and transmitted to the engine controller through OTA to update the supporting parameter data; if the comparison is consistent, there is no need to transmit the controller data; and if the working condition type obtained by clustering is a new classification, the controller data version V1 can be transmitted to the automatic virtual calibration model for calibration of the supporting parameters, and then the calibrated controller data and the new working condition portrait are added to the data version library based on the working condition portrait.

[0180] The detailed scheme is described as follows:

[0181] Step 1101: Analyze product requirements, predefine engine operating conditions, and form a preliminary typical engine operating condition library. The specific steps are as follows:

[0182] Step 1111: Product requirements are based on the development task book, which stipulates engine power, economy, environment, reliability and durability from the customer's perspective. The developed product needs to meet the comprehensive optimal performance of these indicators. An example of an engine product development task book is shown in Table 4:

[0183] Table 4 Task Book

[0184]

[0185] Step 1112: Simulate and design the typical working conditions of the engine by product and model. For example, for a heavy truck tractor, based on step 111 and with reference to relevant standards, the typical working conditions of the engine are relatively complete inputs. The working condition output parameter categories of the heavy truck tractor are such as [speed V1, torque N1, vehicle speed V2, ...]. For example, for a truck category, with a total design mass of 5500kg as the distinction, the vehicle speed conditions and proportions in the urban, suburban and high-speed areas are as shown in Table 5:

[0186] Table 5 Example of truck operating condition table

[0187]

[0188] Step 1102: R&D engineers select engine structural parameters (selection) according to the development task book, set up the test process according to the selection and calibrate the engine performance parameters such as speed, fuel consumption, torque, power, noise, etc. The performance calibration process and result data of the same series of products are accumulated to form an engine calibration big data model library. As the data accumulates, the input working conditions can be automatically calibrated to the engine performance parameters and form a data version, which is the automatic virtual calibration big data model for engine product development. The specific steps are as follows:

[0189] Step 1121: Product R&D engineers select product structural parameters based on the engine development task book (step 1111), such as product supporting industry, cylinder diameter, quality, appearance size, ECU hardware and software parameters, etc., and also need to select parameter ranges such as power, economy, environmental adaptability, durability, and emissions to be calibrated through tests, such as fuel injection volume during ignition, air-fuel ratio, OBD calibration, etc.

[0190] Step 1122: Manual calibration of engine performance parameters: During the bench test, the R&D engineer installs the engine and sets various parameter options according to the test content. Examples of input parameters are shown in Table 6:

[0191] Table 6 Input parameters

[0192]

[0193] After fueling, the bench test results are output for R&D engineers to calibrate engine performance parameters to obtain optimal engine performance. Examples of test output parameters are shown in Table 7:

[0194] Table 7 Test output parameters

[0195]

[0196] This manual calibration process usually consumes a large amount of fuel and also requires manual supervision of the test bench, which is time-consuming and inefficient.

[0197] Step 1123: Automatic calibration of engine performance parameters: The massive engine calibration parameters accumulated during the R&D bench test are stored in the database, and a large engine performance parameter calibration model is established in stages according to the product R&D system (process). The product development task book target is used as the control threshold in all process links, and the baseline model is set as shown in formula (1).

[0198] Among them, formula (1) is the engine performance index based on global optimization, eco t Indicates economic indicators, pow t Indicates dynamic index, env t Represents environmental indicators, rea t Represents the reliability index, dur t represents the durability index, ε represents other influencing factors, and the expected value range of the parameter is in brackets. t ,pow t ,env t ,rea t ,dur t The indicators are respectively extracted by variable identification and weighted extraction based on the collected engine performance indicator parameters by principal component analysis / factor analysis / fuzzy comprehensive evaluation and other methods. Basic examples are shown in formulas (3) to (7).

[0199] Formula (3) to Formula (7) respectively illustrate the measurement formulas of various dimensions of the overall engine performance indicators. Each dimensional indicator is composed of several specific, collectable and quantifiable component indicators. t The engine economy index consists of multiple sub-indexes 1t ,e 2t ,...,e nt The extraction of economic indicators can be achieved through regression model, principal component, factor analysis, fuzzy comprehensive evaluation, hierarchical analysis method and other methods.

[0200] On this basis, Z in formula (1) is a global description of the comprehensive performance of the engine. According to the classic automobile reliability theory, the performance trend of the product conforms to the Weibull distribution function. In this application, the comprehensive performance Z of the engine presents a Weibull exponential decay curve with the consumption of time / kilometers. The parameter value of this function can be obtained in two ways: one is the parameter value obtained in the simulation design stage of new product development, and the other is obtained by modeling and solving the engine historical maintenance big data. Therefore, the value range of Z at each observation time can be set to the 95% quantile interval of the corresponding value of the Weibull function curve. If it exceeds this confidence interval, it means that some dimensional indicators deviate from the calibration indicator range.

[0201] Furthermore, for each component index such as e1 tx1 to x is affected by many factors. n , determined according to the requirements of its own attributes, these influencing factors can be classified into engine operating condition related variables x1, x2, ..., x n-m and non-operating condition related variables x n-m+1 ,...x n .As shown in formula (8).

[0202] The process of R&D engineers calibrating engine performance indicators is the process of determining the optimal boundaries of each performance indicator. Opt means taking a reasonable optimal value that meets the basic requirements of the product development task book and the comprehensive evaluation requirements of the overall product performance. n The input is divided into operating condition variables and non-operating condition variables, among which the operating condition variables are the focus of the present invention and are also the key factors affecting engine performance. Once the user's typical operating condition is defined, the automatic calibration model inputs the newly identified typical operating condition, obtains the optimal solution of each performance index under the global optimality of formulas (1)-(8), and then generates a new data version that is synchronized to the electronic control unit (ECU) for execution to maintain the optimal engine performance.

[0203] Step 1103: After all engine performance indicators are calibrated, a data version is formed and recorded in the electronic control unit (ECU). The various parameters of the engine under the calibration conditions operate according to the calibration data indicators.

[0204] Step 1104: Relevant performance parameters and operating condition parameters are collected based on technical feasibility and practicality. R&D engineers analyze the operating condition parameters, extract typical operating conditions, and calibrate and optimize engine performance indicators based on technical maturity.

[0205] Step 1105: Collect key engine performance parameters and environmental parameters, automatically extract new typical operating conditions in the cloud, use the new operating condition data as input for the automatic virtual calibration model, and generate a new controller data version. The specific steps are as follows:

[0206] Step 1151: Engine parameter data collection technology can be implemented by adding sensors to the vehicle or reading engine controller data through proprietary equipment.

[0207] Step 1152: Dynamic automatic clustering of engine operating condition data. Existing operating condition clustering mostly clusters vehicle speed, rotation speed and torque parameters, and clustering algorithms include Markov chain, decision tree, etc. Different from traditional clustering strategies, this example proposes a multivariate automatic clustering method. Fig.12 The functional flow chart for data collection and working condition clustering is as follows:

[0208] (1) Feature variable extraction. Based on the variables that can be collected, environmental conditions and driving conditions variables are selected as model inputs. Environmental condition parameters include temperature, humidity, altitude, slope, etc. Driving condition parameters include speed, RPM (Revolutions Per Minute), torque, load, acceleration, idle, etc. Model input variables can also have feature parameters extracted from derived variables of environmental conditions and driving conditions, such as average speed AverageSpeed, acceleration time ratio AccelerationRate, idle time ratio IdleRate, speed standard deviation SpeedSD, speed variance SpeedDeviation, acceleration standard deviation AccelerationSD, etc.

[0209] (2) Data cleaning. The selected variables are processed, including short-run segmentation, default value processing, and standardization. For mutation data and default data in the time series, the average smoothing, regression prediction, and median filling methods can be considered to obtain more objective and accurate data.

[0210] (3) Dynamic clustering rule setting. According to different engine uses and industry segmentation rules, heavy truck tractors can be clustered by driving cycles, mileage, etc., and construction machinery vehicles can be clustered by engine running time. If clustering is performed based on the operating conditions experienced in 10 driving cycles (10 times of starting, running to shutting down, and one driving cycle can travel tens of kilometers or even more than 100 kilometers), clustering can be performed based on the running time of 10 hours (80 km / h means 800 km). The specific parameters of the dynamic clustering rules here can be set according to the preferences of the technicians.

[0211] (4) Cluster analysis of working conditions. This application does not impose any restrictions on clustering algorithms. For example, clustering algorithms include K-Means, hierarchical clustering, DBSCAN (Density-Based Spatial Clustering of Application with Noise), SOM (Self-organizing Maps, model-based clustering), and GMM (Gaussian Mixture Model). Preferably, a clustering algorithm of a Gaussian mixture model can be used in this application. The Gaussian mixture model is based on a statistical model of finite mixtures and can eliminate the fragility brought about by the rigid and fast judgment method of traditional clustering algorithms. The general form of the probability distribution function of a Gaussian mixture model is: , is the coefficient to be estimated, , , is the Gaussian distribution density, are the parameters to be estimated for the model, is the kth sub-model, and the maximum likelihood estimation method (EM) is generally used to estimate the parameters θ of the Gaussian mixture model.

[0212] (5) Establish an engine operating condition profile library. The engine operating condition profile library is established according to different supporting industries, supporting sub-industries, supporting markets and engine series. Static information comes from the service records when the product is sold, such as supporting industry (trucks), supporting sub-industries (heavy trucks), supporting markets (tractors), supporting sub-markets (material distribution), engine series (12H), engine number (102H3230X33), etc. The dynamic operating conditions come from the Gaussian mixture clustering of the parameters sent back by the networked engine (a certain type of parameter involved in the clustering), such as vehicle speed (59km / h), torque (50N.m), temperature (30℃), humidity (70%), altitude (300m), intake pressure (7.5bar), NO X (20ppm), etc. There are direct working conditions (directly classified by multiple data parameter ranges or types), indirect working conditions (calculating multiple parameters and classifying multiple calculated parameters), mixed working conditions (working conditions classified by direct parameters and indirect parameters at the same time), etc. Examples of working condition portraits are shown in Table 8:

[0213] Table 8 Working condition portrait

[0214]

[0215] At the system database level, it can be accessed in the form of a working condition profile dictionary, as shown below:

[0216] Auto_work_conditions:

[0217] {"industry":"truck",

[0218] "sub_industry": "Heavy Trucks",

[0219] "market": "tractor",

[0220] "sub_market": "Logistics and Transportation",

[0221] "engine_series": "12H",

[0222] "engine_number":"102H3230X33",

[0223] “Work_conditions”:

[0224] {

[0225] “cluster1”:“10001”,

[0226] “parameters”:

[0227] {“speed”:“59km / h”,

[0228] “torch”:“50N.m”,

[0229] “temperature”:“30℃”,

[0230] “humidity”:“90%”,

[0231] “altitude”: “300m”,

[0232] “intake_air_pressure”: “7.5bar”,

[0233] “NO X ”:“20ppm” ...

[0235] }

[0236] “cluster2”:“10002”,

[0237] “parameters”:

[0238] {“speed”:“40km / h”,

[0239] “torch”:“43N.m”,

[0240] “temperature”:“28℃”,

[0241] “humidity”:“60%”,

[0242] “altitude”: “200m”,

[0243] “intake_air_pressure”: “7bar”,

[0244] “NO X ”:“15ppm” ...

[0246] }

[0247] }

[0248] }

[0249] Under the conditions of step (3), new operating condition type clusters are dynamically generated based on the operating condition clustering analysis algorithm. For clustering under different operating conditions, the newly added operating condition type cluster can be inserted into the above-mentioned operating condition portrait dictionary library.

[0250] Step 1106: After the new working condition profile data is identified, the cloud data is fed back to the virtual calibration large model to generate a new engine ECU controller data version, which is matched to the latest engine working condition through remote data upgrade to meet the optimal indicators of engine performance. The specific steps are as follows:

[0251] Step 1161: Based on the new working condition profile data cluster formed in step 1105, synchronize to step 1123 of the virtual calibration large model, and generate a new ECU controller data version after model training. The controller data version stores engine working condition data profiles and controller data versions of different series and purposes, and can be matched with the working condition profile library in step 1152 to query and identify the latest controller data version. An example is as follows:

[0252] Engine_ecu_version:

[0253] {"engine_series": "12H",

[0254] "ecu_version": "VXXXX-01",

[0255] "engine_number": "102H3230X33",

[0256] “ecu_data”:

[0257] {{"cluster1":"10001",

[0258] “parameters”:

[0259] {“speed”:“59km / h”,

[0260] "torch": "50N.m",

[0261] "temperature": "30℃",

[0262] "humidity": "90%",

[0263] “altitude”: “300m”,

[0264] “intake_air_pressure”: “7.5bar”,

[0265] “NO X ”:“20ppm” ...

[0267] {

[0268] }

[0269] {"cluster2":"10002",

[0270] “parameters”:

[0271] {“speed”:“40km / h”,

[0272] "torch": "43N.m",

[0273] "temperature": "28℃",

[0274] "humidity": "60%",

[0275] “altitude”: “200m”,

[0276] "intake_air_pressure": "7bar",

[0277] “NO X ”:“15ppm” ...

[0279] }

[0280] }

[0281] {“cluster N”:

[0282] }

[0283] }

[0284] }

[0285] Step 1162: After the new engine ECU data version is generated, the data can be sent through the cloud, that is, OTA technology. After the new data takes effect, the performance of the engine can be significantly improved. The subsequent engine operating conditions can be continuously dynamically clustered and analyzed according to step 1105, and finally a dynamically adaptable and updated engine operating condition portrait library is formed. This operating condition portrait library can meet the optimal performance of the engine through a virtual calibration large model.

[0286] In summary, this application proposes an engine performance index calibration optimization method based on operating condition adaptive learning from the perspective of the technical difficulties between engine operating conditions and engine performance parameters. The key points of the conception are mainly the following:

[0287] 1) Manual analysis of operating parameters is improved to dynamic analysis of operating parameters of networked engine data;

[0288] 2) The static storage of the engine operating condition profile library is improved to dynamic clustering update;

[0289] 3) Engine performance parameter calibration is improved to automatic calibration using big data models;

[0290] 4) Offline update of engine controller parameters is improved to automatically send data generated by dynamic calibration.

[0291] It can be seen that this application proposes a dynamic operating condition clustering technology based on big data from the perspective of engine operating conditions, and updates the engine ECU data version through a virtual calibration model to achieve the goal of optimizing engine performance. Compared with traditional methods, the main advantages of this technology are as follows:

[0292] (1) Automation of the engine virtual calibration model. Traditional engine calibration relies on simulation and testing. After inputting the operating parameters, the engine economy, power and other targets are set. The traditional method is time-consuming and energy-consuming. The engine automatic virtual calibration model proposed in this example relies on the experience data accumulated by R&D engineers over the years to establish a big data model. By inputting the operating data, the optimal performance parameters can be obtained through the automatic calibration big model, which solves the time-consuming, energy-consuming and dynamic calculation problems of traditional calibration technology.

[0293] (2) Dynamic clustering of engine operating conditions. Traditional operating condition clustering relies on R&D engineers to analyze road spectra and manually update the operating conditions. The parameters analyzed are limited and cannot fully represent the actual operating condition types of the engine. The inability to dynamically update is a drawback of traditional technology. The dynamic clustering technology of engine operating conditions proposed in this case can dynamically expand and cluster the collected parameters, solving the problems of engineers' long operating condition analysis cycle, irregular storage, and no dynamic update.

[0294] (3) Dynamic optimization of engine performance parameters. In the process of implementing traditional technologies, R&D engineers analyze the working conditions offline, test the working condition type data obtained, obtain a new engine controller data version, and then send the data to the engine through the service station. This process has a long cycle and many customer complaints. The dynamic working condition clustering data proposed in this application is directly transmitted to the virtual calibration large model, and the calibration parameters are calculated in the cloud to form the engine controller data version. With the help of OTA technology, it is dynamically sent to the engine, which can effectively solve the problems of slow optimization of engine performance parameters and poor adaptability to working conditions;

[0295] In addition, the present application can also summarize technical features such as engine performance parameter optimization model technology, clustering parameter dynamic update technology, engine controller data dynamic generation and distribution / flash technology, and engine operating condition portrait dynamic expansion technology.

[0296] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0297] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0298] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0299] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A method for processing engine performance calibration, characterized in that: The method comprises: Obtaining operating parameters of the engine, wherein the operating parameters include at least a plurality of operating condition parameters; According to the operating parameters, a current operating condition profile of the engine is obtained; Using a calibration function model, obtaining a target data version corresponding to the current operating condition portrait, wherein the target data version includes support parameters corresponding to the control strategy of the engine; The calibration function model represents: a functional relationship between the performance index of the engine and the supporting parameters of the controller of the engine and the operating condition profile of the engine; Sending the target data version to the controller of the engine, and having the controller execute the control strategy according to the supporting parameters in the target data version, so that the performance index of the engine meets the optimization condition; Before obtaining the target data version corresponding to the current working condition portrait by using the calibration function model, the method further includes: In the data version library, searching whether there is an optimized data version that matches the current working condition profile; The data version library contains at least one optimized data version, and the optimized data version corresponds to a typical operating condition portrait; the supporting parameters in the optimized data version enable the performance index of the engine under the typical operating condition portrait to meet the optimization condition when the controller of the engine executes the control strategy; If an optimized data version matching the current operating condition portrait is found in the data version library, the found optimized data version is determined as the target data version corresponding to the current operating condition portrait; If no optimized data version matching the current operating condition portrait is found in the data version library, executing the calibration function model to obtain the target data version corresponding to the current operating condition portrait; In the data version library, search whether there is an optimized data version that matches the current working condition profile, including: Using a working condition clustering analysis algorithm, obtaining a current working condition type corresponding to the current working condition portrait; Comparing the current working condition type with the working condition type of the typical working condition portrait; If there is a typical working condition portrait in the data version library whose working condition type is consistent with the current working condition type, a first search result is obtained; the first search result indicates that: in the data version library, the optimized data version corresponding to the typical working condition portrait whose working condition type is consistent with the current working condition type is the optimized data version found to match the current working condition portrait; If there is no typical working condition portrait in the data version library whose working condition type is consistent with the current working condition type, a second search result is obtained, wherein the second search result indicates that: no optimized data version matching the current working condition portrait is found in the data version library; Or, in the data version library, search whether there is an optimized data version that matches the current working condition profile, including: Comparing the current working condition portrait with the typical working condition portrait in the data version library; If there is a typical working condition portrait in the data version library that satisfies the working condition similarity condition with the current working condition portrait, a first search result is obtained; the first search result indicates that: in the data version library, the optimized data version corresponding to the typical working condition portrait that satisfies the working condition similarity condition with the current working condition portrait is the optimized data version found to match the current working condition portrait; If there is no typical operating condition portrait in the data version library that satisfies the operating condition similarity condition with the current operating condition portrait, a second search result is obtained, and the second search result indicates that no optimized data version matching the current operating condition portrait is found in the data version library.

2. The method according to claim 1, characterized in that Using the calibration function model, the target data version corresponding to the current working condition portrait is obtained, including: Inputting the operating condition parameters in the current operating condition portrait into the calibration function model; adjusting support parameters in the calibration function model; The supporting parameters that make the performance indicators of the engine output by the calibration function model meet the optimization conditions are determined as the target data version corresponding to the current operating condition portrait.

3. The method according to claim 1, characterized in that After determining the support parameters that make the performance index of the engine output by the calibration function model meet the optimization condition as the target data version corresponding to the current operating condition portrait, the method further includes: The target data version corresponding to the current working condition portrait is added to the data version library as an optimized data version.

4. The method according to claim 1, characterized in that Before sending the target data version to the controller of the engine, the method further includes: determining whether the target data version is consistent with a current data version used by a controller of the engine; If the target data version is inconsistent with the current data version, sending the target data version to the controller of the engine is performed.

5. The method according to claim 1, characterized in that Obtain engine operating parameters, including: A plurality of sensors deployed on the engine are used to collect a plurality of operating parameters of the engine to obtain operating parameters of the engine.

6. The method according to claim 1, characterized in that The calibration function model is represented by a first function model, the first function model is composed of a plurality of second function models, and each of the second function models is respectively composed of a plurality of third function models; Wherein, the first function model represents: the functional relationship between the overall performance index of the engine and a plurality of component performance indexes; Each of the second function models corresponds to one of the component performance indicators; the second function model represents: the functional relationship between the component performance indicator and a plurality of subdivision indicators; Each of the third function models corresponds to one of the subdivision indicators; the third function model represents: the functional relationship between the subdivision indicator and the supporting parameter and the operating condition parameter in the operating condition portrait of the engine.

7. A processing device for engine performance calibration, characterized in that: The device comprises: A parameter obtaining unit, used to obtain operating parameters of the engine, wherein the operating parameters at least include a plurality of operating condition parameters; A portrait obtaining unit, used for obtaining a current operating condition portrait of the engine according to the operating parameters; A data acquisition unit, used to obtain a target data version corresponding to the current operating condition portrait by using a calibration function model, wherein the target data version includes support parameters corresponding to the control strategy of the engine; The calibration function model represents: a functional relationship between the performance index of the engine and the supporting parameters of the controller of the engine and the operating condition profile of the engine; A data sending unit, used for sending the target data version to the controller of the engine, so that the controller executes the control strategy according to the supporting parameters in the target data version, so that the performance index of the engine meets the optimization condition; A search unit, used for searching in a data version library whether there is an optimized data version matching the current working condition portrait before obtaining the target data version corresponding to the current working condition portrait by using a calibration function model; The data version library contains at least one optimized data version, and the optimized data version corresponds to a typical operating condition portrait; the supporting parameters in the optimized data version enable the performance index of the engine under the typical operating condition portrait to meet the optimization condition when the controller of the engine executes the control strategy; If an optimized data version matching the current operating condition portrait is found in the data version library, the found optimized data version is determined as the target data version corresponding to the current operating condition portrait; If no optimized data version matching the current operating condition portrait is found in the data version library, executing the calibration function model to obtain the target data version corresponding to the current operating condition portrait; In the data version library, search whether there is an optimized data version that matches the current working condition profile, including: Using a working condition clustering analysis algorithm, obtaining a current working condition type corresponding to the current working condition portrait; Comparing the current working condition type with the working condition type of the typical working condition portrait; If there is a typical working condition portrait in the data version library whose working condition type is consistent with the current working condition type, a first search result is obtained; the first search result indicates that: in the data version library, the optimized data version corresponding to the typical working condition portrait whose working condition type is consistent with the current working condition type is the optimized data version found to match the current working condition portrait; If there is no typical working condition portrait in the data version library whose working condition type is consistent with the current working condition type, a second search result is obtained, wherein the second search result indicates that: no optimized data version matching the current working condition portrait is found in the data version library; Or, in the data version library, search whether there is an optimized data version that matches the current working condition profile, including: Comparing the current working condition portrait with the typical working condition portrait in the data version library; If there is a typical working condition portrait in the data version library that satisfies the working condition similarity condition with the current working condition portrait, a first search result is obtained; the first search result indicates that: in the data version library, the optimized data version corresponding to the typical working condition portrait that satisfies the working condition similarity condition with the current working condition portrait is the optimized data version found to match the current working condition portrait; If there is no typical operating condition portrait in the data version library that satisfies the operating condition similarity condition with the current operating condition portrait, a second search result is obtained, and the second search result indicates that no optimized data version matching the current operating condition portrait is found in the data version library.

Images