CN113158436B - Method and related device for generating post-processing model by using virtual calibration system - Google Patents
Method and related device for generating post-processing model by using virtual calibration system Download PDFInfo
- Publication number
- CN113158436B CN113158436B CN202110332328.3A CN202110332328A CN113158436B CN 113158436 B CN113158436 B CN 113158436B CN 202110332328 A CN202110332328 A CN 202110332328A CN 113158436 B CN113158436 B CN 113158436B
- Authority
- CN
- China
- Prior art keywords
- model
- data
- tested
- post
- test data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Engines (AREA)
Abstract
The embodiment of the application provides a method and a related device for generating a post-processing model by using a virtual calibration system, which are used for improving the precision of input data so as to shorten the research and development period. The method of the embodiment of the application comprises the following steps: acquiring test data, wherein the test data comprises small sample test data and a model to be tested, and the small sample test data is test data for performing an operation test according to a post-treatment catalyst carrier sample; building a simulation post-processing module according to the model to be tested; calibrating the simulation post-processing module according to the hand sample test data to obtain a target post-processing module model; and operating the target post-processing module model to obtain operation data. Inputting the operation data into the model to be tested; running the model to be tested to obtain running data of the model to be tested; debugging the running data of the model to be tested according to preset data to obtain a debugging result; and updating the data of the model to be tested according to the debugging result to obtain a target model.
Description
Technical Field
The embodiment of the application relates to the field of virtual calibration, in particular to a method for generating a post-processing model by using a virtual calibration system and a related device.
Background
In the process of research and development of an engine, simulation testing is a method for saving development period and development consumption.
In the prior art, an engine model used in an engine research and development process is used for inputting experimental data into a basic model to generate a target model and simulating the target model, but when the experimental data is obtained, engine experimental data parameters can be calibrated only according to experience of a developer, so that the input data has defects or the precision cannot reach an experimental standard, the model calibration work needs to be repeated, and further the research and development period is prolonged.
Disclosure of Invention
The embodiment of the application provides a method and a related device for generating a post-processing model by using a virtual calibration system, which are used for improving the precision of input data so as to shorten the research and development period.
A first aspect of an embodiment of the present application provides a method for generating a post-processing model using a virtual calibration system, including:
acquiring test data, wherein the test data comprises small sample test data and a model to be tested, and the small sample test data is test data for performing an operation test according to a post-treatment catalyst carrier sample;
building a simulation post-processing module according to the model to be tested;
calibrating the simulation post-processing module according to the hand sample test data to obtain a target post-processing module model;
and operating the target post-processing module model to obtain operation data.
Inputting the operation data into the model to be tested;
running the model to be tested to obtain running data of the model to be tested;
debugging the running data of the model to be tested according to preset data to obtain a debugging result;
and updating the data of the model to be tested according to the debugging result to obtain a target model.
Optionally, after obtaining test data, where the test data includes a small sample test data and a model to be tested, and the small sample test data is test data for performing an operation test according to a sample of a carrier of the aftertreatment catalyst, the method further includes:
excluding discrete points in the test data and updating the test data.
Optionally, after the data of the model to be tested is updated according to the debugging result to obtain the target model, the method further includes:
and inputting the target model into an interface model through a CMC (carboxy methyl cellulose) interface, wherein the interface model is directly used on an engine model, the engine model is an engine which uses the model to be tested for post-processing, and the interface model and the model to be tested are synchronously established and use common parameters.
Optionally, the operating the target post-processing module model to obtain the operating data includes:
operating the target post-processing module model to obtain initial operation data;
judging whether the initial operation data accords with preset data or not;
if not, comparing the initial operation data with the preset data to obtain a first comparison result.
And adjusting and updating the target post-processing module model according to the first comparison result, and then running the target post-processing module model again until the initial running data accords with the preset data.
And determining the initial operation data as operation data.
Optionally, the calibrating the simulation post-processing module according to the hand sample test data to obtain a target post-processing module model includes:
performing data matching on the sample test data and the sub-module of the analog post-processing module to obtain a matching result;
and calibrating the sub-module of the simulation post-processing module respectively according to the matching result and the sample test data to obtain a target post-processing module model.
Optionally, inputting the operation data into the model to be tested includes:
and importing the sample test data in the operation data into the model to be tested.
Optionally, the debugging the to-be-tested model operation data according to preset data to obtain a debugging result includes:
comparing the model operation data to be tested with a preset operation index to obtain a second comparison result;
and debugging the model to be tested according to the second comparison result until the operation data of the model to be tested meets the preset operation index, and generating a debugging result.
A second aspect of the present application provides an apparatus for generating a post-processing model using a virtual calibration system, including:
the device comprises an acquisition unit, a test data processing unit and a test data processing unit, wherein the acquisition unit is used for acquiring test data, the test data comprises small sample test data and a model to be tested, and the small sample test data is test data for performing an operation test according to a post-treatment catalyst carrier sample;
the building unit is used for building a simulation post-processing module according to the model to be tested;
the calibration unit is used for calibrating the simulation post-processing module according to the hand sample test data to obtain a target post-processing module model;
and the first operation unit is used for operating the target post-processing module model to obtain operation data.
The first input unit is used for inputting the operation data into the model to be tested;
the second operation unit is used for operating the model to be tested to obtain operation data of the model to be tested;
the debugging unit is used for debugging the running data of the model to be tested according to preset data to obtain a debugging result;
and the updating unit is used for updating the data of the model to be tested according to the debugging result to obtain the target model.
Optionally, the apparatus further comprises:
and the eliminating unit is used for eliminating discrete points in the test data and updating the test data.
Optionally, the apparatus further comprises:
and the second input unit is used for inputting the target model into an interface model through a CMC interface, the interface model is directly used on an engine model, the engine model is an engine which uses the model to be tested for post-processing, and the interface model and the model to be tested are synchronously established and use common parameters.
Optionally, the first operation unit includes:
the first operation module is used for operating the target post-processing module model and acquiring initial operation data;
the judging module is used for judging whether the initial operation data accords with preset data or not;
and the first comparison module is used for comparing the initial operation data with the preset data to obtain a first comparison result when the judgment result of the judgment module is negative.
And the second operation module is used for adjusting and updating the target post-processing module model according to the first comparison result and then operating the target post-processing module model again until the initial operation data accords with the preset data.
And the determining module is used for determining the initial operation data as the operation data.
Optionally, the calibration unit includes:
the matching module is used for performing data matching on the sample test data and the sub-module of the simulation post-processing module to obtain a matching result;
and the calibration module is used for respectively calibrating the sub-modules of the simulation post-processing module according to the matching result and the sample test data to obtain a target post-processing module model.
Optionally, the first input unit includes:
and the input module is used for importing the sample test data in the running data into the model to be tested.
Optionally, the debugging unit includes:
the second comparison module is used for comparing the operation data of the model to be tested with a preset operation index to obtain a second comparison result;
and the debugging module is used for debugging the model to be tested according to the second comparison result until the operation data of the model to be tested meets the preset operation index, and generating a debugging result.
A third aspect of the present application provides an apparatus for generating a post-processing model using a virtual calibration system, including:
the device comprises a processor, a memory, an input and output unit and a bus;
the processor is connected with the memory, the input and output unit and the bus;
the processor specifically performs the following operations:
acquiring test data, wherein the test data comprises small sample test data and a model to be tested, and the small sample test data is test data for performing an operation test according to a post-treatment catalyst carrier sample;
building a simulation post-processing module according to the model to be tested;
calibrating the simulation post-processing module according to the hand sample test data to obtain a target post-processing module model;
and operating the target post-processing module model to obtain operation data.
Inputting the running data into the model to be tested;
running the model to be tested to obtain running data of the model to be tested;
debugging the running data of the model to be tested according to preset data to obtain a debugging result;
and updating the data of the model to be tested according to the debugging result to obtain a target model.
According to the technical scheme, the post-processing module model identical to the model to be tested is built through the test data, the test data are operated through the post-processing module model, the operation result is suitable for the model to be tested, and data correction is performed on the model to be tested, so that the accuracy of the post-processing model parameter calibration value input into the engine is improved.
Drawings
FIG. 1 is a schematic flow chart illustrating an embodiment of a method for generating a post-processing model using a virtual calibration system according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart illustrating a method for generating a post-processing model using a virtual calibration system according to another embodiment of the present disclosure;
FIG. 3 is a schematic structural diagram of an embodiment of an apparatus for generating a post-processing model using a virtual calibration system according to an embodiment of the present disclosure;
FIG. 4 is a schematic structural diagram of an apparatus for generating a post-processing model using a virtual calibration system according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of another embodiment of an apparatus for generating a post-processing model by using a virtual calibration system in the embodiment of the present application.
Detailed Description
The embodiment of the application provides a method and a related device for generating a post-processing model by using a virtual calibration system, which are used for improving the precision of input data so as to shorten the research and development period.
The technical solutions in the embodiments of the present application will be clearly and completely described in the embodiments of the present application with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In the embodiment of the present application, the execution subject may be a device capable of performing logical operations on data, such as a system, a server, and a terminal, and the following embodiment will be described with the terminal as the execution subject.
Referring to fig. 1, an embodiment of the present application provides an embodiment of a method for generating a post-processing model using a virtual calibration system, including:
101. acquiring test data, wherein the test data comprises small sample test data and a model to be tested, and the small sample test data is test data for performing an operation test according to a post-treatment catalyst carrier sample;
specifically, in the test process, test data of a small sample test bed and original data of post-processing test data of an engine test bed are used, wherein the small sample test is to take a part of a post-processing catalyst carrier as a sample, exhaust gas is introduced, parameters of the gas before and after passing through the sample, including various emission substances such as nitrogen oxide, carbon oxide, nitrous oxide, ammonia gas and oxygen, and parameters of temperature, pressure and flow of the exhaust gas, are collected, and the engine test bed is integral operation data of the whole engine in the test process, wherein the integral operation data of the whole engine in the test process comprise test data of a post-processing system of the engine.
102. Building a simulation post-processing module according to the model to be tested;
in the embodiment of the application, the engine test bed is convenient to debug subsequently, and the test terminal can input post-processing engine bed test data into an Element Pool.
Specifically, set up each catalyst converter module of aftertreatment module including establishing, front and back nitrogen oxygen temperature part and CMC interface model, engine aftertreatment module is used for carrying out purification treatment to the tail gas that the engine discharged, wherein, the catalyst converter module is arranged in catalyzing the gaseous pollutants that contains in the tail gas, thereby decompose gaseous pollutants, the catalyst converter module will carry out effective catalysis to tail gas and need be in the temperature interval that is fit for work, nitrogen oxygen temperature part is used for reading the gas temperature of input catalyst converter module and output catalyst converter module, thereby confirm the operating temperature of catalyst converter module.
In the actual test process, two models, namely an offline model and a CMC interface model used for integration, are synchronously established during post-processing modeling, the CMC interface model is a model really used for a virtual calibration rack, the format of the model is compiled and integrated, but the defect of inconvenience in debugging exists, so that an offline model is established, the two models share parameters, and when the offline debugging is finished, the CMC interface model verifies the data of the offline model, and then determines that the model can be input into an engine test bed for a complete machine integration test.
103. Calibrating the simulation post-processing module according to the hand sample test data to obtain a target post-processing module model;
in the step, the small sample data is mainly used for calibrating the post-processing module model, which is the basis of the precision of the whole post-processing model.
Specifically, in the calibration process, firstly, parameters such as the size of a small sample and the like are correctly input, whether test data meet requirements is checked, original test data of the small sample are converted according to data requirements of an actual test engine, the magnitude of the parameters such as ammonia storage, ammonia oxidation and nitric oxide oxidation is guaranteed to be the applicable magnitude of the test engine, then model initial state touch work is carried out, the touch work is a post-processing module after preliminary processing is carried out on operation data to obtain touch data, and a test terminal can adjust and calibrate the post-processing module according to the touch data.
104. And operating the target post-processing module model to obtain operation data.
On the basis of correctly inputting test parameters, all optimized adjustment parameters need to operate the model according to default values of original data of the engine, check results and determine the initial state of the model to adjust and maintain.
Specifically, after the post-processing module is operated, the data is repeatedly tested and adjusted on the post-processing module according to the default value of the original data of the engine, the operation result and the operation data obtained by the operation in step 103, and the operation data is stored and synchronized into the test data until the operation data of the target post-processing module model meets the operation requirement of the whole engine in the engine test bed.
Under the condition that the appropriate parameter magnitude of ammonia storage, ammonia oxidation, nitrogen oxide oxidation and the like is confirmed, firstly, the ammonia storage efficiency is debugged, the ammonia oxidation performance is debugged on the basis that the precision meets the requirement, the fast reaction and slow reaction processes of the nitrogen oxide oxidation are debugged on the basis, and then, the result file which is adjusted in the front is set as the carrier parameter.
105. Inputting the operation data into the model to be tested;
the model to be tested is a model of a post-processing system in an engine pedestal, the model and the target post-processing module model share the same data, when the test terminal determines the test data of the target post-processing module model, the test data is input into the model to be tested, and the data of the model to be tested is perfected through the model to be tested after the input data is operated.
106. Running the model to be tested to obtain running data of the model to be tested;
in practical situations, the test terminal can perform further debugging according to the engine bench test data. The method includes the steps that when debugging is conducted on engine bench test data, a model to be tested needs to be operated, and after operation data of the model to be tested are obtained, the model to be tested is adjusted according to the operation data and actual data requirements.
In the step, a small sample calibration result is required to be led into the model to be tested, the small sample calibration result is data of the target post-processing system module model, in the step, model data of the target post-processing system model is preliminarily calibrated through a calibration test, and at the moment, after the preliminary calibration data are input into the model to be tested, data obtained after the model to be tested runs have the reference value of the post-processing system data on the engine bench model.
107. Debugging the running data of the model to be tested according to preset data to obtain a debugging result;
specifically, the test terminal guides the calibrated small sample model results of each catalytic converter component into the post-processing module body, then guides the processed bench test data into the Element Pool, firstly carries out the resistance characteristic calibration of each catalytic converter component, and then carries out the temperature characteristic calibration of each catalytic converter component on the basis. And carrying out calibration on the chemical reaction characteristics of each catalyst on the basis that the calibration results of the resistance characteristics and the temperature characteristics meet the requirements, wherein the calibration result at the moment is a debugging result.
108. And updating the data of the model to be tested according to the debugging result to obtain a target model.
In practical situations, the final data of the model to be tested needs to keep a preset result including performance and emission under the operation condition of the model, and after the model to be tested is subjected to operation adjustment through the steps, the debugging result at the moment can be determined to be the data required by the post-processing system of the engine, which is suitable for being matched with the data performance of the engine pedestal, so that the model to be tested after updating the debugging result is determined to be the target model.
In the embodiment of the application, the test terminal builds a post-processing module model which is the same as the model to be tested through the test data, and runs the test data through the post-processing module model, so that the running result is suitable for the model to be tested, and data correction is performed on the model to be tested, so that the accuracy of the post-processing model parameter calibration value input into the engine is improved.
Referring to fig. 2, another embodiment of a method for generating a post-processing model using a virtual calibration system is provided, including:
201. acquiring test data, wherein the test data comprises small sample test data and a model to be tested, and the small sample test data is test data for performing an operation test according to a post-treatment catalyst carrier sample;
step 201 in this embodiment is similar to step 101 in the previous embodiment, and is not described herein again.
202. Excluding discrete points in the test data and updating the test data;
when the test terminal preprocesses the hand sample test data and the post-processing engine bench test data, the wild points are removed in the processing process, and the data points which do not accord with the logic are corrected to form the test data of the final input version. In this process, multiple rounds of proofreading of the processed data from whole to detail are required.
Specifically, the outliers are abnormal data points scattered in a data concentration area in the test data, in order to ensure the accuracy of the test data, multiple groups of small sample test data can be obtained in an actual situation, the multiple groups of small sample test data are preprocessed in a centralized mode according to a set calculation rule, in the step, in order to ensure that the test data are effective data, the influence of the abnormal data on the test is abandoned, the scattered data points can be eliminated in the test process, the accuracy of the test is improved, and the test times are reduced.
203. Building a simulation post-processing module according to the model to be tested;
step 203 in this embodiment is similar to step 102 in the previous embodiment, and is not repeated here.
204. Performing data matching on the sample test data and the sub-module of the analog post-processing module to obtain a matching result;
the processed sample test data is used as a target result of a sub-module of the post-processing module in the embodiment of the application, when the simulated post-processing module is operated, operation data of each sub-module of the post-processing module can be obtained, and a matching result is obtained by comparing the target result of each sub-module in the sample test data according to the operation data of each sub-module.
205. Calibrating the sub-module of the simulation post-processing module respectively according to the matching result and the sample test data to obtain a target post-processing module model;
and after the test terminal acquires the matching result, the test terminal adjusts the data of the sub-module of the analog post-processing module according to the comparison result until the operation result matches the target result, and the test terminal calibrates the sub-module of the analog post-processing module by taking the data of the sub-module of the post-processing module as target data.
206. Operating the target post-processing module model to obtain initial operation data;
and integrating all the sub-modules into a post-processing module model after the operation results of the sub-modules respectively accord with the target results, and operating the post-processing module model to obtain the background data of the post-processing module model.
Specifically, the background data is operation data of the target post-processing module model during initial operation, the sub-module operation data at the moment can meet the preset data, but the whole operation data is not in compliance, and after the calibration of each sub-module is finished, the integrated module needs to be operated again and calibrated under the condition that the sub-modules are in compliance for abandoning the condition.
207. Judging whether the initial operation data accords with preset data or not;
the preset data takes the hand sample test data as an index, and under the conditions described in the steps, the condition that the operation data is in compliance can also occur when the post-processing module operates, and at the moment, the compliance of the post-processing module needs to be judged. If the operation data of the post-processing module does not conform to the preset data, step 208 is executed, and if the operation data of the post-processing module conforms to the preset data, step 210 is executed.
208. Comparing the initial operation data with the preset data to obtain a first comparison result;
and when the operation data of the post-processing module is not accordant with the preset data, comparing the operation data with the preset data, so as to determine abnormal data according to a comparison result, and determine the items needing to be adjusted in the post-processing module according to the abnormal data.
209. And adjusting and updating the target post-processing module model according to the first comparison result, and then running the target post-processing module model again until the initial running data accords with the preset data.
After the first comparison result is obtained, the test terminal can determine an adjustment item according to the first comparison result, and perform hardware data adjustment on the adjustment item according to a preset rule and a data abnormal condition, so as to adjust the operation data of the post-processing system.
210. Determining the initial operation data as operation data;
and if the judgment result shows that the operation data of the engine does not contain or does not contain any abnormal item any more, determining the data at the moment as the operation data.
211. Importing the sample test data in the running data into the model to be tested;
the model to be tested is a model matched with the whole engine, and the running environment of the model to be tested simulates the running environment of the whole engine. For convenient debugging, the model to be tested is an off-line model, and an interface model using the same data as the model to be tested is arranged on the engine bench. The step is to introduce the adjusted hand sample test data in the operation data into the model to be tested, so that the test terminal can adjust the abnormal data which may be generated according to the operation result of the engine complete machine model.
212. Running the model to be tested to obtain running data of the model to be tested;
step 212 in this embodiment is similar to step 106 in the previous embodiment, and is not described here again.
213. Comparing the model operation data to be tested with a preset operation index to obtain a second comparison result;
after obtaining the running data of the model to be tested, the test terminal compares the running data of the model to be tested with a preset running index, wherein the preset running index is a target result of the running of the aftertreatment system in the engine bench environment, and the index of the model to be tested meets the preset running index when the engine bench test runs.
214. Debugging the model to be tested according to the second comparison result until the operation data of the model to be tested meets the preset operation index, and generating a debugging result;
and determining abnormal data in the model to be tested according to the second comparison result, reversely determining the item of the model to be tested, which needs to be adjusted, adjusting the model to be tested according to a preset adjustment rule, re-operating the adjusted model, comparing preset operation indexes again until no abnormal data exists in the comparison result, and determining the operation data of the model to be tested at the moment as a debugging result.
215. Updating the data of the model to be tested according to the debugging result to obtain a target model;
step 215 in this embodiment is similar to step 108 in the previous embodiment, and is not described here again.
216. And inputting the target model into an interface model through a CMC (carboxy methyl cellulose) interface, wherein the interface model is directly used on an engine model, the engine model is an engine which uses the model to be tested for post-processing, and the interface model and the model to be tested are synchronously established and use common parameters.
Specifically, in the embodiment of the present application, the target model is generated by an offline model, and it can be known from the foregoing steps that the offline model and the interface model share the same data, so that after the target model is determined, the target model can be input into the interface model through the CMC interface, so that the engine frame post-processes the pollutant gas generated during operation through the post-processing system data during operation, and determines the abnormal value more accurately according to the calibrated value.
In the embodiment of the application, the test terminal excludes discrete points in the test data, and improves the data accuracy of the finally generated target model through repeated debugging.
Referring to fig. 3, an embodiment of the present application provides an apparatus for generating a post-processing model using a virtual calibration system, including:
the acquisition unit 301 is configured to acquire test data, where the test data includes small sample test data and a model to be tested, and the small sample test data is test data for performing an operation test according to a post-processing catalyst carrier sample;
a building unit 302, configured to build a simulation post-processing module according to the model to be tested;
a calibration unit 303, configured to calibrate the simulated post-processing module according to the hand sample test data, so as to obtain a target post-processing module model;
a first running unit 304, configured to run the target post-processing module model to obtain running data.
A first input unit 305 for inputting the operation data into the model to be tested;
the second operation unit 306 is configured to operate the model to be tested, so as to obtain operation data of the model to be tested;
the debugging unit 307 is configured to debug the running data of the model to be tested according to preset data to obtain a debugging result;
and the updating unit 308 is configured to update the data of the model to be tested according to the debugging result to obtain a target model.
In this embodiment, the functions of the units correspond to those of the steps in the embodiment shown in fig. 1, and are not described herein again.
Referring to fig. 4, another embodiment of an apparatus for generating a post-processing model using a virtual calibration system is provided, including:
the acquisition unit 401 is configured to acquire test data, where the test data includes small sample test data and a model to be tested, and the small sample test data is test data for performing an operation test according to a post-processing catalyst carrier sample;
an excluding unit 402, configured to exclude discrete points in the test data and update the test data.
A building unit 403, configured to build a simulation post-processing module according to the model to be tested;
a calibration unit 404, configured to calibrate the simulated post-processing module according to the hand sample test data, so as to obtain a target post-processing module model;
a first operation unit 405, configured to operate the target post-processing module model to obtain operation data.
A first input unit 406, configured to input the operation data into the model to be tested;
the second operation unit 407 is configured to operate the model to be tested, so as to obtain operation data of the model to be tested;
the debugging unit 408 is configured to debug the running data of the model to be tested according to preset data to obtain a debugging result;
and the updating unit 409 is used for updating the data of the model to be tested according to the debugging result to obtain a target model.
A second input unit 410, configured to input the target model into an interface model through a CMC interface, where the interface model is directly used on an engine model, the engine model is an engine that uses the model to be tested for post-processing, and the interface model and the model to be tested are synchronously established and use a common parameter.
In the embodiment of the present application, the first operation unit 405 includes:
a first operation module 4051, configured to operate the target post-processing module model, and obtain initial operation data;
a judging module 4052, configured to judge whether the initial operating data meets preset data;
a first comparing module 4053, configured to compare the initial operating data with the preset data to obtain a first comparison result when the determining module determines that the result is negative.
A second running module 4054, configured to adjust and update the target post-processing module model according to the first comparison result, and then run the target post-processing module model again until the initial running data matches the preset data.
And the determining module is used for determining the initial operation data as the operation data.
In the embodiment of the present application, the calibration unit 404 includes:
the matching module 4041 is used for performing data matching on the sample test data and the sub-module of the post-simulation processing module to obtain a matching result;
and the calibration module 4042 is used for calibrating the sub-modules of the simulation post-processing module respectively according to the matching result and the sample test data to obtain a target post-processing module model.
In the embodiment of the present application, the first input unit 406 includes:
the input module 4061 is configured to import the sample test data in the operation data into the model to be tested.
In the embodiment of the present application, the debugging unit 408 includes:
the second comparison module 4081 is used for comparing the model operation data to be tested with a preset operation index to obtain a second comparison result;
the debugging module 4082 is configured to debug the model to be tested according to the second comparison result until the operation data of the model to be tested meets the preset operation index, so as to generate a debugging result.
In this embodiment, the functions of the units correspond to the steps in the embodiment shown in fig. 2, and are not described herein again.
Referring to fig. 5, another embodiment of an apparatus for generating a post-processing model using a virtual calibration system is provided, including:
a processor 501, a memory 502, an input/output unit 503, and a bus 504;
the processor 501 is connected to the memory 502, the input/output unit 503, and the bus 504;
the processor 501 specifically executes operations corresponding to the method steps in fig. 1 to fig. 2.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one type of logical functional division, and other divisions may be realized in practice, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like.
Claims (9)
1. A method of generating a post-processing model using a virtual calibration system, comprising:
acquiring test data, wherein the test data comprises small sample test data and a model to be tested, and the small sample test data is test data for performing an operation test according to a post-treatment catalyst carrier sample;
building a simulation post-processing module according to the model to be tested;
calibrating the simulation post-processing module according to the hand sample test data to obtain a target post-processing module model;
operating the target post-processing module model to obtain initial operation data;
judging whether the initial operation data accords with preset data or not;
if not, comparing the initial operation data with the preset data to obtain a first comparison result;
adjusting and updating the target post-processing module model according to the first comparison result, and then running the target post-processing module model again until the initial running data accords with the preset data;
determining the initial operating data as operating data;
inputting the running data into the model to be tested;
running the model to be tested to obtain running data of the model to be tested;
debugging the running data of the model to be tested according to preset data to obtain a debugging result;
and updating the data of the model to be tested according to the debugging result to obtain a target model.
2. The method of claim 1, wherein after obtaining test data, the test data including a swatch test data and a model to be tested, the swatch test data being test data for a running test from a post-treatment catalyst carrier sample, the method further comprises:
excluding discrete points in the test data and updating the test data.
3. The method of claim 1, wherein after updating the data of the model to be tested according to the debugging result to obtain a target model, the method further comprises:
and inputting the target model into an interface model through a CMC (carboxy methyl cellulose) interface, wherein the interface model is directly used on an engine model, the engine model is an engine which uses the model to be tested for post-processing, and the interface model and the model to be tested are synchronously established and use common parameters.
4. The method of any one of claims 1 to 3, wherein said calibrating the simulated post-processing module based on the hand sample test data to obtain a target post-processing module model comprises:
performing data matching on the sample test data and the sub-module of the analog post-processing module to obtain a matching result;
and calibrating the sub-module of the simulation post-processing module respectively according to the matching result and the sample test data to obtain a target post-processing module model.
5. The method of any of claims 1 to 3, wherein entering the operational data into the model to be tested comprises:
and importing the sample test data in the operation data into the model to be tested.
6. The method according to any one of claims 1 to 3, wherein the debugging the model operation data to be tested according to preset data to obtain a debugging result comprises:
comparing the model operation data to be tested with a preset operation index to obtain a second comparison result;
and debugging the model to be tested according to the second comparison result until the operation data of the model to be tested meets the preset operation index, and generating a debugging result.
7. An apparatus for generating a post-processing model using a virtual calibration system, comprising:
the device comprises an acquisition unit, a test data processing unit and a test data processing unit, wherein the acquisition unit is used for acquiring test data, the test data comprises small sample test data and a model to be tested, and the small sample test data is test data for performing an operation test according to a post-treatment catalyst carrier sample;
the building unit is used for building a simulation post-processing module according to the model to be tested;
the calibration unit is used for calibrating the simulation post-processing module according to the hand sample test data to obtain a target post-processing module model;
the first operation unit is used for operating the target post-processing module model to obtain operation data;
the first input unit is used for inputting the operation data into the model to be tested;
the second operation unit is used for operating the model to be tested to obtain operation data of the model to be tested;
the debugging unit is used for debugging the running data of the model to be tested according to preset data to obtain a debugging result;
the updating unit is used for updating the data of the model to be tested according to the debugging result to obtain a target model;
the first operation unit includes:
the first operation module is used for operating the target post-processing module model and acquiring initial operation data;
the judging module is used for judging whether the initial operation data accords with preset data or not;
the first comparison module is used for comparing the initial operation data with the preset data to obtain a first comparison result when the judgment result of the judgment module is negative;
the second operation module is used for adjusting and updating the target post-processing module model according to the first comparison result and then operating the target post-processing module model again until the initial operation data accords with the preset data;
and the determining module is used for determining the initial operation data as the operation data.
8. The apparatus of claim 7, further comprising:
and the excluding unit is used for excluding discrete points in the test data and updating the test data.
9. The apparatus of claim 7, further comprising:
and the second input unit is used for inputting the target model into an interface model through a CMC (carboxy methyl cellulose) interface, the interface model is directly used on an engine model, the engine model is an engine which uses the model to be tested for post-processing, and the interface model and the model to be tested are synchronously established and use common parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110332328.3A CN113158436B (en) | 2021-03-29 | 2021-03-29 | Method and related device for generating post-processing model by using virtual calibration system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110332328.3A CN113158436B (en) | 2021-03-29 | 2021-03-29 | Method and related device for generating post-processing model by using virtual calibration system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113158436A CN113158436A (en) | 2021-07-23 |
| CN113158436B true CN113158436B (en) | 2023-03-21 |
Family
ID=76885131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110332328.3A Active CN113158436B (en) | 2021-03-29 | 2021-03-29 | Method and related device for generating post-processing model by using virtual calibration system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113158436B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105223022A (en) * | 2015-11-17 | 2016-01-06 | 潍柴动力股份有限公司 | A kind of catalyzer checking device based on engine pedestal and method |
| CN109582525A (en) * | 2018-10-19 | 2019-04-05 | 京信通信系统（中国）有限公司 | Test code verification method, verifying device, equipment and storage medium |
| CN110344918A (en) * | 2018-04-05 | 2019-10-18 | Avl李斯特有限公司 | The functional check method of exhaust gas aftertreatment |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102014007433A1 (en) * | 2014-05-22 | 2015-12-17 | Man Truck & Bus Ag | Method for calibrating a control unit that controls or regulates a technical process that can be described by reaction kinetic equations, in particular for calibrating a control unit that controls or regulates exhaust gas aftertreatment in an exhaust gas stream of an internal combustion engine |
| CN106226085B (en) * | 2016-07-22 | 2018-10-19 | 杭州银轮科技有限公司 | Diesel SCR after-treatment system exhaust pipe urea crystals test method |
| CN106483244B (en) * | 2016-09-09 | 2019-04-02 | 浙江大学 | Flowing reactive experimental rig for SCR catalyst dynamic response test |
| CN108647430B (en) * | 2018-05-09 | 2022-02-08 | 中国重汽集团济南动力有限公司 | DPF carbon loading calculation method |
| CN110414089A (en) * | 2019-07-10 | 2019-11-05 | 一汽解放汽车有限公司 | The simulated prediction method of vehicle PEMS discharge based on Engine Universal Characteristics |
| CN110425022A (en) * | 2019-08-14 | 2019-11-08 | 广西玉柴机器股份有限公司 | Optimize the method for DPF carbon carrying capacity calibration effect |
| CN110987476A (en) * | 2019-12-26 | 2020-04-10 | 里卡多科技咨询(上海)有限公司 | Virtual calibration test method and system suitable for automobile power assembly calibration test |
| CN111828150B (en) * | 2020-07-16 | 2021-08-17 | 一汽解放汽车有限公司 | Control method for urea injection of engine post-processor |
| CN111830190B (en) * | 2020-07-23 | 2021-05-11 | 安徽江淮汽车集团股份有限公司 | Calibration method, device, equipment and storage medium for oxidation type catalyst |
| CN112305938B (en) * | 2020-09-23 | 2021-11-30 | 东风汽车集团有限公司 | Control model open-loop simulation verification method, device, equipment and medium |
-
2021
- 2021-03-29 CN CN202110332328.3A patent/CN113158436B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105223022A (en) * | 2015-11-17 | 2016-01-06 | 潍柴动力股份有限公司 | A kind of catalyzer checking device based on engine pedestal and method |
| CN110344918A (en) * | 2018-04-05 | 2019-10-18 | Avl李斯特有限公司 | The functional check method of exhaust gas aftertreatment |
| CN109582525A (en) * | 2018-10-19 | 2019-04-05 | 京信通信系统（中国）有限公司 | Test code verification method, verifying device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113158436A (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10672202B2 (en) | Configurable inferential sensor for vehicle control systems | |
| CN106850372B (en) | Method and system for testing controller CAN signal | |
| CN103235759A (en) | Method and device for generating test cases | |
| US11448588B2 (en) | Analyzer, analysis method, analyzer program, and analysis learning device | |
| JP2010256354A (en) | Method and device for verifying automation system | |
| CN112067222B (en) | Multi-degree-of-freedom vibration platform collaborative simulation detection method and detection system | |
| CN113904967B (en) | Automatic testing device and testing method for automobile CAN communication module interface software | |
| CN113158436B (en) | Method and related device for generating post-processing model by using virtual calibration system | |
| CN111537143B (en) | Performance test method and device of pressure sensor and storage medium | |
| CN110595795B (en) | Vehicle emission comparison test method, device, equipment and computer readable storage medium | |
| CN109309598B (en) | Sampling point automatic test system and method for tested vehicle-mounted module with CAN function | |
| CN111830190B (en) | Calibration method, device, equipment and storage medium for oxidation type catalyst | |
| CN113191071B (en) | Method for virtually calibrating engine model and related device thereof | |
| CN113591314A (en) | Sensor credibility evaluation method, sensor credibility evaluation device, computer equipment and medium | |
| US9075939B2 (en) | Method for co-simulation of two or more mathematical models | |
| CN116008252B (en) | Quantitative analysis method and device for mixture under Raman spectrum | |
| CN109002397B (en) | Controller smoking test system and test method | |
| CN114661615B (en) | FPGA software testing method and device | |
| CN109446004A (en) | A kind of method of automatic test GPU | |
| CN114168399A (en) | Signal processing unit testing method and system | |
| CN112084667A (en) | Test case generation method and device and electronic equipment | |
| CN111752823A (en) | Method, device and equipment for testing vehicle-mounted power supply application software | |
| CN113220725B (en) | Stream computing data testing method based on batch computing and related equipment | |
| CN116086560B (en) | Multi-factor coupled engine universal oil consumption correction method and system | |
| CN112083917B (en) | Calculation parameter generation method based on flight parameter data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |