Engine pedestal calibration test method, device and equipment based on vibration signals

Abstract

The invention relates to the technical field of engines, in particular to an engine pedestal calibration test method, device and equipment based on vibration signals, and the method comprises the steps: determining a plurality of test conditions, and collecting vibration signal data and noise signal data in a plurality of directions based on each test condition; inputting the vibration signal data and the noise signal data of the plurality of test conditions into a target noise prediction model to obtain a current noise prediction value of the engine; an objective function is determined based on oil consumption, emission and noise of an engine as an optimization objective, the rotating speed, torque, an air inlet VVT angle and an exhaust VVT angle of the engine are adjusted through bench testing, a preset genetic algorithm is adopted, and the objective function is optimized based on a current noise predicted value. And the engine intake and exhaust VVT angle meeting the preset oil consumption, emission and noise conditions is obtained. Therefore, the problem that NVH calibration and performance calibration of the engine are difficult to carry out synchronously is solved.

Description

Technical Field

[0001] The present application relates to the field of engine technology, and in particular to a vibration signal-based engine bench calibration test method, device and equipment. Background Art

[0002] As passenger car users pay more and more attention to the NVH performance of the whole vehicle, the engine, as the main source of vehicle noise, has become increasingly prominent in terms of NVH. At present, the technology to solve engine NVH has gradually evolved from the early noise control methods of sound insulation accessories such as partial shielding and full shielding to the control of noise in multiple dimensions and methods such as parameterization of engine body structure design, dynamic control of engine combustion system, and acoustic wrapping. The purpose of engine bench NVH calibration is to improve engine combustion noise by optimizing the calibration of performance parameters. However, from the practical operation level, there are the following two problems:

[0003] (1) Engine NVH testing requires a professional semi-anechoic laboratory, a low-noise dynamometer, and high-precision noise testing equipment. Generally speaking, it is difficult to conduct it simultaneously with important performance tests such as engine power, emissions, and economy. Therefore, it is difficult to find a suitable test bench to meet the needs of performance calibration engineers and NVH engineers to work simultaneously. If two test benches are used to perform NVH calibration and performance calibration at the same time, NVH engineers and performance calibration engineers will need to test and iterate repeatedly to obtain a complete MAP;

[0004] (2) The MAP obtained based on the NVH test bench and the performance calibration test bench is not necessarily the optimal MAP within the adjustable range. Summary of the invention

[0005] The present application provides an engine bench calibration test method, device and equipment based on vibration signals to solve the problem that the NVH calibration and performance calibration of the engine are difficult to carry out simultaneously.

[0006] The first aspect of the present application provides an engine bench calibration test method based on vibration signals, comprising the following steps: determining multiple test conditions, and based on each test condition, collecting vibration signal data and noise signal data in multiple directions; inputting the vibration signal data and noise signal data of the multiple test conditions into a target noise prediction model to obtain a current noise prediction value of the engine; determining an objective function based on the fuel consumption, emissions and noise of the engine as optimization targets, adjusting the engine speed, torque, intake VVT ​​angle and exhaust VVT angle through bench testing, and using a preset genetic algorithm to optimize the objective function based on the current noise prediction value to obtain the intake and exhaust VVT angles of the engine that meet preset fuel consumption, emissions and noise conditions.

[0007] Optionally, before the vibration signal data and noise signal data of the multiple test conditions are input into the target noise prediction model to obtain the current noise prediction value of the engine, the method includes: collecting the vibration signal data to be processed and the noise signal data to be processed in multiple directions of the engine under the multiple test conditions; performing root mean square and normalization processing on the vibration signal data to be processed and the noise signal data to be processed to obtain the data to be trained; dividing the data to be trained into a training set and a validation set according to a preset ratio, using the training set to train a preset neural network to obtain an initial noise prediction model, and evaluating the prediction performance of the initial noise prediction model based on the validation set; if the initial noise prediction model meets the preset usage conditions, the initial noise prediction model is used as the target noise prediction model.

[0008] Optionally, evaluating the prediction performance of the initial noise prediction model based on the validation set includes: calculating the explained variance score value and the mean absolute error value of the initial noise prediction model using a calculation formula for the explained variance score and a calculation formula for the mean absolute error; if the explained variance score value is greater than a first preset threshold and the mean absolute error difference is less than a second preset threshold, determining that the initial noise prediction model meets the preset usage conditions.

[0009] Optionally, the calculation formula for the explained variance fraction is:

[0010]

[0011] The calculation formula of the mean absolute error is:

[0012]

[0013] Among them, Var{y} is the variance of the model's predicted value, n samples is the sample size, y is the predicted value of the model, is the true value of the measurement.

[0014] Optionally, the objective function is:

[0015]

[0016] Among them, f BSFC is the engine fuel consumption, is the engine’s emission, f dB is the engine noise, speed is the engine speed, Tor is the engine torque, vcxia is the intake VVT ​​angle, and vcxea is the exhaust VVT angle.

[0017] The second aspect of the present application provides an engine bench calibration test device based on vibration signals, including: an acquisition module, used to determine multiple test conditions, and based on each test condition, collect vibration signal data and noise signal data in multiple directions; an acquisition module, used to input the vibration signal data and noise signal data of the multiple test conditions into a target noise prediction model to obtain a current noise prediction value of the engine; a calibration module, used to determine an objective function based on the fuel consumption, emissions and noise of the engine as optimization targets, adjust the engine speed, torque, intake VVT ​​angle and exhaust VVT angle through bench testing, and use a preset genetic algorithm to optimize the objective function based on the current noise prediction value to obtain the intake and exhaust VVT angles of the engine that meet the preset fuel consumption, emissions and noise conditions.

[0018] Optionally, before the vibration signal data and noise signal data of the multiple test conditions are input into the target noise prediction model to obtain the current noise prediction value of the engine, the acquisition module is also used to: collect the vibration signal data to be processed and the noise signal data to be processed in multiple directions of the engine under the multiple test conditions; obtain the data to be trained after performing root mean square and normalization processing on the vibration signal data to be processed and the noise signal data to be processed; divide the data to be trained into a training set and a validation set according to a preset ratio, use the training set to train a preset neural network to obtain an initial noise prediction model, and evaluate the prediction performance of the initial noise prediction model based on the validation set; if the initial noise prediction model meets the preset usage conditions, the initial noise prediction model is used as the target noise prediction model.

[0019] Optionally, the acquisition module is also used to: calculate the explained variance score value and the mean absolute error value of the initial noise prediction model using the calculation formula of the explained variance score and the calculation formula of the mean absolute error; if the explained variance score value is greater than a first preset threshold and the mean absolute error difference is less than a second preset threshold, it is determined that the initial noise prediction model meets the preset usage conditions.

[0020] Optionally, the calculation formula for the explained variance fraction is:

[0021]

[0022] The calculation formula of the mean absolute error is:

[0023]

[0024] Among them, Var{y} is the variance of the model's predicted value, n samples is the sample size, y is the predicted value of the model, is the true value of the measurement.

[0025] Optionally, the objective function is:

[0026]

[0027] Among them, f BSFC is the engine fuel consumption, is the engine’s emission, f dB is the engine noise, speed is the engine speed, Tor is the engine torque, vcxia is the intake VVT ​​angle, and vcxea is the exhaust VVT angle.

[0028] A third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the engine bench calibration test method based on vibration signals as described in the above embodiment.

[0029] A fourth aspect of the present application provides a computer program product having a computer program stored thereon, which is executed by a processor to implement the engine bench calibration test method based on vibration signals as described in the above embodiments.

[0030] In the above implementation, multiple test conditions are determined, and based on each test condition, vibration signal data and noise signal data in multiple directions are collected, and the vibration signal data and noise signal data of multiple test conditions are input into the target noise prediction model to obtain the current noise prediction value of the engine, and the objective function is determined based on the fuel consumption, emission and noise of the engine as the optimization target, and the engine speed, torque, intake VVT ​​angle and exhaust VVT angle are adjusted through bench testing, and the preset genetic algorithm is used to optimize the objective function based on the current noise prediction value to obtain the engine intake and exhaust VVT angle that meets the preset fuel consumption, emission and noise conditions. In this way, the problem of the difficulty in synchronously carrying out the NVH calibration and performance calibration of the engine is solved, and the online monitoring of the engine noise can be realized in a non-semi-anechoic environment, which can be applied to the bench NVH calibration of engines of all displacements.

[0031] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0033] Figure 1A flow chart of an engine bench calibration test method based on vibration signals provided according to an embodiment of the present application;

[0034] Figure 2 The present invention is a flowchart of an engine bench calibration test method based on a vibration signal according to an embodiment of the present application;

[0035] Figure 3 This is an example diagram of an engine bench calibration test device based on vibration signals according to an embodiment of the present application;

[0036] Figure 4 Schematic diagram of the structure of an electronic device according to an embodiment of the present application.

[0037] Description of reference numerals:

[0038] 10-Engine bench calibration test device based on vibration signal; 100-Acquisition module; 200-Acquisition module; 300-Calibration module; 401-Memory; 402-Processor; 403-Communication interface. DETAILED DESCRIPTION

[0039] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0040] The following describes the engine bench calibration test method, device and equipment based on vibration signals of the embodiment of the present application with reference to the accompanying drawings. In view of the problem that the NVH calibration and performance calibration of the engine mentioned in the above background technology are difficult to be carried out simultaneously, the present application provides an engine bench calibration test method based on vibration signals, in which multiple test conditions are determined, and based on each test condition, vibration signal data and noise signal data in multiple directions are collected, and the vibration signal data and noise signal data of multiple test conditions are input into the target noise prediction model to obtain the current noise prediction value of the engine, and the objective function is determined based on the fuel consumption, emission and noise of the engine as the optimization target, and the engine speed, torque, intake VVT ​​angle and exhaust VVT angle are adjusted through bench testing, and the preset genetic algorithm is used to optimize the objective function based on the current noise prediction value to obtain the engine intake and exhaust VVT angle that meets the preset fuel consumption, emission and noise conditions. Thus, the problem that the NVH calibration and performance calibration of the engine are difficult to be carried out simultaneously is solved, and the engine noise can be monitored online in a non-semi-anechoic environment, which can be applied to the bench NVH calibration of all displacement engines.

[0041] Specifically, Figure 1A schematic flow chart of an engine bench calibration test method based on vibration signals provided in an embodiment of the present application.

[0042] like Figure 1 As shown, the engine bench calibration test method based on vibration signals includes the following steps:

[0043] In step S101 , a plurality of test conditions are determined, and based on each test condition, vibration signal data and noise signal data in a plurality of directions are collected.

[0044] Among them, multiple test conditions include different speeds, different loads, and variable intake and exhaust VVT angles.

[0045] Specifically, Figure 2 As shown, the three-axis acceleration sensor is arranged on the suspension and the main noise radiation surface of the engine. The engine adopts a suspension structure similar to that of the whole vehicle to better simulate the vibration transmission from the engine. For example, during the VVT ​​optimization calibration process, based on the intake and exhaust VVT scanning combination, the vibration signal data of the engine variable load (20% to 100%) and variable speed operating points in the X direction, Y direction and Z direction are collected, and the acoustic microphones are arranged at the front, back, left, right, center of the top surface and four corners of the engine to collect the noise signal data of the engine in multiple directions.

[0046] In step S102, the vibration signal data and noise signal data of multiple test conditions are input into a target noise prediction model to obtain a current noise prediction value of the engine.

[0047] It should be understood that, based on given vibration signal data and noise signal data, the vibration signal data and noise signal data are input into the target noise prediction model to obtain the current noise prediction value of the engine.

[0048] Optionally, in some embodiments, before the vibration signal data and noise signal data of multiple test conditions are input into the target noise prediction model to obtain the current noise prediction value of the engine, the process includes: collecting the vibration signal data to be processed and the noise signal data to be processed in multiple directions of the engine under multiple test conditions; performing root mean square and normalization processing on the vibration signal data to be processed and the noise signal data to be processed to obtain the data to be trained; dividing the data to be trained into a training set and a validation set according to a preset ratio, using the training set to train a preset neural network to obtain an initial noise prediction model, and evaluating the prediction performance of the initial noise prediction model based on the validation set; if the initial noise prediction model meets the preset usage conditions, the initial noise prediction model is used as the target noise prediction model.

[0049] Optionally, in some embodiments, the prediction performance of the initial noise prediction model is evaluated based on the validation set, including: calculating the explainable variance score value and the mean absolute error value of the initial noise prediction model using the calculation formula of the explainable variance score and the calculation formula of the mean absolute error; if the explainable variance score value is greater than a first preset threshold and the mean absolute error difference is less than a second preset threshold, it is determined that the initial noise prediction model meets the preset usage conditions.

[0050] Optionally, in some embodiments, the calculation formula for the explained variance fraction is:

[0051]

[0052] The formula for calculating the mean absolute error is:

[0053]

[0054] Among them, Var{y} is the variance of the model's predicted value, n samples is the sample size, y is the predicted value of the model, is the true value of the measurement.

[0055] It should be noted that the first preset threshold and the second preset threshold can be thresholds set in advance by the user, can be thresholds obtained through a limited number of experiments, or can be thresholds obtained through a limited number of computer simulations. In the embodiment of the present application, the first preset threshold is close to 1, indicating that the prediction performance of the model is better, and the second preset threshold is less than 0.2dB, indicating that the prediction performance of the model is better.

[0056] The preset ratio may be a threshold value preset by a user, a threshold value obtained through a limited number of experiments, or a threshold value obtained through a limited number of computer simulations.

[0057] Specifically, the vibration signal data to be processed and the noise signal data to be processed are collected in multiple directions under the test conditions of different engine speeds, different loads, and variable intake and exhaust VVT angles.

[0058] The root mean square method (RMS) is further used to obtain the stable signal amplitude of the vibration signal data to be processed and the noise signal data to be processed. Since the collected vibration signal data to be processed and the noise signal data to be processed belong to samples of different dimensions, the large difference in the values ​​of different dimensions will have an adverse effect on the model training. Therefore, it is necessary to normalize the vibration signal data to be processed and the noise signal data to be processed. The minimum value of each point in this dimension is subtracted, and then divided by the difference between the maximum and minimum values, so as to map the data to the range of [0, 1]. After preprocessing, the training data is obtained, which can be used for the training and verification of the engine radiation noise prediction model. The normalization calculation formula is as follows:

[0059]

[0060] The training data is further divided randomly (or according to a preset ratio), 80% of the data is used as a training set, and 20% of the data is used as a validation set. There are vibration samples and noise samples in each data set:

[0061] X={x1,x2,…x n}

[0062] Y={y1,y2,…y n}

[0063] Where X represents the engine vibration sample set, and Y represents the noise sample set.

[0064] Furthermore, a neural network algorithm is applied to obtain an initial noise prediction model by training a preset neural network using a training set.

[0065] Furthermore, the prediction performance of the initial noise prediction model is evaluated based on the validation set. Specifically, the explained variance score (EVS) and mean absolute error (MAE) are calculated using the calculation formula of the explained variance score and the calculation formula of the mean absolute error to measure the model accuracy. Among them, EVS represents the score of the regression model. The closer it is to 1, the better the prediction performance of the initial noise prediction model. MAE represents the average error between the model prediction value and the true value, reflecting the average error of the model prediction. The mean absolute error is less than 0.2dB, which means that the prediction performance of the initial noise prediction model is better.

[0066] If the explained variance score approaches 1 and the mean absolute error is less than 0.2dB, the initial noise prediction model is judged to meet the preset usage conditions, and the initial noise prediction model is used as the target noise prediction model. If the initial noise prediction model does not meet the preset usage conditions, the initial noise prediction model can be obtained by replacing the algorithm, expanding the data to be trained, or eliminating outliers in the data to be trained, and retraining the preset neural network.

[0067] In step S103, an objective function is determined based on the engine's fuel consumption, emissions and noise as optimization targets, the engine speed, torque, intake VVT ​​angle and exhaust VVT angle are adjusted through bench testing, and a preset genetic algorithm is used to optimize the objective function based on the current noise prediction value to obtain the engine intake and exhaust VVT angles that meet the preset fuel consumption, emissions and noise conditions.

[0068] In some embodiments, the objective function is:

[0069]

[0070] Among them, f BSFCis the engine fuel consumption, is the engine’s emission, f dB is the engine noise, speed is the engine speed, Tor is the engine torque, vcxia is the intake VVT ​​angle, and vcxea is the exhaust VVT angle.

[0071] It should be understood that bench calibration is to optimize the control parameters of the engine controller (ECU) through various matching tests and result data analysis and calculation to achieve optimal engine performance.

[0072] Specifically, taking the VVT ​​calibration in the bench calibration as an example, by adjusting the intake and exhaust VVT range of each operating condition, the optimal economy at partial load and the power at full load can be achieved, while taking into account combustion stability, emissions, and VVT change gradient, the optimal VVT setting is optimized.

[0073] The embodiment of the present application introduces the NVH evaluation dimension. While taking into account combustion stability, emissions, and VVT gradient indicators, the VVT ​​angle is adjusted to obtain the lowest noise at some operating points, thereby determining the objective function, and applying the NSGA-II algorithm for multi-objective optimization. By adjusting the speed, torque, intake VVT ​​angle, and exhaust VVT angle, the intake and exhaust VVT angles of the engine that meet the optimal fuel consumption, optimal emissions, and minimum NVH are obtained.

[0074] In summary, the main advantages of the embodiments of the present application are as follows:

[0075] 1. The whole machine noise signal can be obtained in real time by only collecting the vibration signals at specific positions of the suspension and the outer surface of the engine, which provides convenience for the tester and post-test processing.

[0076] 2. The whole machine noise can be predicted by vibration signals, which can be carried out on a performance calibration bench without the need to perform engine calibration in a semi-anechoic environment.

[0077] 3. During the performance calibration process, the engine noise under the current operating conditions can be predicted synchronously by adjusting the engine operating conditions, and the noise MAP of the engine can be obtained.

[0078] 4. By adjusting parameters such as VVT angle, injection amount, injection angle, etc., the noise value under different working conditions can be obtained.

[0079] 5. Applicable to NVH calibration of engines of all displacements.

[0080] According to the engine bench calibration test method based on vibration signals proposed in the embodiment of the present application, multiple test conditions are determined, and based on each test condition, vibration signal data and noise signal data in multiple directions are collected, and the vibration signal data and noise signal data of multiple test conditions are input into the target noise prediction model to obtain the current noise prediction value of the engine, and the objective function is determined based on the fuel consumption, emission and noise of the engine as the optimization target, and the engine speed, torque, intake VVT ​​angle and exhaust VVT angle are adjusted through bench testing, and the preset genetic algorithm is used to optimize the objective function based on the current noise prediction value to obtain the engine intake and exhaust VVT angle that meets the preset fuel consumption, emission and noise conditions. In this way, the problem of the difficulty in carrying out the NVH calibration and performance calibration of the engine simultaneously is solved, and the online monitoring of engine noise can be realized in a non-semi-anechoic environment, which can be applied to the bench NVH calibration of engines of all displacements.

[0081] Next, an engine bench calibration test device based on vibration signals proposed in an embodiment of the present application will be described with reference to the accompanying drawings.

[0082] Figure 3 It is a block diagram of an engine bench calibration test device based on vibration signals according to an embodiment of the present application.

[0083] like Figure 3 As shown, the vibration signal-based engine bench calibration test device 10 includes: a collection module 100 , an acquisition module 200 and a calibration module 300 .

[0084] Among them, the acquisition module 100 is used to determine multiple test conditions, and based on each test condition, collect vibration signal data and noise signal data in multiple directions; the acquisition module 200 is used to input the vibration signal data and noise signal data of multiple test conditions into the target noise prediction model to obtain the current noise prediction value of the engine; the calibration module 300 is used to determine the objective function based on the engine's fuel consumption, emissions and noise as optimization targets, adjust the engine's speed, torque, intake VVT ​​angle and exhaust VVT angle through bench testing, and use a preset genetic algorithm to optimize the objective function based on the current noise prediction value to obtain the engine intake and exhaust VVT angles that meet the preset fuel consumption, emissions and noise conditions.

[0085] Optionally, in some embodiments, before the vibration signal data and noise signal data of multiple test conditions are input into the target noise prediction model to obtain the current noise prediction value of the engine, the acquisition module 200 is also used to: collect the vibration signal data to be processed and the noise signal data to be processed in multiple directions of the engine under multiple test conditions; perform root mean square and normalization processing on the vibration signal data to be processed and the noise signal data to be processed to obtain the data to be trained; divide the data to be trained into a training set and a validation set according to a preset ratio, use the training set to train a preset neural network to obtain an initial noise prediction model, and evaluate the prediction performance of the initial noise prediction model based on the validation set. If the initial noise prediction model meets the preset usage conditions, the initial noise prediction model is used as the target noise prediction model.

[0086] Optionally, in some embodiments, the acquisition module 200 is further used to: calculate the explainable variance score value and the mean absolute error value of the initial noise prediction model using the calculation formula of the explainable variance score and the calculation formula of the mean absolute error; if the explainable variance score value is greater than a first preset threshold and the mean absolute error difference is less than a second preset threshold, it is determined that the initial noise prediction model meets the preset usage conditions.

[0087] Optionally, in some embodiments, the calculation formula for the explained variance fraction is:

[0088]

[0089] The formula for calculating the mean absolute error is:

[0090]

[0091] Among them, Var{y} is the variance of the model's predicted value, n samples is the sample size, y is the predicted value of the model, is the true value of the measurement.

[0092] Optionally, in some embodiments, the objective function is:

[0093]

[0094] Among them, f BSFC is the engine fuel consumption, is the engine’s emission, f dB is the engine noise, speed is the engine speed, Tor is the engine torque, vcxia is the intake VVT ​​angle, and vcxea is the exhaust VVT angle.

[0095] It should be noted that the aforementioned explanation of the embodiment of the engine bench calibration test method based on vibration signals is also applicable to the engine bench calibration test device based on vibration signals of this embodiment, which will not be repeated here.

[0096] According to the vibration signal-based engine bench calibration test device proposed in the embodiment of the present application, multiple test conditions are determined, and based on each test condition, vibration signal data and noise signal data in multiple directions are collected, and the vibration signal data and noise signal data of multiple test conditions are input into the target noise prediction model to obtain the current noise prediction value of the engine, and the objective function is determined based on the engine's fuel consumption, emissions and noise as the optimization target, and the engine speed, torque, intake VVT ​​angle and exhaust VVT angle are adjusted through bench testing, and a preset genetic algorithm is used to optimize the objective function based on the current noise prediction value to obtain the engine intake and exhaust VVT angle that meets the preset fuel consumption, emissions and noise conditions. In this way, the problem of the difficulty in synchronously carrying out the NVH calibration and performance calibration of the engine is solved, and the online monitoring of the engine noise can be realized in a non-semi-anechoic environment, which can be applied to the bench NVH calibration of engines of all displacements.

[0097] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0098] Memory 401 , processor 402 , and a computer program stored in the memory 401 and executable on the processor 402 .

[0099] When the processor 402 executes the program, the engine bench calibration test method based on the vibration signal provided in the above embodiment is implemented.

[0100] Furthermore, the electronic device further comprises:

[0101] The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0102] The memory 401 is used to store computer programs that can be executed on the processor 402 .

[0103] The memory 401 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0104] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0105] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0106] The processor 402 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0107] An embodiment of the present application also provides a computer program product, on which a computer program is stored, and when the program is executed by a processor, the engine bench calibration test method based on vibration signals as described above is implemented.

[0108] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0109] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0110] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0111] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer program product for use with an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer program product" can be any device that can contain, store, communicate, propagate or transmit a program for use with an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer program products (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). Furthermore, the computer program product may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example by optically scanning the paper or other medium and then editing, interpreting or, if necessary, processing in another suitable manner, and then storing it in a computer memory.

[0112] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0113] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer program product, which, when executed, includes one or a combination of the steps of the method embodiment.

[0114] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer program product.

[0115] The computer program product mentioned above may be a read-only memory, a disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. An engine bench calibration test method based on vibration signals, characterized in that: The following steps are involved: Determine multiple test conditions, and based on each test condition, collect vibration signal data and noise signal data in multiple directions; Inputting the vibration signal data and the noise signal data of the plurality of test conditions into a target noise prediction model to obtain a current noise prediction value of the engine; An objective function is determined based on the fuel consumption, emissions and noise of the engine as optimization targets, the engine speed, torque, intake VVT ​​angle and exhaust VVT angle are adjusted through bench testing, and a preset genetic algorithm is used to optimize the objective function based on the current noise prediction value to obtain the engine intake and exhaust VVT angles that meet the preset fuel consumption, emissions and noise conditions.

2. The method according to claim 1, characterized in that Before inputting the vibration signal data and the noise signal data of the plurality of test conditions into the target noise prediction model to obtain the current noise prediction value of the engine, the method comprises: Collecting vibration signal data to be processed and noise signal data to be processed in multiple directions of the engine under the multiple test conditions; Performing root mean square and normalization processing on the vibration signal data to be processed and the noise signal data to be processed to obtain data to be trained; The data to be trained is divided into a training set and a validation set according to a preset ratio, a preset neural network is trained using the training set to obtain an initial noise prediction model, and the prediction performance of the initial noise prediction model is evaluated based on the validation set. If the initial noise prediction model meets the preset usage conditions, the initial noise prediction model is used as the target noise prediction model.

3. The method according to claim 2, characterized in that The evaluating the prediction performance of the initial noise prediction model based on the validation set includes: Calculate the explained variance score value and the mean absolute error value of the initial noise prediction model using the calculation formula of the explained variance score and the calculation formula of the mean absolute error; If the explained variance score value is greater than a first preset threshold and the mean absolute error difference is less than a second preset threshold, it is determined that the initial noise prediction model meets the preset usage condition.

4. The method according to claim 3, characterized in that The calculation formula for the explained variance fraction is: The calculation formula of the mean absolute error is: Among them, Var{y} is the variance of the model's predicted value, n samples is the sample size, y is the predicted value of the model, is the true value of the measurement.

5. The method according to claim 1, characterized in that The objective function is: Among them, f BSFC is the engine fuel consumption, is the engine’s emission, f dB is the engine noise, speed is the engine speed, Tor is the engine torque, vcxia is the intake VVT ​​angle, and vcxea is the exhaust VVT angle.

6. An engine bench calibration test device based on vibration signals, characterized in that: The device includes: An acquisition module, used to determine multiple test conditions, and based on each test condition, to acquire vibration signal data and noise signal data in multiple directions; An acquisition module, used for inputting the vibration signal data and the noise signal data of the plurality of test conditions into a target noise prediction model to obtain a current noise prediction value of the engine; A calibration module is used to determine an objective function based on the fuel consumption, emissions and noise of the engine as optimization targets, adjust the engine speed, torque, intake VVT ​​angle and exhaust VVT angle through bench testing, and use a preset genetic algorithm to optimize the objective function based on the current noise prediction value to obtain the engine intake and exhaust VVT angles that meet the preset fuel consumption, emissions and noise conditions.

7. The device according to claim 6, characterized in that Before inputting the vibration signal data and noise signal data of the plurality of test conditions into the target noise prediction model to obtain the current noise prediction value of the engine, the acquisition module is further used to: Collecting vibration signal data to be processed and noise signal data to be processed in multiple directions of the engine under the multiple test conditions; Performing root mean square and normalization processing on the vibration signal data to be processed and the noise signal data to be processed to obtain data to be trained; The data to be trained is divided into a training set and a validation set according to a preset ratio, a preset neural network is trained using the training set to obtain an initial noise prediction model, and the prediction performance of the initial noise prediction model is evaluated based on the validation set. If the initial noise prediction model meets the preset usage conditions, the initial noise prediction model is used as the target noise prediction model.

8. The device according to claim 7, characterized in that The acquisition module is further used for: Calculate the explained variance score value and the mean absolute error value of the initial noise prediction model using the calculation formula of the explained variance score and the calculation formula of the mean absolute error; If the explained variance score value is greater than a first preset threshold and the mean absolute error difference is less than a second preset threshold, it is determined that the initial noise prediction model meets the preset usage condition.

9. A vehicle, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the engine bench calibration test method based on vibration signals as claimed in any one of claims 1 to 5.

10. A computer program product, wherein the computer program product stores a computer program, characterized in that: When the program is executed by a processor, the engine bench calibration test method based on vibration signals as described in any one of claims 1 to 5 is implemented.

Images