阅读说明：本技术 发动机怠速声品质优化方法、系统以及发动机 (Engine idling sound quality optimization method and system and engine ) 是由 徐可鹏 时胜文 曹虎 于 2021-08-13 设计创作，主要内容包括：本发明公开了一种发动机怠速声品质优化方法、系统以及发动机,方法包括获取发动机的多个噪声数据样本,并基于噪声数据样本确定声品质客观心理学参量以及声品质主观评价等级分数；根据声品质客观心理学参量以及声品质主观评价等级分数确定线性回归模型；建立发动机的喷射参数与声品质客观心理学参量的预测模型；基于线性回归模型以及预测模型建立喷射参数以及声品质主观评价等级分数之间的传递函数；求解传递函数,得到发动机的最优喷射参数。本发明通过最优化发动机的喷射参数来改变发动机的燃烧状态,解决了现有技术无法从根源上对发动机的声品质进行优化的技术问题,实现了从根源上优化发动机的声品质的技术效果,提高了产品的竞争力。(The invention discloses an engine idling sound quality optimization method, an engine idling sound quality optimization system and an engine, wherein the method comprises the steps of obtaining a plurality of noise data samples of the engine, and determining objective psychological parameters of sound quality and subjective evaluation grade scores of the sound quality based on the noise data samples; determining a linear regression model according to the objective psychological parameters of the sound quality and the subjective evaluation grade scores of the sound quality; establishing a prediction model of the injection parameters and the acoustic quality objective psychology parameters of the engine; establishing a transfer function between the injection parameters and the sound quality subjective evaluation grade scores based on the linear regression model and the prediction model; and solving the transfer function to obtain the optimal injection parameter of the engine. The combustion state of the engine is changed by optimizing the injection parameters of the engine, the technical problem that the sound quality of the engine cannot be optimized fundamentally in the prior art is solved, the technical effect of optimizing the sound quality of the engine fundamentally is achieved, and the product competitiveness is improved.)

1. An engine idle sound quality optimization method, comprising:

acquiring a plurality of noise data samples of an engine, and determining an acoustic quality objective psychology parameter and an acoustic quality subjective evaluation grade score based on the noise data samples;

determining a linear regression model according to the acoustic quality objective psychology parameters and the acoustic quality subjective evaluation grade scores;

establishing a prediction model of injection parameters of the engine and the acoustic quality objective psychology parameters, wherein the injection parameters comprise a main injection advance angle, a pilot injection interval angle, pilot injection quantity and rail pressure;

establishing a transfer function between the injection parameters and the sound quality subjective evaluation grade score based on the linear regression model and the prediction model;

and solving the transfer function to obtain the optimal injection parameter of the engine.

2. The engine idle sound quality optimization method of claim 1, wherein the determining a linear regression model based on the objective psychology parameter of sound quality and the subjective evaluation level score of sound quality comprises:

and establishing the linear regression model of the acoustic quality objective psychological parameters and the acoustic quality subjective evaluation grade scores by using a support vector machine algorithm.

3. The engine idle sound quality optimization method of claim 1, wherein obtaining a plurality of noise data samples for an engine and determining a sound quality objective psychology parameter and a sound quality subjective assessment rating score based on the noise data samples comprises:

obtaining a plurality of noise data samples of an engine;

calculating the acoustic quality objective psychology parameters of each of the noise data samples;

and carrying out subjective evaluation on the noise data sample to obtain the sound quality subjective evaluation grade score.

4. The engine idle sound quality optimization method of claim 3, wherein the subjectively evaluating the noise data samples to obtain the sound quality subjective evaluation rating score comprises:

and subjectively evaluating the noise data sample based on a grade evaluation method to obtain a sound quality subjective evaluation grade score.

5. The engine idle sound quality optimization method of claim 3, wherein said calculating the sound quality objective psychology parameter for each of the noise data samples comprises:

the loudness, sharpness, roughness, waviness and a-weight sound pressure level of each of the noise data samples are calculated.

6. The engine idle sound quality optimization method of claim 1, further comprising, prior to said obtaining noise data samples for an engine and determining a sound quality objective psychology parameter and a sound quality subjective assessment rating score based on said noise data samples:

establishing a combination of a plurality of groups of the injection parameters according to an orthogonal table method;

obtaining the noise data samples for the engine for each set of the injection parameters.

7. The engine idle sound quality optimization method of claim 1, wherein solving the transfer function to obtain optimal injection parameters for the engine comprises:

and solving the transfer function through a genetic algorithm to obtain the optimal injection parameter of the engine.

8. The engine idle sound quality optimization method of claim 1, further comprising, after obtaining the optimal injection parameters:

controlling the engine to operate based on the optimal injection parameter.

9. An engine idle sound quality optimization system, comprising:

the system comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring a plurality of noise data samples of an engine and determining an acoustic quality objective psychological parameter and an acoustic quality subjective evaluation grade score based on the noise data samples;

the model determining unit is used for determining a linear regression model according to the acoustic quality objective psychological parameters and the acoustic quality subjective evaluation grade scores;

the first establishing unit is used for establishing a prediction model of injection parameters of the engine and the acoustic quality objective psychological parameters, wherein the injection parameters comprise a main injection advance angle, a pilot injection interval angle, pilot injection quantity and rail pressure;

a second establishing unit configured to establish a transfer function between the injection parameter and the sound quality subjective evaluation grade score based on the linear regression model and the prediction model;

and the solving unit is used for solving the transfer function to obtain the optimal injection parameter of the engine.

10. An engine comprising the engine idle sound quality optimization system of claim 9.

Technical Field

The embodiment of the invention relates to the technical field of sound quality, in particular to an engine idling sound quality optimization method and system and an engine.

Background

With the continuous improvement of the performance requirements of clients on NVH (Noise, Vibration and Harshness), the Noise optimization aiming at the sound pressure level alone cannot meet the requirements of the clients on comfort level, the sound quality reflects the subjective feeling of people on the Noise, and the improvement of the sound quality has great significance on improving the product competitiveness.

However, at present, there is no mature and effective sound quality optimization method, which is mainly performed by an active sound production control system (active noise reduction) on the whole vehicle, and the method mainly performs sound quality optimization by a method of canceling a part of frequency noise, but does not perform sound quality optimization fundamentally, and has the disadvantages of complex algorithm, large influence of environmental factors, and poor robustness.

Disclosure of Invention

The invention provides an engine idling sound quality optimization method and system and an engine, and solves the technical problem that the sound quality of the engine cannot be optimized fundamentally in the prior art.

The embodiment of the invention provides an engine idling sound quality optimization method, which comprises the following steps:

acquiring a plurality of noise data samples of an engine, and determining an acoustic quality objective psychology parameter and an acoustic quality subjective evaluation grade score based on the noise data samples;

determining a linear regression model according to the acoustic quality objective psychology parameters and the acoustic quality subjective evaluation grade scores;

establishing a prediction model of injection parameters of the engine and the acoustic quality objective psychology parameters, wherein the injection parameters comprise a main injection advance angle, a pilot injection interval angle, pilot injection quantity and rail pressure;

establishing a transfer function between the injection parameters and the sound quality subjective evaluation grade score based on the linear regression model and the prediction model;

and solving the transfer function to obtain the optimal injection parameter of the engine.

Further, the determining a linear regression model according to the objective psychology parameters of the acoustic quality and the subjective evaluation grade score of the acoustic quality comprises:

and establishing the linear regression model of the acoustic quality objective psychological parameters and the acoustic quality subjective evaluation grade scores by using a support vector machine algorithm.

Further, the obtaining a plurality of noise data samples of the engine and determining the acoustic quality objective psychology parameter and the acoustic quality subjective evaluation grade score based on the noise data samples comprises:

obtaining a plurality of noise data samples of an engine;

calculating the acoustic quality objective psychology parameters of each of the noise data samples;

and carrying out subjective evaluation on the noise data sample to obtain the sound quality subjective evaluation grade score.

Further, the subjectively evaluating the noise data sample to obtain the sound quality subjective evaluation grade score includes:

and subjectively evaluating the noise data sample based on a grade evaluation method to obtain a sound quality subjective evaluation grade score.

Further, said calculating said objective psychology parameter of sound quality for each of said noise data samples comprises:

the loudness, sharpness, roughness, waviness and a-weight sound pressure level of each of the noise data samples are calculated.

Further, before the obtaining of noise data samples of the engine and the determining of the acoustic quality objective psychological parameters and the acoustic quality subjective evaluation grade scores based on the noise data samples, the method further comprises:

establishing a combination of a plurality of groups of the injection parameters according to an orthogonal table method;

obtaining the noise data samples for the engine for each set of the injection parameters.

Further, solving the transfer function to obtain the optimal injection parameter of the engine comprises:

and solving the transfer function through a genetic algorithm to obtain the optimal injection parameter of the engine.

Further, after obtaining the optimal injection parameter, the method further includes:

controlling the engine to operate based on the optimal injection parameter.

The embodiment of the invention also provides an engine idling sound quality optimization system, which comprises:

the system comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring a plurality of noise data samples of an engine and determining an acoustic quality objective psychological parameter and an acoustic quality subjective evaluation grade score based on the noise data samples;

the model determining unit is used for determining a linear regression model according to the acoustic quality objective psychological parameters and the acoustic quality subjective evaluation grade scores;

the first establishing unit is used for establishing a prediction model of injection parameters of the engine and the acoustic quality objective psychological parameters, wherein the injection parameters comprise a main injection advance angle, a pilot injection interval angle, pilot injection quantity and rail pressure;

a second establishing unit configured to establish a transfer function between the injection parameter and the sound quality subjective evaluation grade score based on the linear regression model and the prediction model;

and the solving unit is used for solving the transfer function to obtain the optimal injection parameter of the engine.

Embodiments of the present invention also provide an engine comprising an engine idle sound quality optimization system as claimed in claim 9 above.

The embodiment of the invention discloses an engine idling sound quality optimization method, an engine idling sound quality optimization system and an engine, wherein the method comprises the steps of obtaining a plurality of noise data samples of the engine, and determining objective psychology parameters of sound quality and subjective evaluation grade scores of the sound quality based on the noise data samples; determining a linear regression model according to the objective psychological parameters of the sound quality and the subjective evaluation grade scores of the sound quality; establishing a prediction model of the injection parameters and the acoustic quality objective psychology parameters of the engine; establishing a transfer function between the injection parameters and the sound quality subjective evaluation grade scores based on the linear regression model and the prediction model; and solving the transfer function to obtain the optimal injection parameter of the engine. According to the embodiment of the invention, the combustion state of the engine is changed by optimizing the injection parameters of the engine, the technical problem that the sound quality of the engine cannot be optimized fundamentally in the prior art is solved, the technical effect of optimizing the sound quality of the engine fundamentally is realized, and the product competitiveness is improved.

Drawings

FIG. 1 is a flow chart of a method for optimizing engine idle sound quality provided by an embodiment of the present invention;

fig. 2 is a flow chart of establishing a linear regression model between objective psychology parameters of acoustic quality and subjective evaluation grade scores of acoustic quality according to an embodiment of the present invention;

FIG. 3 is a flow chart of the method for establishing a prediction model between an injection parameter and an acoustic quality objective psychology parameter according to an embodiment of the present invention

FIG. 4 is a diagram of a neural network architecture provided by an embodiment of the present invention;

FIG. 5 is a diagram of neural network prediction results for a training set provided by an embodiment of the present invention;

FIG. 6 is a diagram of neural network prediction results for a validation set provided by an embodiment of the present invention;

FIG. 7 is a graph of neural network prediction results for a test set provided by an embodiment of the present invention;

FIG. 8 is a graph of the integrated neural network prediction results for the training set, validation set, and test set provided by embodiments of the present invention;

FIG. 9 is a flow chart of establishing a transfer function and performing global optimization according to an embodiment of the present invention;

FIG. 10 is a flow chart of another engine idle sound quality optimization method provided by an embodiment of the present invention;

FIG. 11 is a flow chart of yet another engine idle sound quality optimization method provided by an embodiment of the present invention;

FIG. 12 is a flow chart of yet another engine idle sound quality optimization method provided by an embodiment of the present invention;

fig. 13 is a block diagram of an engine idle sound quality optimization system according to an embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

It should be noted that the terms "first", "second", and the like in the description and claims of the present invention and the accompanying drawings are used for distinguishing different objects, and are not used for limiting a specific order. The following embodiments of the present invention may be implemented individually, or in combination with each other, and the embodiments of the present invention are not limited in this respect.

FIG. 1 is a flow chart of a method for optimizing the idle sound quality of an engine according to an embodiment of the present invention. Fig. 2 is a flowchart of establishing a linear regression model between objective psychology parameters of acoustic quality and subjective evaluation grade scores of acoustic quality according to an embodiment of the present invention.

As shown in fig. 1, the method for optimizing the idle sound quality of the engine specifically includes the following steps:

step S101, a plurality of noise data samples of the engine are obtained, and the acoustic quality objective psychology parameters and the acoustic quality subjective evaluation grade scores are determined based on the noise data samples.

Specifically, the sound quality subjective evaluation grade score refers to the degree of satisfaction of an individual with sound, and the higher the grade, the higher the degree of satisfaction of the individual with sound. Taking a diesel engine as an example, acquiring noise data of different diesel engine models under different working conditions and different measuring point positions to obtain a plurality of noise data samples, searching healthy people of different ages due to different groups of people with different sensitivities to sounds of different frequency bands, and performing subjective evaluation on each noise data sample under the same set environmental condition to obtain a sound quality subjective evaluation grade score; and calculating the acoustic quality objective psychology parameters of each noise data sample by LMS software.

And S102, determining a linear regression model according to the acoustic quality objective psychology parameters and the acoustic quality subjective evaluation grade scores.

Optionally, in step S102, determining a linear regression model according to the objective psychology parameters of the acoustic quality and the subjective evaluation grade score of the acoustic quality includes: and establishing a linear regression model of the acoustic quality objective psychology parameters and the acoustic quality subjective evaluation grade scores by using a support vector machine algorithm.

Specifically, as shown in fig. 2, after obtaining the acoustic quality objective psychology parameters and the acoustic quality subjective evaluation grade scores of the noise data samples, a linear regression model of the acoustic quality objective psychology parameters and the acoustic quality subjective evaluation grade scores is established by using a Support Vector Machine algorithm with the acoustic quality objective psychology parameters as input and the acoustic quality subjective evaluation grade scores as output, wherein the Support Vector Machine (SVM) algorithm is a supervised learning model for analyzing data by using classification and regression analysis and a related learning algorithm thereof.

Step S103, establishing a prediction model of the injection parameters and the acoustic quality objective psychology parameters of the engine, wherein the injection parameters comprise a main injection advance angle, a pilot injection interval angle, pilot injection quantity and rail pressure.

Specifically, the injection parameters determining the combustion state of the engine mainly comprise a main injection advance angle, a pilot injection interval angle, pilot injection quantity and rail pressure, the established prediction model is a neural network model, the artificial neural network is a basic principle based on a neural network in biology, and after understanding and abstracting a human brain structure and an external stimulation response mechanism, a network topology knowledge is taken as a theoretical basis to simulate an all-time mathematical model of a processing mechanism of a neural system of a human brain on complex information.

Fig. 3 is a flowchart of establishing a prediction model between the injection parameters and the acoustic quality objective psychology parameters according to an embodiment of the present invention. As shown in fig. 3, the injection parameters are used as input, the acoustic quality objective psychology parameters are used as output, and an artificial neural network model (i.e. the above prediction model) between the injection parameters and the acoustic quality objective psychology parameters is established by using a neural network algorithm. Fig. 4 is a diagram of a neural network structure provided in an embodiment of the present invention, where the objective psychology parameters of sound quality include loudness, sharpness, roughness, fluctuation, a weighted sound pressure level, and the like shown in fig. 4, after an artificial neural network model is established, the established artificial neural network structure may be trained through a neural network toolbox provided in Matlab software, and the Training results are shown in fig. 5 to 8, where the prediction performance is verified by using a decision coefficient R between a predicted value Y and a Test value T of the artificial neural network model, and it is required that R values of a Training set (Training set), a validity set (verification set), and a Test set (Test set) are all 9 or more.

In addition, in order to ensure that the established prediction model of the injection parameters and the acoustic quality objective psychological parameters has higher precision, high-quality injection parameters need to be reasonably and accurately acquired to serve as test data for neural network modeling, and for example, a combination of multiple groups of injection parameters can be established by adopting an orthogonal table method.

And step S104, establishing a transfer function between the injection parameters and the sound quality subjective evaluation grade scores based on the linear regression model and the prediction model.

Specifically, fig. 9 is a flowchart for establishing a transfer function and performing global optimization according to an embodiment of the present invention, and as shown in fig. 9, after obtaining a linear regression model and a prediction model, an artificial neural network prediction model between an injection parameter and an acoustic quality objective psychology parameter and a univariate linear regression model between the acoustic quality objective psychology parameter and an acoustic quality subjective rating level score are integrated, and finally, a transfer function between the injection parameter and the acoustic quality subjective rating level score is obtained.

And step S105, solving the transfer function to obtain the optimal injection parameter of the engine.

Specifically, after a transfer function between the injection parameters and the sound quality subjective rating grade scores is obtained, the transfer function is used as a fitness function, the maximum value of the sound quality subjective rating grade scores is used as a target, the selectable range of the injection parameters is used as a constraint, the injection parameter combination is used as an individual, global optimization is carried out through a genetic algorithm toolbox carried by Matlab software, the optimal injection parameters are finally obtained, the engine is controlled to work by the optimal injection parameters, and the sound quality of the engine working based on the optimal injection parameters is optimal.

As shown in fig. 9, the specific steps for global optimization using genetic algorithm are as follows: firstly, carrying out gene coding on the injection parameters to generate an initial population; secondly, calculating individual fitness and performing species group optimization; thirdly, judging whether the convergence requirement is met, if so, executing the fourth step of chromosome decoding to output the optimal individual, ending the global optimization, and if not, executing the fifth step of selection, crossing and variation in sequence; sixthly, recalculating individual fitness after selecting cross variation and performing population group optimization; and seventhly, generating a K +1 generation population, and returning to the third step again to judge whether the convergence requirement is met.

Alternatively, in step S105, solving the transfer function to obtain the optimal injection parameter of the engine includes: and solving the transfer function through a genetic algorithm to obtain the optimal injection parameter of the engine.

Specifically, the genetic algorithm is a calculation model of a biological evolution process that simulates natural selection and genetic mechanism of a biological evolution theory, and is a method for searching for an optimal solution by simulating the natural evolution process. The genetic algorithm has inherent hidden parallelism and better global optimization capability, can automatically acquire and guide an optimized search space, adaptively adjusts the search direction, does not need a determined rule, therefore, the global optimization is carried out through a genetic algorithm toolbox carried by Matlab software, the global optimal value can be found in a shorter time, and the defect that the ordinary calibration method is trapped in local optimization due to control of a single variable is avoided.

According to the embodiment of the invention, the combustion state of the engine is changed by optimizing the injection parameters of the engine, the technical problem that the sound quality of the engine cannot be optimized fundamentally in the prior art is solved, the technical effect of optimizing the sound quality of the engine fundamentally is realized, and the product competitiveness is improved.

Based on the technical scheme, the embodiment optimizes the multiple noise data samples of the engine and determines the objective psychological parameters of the sound quality and the subjective evaluation grade scores of the sound quality based on the noise data samples. Fig. 10 is a flowchart of another method for optimizing the idle sound quality of the engine according to the embodiment of the present invention, and as shown in fig. 10, the method for optimizing the idle sound quality of the engine according to the embodiment includes the following steps:

in step S201, a plurality of noise data samples of the engine are acquired.

Specifically, noise data of different diesel engine models under different working conditions and different measuring point positions are collected, and a plurality of noise data samples are obtained.

Step S202, calculating the acoustic quality objective psychology parameter of each noise data sample.

Optionally, in step S202, the calculating the acoustic quality objective psychology parameter of each noise data sample includes: loudness, sharpness, roughness, waviness, and a-weighted sound pressure level are calculated for each noisy data sample.

Specifically, the LMS software can be used for calculating the sound quality objective psychology parameters such as loudness, sharpness, roughness, fluctuation and A weighting sound pressure level of each noise data sample, wherein the loudness reflects subjective perception degree of human beings on sound intensity, the sharpness is used for describing the proportion of high-frequency noise in a frequency spectrum, the roughness is used for representing the perception degree of human beings on real-time change of a sound signal, and the fluctuation is used for reflecting the amplitude modulation characteristic of the sound.

Step S203, the noise data samples are subjectively evaluated to obtain the sound quality subjective evaluation grade scores.

Optionally, in step S203, subjectively evaluating the noise data sample, and obtaining the subjective evaluation level score of the sound quality includes: and subjectively evaluating the noise data sample based on a grade evaluation method to obtain the sound quality subjective evaluation grade score.

Specifically, the level scoring method is to divide an attribute of the sound quality into a plurality of levels, and each level is divided into different scores. Table 1 is a rating scale scoring table, and referring to table 1, it is possible to group people with healthy body according to different age groups, and then subjectively score each noise data sample by rating scale scoring for different groups of people under the same set environmental condition.

TABLE 1 grade scoring method scoring table

And step S204, determining a linear regression model according to the acoustic quality objective psychology parameters and the acoustic quality subjective evaluation grade scores.

Step S205, a prediction model of the injection parameters and the acoustic quality objective psychology parameters of the engine is established, wherein the injection parameters comprise a main injection advance angle, a pilot injection interval angle, pilot injection quantity and rail pressure.

And step S206, establishing a transfer function between the injection parameters and the sound quality subjective evaluation grade scores based on the linear regression model and the prediction model.

And step S207, solving the transfer function to obtain the optimal injection parameter of the engine.

According to the embodiment of the invention, the combustion state of the engine is changed by optimizing the injection parameters of the engine, the technical problem that the sound quality of the engine cannot be optimized fundamentally in the prior art is solved, the technical effect of optimizing the sound quality of the engine fundamentally is realized, and the product competitiveness is improved.

FIG. 11 is a flow chart of yet another engine idle sound quality optimization method provided by an embodiment of the present invention.

Based on the above technical solution, before obtaining a plurality of noise data samples of the engine and determining the objective psychology parameters of the acoustic quality and the subjective evaluation grade score of the acoustic quality based on the noise data samples, as shown in fig. 8, the method for optimizing the acoustic quality of the engine in idle speed further includes the following steps:

in step S301, a combination of a plurality of sets of injection parameters is established according to an orthogonal table method.

Specifically, modeling of data is generally not independent of DOE (Design of Experiment), and in the embodiment of the present invention, the Experiment Design uses an orthogonal table method to establish a combination of multiple sets of injection parameters, and the orthogonal table method is a basic tool for arranging experiments and analyzing test results in the orthogonal Design, and has the following two features: (1) in each column, the number of occurrences of different numbers is equal; (2) the arrangement modes of the numbers in any two columns are complete and balanced. The combination of multiple sets of injection parameters may be obtained using the balanced match characteristics of the orthogonal tables. Table 2 exemplarily shows the injection parameter combinations established according to the orthogonal table method.

TABLE 2 combination of injection parameters

Main injection advance angle	Pre-spray interval angle	Amount of pilot fuel injected	Rail pressure
				-2.0	5.0	1.2	349527
-2.0	5.5	1.3	359603
				…	…	…	…
-1.5	5.0	1.4	390757
				-1.5	5.5	1.5	401867
…	…	…	…
				-1	5.0	1.7	431507
-1	5.5	1.8	442170
				…	…	…	…
-0.5	5.0	1.9	473430
				-0.5	5.5	2.0	485057
…	…	…	…
				0	5.0	2.1	516740
0	5.5	2.2	527400
				…	…	…	…

In step S302, noise data samples of the engine for each set of injection parameters are obtained.

Specifically, referring to fig. 3, after obtaining multiple sets of injection parameters by the orthogonal table method, noise data samples of the diesel engine under different working conditions are obtained for each set of injection parameters.

Step S303, determining the objective psychology parameters of the sound quality and the subjective evaluation grade scores of the sound quality based on the noise data samples.

And step S304, determining a linear regression model according to the acoustic quality objective psychology parameters and the acoustic quality subjective evaluation grade scores.

Step S305, establishing a prediction model of the injection parameters and the acoustic quality objective psychology parameters of the engine, wherein the injection parameters comprise a main injection advance angle, a pilot injection interval angle, pilot injection quantity and rail pressure.

And step S306, establishing a transfer function between the injection parameters and the sound quality subjective evaluation grade scores based on the linear regression model and the prediction model.

And step S307, solving the transfer function to obtain the optimal injection parameter of the engine.

According to the embodiment of the invention, the combustion state of the engine is changed by optimizing the injection parameters of the engine, the technical problem that the sound quality of the engine cannot be optimized fundamentally in the prior art is solved, the technical effect of optimizing the sound quality of the engine fundamentally is realized, and the product competitiveness is improved.

FIG. 12 is a flow chart of yet another engine idle sound quality optimization method provided by an embodiment of the present invention.

Based on the above technical solution, after obtaining the optimal injection parameter, as shown in fig. 9, the method for optimizing the idle sound quality of the engine further includes the following steps:

step S401, a plurality of noise data samples of the engine are obtained, and the acoustic quality objective psychology parameters and the acoustic quality subjective evaluation grade scores are determined based on the noise data samples.

Step S402, determining a linear regression model according to the acoustic quality objective psychology parameters and the acoustic quality subjective evaluation grade scores.

Step S403, establishing a prediction model of the injection parameters and the acoustic quality objective psychology parameters of the engine, wherein the injection parameters comprise a main injection advance angle, a pilot injection interval angle, pilot injection quantity and rail pressure.

And step S404, establishing a transfer function between the injection parameters and the sound quality subjective evaluation grade scores based on the linear regression model and the prediction model.

And S405, solving the transfer function to obtain the optimal injection parameter of the engine.

In step S406, engine operation is controlled based on the optimum injection parameters.

Specifically, after the optimal injection parameters are obtained through solving, the engine is controlled to work through the optimal injection parameters, and the sound quality of the engine working based on the optimal injection parameters is optimal.

The noise quality optimization method disclosed by the embodiment of the invention is implemented by a data calibration method, namely, a method for controlling the engine by adopting the optimal injection parameters is used for noise quality optimization, the noise quality optimization can be realized without changing hardware configuration in the diesel engine, the research and development period for optimizing the noise quality of the engine is effectively shortened, the cost of manpower and material resources is reduced, and the cost performance is high.

The embodiment of the invention also provides an engine idle speed sound quality optimization system, which is used for executing the engine idle speed sound quality optimization method provided by the embodiment of the invention.

Fig. 13 is a block diagram of an engine idle sound quality optimization system according to an embodiment of the present invention. As shown in fig. 13, the engine idle sound quality optimization system mainly includes: an obtaining unit 10, a model determining unit 20, a first establishing unit 30, a second establishing unit 40, and a solving unit 50, wherein:

the system comprises an acquisition unit 10, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring a plurality of noise data samples of the engine and determining an acoustic quality objective psychological parameter and an acoustic quality subjective evaluation grade score based on the noise data samples;

the model determining unit 20 is used for determining a linear regression model according to the acoustic quality objective psychology parameters and the acoustic quality subjective evaluation grade scores;

the first establishing unit 30 is used for establishing a prediction model of the injection parameters and the acoustic quality objective psychological parameters of the engine, wherein the injection parameters comprise a main injection advance angle, a pilot injection interval angle, pilot injection quantity and rail pressure;

a second establishing unit 40 for establishing a transfer function between the injection parameter and the sound quality subjective evaluation grade score based on the linear regression model and the prediction model;

and the solving unit 50 is used for solving the transfer function to obtain the optimal injection parameters of the engine.

By using the idle speed sound quality optimization system of the engine provided by the embodiment of the invention, the technical problem that the sound quality of the engine cannot be optimized fundamentally in the prior art is solved, the technical effect of optimizing the sound quality of the engine fundamentally is realized, and the product competitiveness is improved.

Optionally, the model determining unit 20 is specifically configured to: and establishing a linear regression model of the acoustic quality objective psychology parameters and the acoustic quality subjective evaluation grade scores by using a support vector machine algorithm.

Optionally, the obtaining unit 10 includes:

an acquisition subunit for acquiring a plurality of noise data samples of the engine;

the calculating subunit is used for calculating the acoustic quality objective psychology parameters of each noise data sample;

and the evaluation subunit is used for carrying out subjective evaluation on the noise data sample to obtain the sound quality subjective evaluation grade score.

Optionally, the evaluation subunit is specifically configured to: and subjectively evaluating the noise data sample based on a grade evaluation method to obtain the sound quality subjective evaluation grade score.

Optionally, the calculating subunit is specifically configured to: loudness, sharpness, roughness, waviness, and a-weighted sound pressure level are calculated for each noisy data sample.

Optionally, before the obtaining unit 10 obtains noise data samples of the engine and determines the objective psychology parameters of the sound quality and the subjective evaluation grade score of the sound quality based on the noise data samples, the engine idle sound quality optimization system further includes:

a parameter determination unit for establishing a combination of a plurality of sets of injection parameters according to an orthogonal table method;

and the sample acquisition unit is used for acquiring noise data samples of the engine under each set of injection parameters.

Optionally, the solving unit 50 is specifically configured to: and solving the transfer function through a genetic algorithm to obtain the optimal injection parameter of the engine.

Optionally, after the solving unit 50 obtains the optimal injection parameter, the engine idle sound quality optimization system further includes:

and the control unit is used for controlling the engine to work based on the optimal injection parameters.

The engine idle sound quality optimization system provided by the embodiment of the present invention uses the engine idle sound quality optimization method in the above embodiment, so that the engine idle sound quality optimization system provided by the embodiment of the present invention also has the beneficial effects described in the above embodiment, and details are not described herein again.

The embodiment of the invention also provides an engine, which comprises the idling sound quality optimization system of the engine in any one of the embodiments.

The engine provided by the embodiment of the invention comprises the engine idling sound quality optimization system in the embodiment, so that the engine provided by the embodiment of the invention also has the beneficial effects described in the embodiment, and details are not repeated herein.

In the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.

Finally, it should be noted that the above-mentioned embodiments are only preferred embodiments of the present invention and the technical principles applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.