CN113221438B - Method for evaluating sound quality of permanent magnet synchronous motor - Google Patents
Method for evaluating sound quality of permanent magnet synchronous motor Download PDFInfo
- Publication number
- CN113221438B CN113221438B CN202110368998.0A CN202110368998A CN113221438B CN 113221438 B CN113221438 B CN 113221438B CN 202110368998 A CN202110368998 A CN 202110368998A CN 113221438 B CN113221438 B CN 113221438B
- Authority
- CN
- China
- Prior art keywords
- noise
- group
- sound quality
- samples
- permanent magnet
- 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
Abstract
The invention relates to a new energy vehicle technology, in particular to a sound quality evaluation method of a permanent magnet synchronous motor, which comprises the following steps: establishing a sound sample database of the permanent magnet synchronous motor; data acquisition and screening; calculating the noise signal sound quality objective parameters through LMS.test.Lab and MATLAB software; aiming at the noise characteristic of the motor, a grouping and pairing comparison method for selecting associated samples based on Bradley-Kullback selection weight is established, and the traditional grouping and pairing comparison method is improved; and (3) establishing an RBF neural network acoustic quality prediction model according to the calculation result of the subjective and objective parameters, and correcting the model through a multi-population genetic algorithm (MPGA). The method avoids the phenomenon that the acoustic quality of the associated samples is positioned at the extreme position in the group and loses the association effect when the number of the groups of the associated samples is large. Moreover, the method has no limitation on the maximum number of groups and can be applied to any number of noise samples.
Description
Technical Field
The invention belongs to the technical field of new energy vehicles, and particularly relates to a sound quality evaluation method for a permanent magnet synchronous motor.
Background
Compared with the traditional automobile, the new energy automobile has qualitative change in energy conversion mode, and the driving power is provided by a high-speed driving motor. The following steps are cancelled: engines, oil supply systems, intake and exhaust systems, and the like. Therefore, the noise of the driving and energy supply system taking the driving motor as the core is the main and unique noise component of the new energy automobile. Therefore, the noise level of the driving motor of the new energy automobile is controlled, and the comfort performance of the product can be greatly improved.
For a new energy automobile, the noise of a driving motor is an important component of the noise in the automobile, and how to control the noise in the automobile and how to improve the sound quality of the noise in the automobile still needs to be solved from the source and the sound quality of the noise of the driving motor is improved. Therefore, the control and evaluation of the sound quality of the permanent magnet synchronous motor become the focus of the current research.
The traditional grouping pair comparison method determines the associated samples in advance, so that when the grouping is more, the associated samples are poor in adaptability to the following sample groups, and the evaluation accuracy is reduced in the inversion of the evaluation result.
Therefore, on the basis of the original sound quality evaluation system, a more reasonable, more comprehensive and more systematic subjective evaluation method needs to be provided, so that more accurate support is provided for the establishment of a sound quality prediction model of the permanent magnet synchronous motor.
Disclosure of Invention
In order to solve the problems existing in the background art, the invention provides a grouping pair comparison method based on Bradley-Kullback improvement.
In order to solve the technical problems, the invention adopts the following technical scheme: a sound quality evaluation method for a permanent magnet synchronous motor comprises the following steps:
step 1, collecting multi-working-condition and multi-measuring-point noise samples of a permanent magnet synchronous motor; shearing and preprocessing the collected noise sample, and establishing a sound sample database of the permanent magnet synchronous motor;
step 2, based on the sound sample database in the step 1, organizing the tested personnel to carry out subjective listening and examining tests by adopting a Bradley-Kullback improved grouping and pairing comparison method as a subjective evaluation method, carrying out weighting consistency screening on the listening and examining results, and rejecting data with larger deviation;
step 3, based on the sound sample database obtained in the step 2, calculating the sound quality objective parameters by using LMS.test.Lab and MATLAB software;
step 4, taking the two-stage evaluation parameters with objective sound quality extracted in the step 3 as input, taking the subjective evaluation result in the step 2 as output, adopting an RBF neural network to carry out subjective and objective modeling on the sound quality of the permanent magnet synchronous motor, and analyzing the influence of the initial parameters of the network on the model performance;
and 5, correcting the model by adopting a multi-population genetic algorithm MPGA according to the objective parameter analysis result in the step 4.
In the method for evaluating the sound quality of the permanent magnet synchronous motor, the grouping pair comparison method based on Bradley-Kullback improvement in the step 2 specifically comprises the following steps:
step 2.1, grouping the collected noise signals of the permanent magnet synchronous motor according to the rotating speed and the torque, wherein the quantity of the noise in each group is 8-15 parts, and the grouping number is adjusted according to the total quantity of the collected noise signals of the motor;
step 2.2, carrying out subjective evaluation on the first group of noise signals by a pairwise comparison method, wherein the scoring mode is that 1 score is given to the noise i more comfortably than j, and 0 score is given to the noise i otherwise; setting the number of the first group of noise signals as M, and removing unreasonable evaluation subjects through weighting consistency coefficient inspection to obtain M 1 A valid evaluation result; summarizing the noise signal scores of all working conditions, and setting the value as n i Theoretical n i The maximum value obtained is N i ,N i =M 1 *m;
Step 2.3, setting the sound quality capability parameter values of all the noise samples in the first group as gamma i Record N ij Is an individual x i And x j Comparing the total number of times, n, with each other ij Is an individual x i Is superior to x j Provided that each comparison is independent of the other, i.e. n ij Obey binomial distribution bin (N) ij ,P ij ) Then, there are: n is a radical of an alkyl radical i =sum(n ij );N i =sum(N ij );
Step 2.4, setting individual capability parameter gamma i The maximum likelihood value of (d) is L, obtained from Bradley model:
step 2.5, simplifying the formula (1) by a maximum likelihood method to obtain a formula (2), and solving the formula (2) to obtain a first group of sound quality capability parameter values of all noise samples:
step 2.6, substituting the sound quality capability parameter value of each noise signal obtained in the step 2.5 back into the Logit model to obtain a first group of all noise sample selection probability matrixes;
step 2.7, carrying out weight analysis on the selection probability matrix obtained in the step 2.6 through a sum-product method to obtain a first group of noise signal sound quality selection weights;
step 2.8, the optimal position of the associated sample is calculated for the first group of noise sample selection probability matrix through a Kullback distance test formula (3), and when U is at the position of the maximum value, the corresponding associated sample is in the optimal selection interval:
wherein X ij Selecting the probability of the sample i in the pair-wise comparison for the noise samples i and j, E (·) being the mean value, m being the total number of the noise samples in the group;
step 2.9, determining grouping pair comparison method correlation samples which simultaneously meet the requirement that the selection weight values are positioned at two ends of the group mean value and are positioned in the Kullback optimal correlation sample interval;
step 2.10, passing formulaPerforming data inversion on each group of evaluation results, wherein T 1j And T 2j In order to evaluate the evaluation value alpha of the associated sample in the original group as a scaling coefficient, beta is a translation adjustment amount, i is the number of the noise sample in each group, and j is a group number.
Compared with the prior art, the invention has the beneficial effects that: and establishing a grouping pair comparison method for selecting the associated samples based on the Bradley-Kullback selection weight, and determining the associated samples through the Bradley selection weight and the Kullback optimal distance position. The associated samples are selected in a self-adaptive mode, and the phenomenon that the acoustic quality of the associated samples is located at the extreme positions in the group and loses the associated effect when the number of the groups of the associated samples is large is avoided. The method has no limitation of the maximum number of groups and can be applied to any number of noise samples.
Drawings
Fig. 1 is a flow chart of evaluating sound quality of a permanent magnet synchronous motor according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of correlation sample selection of the Bradley-Kullback adaptive grouping and comparing method according to an embodiment of the present invention;
FIG. 3 is a diagram of an MPGA-RBF neural network structure model according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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 invention.
It should be noted that the embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
The present invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
The embodiment is realized by the following technical scheme, and the method for evaluating the sound quality of the permanent magnet synchronous point machine comprises the following steps:
step a: a noise sample database of the permanent magnet synchronous motor is established, and the method comprises the following steps:
(1) Collecting multi-working-condition and multi-measuring-point noise samples of the permanent magnet synchronous motor;
(2) Shearing and preprocessing the collected sound sample, and establishing a sample database;
step b: and organizing the tested personnel to carry out subjective listening and auditing tests by adopting a Bradley-Kullback improved grouping and pairing comparison method, and carrying out weighted consistency screening on the listening and auditing results to remove data with larger deviation.
Step c, passing through a formulaPerforming data inversion on each group of evaluation results, wherein T 1j And T 2j Evaluating a value alpha in the original group for the associated sample as a proportionality coefficient; beta is the translational adjustment amount; i isThe noise samples are numbered inside each group; j is the group number.
Step d: and c, calculating the objective parameters of the sound quality by using LMS.test.Lab and MATLAB software based on the sound sample database in the step c.
Step e: and d, taking the two-stage evaluation parameters with objective sound quality extracted in the step d as input, taking the subjective evaluation result in the step c as output, performing subjective and objective modeling on the sound quality of the permanent magnet synchronous motor by adopting an RBF neural network, and analyzing the influence of the initial parameters of the network on the performance of the model.
Step f: and e, modifying the model by adopting a multi-population genetic algorithm (MPGA) according to the objective parameter analysis result in the step e.
And in the step b, based on a Bradley-Kullback improved grouping and pairing comparison method, grouping the collected noise signals of the permanent magnet synchronous motor according to the rotating speed and the torque, wherein the quantity of the noise in each group is 8-15 parts, and the grouping number is adjusted according to the total quantity of the collected noise signals of the motor.
And in the step b, based on a Bradley-Kullback improved grouping pair comparison method, carrying out subjective evaluation on the first group of noise signals through the pair comparison method, wherein the scoring mode is that the noise i is scored by 1 point more comfortably than j, and otherwise, the noise i is scored by 0 point. Let m be the number of noise signals in the first group. Removing unreasonable evaluation subject by weighting consistency coefficient test to obtain M 1 And (5) effectively evaluating the result. Summarizing the noise signal scores of all working conditions, and setting the value as n i (averaging the values is the traditional subjective evaluation score mean value), and let n be theoretically i The maximum value obtained is N i ,N i =M 1 *m。
And in the step b, the Bradley-Kullback improved grouping pair comparison method is adopted, and the sound quality capability parameter value of all the noise samples in the first group is set as gamma i Record N ij Is an individual x i And x j Comparing the total number of times, n, with each other ij Is an individual x i Is superior to x j Provided that each comparison is independent of the other, i.e. n ij Obey binomial distribution bin (N) ij ,P ij ) Then, there are: n is a radical of an alkyl radical i =sum(n ij );N i =sum(N ij )。
And in step b, the Bradley-Kullback improved grouping pair comparison method is used for setting the individual capacity parameter gamma i The maximum likelihood value of (d) is L, obtained from Bradley model:
and in the step b, the Bradley-Kullback improved grouping pair comparison method simplifies the formula (1) by the maximum likelihood method to obtain a formula (2), and solves the formula (2) to obtain a first group of all noise sample sound quality capability parameter values.
And, in step b, the Bradley-Kullback modified packet pair comparison method, by Kullback distance test equation (3), wherein X ij The probability of selecting sample i in the pair-wise comparison for noise samples i and j, E (·) is the mean, and m is the total number of noise samples in the set. And performing associated sample optimal position calculation on the first group of noise sample selection probability matrixes, wherein when U is at the maximum position, the corresponding associated sample is in the optimal selection interval.
And in the step b, the Bradley-Kullback improved grouping pair comparison method simultaneously meets the condition that the selection weights are positioned at two ends of the intra-group mean value and positioned in the Kullback optimal associated sample interval, namely the determined grouping pair comparison method associated sample is obtained. As shown in fig. 2.
Through listening experiments, a traditional grouping and pairing comparison method is set to carry out subjective evaluation on all samples to obtain evaluation results, and the accuracy of the method is verified through correlation and prediction model precision analysis.
In specific implementation, the noise data of the permanent magnet synchronous motor under various working conditions is tested, and loudness, sharpness, roughness, jitter, semantic definition and the like are used as primary objective evaluation indexes; the method comprises the steps of subjectively evaluating a motor noise sample by adopting a grouping and comparing method improved based on Bradley-Kullback selection weight, and establishing a permanent magnet synchronous motor sound quality subjective and objective evaluation prediction model by utilizing an MPGA-RBF neural network. Fig. 1 shows a novel sound quality evaluation process of a permanent magnet synchronous motor, and the method specifically includes the following steps:
(1) Establishing a noise sample database of a permanent magnet synchronous motor
The method is characterized in that a noise sampling test of the permanent magnet synchronous motor is carried out in a precise-level and semi-free sound field noise laboratory, and multi-working-condition and multi-point noise samples of the permanent magnet synchronous motor are collected by referring to standard determination test schemes such as national standard GB/T10069.1-2006 (rotating motor noise determination method and limit), GB/T755-2019 (rotating motor quota and performance), GB/T6379.6-2009 (measurement method and accuracy of result), ISO 112004-2014 (acoustics, noise machine and equipment), and the like.
And shearing and preprocessing the collected sound sample, and establishing a sample database. Requirements for sound samples: 1) The shearing is not suitable for being too long or too short, the general length is 3-8s, and the too long or too short can influence the subjective evaluation accuracy of the hearing and auditing personnel; 2) The sound samples are WAV waveform files and cannot be stored into files such as MP3 files, and sound distortion caused by signal conversion is avoided. 3) And 1.5s silence is inserted at the end of the time domain signal of each sound sample, and the measure can avoid the masking effect among the sound samples from influencing the evaluation result.
(2) Subjective evaluation of noise signals of permanent magnet synchronous motor
And a, grouping the sound samples according to the whole number based on the sound sample database in the step (1), wherein the grouping needs to follow that the number of the noise samples in each group is 8-15, and the condition that similar working conditions are intensively distributed in the same group is avoided.
And b, carrying out subjective evaluation on the first group of noise by adopting a pair comparison method according to the grouping condition in the step a.
C, according to the evaluation result of the step b, removing the evaluation result through weighting consistency coefficient inspectionUnreasonable evaluation of subjects to obtain M 1 And (5) effectively evaluating the result. Summarizing the noise signal scores of all working conditions to obtain the total evaluation score n of each noise sample i By the formula N i =M 1 * m calculating the maximum result N that the total score of the evaluation may appear i 。
D, expanding through a explained function to obtain a probability explained function formula of each noise sample selection:
and e, simplifying the formula (1) of the interpretation function by a maximum interpretation method to obtain a formula (2), and solving the formula (2), wherein the result is the sound quality score of the group of noise signals.
And f, substituting the result obtained in the step e back into the Logit model to obtain the selection probability matrix of all the noise samples in the reorganization.
And g, calculating the selection probability matrix obtained in the step f by a sum-product method and a Kullback distance test formula, and selecting the selection weight of the middle layer and the noise sample at the optimal position as a correlation sample.
And h, placing the associated samples into the next group, performing subjective evaluation, and repeating the steps b to h.
Step i, passing formulaAnd carrying out data inversion on each group of evaluation results to obtain all noise sample evaluation results.
In the example, the grouping pair comparison method improved by the Bradley-Kullback selection weight is used for subjectively evaluating the motor noise of 24 different working conditions. An MPGA-RBF neural network is used as a sound quality prediction model, and the network structure is shown in figure 3.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made without departing from the spirit and scope of the invention.
Claims (1)
1. A method for evaluating the sound quality of a permanent magnet synchronous motor is characterized by comprising the following steps:
step 1, collecting multi-working-condition and multi-measuring-point noise samples of a permanent magnet synchronous motor; shearing and preprocessing the collected noise sample, and establishing a sound sample database of the permanent magnet synchronous motor;
step 2, based on the sound sample database in the step 1, organizing the tested personnel to carry out subjective listening and examining tests by adopting a Bradley-Kullback improved grouping and pairing comparison method as a subjective evaluation method, carrying out weighting consistency screening on the listening and examining results, and rejecting data with larger deviation;
step 3, based on the sound sample database obtained in the step 2, calculating the sound quality objective parameters by using LMS.test.Lab and MATLAB software;
step 4, taking the two-stage evaluation parameters with objective sound quality extracted in the step 3 as input, taking the subjective evaluation result in the step 2 as output, adopting an RBF neural network to carry out subjective and objective modeling on the sound quality of the permanent magnet synchronous motor, and analyzing the influence of the initial parameters of the network on the model performance;
step 5, correcting the model by adopting a multi-population genetic algorithm MPGA according to the objective parameter analysis result in the step 4;
the grouping pair comparison method based on the Bradley-Kullback improvement specifically comprises the following steps:
step 2.1, grouping the collected noise signals of the permanent magnet synchronous motor according to the rotating speed and the torque, wherein the quantity of the noise in each group is 8-15 parts, and the grouping number is adjusted according to the total quantity of the collected noise signals of the motor;
step 2.2, scoring the first group of noise signals; setting the number of the first group of noise signals as m, and weighting the consistency coefficientChecking to remove unreasonable evaluation subject to obtain M 1 (ii) a valid evaluation result; summarizing the noise signal scores of all working conditions to be n i ,n i The maximum value obtained is N i ,N i =M 1 *m;
Step 2.3, setting the sound quality capability parameter values of all the noise samples in the first group as gamma i Record N ij Is an individual x i And x j Comparing the total number of times, n, with each other ij Is an individual x i Is superior to x j Each comparison being independent of the other, i.e. n ij Obey binomial distribution bin (N) ij ,P ij ) Then, there are: n is i =sum(n ij );N i =sum(N ij );
Step 2.4, setting individual ability parameter gamma i Has a maximum likelihood value of L, obtained from the Bradley model:
step 2.5, simplifying the formula (1) by a maximum likelihood method to obtain a formula (2), and solving the formula (2) to obtain a first group of sound quality capability parameter values of all noise samples:
step 2.6, substituting the sound quality capability parameter value of each noise signal obtained in the step 2.5 back into the Logit model to obtain a first group of all noise sample selection probability matrixes;
step 2.7, carrying out weight analysis on the selection probability matrix obtained in the step 2.6 through a sum-product method to obtain a first group of noise signal sound quality selection weights;
step 2.8, the best position of the associated sample is calculated for the first group of noise sample selection probability matrix through a Kullback distance test formula (3), and when U is at the maximum position, the corresponding associated sample is in the best selection interval:
wherein, X ij Selecting the probability of the sample i in the pair-wise comparison for the noise samples i and j, E (·) being the mean value, m being the total number of the noise samples in the group;
step 2.9, determining grouping pair comparison method correlation samples which simultaneously meet the condition that the selection weight values are positioned at two ends of the group mean value and are positioned in the Kullback optimal correlation sample interval;
step 2.10, passing formulaPerforming data inversion on each group of evaluation results, wherein T 1j And T 2j For evaluation values of the associated samples in the original groups, alpha is a scaling coefficient, beta is a translation adjustment amount, i is the number of the noise samples in each group, and j is a group number.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110368998.0A CN113221438B (en) | 2021-04-06 | 2021-04-06 | Method for evaluating sound quality of permanent magnet synchronous motor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110368998.0A CN113221438B (en) | 2021-04-06 | 2021-04-06 | Method for evaluating sound quality of permanent magnet synchronous motor |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113221438A CN113221438A (en) | 2021-08-06 |
CN113221438B true CN113221438B (en) | 2022-10-18 |
Family
ID=77086400
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110368998.0A Active CN113221438B (en) | 2021-04-06 | 2021-04-06 | Method for evaluating sound quality of permanent magnet synchronous motor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113221438B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116429245B (en) * | 2023-06-13 | 2023-09-01 | 江铃汽车股份有限公司 | Method and system for testing noise of wiper motor |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2005066927A1 (en) * | 2004-01-09 | 2005-07-21 | Toudai Tlo, Ltd. | Multi-sound signal analysis method |
US7478043B1 (en) * | 2002-06-05 | 2009-01-13 | Verizon Corporate Services Group, Inc. | Estimation of speech spectral parameters in the presence of noise |
CN110688712A (en) * | 2019-10-11 | 2020-01-14 | 湖南文理学院 | Evaluation index for objective annoyance degree of automobile wind vibration noise sound quality and calculation method thereof |
CN110737970A (en) * | 2019-09-24 | 2020-01-31 | 天津大学 | engine acceleration sound quality evaluation method |
CN112560302A (en) * | 2020-11-30 | 2021-03-26 | 武汉科技大学 | Electromagnetic noise simulation calculation method under acceleration condition of permanent magnet synchronous motor |
-
2021
- 2021-04-06 CN CN202110368998.0A patent/CN113221438B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7478043B1 (en) * | 2002-06-05 | 2009-01-13 | Verizon Corporate Services Group, Inc. | Estimation of speech spectral parameters in the presence of noise |
WO2005066927A1 (en) * | 2004-01-09 | 2005-07-21 | Toudai Tlo, Ltd. | Multi-sound signal analysis method |
CN110737970A (en) * | 2019-09-24 | 2020-01-31 | 天津大学 | engine acceleration sound quality evaluation method |
CN110688712A (en) * | 2019-10-11 | 2020-01-14 | 湖南文理学院 | Evaluation index for objective annoyance degree of automobile wind vibration noise sound quality and calculation method thereof |
CN112560302A (en) * | 2020-11-30 | 2021-03-26 | 武汉科技大学 | Electromagnetic noise simulation calculation method under acceleration condition of permanent magnet synchronous motor |
Non-Patent Citations (2)
Title |
---|
Unsupervised Detection of Anomalous Sound Based on Deep Learning and the Neyman–Pearson Lemma;Yuma Koizumi 等;《IEEE/ACM TRANSACTIONS ON AUDIO,》;20190131;第212-224页 * |
基于Bradley-Terry模型的学术期刊影响力分析;曲皎 等;《辽宁师范大学学报(自然科学版)》;20180930;第41卷(第3期);第326-331页 * |
Also Published As
Publication number | Publication date |
---|---|
CN113221438A (en) | 2021-08-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112001128B (en) | Axial flow compressor stall surge prediction method based on deep learning | |
CN110737970A (en) | engine acceleration sound quality evaluation method | |
CN110688712A (en) | Evaluation index for objective annoyance degree of automobile wind vibration noise sound quality and calculation method thereof | |
CN101672690A (en) | Method for objectively and quantifiably evaluating noise fret degree in vehicle based on auditory model | |
EP2413313B1 (en) | Method and device for audio signal classification | |
CN103546853A (en) | Speaker abnormal sound detecting method based on short-time Fourier transformation | |
CN104050974A (en) | Sound signal analysis apparatus, sound signal analysis method and sound signal analysis program | |
CN113221438B (en) | Method for evaluating sound quality of permanent magnet synchronous motor | |
CN112580588B (en) | Intelligent flutter signal identification method based on empirical mode decomposition | |
CN111951430B (en) | Vehicle drivability evaluation method and system | |
CN113763986A (en) | Air conditioner indoor unit abnormal sound detection method based on sound classification model | |
CN111598395A (en) | Engine sound quality comprehensive evaluation method | |
CN111798109B (en) | Material friction abnormal sound matching method | |
CN115796705B (en) | New energy automobile electric drive assembly NVH grading evaluation method | |
CN116558632A (en) | Engine sound quality prediction method | |
CN115900802A (en) | Universal dynamic compensation method for multi-type sensors | |
CN112233693B (en) | Sound quality evaluation method, device and equipment | |
CN113686584A (en) | Engine idling sound quality optimization method and system and engine | |
CN115752707A (en) | Exhaust sound quality evaluation method based on rotation speed sections | |
CN116644658B (en) | Gas discharge temperature inversion method based on physical information neural network | |
CN116434775A (en) | Audio injection-oriented superimposed sound vexation degree modeling method | |
CN110334310B (en) | Method and device for determining power curve of fan | |
Zhang | Analysis of the Art and Emotional Skills of College Vocal Singing in the Age of Big Data | |
CN117933090A (en) | Method for predicting sound pressure level in vehicle based on support vector regression | |
Zhou | The Influence of Acoustic Parameters and Tuning Orientation on User Experience |
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 |