CN114186824A - In-vehicle smell evaluation model construction method and in-vehicle smell evaluation method - Google Patents
In-vehicle smell evaluation model construction method and in-vehicle smell evaluation method Download PDFInfo
- Publication number
- CN114186824A CN114186824A CN202111440568.1A CN202111440568A CN114186824A CN 114186824 A CN114186824 A CN 114186824A CN 202111440568 A CN202111440568 A CN 202111440568A CN 114186824 A CN114186824 A CN 114186824A
- Authority
- CN
- China
- Prior art keywords
- odor
- mixed
- concentration
- gas sample
- subjective
- 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.)
- Pending
Links
Images
Classifications
-
- 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
-
- 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
Abstract
The embodiment of the invention discloses an in-vehicle smell evaluation model construction method and an in-vehicle smell evaluation method. The method for constructing the interior smell evaluation model comprises the following steps: calculating a mixed pollutant smell threshold value of a target vehicle type according to the mixed pollutant concentration and the mixed pollutant odor concentration of an original gas sample in the target vehicle type; wherein the mixed contaminants comprise a plurality of volatile contaminants; constructing a relation model between the concentration of the mixed pollutants in the gas in the vehicle of the target vehicle type and the objective smell intensity by utilizing the olfactive threshold value of the mixed pollutants and the Weber-Fisher subjective and objective coupling law; and training undetermined parameters in the relation model by taking the mixed pollutant concentration and subjective odor intensity of the original gas sample under different dilution times as training data to obtain the trained relation model. The model constructed by the embodiment does not need to distinguish single pollutant components, and has smaller error.
Description
Technical Field
The embodiment of the invention relates to the field of in-vehicle smell evaluation, in particular to an in-vehicle smell evaluation model construction method and an in-vehicle smell evaluation method.
Background
In recent years, the demand for a healthy cabin by passengers has been increasing. When unpleasant smells exist in the vehicle, the smell sense organs of the vehicle can be stimulated, and even psychological and physiological influences can be caused to the human body. Therefore, the odor problem in the vehicle is to be solved.
Currently, in-vehicle odor evaluation methods in the automotive industry generally require discrimination of which single pollutant components are included in a gas sample. Specifically, the major contaminants in a gas sample are first determined by complex instrumental testing or subjective identification of a person; and then, a gas analysis model is constructed by combining the specific material attributes of each pollutant, so that the odor evaluation in the vehicle is realized. The method has a complex process, various and large-sized professional instruments are involved, and meanwhile, because only a few main pollutants with the most obvious content in the gas sample can be determined, and other pollutant components are omitted, the evaluation result is not accurate enough.
Disclosure of Invention
The embodiment of the invention provides an in-vehicle smell evaluation model construction method and an in-vehicle smell evaluation method.
In a first aspect, an embodiment of the present invention provides a method for constructing an in-vehicle smell evaluation model, including:
calculating a mixed pollutant smell threshold value of a target vehicle type according to the mixed pollutant concentration and the mixed pollutant odor concentration of an original gas sample in the target vehicle type; wherein the mixed contaminants comprise a plurality of volatile contaminants;
constructing a relation model between the concentration of the mixed pollutants in the gas in the vehicle of the target vehicle type and the objective smell intensity by utilizing the olfactive threshold value of the mixed pollutants and the Weber-Fisher subjective and objective coupling law;
training undetermined parameters in the relation model by taking the mixed pollutant concentration and subjective odor intensity of the original gas sample under different dilution times as training data to obtain a trained relation model; wherein the subjective odor intensity comprises: odor intensity evaluation of the gas samples by odor evaluators.
In a second aspect, an embodiment of the present invention provides an in-vehicle smell evaluation method, including:
obtaining the trained relation model by using the method of the embodiment;
and inputting the concentration of the mixed pollutants of the gas sample to be detected in the target vehicle type into the trained relation model, and predicting the objective odor intensity of the gas sample to be detected.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a memory for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the in-vehicle smell evaluation model building method or the in-vehicle smell evaluation method according to any of the embodiments.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the in-vehicle smell evaluation model building method or the in-vehicle smell evaluation method according to any one of the embodiments.
On one hand, the odor evaluation model of the gas in the vehicle is constructed through the mixed pollutants in the gas sample, so that the single substance component in the mixed pollutants is prevented from being distinguished through complex instrument detection or human identification, and errors caused by missing of the single pollutant type are eliminated; on the other hand, the mixed pollutant concentration and the mixed pollutant smell threshold value are introduced into the smell evaluation model to replace the calculation of the mixed pollutant odor concentration, so that the acquisition difficulty and the calculation times of independent variables are reduced, and the intercept is increased in the smell evaluation model, so that the model is more in line with objective practice.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for constructing an in-vehicle smell evaluation model according to an embodiment of the present invention;
fig. 2 is a flowchart of an in-vehicle smell assessment method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. 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.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should also be noted that, 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.
Fig. 1 is a flowchart of a method for constructing an in-vehicle smell evaluation model according to an embodiment of the present invention. The method is suitable for constructing the condition of the in-vehicle smell evaluation model through the concentration of the mixed pollutants in the in-vehicle gas, and is executed by the electronic equipment. As shown in fig. 1, the method specifically includes:
s110, calculating a mixed pollutant smell threshold value of the target vehicle type according to the mixed pollutant concentration and the mixed pollutant odor concentration of the original gas sample in the target vehicle type.
The odor evaluation model of the embodiment is constructed for vehicle types, and different vehicle types correspond to different odor evaluation models. Optionally, after the target vehicle model is selected, the vehicle of the target vehicle model is sealed for 16 hours under the environmental conditions of 25 ℃ and 50% relative humidity, and then the in-vehicle gas is sampled by using the lung suction type gas pump to obtain an original gas sample.
The vehicle interior gas of the target vehicle type comprises a plurality of volatile pollutants, mixed pollutants refer to the sum of all the volatile pollutants in the vehicle, and the mixed pollutant concentration refers to the total concentration (unit: mg/L) of all the volatile pollutants in the vehicle interior gas.
The present embodiment does not need to determine the single pollutant component included in the in-vehicle gas, but rather, constructs a gas analysis model using the mixed pollutants included in the in-vehicle gas. Specifically, the present embodiment extends the concept of odor concentration and odor threshold for a single substance to mixed pollutants, defining a mixed pollutant concentration and mixed pollutant odor threshold.
The olfactory threshold of the mixed pollutants refers to the concentration (unit: mg/L) of the mixed pollutants which causes the minimum stimulation of human olfactory sense, and is determined by the components of the mixed pollutants (namely, which volatile pollutants are included in the mixed pollutants); the mixed pollutant smell threshold value is an inherent property of the mixed pollutant and is independent of clean air in the vehicle. The odor concentration of the mixed pollutants refers to the dilution multiple (dimensionless) of the in-vehicle gas sample containing the mixed pollutants when the in-vehicle gas sample is continuously diluted to the odor threshold value of the mixed pollutants by odorless clean air.
For a single substance, the olfactory threshold (mg/L) is substance concentration (mg/L)/substance odor concentration (dimensionless). The present embodiment extends this algorithm to mixed contaminants, then: the odor threshold value (mg/L) of the mixed pollutant is equal to the concentration (mg/L) of the mixed pollutant/the odor concentration (dimensionless) of the mixed pollutant. And the obtained mixed pollutant smell threshold value is used for constructing a relation model between the mixed pollutant concentration of the gas in the vehicle and the objective smell intensity.
S120, constructing a relation model between the concentration of the mixed pollutants in the gas in the vehicle of the target vehicle type and the objective odor intensity by using the olfactive threshold value of the mixed pollutants and the Weber-Fisher subjective and objective coupling law.
The weber-fisher subjective and objective coupling law is a law showing the relationship between a psychological quantity and a physical quantity, and can be expressed as:
S＝a*lgx (1)
where S represents sensory intensity, x represents stimulus intensity, and a is a constant. Briefly, this law states that all human senses are not proportional to the corresponding stimulus intensity (intensity corresponding to a physical quantity), but are proportional to the usual logarithm of the corresponding stimulus intensity. I.e. the stimulus intensity reaches a certain threshold, to cause a change in the sensory intensity of the person.
Specifically, in the olfactory field, S represents the objective odor intensity of a single substance, and x represents the odor concentration of a single substance. The present application extends the objective coupling law from a single substance to a mixed pollutant, then for a mixed pollutant, S represents the objective odor intensity of the mixed pollutant and x represents the mixed pollutant odor concentration.
However, the calculation of the odor concentration of the mixed pollutants presents the following difficulties: 1) for the same vehicle type, the odor concentration of mixed pollutants in the vehicle is different under the influence of ventilation conditions, illumination conditions and the like under different environments, and the odor concentration of the mixed pollutants needs to be recalculated for each gas sample to be detected; 2) the odor concentration of mixed pollutants of a certain gas sample is calculated by a complex method and is not easy to obtain.
Therefore, the present embodiment introduces the sniff threshold of mixed pollutants into weber-fisher subjective and objective coupling law, and substitutes x ═ C/ODT into formula (1), resulting in the following model:
S＝a*lg(C/ODT) (2)
wherein C represents the mixed pollutant concentration and ODT represents the mixed pollutant olfactory threshold.
Compared with the odor concentration of mixed pollutants: 1) for the same vehicle type, the vehicle interior components and the vehicle materials are basically the same, so the mixed pollutants in the vehicle are basically the same, the odor threshold value of the mixed pollutants is approximate to a fixed value, the mixed pollutants can be repeatedly used after being measured once, and recalculation for each gas sample to be measured is not needed; 2) the concentration of the mixed pollutants of a certain gas sample can be directly measured by a testing instrument, and the acquisition way is more convenient.
When the odor concentration of the mixed pollutant of the gas sample is 1, C is ODT, and the objective odor intensity of the gas sample is the objective odor intensity corresponding to the odor threshold value. Therefore, it can be seen from the scale of odor intensity shown in table 1 that: the odor threshold of the mixed pollutants is taken as the concentration of the mixed pollutants which causes the minimum stimulation to the human olfactory sense, and the corresponding objective odor intensity is between 1.5 (the odor can be sensed, but the intensity is weak) and 2 (the odor can be sensed, the intensity is obvious, but the discomfort is not caused). In the model of formula (2), when C is ODT, S is a, lg (C/ODT), and a, lg1 is 0, which is not in agreement with the objective reality.
TABLE 1
| Odor intensity rating | Description of the odor State Standard |
| 1 | Can not sense peculiar smell |
| 1.5 | Can sense off flavor, but weak strength |
| 2 | Can sense off-flavor, has obvious strength, but does not cause discomfort |
| 3 | Obvious peculiar smell and no discomfort |
| 4 | Cause discomfort |
| 5 | Cause intense discomfort |
| 6 | Is not acceptable |
For the above reasons, the optimization of the relational model of equation (2) is continued, resulting in the following model:
S＝a*lg(C/ODT)+b； (3)
wherein b is a constant. In the model, C is the input of the model, S is the output of the model, and a and b are undetermined parameters.
S130, training undetermined parameters in the relation model by taking the mixed pollutant concentration and subjective odor intensity of the original gas sample under different dilution times as training data to obtain a trained relation model; wherein the subjective odor intensity comprises: odor intensity evaluation of the gas samples by odor evaluators.
Specifically, firstly, the original gas sample is dynamically diluted by clean air to obtain gas samples with different dilution times. And detecting the concentration of mixed pollutants of the gas samples with different dilution times by using a photoionization detector. The photoionization detector is convenient to move and detect; and the detection range is wide, the precision is high, the response is fast, and no loss exists.
Meanwhile, a plurality of odor evaluators evaluate the odor intensity of the gas samples with different dilution times, and the evaluation result is the subjective odor intensity. The subjective odor intensity given by all odor evaluators was averaged for any dilution of the gas sample as the final subjective odor intensity for that dilution. Each odor evaluator is trained and examined professionally, and the subjective odor intensity provided by the odor evaluator has high accuracy; and averaging the evaluation results of a plurality of odor evaluators, so that the final subjective odor intensity is closer to the real odor intensity.
And finally, taking the measured mixed pollutant concentrations of the gas samples with different dilution times as input data of the relational model, taking the mixed pollutant concentrations of the gas samples with different dilution times given by an odor evaluator as output data of the relational model, training the relational model, and determining specific numerical values of undetermined parameters a and b in the model.
And after specific numerical values of a and b are determined, substituting the specific numerical values into the formula (3), and obtaining a trained relation model. The model can represent the relation between the mixed pollutant concentration and the odor evaluation intensity of the gas sample in the target vehicle type vehicle, and the odor evaluation intensity of the sample can be predicted through the mixed pollutant concentration of the gas sample to be detected. Since the odor evaluation intensity predicted by the relational model is not subjectively given by odor evaluators but predicted by an objective model obtained by big data training, the odor evaluation intensity is referred to as objective odor evaluation intensity for the convenience of distinction and description.
Alternatively, in the model training, the initial value range of b is set to (1.5, 2).
As described in the above embodiment, the intercept b in the relational model represents the objective odor intensity corresponding to the mixed pollutant concentration C of the gas sample being equal to the mixed pollutant odor threshold ODT, and should be between 1.5 and 2. In order to improve the training efficiency and the training precision, the initial range of b is set to (1.5,2) in the model training, so that the model convergence can be accelerated, and the fitting degree of the model can be improved.
The technical effect of the embodiment is as follows: on one hand, the odor evaluation model of the gas in the vehicle is constructed through the mixed pollutants in the gas sample, so that the situation that single substance components in the mixed pollutants are distinguished through complex instrument detection or human identification is avoided, and errors caused by missing of single pollutant types are eliminated; on the other hand, the mixed pollutant concentration and the mixed pollutant smell threshold value are introduced into the smell evaluation model to replace the calculation of the mixed pollutant odor concentration, so that the acquisition difficulty and the calculation times of independent variables are reduced, and the intercept is increased in the smell evaluation model, so that the model is more in line with objective practice.
On the basis of the above and following examples, the present example details the calculation process of the mixed pollutant odor concentration of the gas sample. Optionally, calculating a mixed pollutant odor threshold value of the target vehicle type according to the mixed pollutant concentration and the mixed pollutant odor concentration of the original gas sample in the target vehicle type, and the method comprises the following steps:
step one, obtaining subjective odor intensity of the original gas sample given by a plurality of odor evaluators under different dilution times.
The subjective odor intensity of the gas samples with different dilution times given by a plurality of odor evaluators in the above embodiment can be multiplexed, and other odor evaluators can be organized to evaluate the subjective odor intensity independently.
And step two, selecting two subjective odor intensities closest to the 1.5-grade odor intensity and the front and back of the subjective odor intensity from a plurality of subjective odor intensities given by each odor evaluator as a first subjective odor intensity and a second subjective odor intensity, or selecting two subjective odor intensities closest to the 2-grade odor intensity and the front and back of the subjective odor intensity as the first subjective odor intensity and the second subjective odor intensity.
The first subjective odor intensity and the second subjective odor intensity are used for estimating the dilution factor corresponding to the odor threshold value of the mixed pollutant. Specifically, if the odor threshold of the mixed pollutants is judged to be high, two subjective odor intensities closest to the 1.5-level odor intensity are selected as a first subjective odor intensity and a second subjective odor intensity; and if the odor threshold value of the mixed pollutants is judged to be lower, two subjective odor intensities closest to the 1.5-grade odor intensity are selected as the first subjective odor intensity and the second subjective odor intensity. And if the odor threshold value of the mixed pollutants cannot be judged in advance, selecting a first subjective odor intensity and a second subjective odor intensity before and after any one of the subjective odor intensity of the grade 1.5 or the subjective odor intensity of the grade 2.0.
And thirdly, calculating the geometric mean value of the dilution times corresponding to the first subjective odor intensity and the second subjective odor intensity to obtain the odor concentration of the mixed pollutants given by each odor evaluator.
As described in the above embodiment, the odor concentration of the mixed pollutant is essentially the dilution factor corresponding to the odor threshold of the mixed pollutant, so the embodiment estimates the dilution factor corresponding to the odor threshold of the mixed pollutant according to the dilution factor corresponding to the first subjective odor intensity and the second subjective odor intensity of each odor evaluator, and uses the estimated dilution factor as the odor concentration of the mixed pollutant given by each odor evaluator.
Specifically, for each odor evaluator, geometric mean is obtained by the dilution factor corresponding to the first subjective odor intensity and the dilution factor corresponding to the second subjective odor intensity, and the geometric mean is used as the odor concentration of the mixed pollutant given by each odor evaluator. According to formula (1): s ═ a × lgx, it is known that odor concentration x and odor intensity S are in an exponential relationship, and here, geometric averaging of two dilution factors (i.e., odor concentration x) corresponds to arithmetic averaging of two subjective odor intensities. And the arithmetic mean of the two subjective odor intensities is approximately equal to the subjective odor intensity corresponding to the odor threshold value of the mixed pollutants, so that the estimation of the odor concentration is realized through the subjective odor intensity.
And step four, solving the arithmetic mean value of the odor concentration of the mixed pollutants given by the plurality of odor evaluators to obtain the odor concentration of the mixed pollutants.
And (4) performing an arithmetic average on the odor concentration of the mixed pollutant given by all odor evaluators to obtain the odor concentration of the mixed pollutant.
On the basis of the above embodiment and the following embodiment, the present embodiment adds a link of performing feedback verification on the trained relationship model. Optionally, after training the parameters to be determined in the relationship model by using the mixed pollutant concentration and subjective odor intensity of the original gas sample at different dilution times as training data, the method further includes: solving the fitting degree of the trained relation model to the training data; and if the fitting degree is smaller than a preset fitting degree threshold value, replacing the original gas sample and/or increasing the number of dilution times of the original gas sample, returning to the step of taking the mixed pollutant concentration and the subjective odor intensity of the original gas sample under different dilution times as training data, and training undetermined parameters in the relation model until the fitting degree is larger than or equal to the fitting degree threshold value.
In the embodiment, the trained relation model is verified by adopting the model fitting degree, the fitting degree is greater than or equal to a preset fitting degree threshold value, the model fitting is proved to be good, otherwise, the original gas sample can be replaced, and the original gas sample is collected from other vehicles of the target vehicle type to continue training or retrain; training or retraining can be continued by increasing the number of dilution times of the original gas sample, so that the subjective odor intensity given by the odor evaluator has finer granularity, thereby improving the fitting degree of the model.
Fig. 2 is a flowchart of an in-vehicle smell evaluation method provided in an embodiment of the present invention, and is suitable for a case where the in-vehicle smell evaluation is performed by using the trained relationship model in any one of the above embodiments. The present embodiment is performed by an electronic device. As shown in fig. 2, the method specifically includes:
s210, obtaining the trained relation model by using the method provided by any one of the above embodiments.
S210, inputting the concentration of the mixed pollutants of the gas sample to be detected in the vehicle of the target vehicle type into the trained relation model, and predicting the objective odor intensity of the gas sample to be detected.
As described in the above embodiment, since the vehicle interior components and the vehicle materials are substantially the same for the same vehicle type, the mixed pollutants in the vehicle are substantially the same, and the odor threshold of the mixed pollutants is approximately a fixed value. Therefore, the relation model is constructed for the vehicle type, and different vehicle types correspond to different relation models.
After the trained relation model is obtained for the target vehicle type, the model can be used for predicting the objective odor intensity of any gas sample to be detected in the target vehicle type.
Optionally, after inputting the mixed pollutant concentration of the gas sample to be tested in the vehicle of the target vehicle type into the trained relationship model and predicting the objective odor intensity of the gas sample to be tested, the method further includes the following steps:
the method comprises the steps of firstly, obtaining the odor type and the odor pleasure degree of the gas sample to be detected given by a plurality of odor evaluators, and obtaining the subjective odor intensity of the gas sample to be detected under different dilution times.
After the objective odor intensity of the gas sample to be measured is predicted, two subjective evaluation indexes of odor type and odor pleasure degree are also considered.
And step two, calculating the odor concentration of the mixed pollutants of the gas sample to be detected according to the subjective odor intensities of the gas sample to be detected.
In the step, the odor concentration of the mixed pollutants of the gas sample to be measured is calculated by the method described in the above embodiment. Although the odor concentration of the mixed pollutants is calculated through subjective odor intensity, the odor concentration is essentially the gas attribute objectively existing in a gas sample to be measured and is an objective evaluation index.
And step three, if the odor concentration, the objective odor intensity, the odor type and the odor pleasure degree of the mixed pollutants of the gas sample to be detected all reach the standard, the odor in the vehicle where the gas sample to be detected is located reaches the standard.
Finally, two objective evaluation indexes are: objective odor intensity and mixed pollutant odor concentration, and two subjective evaluation indices: and combining the odor type and the odor pleasure degree to comprehensively evaluate the gas sample to be tested. And only if the four indexes reach the standard, the gas sample to be detected reaches the standard. Specifically, if the odor concentration is less than a set odor concentration threshold value, the odor concentration is considered to reach the standard; if the objective odor intensity is smaller than the set odor intensity threshold value, the objective odor intensity is considered to reach the standard; if the set odor type is not contained in the odor types, the odor types are considered to reach the standard; and if the odor pleasure degree is greater than or equal to the set pleasure degree threshold value, the odor pleasure degree is considered to reach the standard. The odor concentration threshold, the odor intensity threshold, the set odor type and the pleasure degree threshold can be obtained through statistics in a big data mode.
The embodiment combines objective evaluation indexes and subjective evaluation indexes to perform multi-dimensional comprehensive evaluation on the gas sample to be measured, and can more comprehensively represent the problem of the smell state in the vehicle.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 3, the electronic device includes a processor 30, a memory 31, an input device 32, and an output device 33; the number of processors 30 in the device may be one or more, and one processor 30 is taken as an example in fig. 3; the processor 30, the memory 31, the input means 32 and the output means 33 in the device may be connected by a bus or other means, as exemplified by the bus connection in fig. 3.
The memory 31 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the in-vehicle smell evaluation model building method or the in-vehicle smell evaluation method in the embodiment of the present invention. The processor 20 executes various functional applications and data processing of the device by running software programs, instructions, and modules stored in the memory 31, thereby implementing the in-vehicle smell evaluation model building method or the in-vehicle smell evaluation method described above.
The memory 31 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 31 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 31 may further include memory located remotely from the processor 30, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 32 may be used to receive input numeric or character information and to generate key signal inputs relating to user settings and function controls of the apparatus. The output device 33 may include a display device such as a display screen.
An embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored, where the computer program, when executed by a processor, implements the in-vehicle smell evaluation model building method or the in-vehicle smell evaluation method according to any embodiment.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for constructing an in-vehicle smell evaluation model is characterized by comprising the following steps:
calculating a mixed pollutant smell threshold value of a target vehicle type according to the mixed pollutant concentration and the mixed pollutant odor concentration of an original gas sample in the target vehicle type; wherein the mixed contaminants comprise a plurality of volatile contaminants;
constructing a relation model between the concentration of the mixed pollutants in the gas in the vehicle of the target vehicle type and the objective smell intensity by utilizing the olfactive threshold value of the mixed pollutants and the Weber-Fisher subjective and objective coupling law;
training undetermined parameters in the relation model by taking the mixed pollutant concentration and subjective odor intensity of the original gas sample under different dilution times as training data to obtain a trained relation model; wherein the subjective odor intensity comprises: odor intensity evaluation of the gas samples by odor evaluators.
2. The method of claim 1, wherein calculating the mixed pollutant odor threshold for a target vehicle type based on the mixed pollutant concentration and the mixed pollutant odor concentration of the raw gas sample within the target vehicle type comprises:
obtaining subjective odor intensity of the original gas sample given by a plurality of odor evaluators under different dilution times;
selecting two subjective odor intensities closest to the front and back of the odor intensity of 1.5 grades as a first subjective odor intensity and a second subjective odor intensity from a plurality of subjective odor intensities given by each odor evaluator, or selecting two subjective odor intensities closest to the front and back of the odor intensity of 2 grades as the first subjective odor intensity and the second subjective odor intensity;
calculating the geometric mean value of the dilution times corresponding to the first subjective odor intensity and the second subjective odor intensity to obtain the odor concentration of the mixed pollutants given by each odor evaluator;
and solving the arithmetic mean value of the odor concentration of the mixed pollutants given by the plurality of odor evaluators to obtain the odor concentration of the mixed pollutants.
3. The method of claim 1 or 2, wherein after training the parameters to be determined in the relational model by using the mixed pollutant concentration and subjective odor intensity of the original gas sample at different dilution factors as training data, the method further comprises:
solving the fitting degree of the trained relation model to the training data;
and if the fitting degree is smaller than a preset fitting degree threshold value, replacing the original gas sample and/or increasing the number of dilution times of the original gas sample, returning to the step of taking the mixed pollutant concentration and the subjective odor intensity of the original gas sample under different dilution times as training data, and training undetermined parameters in the relation model until the fitting degree is larger than or equal to the fitting degree threshold value.
4. A method according to any of claims 1-3, wherein the relational model is:
S＝a*lg(C/ODT)+b；
wherein C denotes the mixed pollutant concentration, S denotes the objective odor intensity, a and b denote pending parameters, and ODT denotes the mixed pollutant odor threshold.
5. The method of claim 4, wherein training the undetermined parameters in the relational model using the mixed pollutant concentration and subjective odor intensity of the raw gas sample at different dilution factors as training data comprises:
in the model training, the initial value range of b is set to (1.5, 2).
6. The method of claim 1, wherein calculating the mixed pollutant odor threshold for a target vehicle type based on the mixed pollutant concentration and the mixed pollutant odor concentration of the raw gas sample within the target vehicle type comprises:
and detecting the mixed pollutant concentration of the original gas sample by a photoionization detector.
7. An in-vehicle smell evaluation method is characterized by comprising the following steps:
obtaining the trained relational model using the method of any one of claims 1-6;
and inputting the concentration of the mixed pollutants of the gas sample to be detected in the target vehicle type into the trained relation model, and predicting the objective odor intensity of the gas sample to be detected.
8. The method according to claim 7, wherein after inputting the mixed pollutant concentration of the target vehicle interior gas sample to be tested into the trained relational model and predicting the objective odor intensity of the gas sample to be tested, the method further comprises:
obtaining the odor type and the odor pleasure degree of the gas sample to be detected, which are given by a plurality of odor evaluators, and the subjective odor intensity of the gas sample to be detected under different dilution times;
calculating the odor concentration of mixed pollutants of the gas sample to be detected according to the subjective odor intensities of the gas sample to be detected;
and if the odor concentration, the objective odor intensity, the odor type and the odor pleasure degree of the mixed pollutants of the gas sample to be detected all reach the standard, the odor in the vehicle of the vehicle in which the gas sample to be detected is located reaches the standard.
9. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the in-vehicle smell evaluation model building method according to any one of claims 1 to 6, or the in-vehicle smell evaluation method according to claim 7 or 8.
10. A computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing the in-vehicle smell evaluation model construction method according to any one of claims 1 to 6, or the in-vehicle smell evaluation method according to claim 7 or 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111440568.1A CN114186824A (en) | 2021-11-30 | 2021-11-30 | In-vehicle smell evaluation model construction method and in-vehicle smell evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111440568.1A CN114186824A (en) | 2021-11-30 | 2021-11-30 | In-vehicle smell evaluation model construction method and in-vehicle smell evaluation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114186824A true CN114186824A (en) | 2022-03-15 |
Family
ID=80541781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111440568.1A Pending CN114186824A (en) | 2021-11-30 | 2021-11-30 | In-vehicle smell evaluation model construction method and in-vehicle smell evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114186824A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115290784A (en) * | 2022-08-03 | 2022-11-04 | 南京中车浦镇城轨车辆有限责任公司 | Method for determining unpleasant odor substances in vehicle |
| WO2023231873A1 (en) * | 2022-05-30 | 2023-12-07 | 北京车和家汽车科技有限公司 | Method and apparatus for detecting in-vehicle smell, and electronic device |
-
2021
- 2021-11-30 CN CN202111440568.1A patent/CN114186824A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023231873A1 (en) * | 2022-05-30 | 2023-12-07 | 北京车和家汽车科技有限公司 | Method and apparatus for detecting in-vehicle smell, and electronic device |
| CN115290784A (en) * | 2022-08-03 | 2022-11-04 | 南京中车浦镇城轨车辆有限责任公司 | Method for determining unpleasant odor substances in vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114186824A (en) | In-vehicle smell evaluation model construction method and in-vehicle smell evaluation method | |
| CN106897570B (en) | Chronic obstructive pulmonary disease testing system based on machine learning | |
| CN108918691B (en) | Method for determining odor substances in vehicle and method for tracing odor substances in vehicle | |
| US6834530B2 (en) | Odor measuring apparatus | |
| US10001410B2 (en) | Quantitative elemental profiling in optical emission spectroscopy | |
| KR101022267B1 (en) | System for monitoring odor | |
| JP2002535023A5 (en) | ||
| WO2013161315A1 (en) | System which provides content | |
| CN106596860A (en) | Automobile odor detection method and detection system | |
| KR101510861B1 (en) | System and Method for complex malodor analysis | |
| CN108120803B (en) | Online monitoring method and device for concentration of negative oxygen ions in air | |
| JP5199685B2 (en) | Examination value conversion program for health check | |
| CN115236045A (en) | Method and device for determining chemical oxygen demand in water by using fluorescence spectrometry and storage medium | |
| Hobbs et al. | Development of a relationship between olfactory response and major odorants from organic wastes | |
| JP5109932B2 (en) | Odor measuring device | |
| CN112816430A (en) | Water body environment monitoring method and device | |
| US20150025847A1 (en) | Quantitative elemental profiling in optical emission spectroscopy | |
| Wargocki et al. | Measurements of perceived indoor air quality | |
| Berglund et al. | A psychological detection method in environmental research | |
| CN105891455A (en) | Method, device, client and system for detecting alcohol | |
| Bitter et al. | Estimation of odour intensity of indoor air pollutants from building materials with a multi-gas sensor system | |
| Chanonsirivorakul et al. | A study of relationship between sensor response and odor perception in human | |
| Friedrich et al. | From spike to graph—A complete automated single-spike analysis | |
| Gutierrez-Osuna et al. | Correlation of sensory analysis with electronic nose data for swine odor remediation assessment | |
| CN115290784A (en) | Method for determining unpleasant odor substances in vehicle |
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 |