Method for constructing a vehicle interior odor evaluation model and method for evaluating vehicle interior odor
By constructing the in -car smell evaluation model based on hybrid pollutants, the problems of complex and inaccurate odor evaluation in existing technologies have been solved, and more efficient and accurate in -car odor evaluation has been achieved.
Patent Information
- Application Number
- CN202111440568.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-11-30
- Publication Date
- 2025-01-28
- Estimated Expiration
- 2041-11-30
AI Technical Summary
The existing automotive industry has complex methods for evaluating in-vehicle odors, which requires the distinction between single pollutants in gas samples, and the inability to accurately evaluate mixed pollutants, resulting in inaccurate evaluation of evaluation results.
Build a smell evaluation model in the car through the hybrid pollutants in the gas sample, use the olfactory threshold value of hybrid pollutants and Weber Fishner's subjective coupling law to establish a relationship model between the concentration of hybrid pollutants and the intensity of objective odor to perform odor evaluation Essence
Simplified the smell evaluation process, avoiding the complexity of the separation of single pollutants, improved the accuracy of the evaluation results, and reduced the difficulty of acquisition and calculation of independent variables.
Smart Images
Figure CN114186824B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the field of in-vehicle odor evaluation, and in particular to an in-vehicle odor evaluation model construction method and an in-vehicle odor evaluation method. Background Art
[0002] In recent years, passengers have increasingly demanded a healthy cabin. When there is an unpleasant odor in the car, it will stimulate the human olfactory organ and even cause psychological and physiological effects on the human body. Therefore, the odor problem in the car needs to be solved urgently.
[0003] At present, the in-car odor evaluation method in the automotive industry usually requires identifying which single pollutant components are included in the gas sample. Specifically, the main pollutants in the gas sample are first determined through complex instrument detection or subjective identification by people; then, the gas analysis model is constructed based on the unique material properties of each pollutant to achieve in-car odor evaluation. This method is complex and involves a variety of professional instruments with large volumes. At the same time, since only the most significant main pollutants in the gas sample can be determined, other pollutant components are omitted, making the evaluation results inaccurate. Summary of the invention
[0004] The embodiments of the present invention provide a method for constructing an in-vehicle odor evaluation model and a method for evaluating in-vehicle odor, which construct an in-vehicle gas odor evaluation model through mixed pollutants in a gas sample without distinguishing single substance components in the mixed pollutants.
[0005] In a first aspect, an embodiment of the present invention provides a method for constructing an in-vehicle odor evaluation model, comprising:
[0006] Calculating the mixed pollutant olfactory threshold of the target vehicle type according to the mixed pollutant concentration and the mixed pollutant odor concentration of the original gas sample in the vehicle of the target vehicle type; wherein the mixed pollutant includes a plurality of volatile pollutants;
[0007] Using the olfactory threshold of the mixed pollutants and the Weber-Fechner subjective-objective coupling law, a relationship model between the mixed pollutant concentration and the objective odor intensity of the gas in the target vehicle model is constructed;
[0008] The mixed pollutant concentration and subjective odor intensity of the original gas sample at different dilution multiples are used as training data to train the undetermined parameters in the relationship model to obtain a trained relationship model; wherein the subjective odor intensity includes: the odor intensity evaluation of the gas sample by the odor evaluator.
[0009] In a second aspect, an embodiment of the present invention provides a method for evaluating an odor in a vehicle, comprising:
[0010] Using the method described in the above embodiment, the trained relationship model is obtained;
[0011] The mixed pollutant concentration of the gas sample to be tested in the target vehicle model is input into the trained relationship model to predict the objective odor intensity of the gas sample to be tested.
[0012] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:
[0013] one or more processors;
[0014] a memory for storing one or more programs,
[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the in-vehicle odor evaluation model construction method or the in-vehicle odor evaluation method described in any one of the embodiments.
[0016] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the in-vehicle odor evaluation model construction method or in-vehicle odor evaluation method described in any one of the embodiments.
[0017] On the one hand, the embodiment of the present invention constructs an odor evaluation model for in-vehicle gas through mixed pollutants in gas samples, avoiding the need to distinguish single material components in mixed pollutants through complex instrument detection or human identification, and eliminating errors caused by missing single pollutant types; on the other hand, mixed pollutant concentrations and mixed pollutant olfactory thresholds are introduced into the odor evaluation model to replace the calculation of mixed pollutant odor concentrations, reducing the difficulty of obtaining independent variables and the number of calculations, and adding an intercept to the odor evaluation model to make the model more in line with objective reality. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0019] Figure 1 is a flow chart of a method for constructing an in-vehicle odor evaluation model provided by an embodiment of the present invention;
[0020] Figure 2 is a flow chart of a method for evaluating odor in a vehicle provided by an embodiment of the present invention;
[0021] Figure 3It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.
[0023] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.
[0024] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0025] Figure 1 1 is a flow chart of a method for constructing an in-vehicle odor evaluation model provided by an embodiment of the present invention. The method is applicable to constructing an in-vehicle odor evaluation model based on the concentration of mixed pollutants in the in-vehicle gas, and is executed by an electronic device. Figure 1 As shown, the method specifically includes:
[0026] S110, calculating the mixed pollutant odor threshold of the target vehicle model according to the mixed pollutant concentration and the mixed pollutant odor concentration of the original gas sample in the vehicle of the target vehicle model.
[0027] The odor evaluation model of this embodiment is constructed for vehicle models, and different vehicle models correspond to different odor evaluation models. Optionally, after selecting a target vehicle model, a vehicle of a target vehicle model is sealed for 16 hours under environmental conditions of 25° C. and 50% relative humidity, and then a lung suction air pump is used to sample the gas in the vehicle to obtain an original gas sample.
[0028] The in-car gas of the target vehicle model includes a variety of volatile pollutants. Mixed pollutants refer to the sum of all volatile pollutants in the car, and mixed pollutant concentration refers to the total concentration of all volatile pollutants in the in-car gas (unit: mg / L).
[0029] This embodiment does not need to determine the single pollutant component included in the gas in the vehicle, but uses the mixed pollutants included in the gas in the vehicle to build a gas analysis model. Specifically, this embodiment extends the concept of odor concentration and odor threshold of a single substance to mixed pollutants, and defines mixed pollutant concentration and mixed pollutant odor threshold.
[0030] The mixed pollutant olfactory threshold refers to the concentration of mixed pollutants that causes the minimum stimulation to human olfactory sense (unit: mg / L), which is determined by the composition of the mixed pollutants (i.e., which volatile pollutants are included in the mixed pollutants); the mixed pollutant olfactory threshold is an inherent property of the mixed pollutants themselves and has nothing to do with the clean air in the car. The mixed pollutant odor concentration refers to the dilution multiple (dimensionless) when the gas sample in the car containing mixed pollutants is continuously diluted to the mixed pollutant olfactory threshold with odorless clean air.
[0031] For a single substance, the odor threshold (mg / L) = substance concentration (mg / L) / substance odor concentration (dimensionless). This embodiment extends this algorithm to mixed pollutants, then: mixed pollutant odor threshold (mg / L) = mixed pollutant concentration (mg / L) / mixed pollutant odor concentration (dimensionless). The obtained mixed pollutant odor threshold is used to construct a relationship model between the mixed pollutant concentration and the objective odor intensity of the gas in the vehicle.
[0032] S120, using the mixed pollutant olfactory threshold and the Weber-Fechner subjective-objective coupling law, construct a relationship model between the mixed pollutant concentration and the objective odor intensity of the target vehicle model's interior gas.
[0033] The Weber-Fechner law of subjective-objective coupling is a law that shows the relationship between psychological quantities and physical quantities, which can be expressed as:
[0034] S=a*lgx (1)
[0035] Where S represents the intensity of feeling, x represents the intensity of stimulus, and a is a constant. In simple terms, this law states that all human feelings are not proportional to the corresponding stimulus intensity (the intensity of the corresponding physical quantity), but are proportional to the common logarithm of the corresponding stimulus intensity. That is, only when the stimulus intensity reaches a certain threshold will it cause a change in the intensity of human feelings.
[0036] Specifically in the field of olfaction, for a single substance, S represents the objective odor intensity of the single substance, and x represents the odor concentration of the single substance. This application extends the subjective and objective coupling law from a single substance to mixed pollutants. For mixed pollutants, S represents the objective odor intensity of the mixed pollutants, and x represents the odor concentration of the mixed pollutants.
[0037] However, there are the following difficulties in calculating the odor concentration of mixed pollutants: 1) For the same vehicle model, due to the influence of ventilation conditions, lighting conditions, etc., the odor concentration of mixed pollutants in the gas inside different vehicles in different environments is different. The odor concentration of mixed pollutants needs to be recalculated for each gas sample to be tested; 2) The calculation method of the odor concentration of mixed pollutants of a certain gas sample is complicated and not easy to obtain.
[0038] Therefore, this embodiment introduces the mixed pollutant olfactory threshold into the Weber-Fechner subjective-objective coupling law, and substitutes x=C / ODT into formula (1) to obtain the following model:
[0039] S = a*lg(C / ODT) (2)
[0040] Wherein, C represents the concentration of mixed pollutants, and ODT represents the olfactory threshold of mixed pollutants.
[0041] Compared with the odor concentration of mixed pollutants: 1) For the same model, the components and materials in the car are basically the same, so the mixed pollutants in the car are basically the same, and the olfactory threshold of the mixed pollutants is approximately a fixed value. After being measured once, it can be reused without recalculating for each gas sample to be tested; 2) The mixed pollutant concentration of a gas sample can be directly measured by the test instrument, which is more convenient to obtain.
[0042] When the odor concentration of the mixed pollutants in the gas sample = 1, C = ODT, and the objective odor intensity of the gas sample = the objective odor intensity corresponding to the olfactory threshold. Therefore, according to the classification of odor intensity shown in Table 1, it can be seen that the olfactory threshold of mixed pollutants is the concentration of mixed pollutants that causes the minimum stimulation to human smell, and the corresponding objective odor intensity should be between 1.5 (perceptible odor, but weak intensity) and 2 (perceptible odor, obvious intensity, but does not cause discomfort). In the model of formula (2), when C = ODT, S = a*lg(C / ODT) = a*lg1 = 0, which is inconsistent with objective reality.
[0043] Table 1
[0044] Odor intensity level Standard description of odor status 1 Unable to detect odor 1.5 The odor is perceptible but weak 2 The odor is noticeable, but not unpleasant. 3 The odor is obvious but does not cause discomfort 4 Cause discomfort 5 Causes severe discomfort 6 Unacceptable
[0045] In view of the above reasons, we continue to optimize the relationship model of formula (2) and obtain the following model:
[0046] S=a*lg(C / ODT)+b; (3)
[0047] Where b is a constant. In this model, C is the model input, S is the model output, and a and b are unknown parameters.
[0048] S130. Using the mixed pollutant concentration and subjective odor intensity of the original gas sample at different dilution multiples as training data, train the undetermined parameters in the relationship model to obtain a trained relationship model; wherein the subjective odor intensity includes: the odor intensity evaluation of the gas sample by the odor evaluator.
[0049] Specifically, the original gas sample is first diluted dynamically with clean air to obtain gas samples with different dilution multiples. Then the mixed pollutant concentrations of the gas samples with different dilution multiples are detected by a photoionization detector. The photoionization detector is easy to move and easy to detect; it has a wide detection range, high accuracy, fast response, and no loss.
[0050] At the same time, multiple odor evaluators evaluate the odor intensity of gas samples with different dilution ratios, and the evaluation results are the subjective odor intensity. For any gas sample with a dilution ratio, the subjective odor intensity given by all odor evaluators is averaged as the final subjective odor intensity of the gas sample with that dilution ratio. Among them, each odor evaluator has undergone professional training and assessment, and the subjective odor intensity given by him has good accuracy; the step of averaging the evaluation results of multiple odor evaluators also makes the final subjective odor intensity closer to the real odor intensity.
[0051] Finally, the measured mixed pollutant concentrations of gas samples with different dilution multiples are used as the input data of the relationship model, and the mixed pollutant concentrations of gas samples with different dilution multiples given by the odor evaluators are used as the output data of the relationship model. The relationship model is trained to determine the specific values of the unknown parameters a and b in the model.
[0052] After determining the specific values of a and b and substituting them into formula (3), we get the trained relationship model. This model can represent the relationship between the mixed pollutant concentration of the gas sample in the target vehicle model and the odor evaluation intensity, and can predict the odor evaluation intensity of the sample by the mixed pollutant concentration of the gas sample to be tested. Since the odor evaluation intensity predicted by the relationship model is not given subjectively by the odor evaluator, but predicted by the objective model obtained through big data training, in order to facilitate distinction and description, this odor rating intensity is called objective odor evaluation intensity.
[0053] Optionally, during model training, the initial value range of b is set to (1.5, 2).
[0054] As described in the above embodiment, the intercept b in the relationship model represents the objective odor intensity corresponding to the mixed pollutant concentration C of the gas sample = the mixed pollutant odor threshold ODT, which should be between 1.5 and 2. In order to improve training efficiency and training accuracy, the initial range of b is set to (1.5, 2) in model training, which can accelerate model convergence and improve model fitting.
[0055] The technical effect of this embodiment is as follows: on the one hand, this embodiment constructs an odor evaluation model for in-vehicle gas through mixed pollutants in gas samples, avoiding the need to distinguish single material components in mixed pollutants through complex instrument detection or human identification, and eliminating errors caused by missing single pollutant types; on the other hand, mixed pollutant concentrations and mixed pollutant olfactory thresholds are introduced into the odor evaluation model to replace the calculation of mixed pollutant odor concentrations, reducing the difficulty of obtaining independent variables and the number of calculations, and adding an intercept to the odor evaluation model to make the model more in line with objective reality.
[0056] Based on the above and following embodiments, this embodiment refines the calculation process of the mixed pollutant odor concentration of the gas sample. Optionally, according to the mixed pollutant concentration and the mixed pollutant odor concentration of the original gas sample in the target vehicle model, the mixed pollutant odor threshold of the target vehicle model is calculated, including the following steps:
[0057] Step 1: Obtain the subjective odor intensity of the original gas sample at different dilution multiples given by multiple odor evaluators.
[0058] The subjective odor intensity here can reuse the subjective odor intensity of gas samples with different dilution multiples given by multiple odor evaluators in the above embodiment, or other odor evaluators can be organized to evaluate separately.
[0059] Step 2: From the multiple subjective odor intensities given by each odor evaluator, select the two subjective odor intensities closest to the 1.5-level odor intensity as the first subjective odor intensity and the second subjective odor intensity, or select the two subjective odor intensities closest to the 2-level odor intensity as the first subjective odor intensity and the second subjective odor intensity.
[0060] The first subjective odor intensity and the second subjective odor intensity are used to estimate the dilution multiple corresponding to the olfactory threshold of the mixed pollutants. Specifically, if the olfactory threshold of the mixed pollutants is predicted to be high, the two subjective odor intensities closest to each other before and after the 1.5-level odor intensity are selected as the first subjective odor intensity and the second subjective odor intensity; if the olfactory threshold of the mixed pollutants is predicted to be low, the two subjective odor intensities closest to each other before and after the 1.5-level odor intensity are selected as the first subjective odor intensity and the second subjective odor intensity. If the olfactory threshold of the mixed pollutants cannot be predicted, the first subjective odor intensity and the second subjective odor intensity are selected before and after either the 1.5-level subjective odor intensity or the 2.0-level subjective odor intensity.
[0061] Step 3: Calculate the geometric mean of the dilution factor corresponding to the first subjective odor intensity and the dilution factor corresponding to the second subjective odor intensity to obtain the odor concentration of the mixed pollutants given by each odor evaluator.
[0062] As described in the above embodiment, the odor concentration of mixed pollutants is essentially the dilution factor corresponding to the olfactory threshold of the mixed pollutants. Therefore, this embodiment estimates the dilution factor corresponding to the olfactory threshold of the mixed pollutants based on the dilution factor corresponding to the first subjective odor intensity and the second subjective odor intensity of each odor evaluator, as the odor concentration of mixed pollutants given by each odor evaluator.
[0063] Specifically, for each odor evaluator, the geometric mean of the dilution factor corresponding to the first subjective odor intensity and the dilution factor corresponding to the second subjective odor intensity is taken as the odor concentration of the mixed pollutant given by each odor evaluator. According to formula (1): S = a*lgx, it can be seen that the odor concentration x and the odor intensity S are exponentially related. Here, taking the geometric mean of the two dilution factors (i.e., the odor concentration x) is equivalent to taking the arithmetic mean of the two subjective odor intensities. The arithmetic mean of the two subjective odor intensities is approximately equal to the subjective odor intensity corresponding to the olfactory threshold of the mixed pollutant. Therefore, the odor concentration is estimated through the subjective odor intensity.
[0064] Step 4: Calculate the arithmetic mean of the odor concentrations of the mixed pollutants given by the multiple odor evaluators to obtain the odor concentration of the mixed pollutants.
[0065] The odor concentration of the mixed pollutants given by all odor evaluators is arithmetic averaged to obtain the odor concentration of the mixed pollutants.
[0066] On the basis of the above embodiments and the following embodiments, the present embodiment adds a step of feedback verification of the trained relationship model. Optionally, after training the undetermined parameters in the relationship model using the mixed pollutant concentration and subjective odor intensity of the original gas sample at different dilution multiples as training data, it also includes: solving the degree of fit of the trained relationship model to the training data; if the degree of fit is less than a preset degree of fit threshold, replace the original gas sample and / or increase the number of dilution multiples of the original gas sample, return to the step of training the undetermined parameters in the relationship model using the mixed pollutant concentration and subjective odor intensity of the original gas sample at different dilution multiples as training data, until the degree of fit is greater than or equal to the degree of fit threshold.
[0067] This embodiment uses the model fit to verify the trained relationship model. If the fit is greater than or equal to the preset fit threshold, it proves that the model fit is good. Otherwise, the original gas sample can be replaced and the original gas sample can be collected from other vehicles of the target model to continue training or retraining. The number of dilution multiples of the original gas sample can also be increased to continue training or retraining, so that the subjective odor intensity given by the odor evaluator has a finer granularity, thereby improving the model fit.
[0068] Figure 2 1 is a flow chart of a method for evaluating the odor in a vehicle provided by an embodiment of the present invention, which is applicable to the case where the relationship model trained in any of the above embodiments is used to evaluate the odor in a vehicle. This embodiment is executed by an electronic device. Figure 2 As shown, the method specifically includes:
[0069] S210: Obtain the trained relationship model using the method provided in any of the above embodiments.
[0070] S210, inputting the mixed pollutant concentration of the gas sample to be tested in the vehicle of the target vehicle model into the trained relationship model to predict the objective odor intensity of the gas sample to be tested.
[0071] As described in the above embodiment, for the same vehicle model, the components and materials in the vehicle are basically the same, so the mixed pollutants in the vehicle are basically the same, and the olfactory threshold of the mixed pollutants is approximately a fixed value. Therefore, the relationship model of this application is constructed for the vehicle model, and different vehicle models correspond to different relationship models.
[0072] After obtaining a trained relational model for a target vehicle model, the model can be used to predict the objective odor intensity of any gas sample to be tested from the target vehicle model.
[0073] Optionally, after the mixed pollutant concentration of the gas sample to be tested in the vehicle of the target vehicle type is input into the trained relationship model and the objective odor intensity of the gas sample to be tested is predicted, the following steps are further included:
[0074] Step 1: Obtain the odor type and odor pleasantness of the gas sample to be tested given by multiple odor evaluators, as well as the subjective odor intensity of the gas sample to be tested at different dilution multiples.
[0075] After predicting the objective odor intensity of the gas sample to be tested, the present application also considers two subjective evaluation indicators, odor type and odor pleasantness.
[0076] Step 2: Calculate the odor concentration of the mixed pollutants in the gas sample to be tested based on the multiple subjective odor intensities of the gas sample to be tested.
[0077] This step calculates the odor concentration of the mixed pollutants of the gas sample to be tested by the method described in the above embodiment. Although the odor concentration of the mixed pollutants is calculated by subjective odor intensity, it is essentially an objective gas property of the gas sample to be tested and is an objective evaluation index.
[0078] Step 3: If the odor concentration of the mixed pollutants, the objective odor intensity, the odor type and the odor pleasantness of the gas sample to be tested all meet the standards, the interior odor of the vehicle containing the gas sample to be tested meets the standards.
[0079] Finally, two objective evaluation indicators: objective odor intensity and mixed pollutant odor concentration, and two subjective evaluation indicators: odor type and odor pleasantness are combined to conduct a comprehensive evaluation of the gas sample to be tested. Only when all four indicators meet the standards, the gas sample to be tested is considered to meet the standards. Specifically, if the odor concentration is less than the set odor concentration threshold, the odor concentration is considered to meet the standard; if the objective odor intensity is less than the set odor intensity threshold, the objective odor intensity is considered to meet the standard; if the odor type does not contain the set odor type, the odor type is considered to meet the standard; if the odor pleasantness is greater than or equal to the set pleasantness threshold, the odor pleasantness is considered to meet the standard. Among them, the odor concentration threshold, odor intensity threshold, set odor type and pleasantness threshold can all be obtained through big data statistics.
[0080] This embodiment combines objective evaluation indicators with subjective evaluation indicators to conduct a multi-dimensional comprehensive evaluation of the gas sample to be tested, which can more comprehensively characterize the problem of the odor status in the vehicle.
[0081] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention is shown in FIG. Figure 3As shown, the 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 can be one or more. Figure 3 A processor 30 is taken as an example; the processor 30, memory 31, input device 32 and output device 33 in the device can be connected by a bus or other means. Figure 3 The example of connecting through bus is taken in the following.
[0082] The memory 31 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the in-vehicle odor evaluation model construction method or the in-vehicle odor evaluation method in the embodiments of the present invention. The processor 20 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 31, that is, realizing the in-vehicle odor evaluation model construction method or the in-vehicle odor evaluation method.
[0083] The memory 31 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 31 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 31 may further include a memory remotely arranged relative to the processor 30, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0084] The input device 32 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 33 may include a display device such as a display screen.
[0085] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for constructing an in-vehicle odor evaluation model or the method for evaluating in-vehicle odor of any embodiment is implemented.
[0086] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.
[0087] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0088] The program code embodied on the 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.
[0089] Computer program code for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a 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 may be connected to an external computer (e.g., through the Internet using an Internet service provider).
[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.
Claims
1. A method for constructing a vehicle interior odor evaluation model, characterized in that: include: The mixed pollutant olfactory threshold of the target vehicle model is calculated according to the mixed pollutant concentration and the mixed pollutant odor concentration of the original gas sample in the vehicle of the target vehicle model; wherein the mixed pollutant includes a plurality of volatile pollutants; the mixed pollutant concentration refers to the total concentration of all volatile pollutants in the gas in the vehicle; the mixed pollutant olfactory threshold refers to the mixed pollutant concentration that causes the minimum stimulation to the human sense of smell; the mixed pollutant odor concentration refers to the dilution multiple when the gas sample in the vehicle containing the mixed pollutants is continuously diluted to the mixed pollutant olfactory threshold with odorless clean air; the mixed pollutant olfactory threshold = mixed pollutant concentration / mixed pollutant odor concentration; By using the mixed pollutant olfactory threshold and the Weber-Fechner subjective-objective coupling law, a relationship model between the mixed pollutant concentration and the objective odor intensity of the target vehicle interior gas is constructed; the relationship model is: S = a*lg(C / ODT)+b; Wherein, C represents the concentration of the mixed pollutants, S represents the objective odor intensity of the mixed pollutants, a and b represent undetermined parameters, and ODT represents the olfactory threshold of the mixed pollutants; The mixed pollutant concentration and subjective odor intensity of the original gas sample at different dilution multiples are used as training data to train the undetermined parameters in the relationship model to obtain a trained relationship model; wherein the subjective odor intensity includes: the odor intensity evaluation of the gas sample by the odor evaluator.
2. The method according to claim 1, characterized in that According to the mixed pollutant concentration and the mixed pollutant odor concentration of the original gas sample in the target vehicle model, the mixed pollutant odor threshold of the target vehicle model is calculated, including: Obtaining subjective odor intensities of the original gas sample at different dilution multiples given by multiple odor evaluators; From the multiple subjective odor intensities given by each odor evaluator, the two subjective odor intensities closest to the 1.5-level odor intensity are selected as the first subjective odor intensity and the second subjective odor intensity, or the two subjective odor intensities closest to the 2-level odor intensity are selected as the first subjective odor intensity and the second subjective odor intensity; Calculating the geometric mean of the dilution multiple corresponding to the first subjective odor intensity and the dilution multiple corresponding to the second subjective odor intensity to obtain the odor concentration of the mixed pollutants given by each odor evaluator; The arithmetic mean of the odor concentrations of the mixed pollutants given by the plurality of odor evaluators is calculated to obtain the odor concentration of the mixed pollutants.
3. The method according to claim 1 or 2, characterized in that: After training the undetermined parameters in the relationship model using the mixed pollutant concentrations and subjective odor intensities of the original gas samples at different dilution multiples as training data, the method further includes: Calculating the degree of fit of the trained relational model to the training data; If the degree of fit is less than a preset degree of fit threshold, replace the original gas sample and / or increase the number of dilution multiples of the original gas sample, return to the step of training the pending parameters in the relationship model using the mixed pollutant concentration and subjective odor intensity of the original gas sample at different dilution multiples as training data, until the degree of fit is greater than or equal to the degree of fit threshold.
4. The method according to claim 1, characterized in that: The mixed pollutant concentrations and subjective odor intensities of the original gas samples at different dilution multiples are used as training data to train the undetermined parameters in the relationship model, including: During model training, the initial value range of b is set to (1.5, 2).
5. The method according to claim 1, characterized in that According to the mixed pollutant concentration and the mixed pollutant odor concentration of the original gas sample in the target vehicle model, the mixed pollutant odor threshold of the target vehicle model is calculated, including: The mixed pollutant concentration of the original gas sample is detected by a photoionization detector.
6. A method for evaluating the odor in a vehicle, characterized in that: include: Using the method according to any one of claims 1 to 5, obtaining the trained relationship model; The mixed pollutant concentration of the gas sample to be tested in the target vehicle model is input into the trained relationship model to predict the objective odor intensity of the gas sample to be tested.
7. The method according to claim 6, characterized in that After inputting the mixed pollutant concentration of the gas sample to be tested in the target vehicle model into the trained relationship model and predicting the objective odor intensity of the gas sample to be tested, the method further includes: Obtaining the odor type and odor pleasantness of the gas sample to be tested given by multiple odor evaluators, as well as the subjective odor intensity of the gas sample to be tested at different dilution multiples; Calculating the odor concentration of mixed pollutants in the gas sample to be tested according to the multiple subjective odor intensities of the gas sample to be tested; If the odor concentration of mixed pollutants, objective odor intensity, odor type and odor pleasantness of the gas sample to be tested all meet the standards, the interior odor of the vehicle where the gas sample to be tested is located meets the standards.
8. An electronic device, characterized in that: include: 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 odor evaluation model construction method as described in any one of claims 1 to 5, or the in-vehicle odor evaluation method as described in claim 7 or 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for constructing a vehicle interior odor evaluation model as described in any one of claims 1 to 5, or the method for evaluating vehicle interior odor as described in claim 7 or 6 is implemented.