WO2020186746A1 - 基于电子舌的酱油滋味评价方法、装置、介质和计算设备 - Google Patents

基于电子舌的酱油滋味评价方法、装置、介质和计算设备 Download PDF

Info

Publication number
WO2020186746A1
WO2020186746A1 PCT/CN2019/112052 CN2019112052W WO2020186746A1 WO 2020186746 A1 WO2020186746 A1 WO 2020186746A1 CN 2019112052 W CN2019112052 W CN 2019112052W WO 2020186746 A1 WO2020186746 A1 WO 2020186746A1
Authority
WO
WIPO (PCT)
Prior art keywords
taste
soy sauce
taste parameter
sensory
parameter
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.)
Ceased
Application number
PCT/CN2019/112052
Other languages
English (en)
French (fr)
Inventor
苏国万
赵谋明
李露芳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
South China University of Technology SCUT
Original Assignee
South China University of Technology SCUT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by South China University of Technology SCUT filed Critical South China University of Technology SCUT
Publication of WO2020186746A1 publication Critical patent/WO2020186746A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/0001—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00 by organoleptic means
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/02—Food

Definitions

  • the invention relates to the technical field of soy sauce taste evaluation, in particular to an electronic tongue-based soy sauce taste evaluation method, device, medium and computing equipment.
  • Soy sauce is made from soybeans (or defatted soybeans) and wheat (or bran) as raw materials. It is a liquid condiment with special color, fragrance and taste after cooking, koji making, and fermentation. It is popular among consumers because of its delicious taste. Love is indispensable in the food field and has attracted much attention.
  • the taste mechanism of soy sauce is quite complicated, and it has the characteristics of many flavor components and strong taste.
  • Traditional taste evaluation relies on man-made sensory analysis, but it is not only time-consuming and labor-intensive, low in efficiency, but also easily affected by subjective feelings and external environments, resulting in poor stability and quantification of evaluation results.
  • the first object of the present invention is to overcome the shortcomings and deficiencies of the prior art, and provide an electronic tongue-based soy sauce taste evaluation method, which can accurately and quickly evaluate the taste parameters of soy sauce.
  • the second object of the present invention is to provide an electronic tongue-based soy sauce taste evaluation device.
  • the third object of the present invention is to provide a storage medium.
  • the fourth object of the present invention is to provide a computing device.
  • the first objective of the present invention is achieved by the following technical solution: an electronic tongue-based soy sauce taste evaluation method, characterized in that the steps are as follows:
  • each soy sauce sample obtain the sensory scores of each taste parameter made by a number of persons with sensory experience; each taste parameter includes sour, salty, bitter, sweet, fresh and fullness;
  • the partial least square method is used to analyze the correlation between the sensory score of each taste parameter of soy sauce and the value of each taste parameter, so as to establish each taste of soy sauce Parametric sensory evaluation model;
  • the taste parameter values are collected through the electronic tongue; then the taste parameter values are substituted into the sensory evaluation model of each taste parameter of the soy sauce, and the sensory score of each taste parameter is obtained.
  • the soy sauce sample is a pretreated soy sauce sample
  • the pretreatment refers to diluting the soy sauce sample to a certain multiple with distilled water.
  • Step 1 Place each sensor of the electronic tongue in the soaking solution and stabilize for 90 seconds to preliminarily clean and remove impurities on the surface of the membrane.
  • the umami sensor AAE, the sour sensor CA0, and the salty sensor CT0 of the electronic tongue are placed in the soaking solution as negative
  • the cleaning liquid, the soaking liquid of the bitter sensor C00 and the sweet sensor GL1 of the electronic tongue is the positive electrode cleaning liquid,
  • Step 2 Place each sensor of the electronic tongue in the first reference solution and the second reference solution for 2 minutes;
  • each sensor disposed on the electronic tongue third stable reference solution than 30 seconds, respectively, each measured potential value Vr i, i AAE, CA0 , CT0, C00, GL1;
  • Vr AAE, Vr CA0, Vr CT0 , Vr C00 and Vr GL1 are the electronic tongue umami sensor AAE, sour sensor CA0, salt sensor CT0, bitter sensor C00 and sweet sensor GL1, respectively, measured after being stabilized in the third reference liquid for 30 seconds Potential difference;
  • Step 5 Put the freshness sensor AAE of the electronic tongue in the fourth reference solution and the fifth reference solution for 3 seconds respectively;
  • the established sensory evaluation model for each taste parameter is:
  • F j represents the sensory evaluation model of taste parameter j
  • taste parameter j 1, 2, ..., 6 respectively represent taste parameters of freshness, sourness, saltiness, bitterness, sweetness and fullness;
  • X 1 to X 6 respectively correspond to parameter values representing sour, bitter, fresh, fullness, saltiness and sweetness
  • K j represents a constant in the sensory evaluation model of taste parameter j
  • a j represents the weight corresponding to the sour taste parameter value in the sensory evaluation model of taste parameter j;
  • b j represents the weight corresponding to the bitterness parameter value in the sensory evaluation model of the taste parameter j
  • c j represents the weight corresponding to the umami taste parameter value in the sensory evaluation model of the taste parameter j;
  • d j represents the weight corresponding to the fullness taste parameter value in the sensory evaluation model of the taste parameter j;
  • e j represents the weight corresponding to the salty taste parameter value in the sensory evaluation model of the taste parameter j;
  • f j represents the weight corresponding to the sweet taste parameter value in the sensory evaluation model of the taste parameter j.
  • the method further includes the following steps. After the sensory evaluation model of each taste parameter is obtained, the sensory evaluation model of each taste parameter is evaluated through the correlation coefficient R2 and the root mean square error RMSE value.
  • the method further includes the following steps: for the soy sauce to be tested, after obtaining the sensory scores of each taste parameter, evaluating its taste characteristics according to the score range; specifically:
  • the taste characteristic of the taste parameter is defined as no feeling
  • the taste characteristic of the taste parameter is qualitatively a threshold sense
  • the taste characteristic of the taste parameter is classified as weak
  • the taste characteristic of the taste parameter is classified as medium
  • the taste characteristic of the taste parameter is characterized as strong.
  • each soy sauce sample is placed in a room at 23 ⁇ 2°C, and then a plurality of personnel with sensory experience will perform sensory scores on each taste parameter of each soy sauce sample; quantitative description analysis is used in the sensory score Method, using a 9-point digital scale as the scoring scale.
  • an electronic tongue-based soy sauce taste evaluation device including:
  • the sensory scoring information acquisition module for soy sauce samples is used to obtain sensory scoring information for each taste parameter made by multiple persons with sensory experience for each soy sauce sample obtained; each taste parameter includes sour, salty, bitter, sweet, Freshness and fullness;
  • Soy sauce sample taste parameter value acquisition module used to acquire each taste parameter value collected by the electronic tongue for each soy sauce sample
  • Taste parameter sensory evaluation model establishment module used to analyze the correlation between the sensory score of each taste parameter of soy sauce and the value of each taste parameter using the partial least square method according to the sensory score of each taste parameter of each soy sauce sample and the value of each taste parameter. So as to establish the sensory evaluation model of each taste parameter of soy sauce;
  • the taste parameter value acquisition module of the soy sauce to be tested is used to acquire the taste parameter values collected by the electronic tongue for the soy sauce to be tested;
  • the taste parameter sensory evaluation module is used to substitute the taste parameter values of the soy sauce to be tested into the sensory evaluation model of each taste parameter of the soy sauce to obtain the sensory score of each taste parameter.
  • the third objective of the present invention is achieved by the following technical solution: a storage medium storing a program, and when the program is executed by a processor, the following operations are achieved:
  • the partial least square method was used to analyze the correlation between the sensory score of each taste parameter of soy sauce and the value of each taste parameter, thereby establishing a sensory evaluation model for each taste parameter of soy sauce ;
  • the taste parameter values of the soy sauce to be tested are substituted into the sensory evaluation model of each taste parameter of the soy sauce, and the sensory score of each taste parameter is obtained.
  • the fourth object of the present invention is achieved by the following technical solution: a computing device including a processor and a memory for storing an executable program for the processor, when the processor executes a program stored in the memory, the following operations are implemented:
  • the partial least square method was used to analyze the correlation between the sensory score of each taste parameter of soy sauce and the value of each taste parameter, thereby establishing a sensory evaluation model for each taste parameter of soy sauce ;
  • the taste parameter values of the soy sauce to be tested are substituted into the sensory evaluation model of each taste parameter of the soy sauce, and the sensory score of each taste parameter is obtained.
  • the present invention has the following advantages and effects:
  • soy sauce taste evaluation method of the present invention a plurality of soy sauce samples are first obtained, and for each soy sauce sample obtained, sensory scoring information of each taste parameter made by a plurality of persons with sensory experience is obtained; and through the electronic tongue Collect each taste parameter value of each soy sauce sample; then according to the sensory score of each taste parameter of each soy sauce sample and the value of each taste parameter, use partial least square method to analyze the correlation between the sensory score of each taste parameter and the value of each taste parameter , Establish a sensory evaluation model for each taste parameter of soy sauce; for the soy sauce to be tested, collect each taste parameter value in it through the electronic tongue; then substitute each taste parameter value into the sensory evaluation model of each taste parameter of soy sauce, and get Sensory score of each taste parameter.
  • the present invention establishes a sensory evaluation model for each taste parameter by analyzing the sensory score of each taste parameter in soy sauce and the correlation between each taste parameter value.
  • the soy sauce collected by the electronic tongue
  • the taste parameter values of the soy sauce can be directly substituted into the model to obtain the sensory score of each taste parameter, which has the advantage of being able to accurately and quickly evaluate the taste parameters of the soy sauce; in addition, the taste parameter values of the soy sauce in the method of the present invention are electronic
  • the scoring collected by the tongue device is also performed by a model that has been calculated.
  • the method of the present invention is not affected by humans, and solves the problems of unstable results and low work efficiency caused by artificial sensory analysis in the prior art due to sensory fatigue and environmental influences. . It is of great significance to evaluate and optimize the taste and quality of soy sauce during the production, sales, and eating process.
  • the electronic tongue is used to collect the taste parameter information of the soy sauce.
  • the electronic tongue is a new type of taste detection system, based on the principles of bionics, sensor technology and computer science, using a sensor array to detect food
  • the characteristic electrical response signal of the sample combined with statistical analysis and pattern recognition methods, realizes the analysis and recognition of the taste of the sample;
  • the electronic tongue technology is not only simple to operate, time-saving and labor-saving, but also has stronger objectivity and reproducibility, which can further enhance the soy sauce The accuracy of taste evaluation.
  • Fig. 1 is a flowchart of the method for evaluating the taste of soy sauce according to the present invention.
  • Figure 2 is a block diagram of the structure of the soy sauce taste evaluation device of the present invention.
  • the invention discloses a method for evaluating the taste of soy sauce based on an electronic tongue, as shown in Figure 1, and the steps are as follows:
  • Step S1 Obtain a plurality of soy sauce samples; in this embodiment, the soy sauce sample is a pre-treated soy sauce sample, and the pre-treatment refers to diluting the soy sauce sample to a certain multiple, such as 30 times, with distilled water.
  • 20 soy sauce samples were obtained. To come from different batches, 20 soy sauce samples were put into 20 sample cups.
  • Step S2 for each soy sauce sample, obtain the sensory scores of each taste parameter made by a plurality of persons with sensory experience; the taste parameters include six, which are acid, salty, bitter, sweet, fresh and fullness;
  • each soy sauce sample is placed in an evaluation room at 23 ⁇ 2°C, and an evaluation team is composed of 10 evaluators (5 men and 5 women) with sensory analysis experience.
  • each evaluator has The six taste parameters of the soy sauce sample were scored one by one.
  • the sensory scoring adopts the quantitative description analysis (QDA) method, with a 9-point digital scale as the scoring scale, and the intensity changes from 0 to 9 points are in order of no sensation, threshold sensation, weak, medium, and strong.
  • QDA quantitative description analysis
  • 0 to 1 is divided into no sensation
  • 1 to 3 is divided into threshold sense
  • 3 to 5 is divided into weak
  • 5 to 7 is divided into medium
  • 7 to 9 is divided into strong.
  • Step S3 For each soy sauce sample, collect each taste parameter value through the electronic tongue; in this embodiment, each soy sauce sample is measured in parallel by the electronic tongue for 6 times. For each taste parameter value detected each time, take The average value of the last 3 times is used as the final taste parameter value.
  • Step S4 According to the sensory scores of the taste parameters and the taste parameter values of the soy sauce samples obtained above, the partial least squares method (PLS) is used to analyze the correlation between the sensory scores of the taste parameters of the soy sauce and the taste parameter values.
  • PLS partial least squares method
  • X 1 to X 6 respectively correspond to parameter values representing sour, bitter, fresh, fullness, saltiness and sweetness
  • K j represents a constant in the sensory evaluation model of taste parameter j
  • a j represents the weight corresponding to the sour taste parameter value in the sensory evaluation model of taste parameter j;
  • b j represents the weight corresponding to the bitterness parameter value in the sensory evaluation model of the taste parameter j
  • c j represents the weight corresponding to the umami taste parameter value in the sensory evaluation model of the taste parameter j;
  • d j represents the weight corresponding to the fullness taste parameter value in the sensory evaluation model of the taste parameter j;
  • e j represents the weight corresponding to the salty taste parameter value in the sensory evaluation model of the taste parameter j;
  • f j represents the weight corresponding to the sweet taste parameter value in the sensory evaluation model of the taste parameter j.
  • the partial least square method Establish a sensory evaluation model F 1 for obtaining the fresh taste parameter; according to the sensory score of the taste parameter acid of each soy sauce sample obtained above in step S2 and the taste parameter of fresh, sour, salty, bitter, sweet and fullness of each soy sauce sample Partial least squares method (PLS) was used to establish the sensory evaluation model F 2 to obtain the taste parameter acidity; according to the sensory score of the taste parameter saltiness of each soy sauce sample obtained above in step S2 and the freshness, sourness, saltiness, and saltiness of each soy sauce sample Bitter, sweet and fullness taste parameter values, using partial least squares (PLS) to establish the sensory evaluation model F 3 of the taste parameter saltiness; according to the taste parameter of each soy sauce sample obtained in step S
  • Table 1 shows the expressions of the sensory evaluation model equations for each taste parameter obtained under the 20 soy sauce samples of this example:
  • Step S5 For the soy sauce to be tested, the taste parameter values are collected through the electronic tongue; then the taste parameter values are respectively substituted into the sensory evaluation model of each taste parameter of the soy sauce to obtain the sensory score of each taste parameter.
  • Step S6 For the to-be-tested soy sauce, after obtaining the sensory score of each taste parameter, evaluate its taste characteristics according to the score range; specifically:
  • the taste characteristic of the taste parameter is defined as no feeling
  • the taste characteristic of the taste parameter is qualitatively a threshold sense
  • the taste characteristic of the taste parameter is classified as weak
  • the taste characteristic of the taste parameter is qualified as medium
  • the taste characteristic of the taste parameter is characterized as strong.
  • Table 2 shows the sensory scores and taste characteristics of a soy sauce to be tested in this embodiment
  • the sourness, bitterness, and sweetness of the selected soy sauce defect indicators in this embodiment are within the threshold sense range, the characteristic indicators of umami and saltiness are medium, and the sense of fullness belongs to the weak range.
  • each reference liquid is obtained after the volume of 2.2365g KCl+0.045g tartaric acid is adjusted to 1000mL, and then the taste parameters in the soy sauce are collected through the electronic tongue.
  • Step 1 Place each sensor of the electronic tongue in the soaking solution and stabilize for 90 seconds to preliminarily clean and remove impurities on the surface of the membrane.
  • the umami sensor AAE, the sour sensor CA0, and the salty sensor CT0 of the electronic tongue are placed in the soaking solution as negative
  • the cleaning liquid, the soaking liquid of the bitter sensor C00 and the sweet sensor GL1 of the electronic tongue is the positive electrode cleaning liquid,
  • Step 2 Place each sensor of the electronic tongue in the first reference solution and the second reference solution for 2 minutes;
  • each sensor disposed on the electronic tongue third stable reference solution than 30 seconds, respectively, each measured potential value Vr i, i AAE, CA0 , CT0, C00, GL1;
  • Vr AAE, Vr CA0, Vr CT0 , Vr C00 and Vr GL1 are the electronic tongue umami sensor AAE, sour sensor CA0, salt sensor CT0, bitter sensor C00 and sweet sensor GL1, respectively, measured after being stabilized in the third reference liquid for 30 seconds Potential difference;
  • Step 5 Put the freshness sensor AAE of the electronic tongue in the fourth reference solution and the fifth reference solution for 3 seconds respectively;
  • step S3 if it is executed in step S3, the soy sauce refers to the soy sauce sample; if it is executed in step S5, the soy sauce refers to the soy sauce to be tested.
  • the TS-5000Z electronic tongue of Japanese insent company can be selected.
  • This embodiment discloses an electronic tongue-based soy sauce taste evaluation device, as shown in FIG. 2, including:
  • the sensory scoring information acquisition device for soy sauce samples is used to acquire sensory scoring information for each taste parameter made by a plurality of persons with sensory experience for each acquired soy sauce sample; in this embodiment, 20 soy sauce products can be acquired ; For each soy sauce product, the sensory scoring information of each taste parameter made by multiple persons with sensory experience is obtained; among them, each soy sauce sample can be placed in the evaluation room at 23 ⁇ 2°C, and 10 people with sensory analysis Experienced evaluators (5 males and 5 females) formed an evaluation team. For each soy sauce sample, each evaluator performed sensory scores on the six taste parameters of the soy sauce sample one by one.
  • the soy sauce sample taste parameter value acquisition module is used to acquire the taste parameter values collected by the electronic tongue for each soy sauce sample; the electronic tongue is the TS-5000Z electronic tongue of Japanese insent. Among them, each soy sauce sample was measured in parallel by the electronic tongue for 6 times. For each taste parameter value detected each time, the average value of the last 3 times was taken as the final taste parameter value.
  • Taste parameter sensory evaluation model establishment module used to analyze the correlation between the sensory score of each taste parameter of soy sauce and the value of each taste parameter using the partial least square method according to the sensory score of each taste parameter of each soy sauce sample and the value of each taste parameter.
  • the taste parameter value acquisition module of the soy sauce to be tested is used to acquire the taste parameter values collected by the electronic tongue for the soy sauce to be tested;
  • the taste parameter sensory evaluation module is used to substitute the taste parameter values of the soy sauce to be tested into the sensory evaluation model of each taste parameter of the soy sauce to obtain the sensory score of each taste parameter.
  • the soy sauce taste evaluation device may further include the following functional modules:
  • the sensory model evaluation module is used to evaluate the sensory evaluation model of each taste parameter through the correlation coefficient R2 and the root mean square error RMSE value.
  • the device of this embodiment only uses the division of the above-mentioned functional modules as an example.
  • the above-mentioned function allocation can be completed by different functional modules as needed, that is, the internal structure is divided into different The functional modules to complete all or part of the functions described above.
  • This embodiment discloses a storage medium that stores a program, and when the program is executed by a processor, the following operations are implemented:
  • the partial least square method was used to analyze the correlation between the sensory score of each taste parameter of soy sauce and the value of each taste parameter, thereby establishing a sensory evaluation model for each taste parameter of soy sauce ;
  • the taste parameter values of the soy sauce to be tested are substituted into the sensory evaluation model of each taste parameter of the soy sauce, and the sensory score of each taste parameter is obtained.
  • the storage medium in this embodiment may be a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a USB flash drive, a mobile hard disk, and other media.
  • ROM read-only memory
  • RAM Random Access Memory
  • USB flash drive a mobile hard disk, and other media.
  • This embodiment discloses a computing device that includes a processor and a memory for storing an executable program of the processor, and is characterized in that: when the processor executes a program stored in the memory, the following operations are implemented:
  • the partial least square method was used to analyze the correlation between the sensory score of each taste parameter of soy sauce and the value of each taste parameter, thereby establishing a sensory evaluation model for each taste parameter of soy sauce ;
  • the taste parameter values of the soy sauce to be tested are substituted into the sensory evaluation model of each taste parameter of the soy sauce, and the sensory score of each taste parameter is obtained.
  • the computing device described in this embodiment may be a desktop computer, a notebook computer, a smart phone, a PDA handheld terminal, a tablet computer, or other terminal devices with a processor function.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Physics & Mathematics (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)
  • Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

一种基于电子舌的酱油滋味评价方法、装置、介质和计算设备；评价方法包括如下步骤：获取多个酱油样品；针对于各酱油样品，获取多个具有感官经验的人员所作出的各味觉参数的感官评分；针对于各酱油样品，通过电子舌采集其中的各味觉参数值；根据获取到的各酱油样品的各味觉参数的感官评分以及各味觉参数值，采用偏最小二乘法分析酱油的各味觉参数的感官评分与各味觉参数值的相关性，从而建立酱油的各味觉参数感官评价模型；针对于待测的酱油，通过电子舌采集其中的各味觉参数值；然后将各味觉参数值分别代入到酱油的各味觉参数感官评价模型中，得到各味觉参数的感官评分。能够准确以及快速实现对酱油的各味觉参数进行评价。

Description

基于电子舌的酱油滋味评价方法、装置、介质和计算设备 技术领域
本发明涉及酱油滋味评价技术领域，特别涉及一种基于电子舌的酱油滋味评价方法、装置、介质和计算设备。
背景技术
酱油是以大豆(或脱脂大豆)、小麦(或麸皮)为原料，经蒸煮、制曲、发酵后制成的具有特殊色、香、味的液体调味品，因滋味鲜美醇厚深受消费者喜爱，在食品领域中不可或缺，备受关注。酱油的呈味机理相当复杂，形成了其滋味组分多、且味感浓郁的特点。传统滋味评价依赖于人为感官分析，但不仅费时费力、效率较低，还容易受主观感觉、外界环境的影响，导致评价结果的稳定性、量化性较差。
发明内容
本发明的第一目的在于克服现有技术的缺点与不足，提供一种基于电子舌的酱油滋味评价方法，该方法可以准确以及快速实现对酱油的各味觉参数进行评价。
本发明的第二目的在于提供一种基于电子舌的酱油滋味评价装置。
本发明的第三目的在于提供一种存储介质。
本发明的第四目的在于提供一种计算设备。
本发明的第一目的通过下述技术方案实现：一种基于电子舌的酱油滋味评价方法，其特征在于，步骤如下：
获取多个酱油样品；
针对于各酱油样品，获取多个具有感官经验的人员所作出的各味觉参数的感官评分；各味觉参数包括酸、咸、苦、甜、鲜和饱满感；
针对于各酱油样品，通过电子舌采集其中的各味觉参数值；
根据上述获取到的各酱油样品的各味觉参数的感官评分以及各味觉参数值，采用偏最小二乘法分析酱油的各味觉参数的感官评分与各味觉参数值的相关性，从而建立酱油的各味觉参数感官评价模型；
针对于待测的酱油，通过电子舌采集其中的各味觉参数值；然后将各味觉参数值分别代入到酱油的各味觉参数感官评价模型中，得到各味觉参数的感官评分。
优选的，所述酱油样品为经过预处理后的酱油样品，预处理指的是将酱油样品采用蒸馏水稀释到一定倍数。
更进一步的，通过电子舌采集酱油中各味觉参数值的步骤如下：
步骤1、将电子舌的各传感器分别置于浸泡液中稳定90秒以初步清洗除去膜表面杂质，其中电子舌的鲜味传感器AAE、酸味传感器CA0、咸味传感器CT0置于的浸泡液为负极清洗液，电子舌的苦味传感器C00、甜味传感器GL1置于的浸泡液为正极清洗液，
步骤2、将电子舌的各传感器分别置于第一份参比液和第二份参比液中清洗2分钟；
步骤3、将电子舌的各传感器置于第三份参比液中稳定30秒，分别测得各电势值Vr i，i＝AAE,CA0,CT0,C00,GL1；Vr AAE、Vr CA0、Vr CT0、Vr C00和Vr GL1分别为电子舌的鲜味传感器AAE、酸味传感器CA0、咸味传感器CT0、苦味传感器C00和甜味传感器GL1置于第三份参比液中稳定30秒后测得的电势差；
步骤4、将电子舌的各传感器置于酱油溶液中稳定30秒，分别测得各电势值Vs i，i＝AAE,CA0,CT0,C00,GL1；Vs AAE、Vs CA0、Vs CT0、Vs C00和Vs GL1分别为电子舌的鲜味传感器AAE、酸味传感器CA0、咸味传感器CT0、苦味传感器C00和甜味传感器GL1置于酱油溶液中稳定30秒后测得的电势差；
计算电势差V1 i＝Vs i-Vr i，i＝AAE,CA0,CT0,C00,GL1，得到酱油的鲜、酸、咸、苦和甜味觉参数值；
步骤5、将电子舌的鲜味传感器AAE置于第四份参比溶液和第五份参比溶液分别清洗3秒；
步骤6、将电子舌的鲜味传感器AAE置于第六份参比溶液稳定30秒，测得电势值Vr′ AAE；计算电势差V2＝Vr′ AAE-Vr AAE，作为饱满感味觉参数。
优选的，建立的各味觉参数感官评价模型为：
F j＝K j+a jX 1+b jX 2+c jX 3+d jX 4+e jX 5+f jX 6；
j＝1,2,...,6；
其中F j表示味觉参数j的感官评价模型；味觉参数j＝1,2,...,6分别表示味觉参数鲜、酸、咸、苦、甜和饱满感；
X 1至X 6分别对应表示酸、苦、鲜、饱满感、咸和甜味觉参数值；
K j表示在味觉参数j感官评价模型中的常数；
a j表示在味觉参数j感官评价模型中酸味觉参数值对应的权重；
b j表示在味觉参数j感官评价模型中苦味觉参数值对应的权重；
c j表示在味觉参数j感官评价模型中鲜味觉参数值对应的权重；
d j表示在味觉参数j感官评价模型中饱满感味觉参数值对应的权重；
e j表示在味觉参数j感官评价模型中咸味觉参数值对应的权重；
f j表示在味觉参数j感官评价模型中甜味觉参数值对应的权重。
优选的，还包括如下步骤，在获取到各味觉参数感官评价模型后，通过相关系数R2和均方根误差RMSE值对各味觉参数感官评价模型进行评价。
优选的，还包括如下步骤：针对于待测酱油，在获取到各味觉参数的感官评分后，根据分值范围对其滋味特性进行评价；具体为：
当某味觉参数的感官评分为0～1分时，将该味觉参数的滋味特性定性为无感觉；
当某味觉参数的感官评分为1～3分时，将该味觉参数的滋味特性定性为阈值感；
当某味觉参数的感官评分为3～5分时，将该味觉参数的滋味特性定性为微弱；
当某味觉参数的感官评分为5～7分时，将该味觉参数的滋味特性定性为中等；
当某味觉参数的感官评分为7～9分时，将该味觉参数的滋味特性定性为强烈。
优选的，针对于各酱油样品，将各酱油样品置于23±2℃的室内，然后由多个具有感官经验的人员对各酱油样品各味觉参数进行感官评分；在感官评分中采用定量描述分析法，以9点数字标度为评分标尺。
本发明的第二目的通过下述技术方案实现：一种基于电子舌的酱油滋味评价装置，包括：
酱油样品感官评分信息获取模块，用于针对于获取到的各酱油样品，获取多个具有感官经验的人员所作出的各味觉参数的感官评分信息；各味觉参数包括酸、咸、苦、甜、鲜和饱满感；
酱油样品味觉参数值获取模块，用于获取电子舌针对各酱油样品采集到的各味觉参数值；
味觉参数感官评价模型建立模块，用于根据各酱油样品的各味觉参数的感官评分以及各味觉参数值，采用偏最小二乘法分析酱油的各味觉参数的感官评分与各味觉参数值的相关性，从而建立酱油的各味觉参数感官评价模型；
待测酱油味觉参数值获取模块，用于获取电子舌针对待测酱油采集到的各味觉参数值；
味觉参数感官评价模块，用于将待测酱油的各味觉参数值代入到酱油的各味觉参数感官评价模型中，得到各味觉参数的感官评分。
本发明的第三目的通过下述技术方案实现：一种存储介质，存储有程序，所述程序被处理器执行时，实现如下操作：
针对于获取到的各酱油样品，获取多个具有感官经验的人员所作出的各味觉参数的感官评分信息；
获取电子舌针对各酱油样品采集到的各味觉参数值；
根据各酱油样品的各味觉参数的感官评分以及各味觉参数值，采用偏最小二乘法分析酱油的各味觉参数的感官评分与各味觉参数值的相关性，从而建立酱油的各味觉参数感官评价模型；
获取电子舌针对待测酱油采集到的各味觉参数值；
将待测酱油的各味觉参数值代入到酱油的各味觉参数感官评价模型中，得到各味觉参数的感官评分。
本发明的第四目的通过下述技术方案实现：一种计算设备，包括处理器以及用于存储处理器可执行程序的存储器所述处理器执行存储器存储的程序时，实现如下操作：
针对于获取到的各酱油样品，获取多个具有感官经验的人员所作出的各味觉参数的感官评分信息；
获取电子舌针对各酱油样品采集到的各味觉参数值；
根据各酱油样品的各味觉参数的感官评分以及各味觉参数值，采用偏最小二乘法分析酱油的各味觉参数的感官评分与各味觉参数值的相关性，从而建立酱油的各味觉参数感官评价模型；
获取电子舌针对待测酱油采集到的各味觉参数值；
将待测酱油的各味觉参数值代入到酱油的各味觉参数感官评价模型中，得到各味觉参数的感官评分。
本发明相对于现有技术具有如下的优点及效果：
(1)本发明酱油滋味评价方法中，首先获取多个酱油样品，针对于获取到的各酱油样品，获取多个具有感官经验的人员所作出的各味觉参数的感官评分信息；并且通过电子舌采集到各酱油样品的各味觉参数值；然后根据各酱油样品的各味觉参数的感官评分以及各味觉参数值，采用偏最小二乘法分析出各味觉参数的感官评分与各味觉参数值的相关性，建立得到酱油的各味觉参数感官 评价模型；针对于待测的酱油，通过电子舌采集其中的各味觉参数值；然后将各味觉参数值分别代入到酱油的各味觉参数感官评价模型中，得到各味觉参数的感官评分。由上述可见，本发明通过分析酱油中各味觉参数的感官评分和各味觉参数值的相关性来建立各味觉参数感官评价模型，在需要对酱油的滋味进行评价时，将电子舌采集到的酱油的各味觉参数值直接代入模型中即可得到各味觉参数的感官评分，具有能够准确以及快速实现对酱油的各味觉参数进行评价的优点；另外本发明方法中酱油的各味觉参数值是有电子舌设备采集的，评分也是由已经计算得到的模型进行，因此本发明方法不受人为影响，解决了现有技术中人为感官分析由于感官疲劳、环境影响导致的结果不稳定、工作效率低的问题。对酱油生产销售、食用过程中的滋味品质评价及优化具有重要意义。
(2)本发明酱油滋味评价方法中，采用电子舌采集酱油的味觉参数信息，其中，电子舌是一种新型的味觉检测系统，基于仿生学、传感器技术和计算机科学原理，利用传感器阵列检测食品的特征电响应信号，再结合统计分析、模式识别方法，实现对样品滋味的分析识别；电子舌技术不但操作简单、省时省力，且具有更强的客观性、重现性，能够进一步增强酱油滋味评价的准确性。
附图说明
图1是本发明酱油滋味评价方法流程图。
图2是本发明酱油滋味评价装置结构框图。
具体实施方式
下面结合实施例及附图对本发明作进一步详细的描述，但本发明的实施方式不限于此。
实施例1
本发明公开了一种基于电子舌的酱油滋味评价方法，如图1所示，步骤如下：
步骤S1、获取多个酱油样品；在本实施例中酱油样品为经过预处理后的酱油样品，预处理指的是将酱油样品采用蒸馏水稀释到一定倍数，例如30倍。在 本实施例中获取酱油样品20个，为来不同的批次，将20个酱油样品分别放入到20个样品杯中。
步骤S2、针对于各酱油样品，获取多个具有感官经验的人员所作出的各味觉参数的感官评分；味觉参数包括6个，分别为酸、咸、苦、甜、鲜和饱满感；在本实施例中，将各个酱油样品置于23±2℃的评价室内，由10名具有感官分析经验的评价人员(5男5女)组成评价小组，针对于每个酱油样品，每个评价人员都针对该酱油样品的6个味觉参数分别逐一进行感官评分。在本实施例中，感官评分采用定量描述分析(QDA)法，以9点数字标度为评分标尺，0～9分的强度变化依次为无感觉、阈值感、微弱、中等、强烈5个级别；其中，0～1分为无感觉，1～3分为阈值感，3～5分为微弱，5～7分为中等，7～9分为强烈。例如，评价人员对某味觉参数进行感官评分时，若感官为“无感觉”，则根据经验给出为0～1分；若感官为“阈值感”，则根据经验给出为1～3分；若感官为“微弱”，则根据经验给出为3～5分；若感官为“中等”，则根据经验给出为5～7分；若感官为“强烈”，则根据经验给出为7～9分。
步骤S3、针对于各酱油样品，通过电子舌采集其中的各味觉参数值；在本实施例中每个酱油样品通过电子舌进行6次平行测定，针对于每次检测到各味觉参数值，取最后3次的平均值作为最终的味觉参数值。
步骤S4、根据上述获取到的各酱油样品的各味觉参数的感官评分以及各味觉参数值，采用偏最小二乘法(PLS)分析酱油的各味觉参数的感官评分与各味觉参数值的相关性，从而建立酱油的各味觉参数感官评价模型：
F j＝K j+a jX 1+b jX 2+c jX 3+d jX 4+e jX 5+f jX 6；
j＝1,2,...,6；
其中F j表示味觉参数j的感官评价模型；味觉参数j＝1,2,...,6分别表示味觉参数鲜、酸、咸、苦、甜和饱满感；即F 1为味觉参数鲜的感官评价模型，F 2为味觉参数酸的感官评价模型，F 3为味觉参数咸的感官评价模型，F 4为味觉参数苦的感官评价模型，F 5为味觉参数甜的感官评价模型，F 6为味觉参数饱满感的感官评价模型；
X 1至X 6分别对应表示酸、苦、鲜、饱满感、咸和甜味觉参数值；
K j表示在味觉参数j感官评价模型中的常数；
a j表示在味觉参数j感官评价模型中酸味觉参数值对应的权重；
b j表示在味觉参数j感官评价模型中苦味觉参数值对应的权重；
c j表示在味觉参数j感官评价模型中鲜味觉参数值对应的权重；
d j表示在味觉参数j感官评价模型中饱满感味觉参数值对应的权重；
e j表示在味觉参数j感官评价模型中咸味觉参数值对应的权重；
f j表示在味觉参数j感官评价模型中甜味觉参数值对应的权重。
在本实施例中，根据步骤S2上述获取到的各酱油样品的味觉参数鲜的感官评分以及各酱油样品的鲜、酸、咸、苦、甜和饱满感味觉参数值，采用偏最小二乘法(PLS)建立得到味觉参数鲜的感官评价模型F 1；根据步骤S2上述获取到的各酱油样品的味觉参数酸的感官评分以及各酱油样品的鲜、酸、咸、苦、甜和饱满感味觉参数值，采用偏最小二乘法(PLS)建立得到味觉参数酸的感官评价模型F 2；根据步骤S2上述获取到的各酱油样品的味觉参数咸的感官评分以及各酱油样品的鲜、酸、咸、苦、甜和饱满感味觉参数值，采用偏最小二乘法(PLS)建立得到味觉参数咸的感官评价模型F 3；根据步骤S2上述获取到的各酱油样品的味觉参数苦的感官评分以及各酱油样品的鲜、酸、咸、苦、甜和饱满感味觉参数值，采用偏最小二乘法(PLS)建立得到味觉参数苦的感官评价模型F 4；根据步骤S2上述获取到的各酱油样品的味觉参数甜的感官评分以及各酱油样品的鲜、酸、咸、苦、甜和饱满感味觉参数值，采用偏最小二乘法(PLS)建立得到味觉参数甜的感官评价模型F 5；根据步骤S2上述获取到的各酱油样品的味觉参数饱满感的感官评分以及各酱油样品的鲜、酸、咸、苦、甜和饱满感味觉参数值，采用偏最小二乘法(PLS)建立得到味觉参数饱满感的感官评价模型F 6。
本实施例中，在获取到各味觉参数感官评价模型后，通过相关系数R2和均方根误差RMSE值对各味觉参数感官评价模型进行评价。表1所示为本实施例20个酱油样品下获取到的各味觉参数感官评价模型方程表达式：
表1
Figure PCTCN2019112052-appb-000001
由上述可见，本实施例各味觉参数感官评价模型的相关系R2均控制在0.8以上，可见模型的预测性能良好。
步骤S5、针对于待测的酱油，通过电子舌采集其中的各味觉参数值；然后将各味觉参数值分别代入到酱油的各味觉参数感官评价模型中，得到各味觉参数的感官评分。
步骤S6、针对于待测酱油，在获取到各味觉参数的感官评分后，根据分值范围对其滋味特性进行评价；具体为：
当某味觉参数的感官评分为0～1分时，将该味觉参数的滋味特性定性为无感觉；
当某味觉参数的感官评分为1～3分时，将该味觉参数的滋味特性定性为阈值感；
当某味觉参数的感官评分为3～5分时，将该味觉参数的滋味特性定性为微弱；
当某味觉参数的感官评分为5～7分时，将该味觉参数的滋味特性定性为中 等；
当某味觉参数的感官评分为7～9分时，将该味觉参数的滋味特性定性为强烈。
如表2所示为本实施例中取的一个待测酱油所获取到的感官评分和滋味特性；
表2
滋味指标 鲜 酸 咸 苦 甜 饱满感
感官评分 6.31 2.13 5.98 1.95 1.63 3.26
滋味定性 中等 阈值感 中等 阈值感 阈值感 微弱
由上表可见，本实施例上述所选取的待测酱油缺陷性指标酸味、苦味、甜味在阈值感范围内，特征性指标鲜味、咸味为中等，饱满感属于微弱范围。
本实施例上述步骤S3和步骤S5执行前中，准备6份参比液，每份参比液由2.2365g KCl+0.045g酒石酸定容至1000mL后得到，然后通过电子舌采集酱油中各味觉参数值，具体步骤如下：
步骤1、将电子舌的各传感器分别置于浸泡液中稳定90秒以初步清洗除去膜表面杂质，其中电子舌的鲜味传感器AAE、酸味传感器CA0、咸味传感器CT0置于的浸泡液为负极清洗液，电子舌的苦味传感器C00、甜味传感器GL1置于的浸泡液为正极清洗液，
步骤2、将电子舌的各传感器分别置于第一份参比液和第二份参比液中清洗2分钟；
步骤3、将电子舌的各传感器置于第三份参比液中稳定30秒，分别测得各电势值Vr i，i＝AAE,CA0,CT0,C00,GL1；Vr AAE、Vr CA0、Vr CT0、Vr C00和Vr GL1分别为电子舌的鲜味传感器AAE、酸味传感器CA0、咸味传感器CT0、苦味传感器C00和甜味传感器GL1置于第三份参比液中稳定30秒后测得的电势差；
步骤4、将电子舌的各传感器置于酱油溶液中稳定30秒，分别测得各电势值Vs i，i＝AAE,CA0,CT0,C00,GL1；Vs AAE、Vs CA0、Vs CT0、Vs C00和Vs GL1分别为电子舌的鲜味传感器AAE、酸味传感器CA0、咸味传感器CT0、苦味传感器C00和甜味传感器GL1置于酱油溶液中稳定30秒后测得的电势差；
计算电势差V1 i＝Vs i-Vr i，i＝AAE,CA0,CT0,C00,GL1，得到酱油的鲜、酸、咸、苦和甜味觉参数值；
步骤5、将电子舌的鲜味传感器AAE置于第四份参比溶液和第五份参比溶液分别清洗3秒；
步骤6、将电子舌的鲜味传感器AAE置于第六份参比溶液稳定30秒，测得电势值Vr′ AAE；计算电势差V2＝Vr′ AAE-Vr AAE，作为饱满感味觉参数。
在上述步骤中，若是在步骤S3中执行，则其中的酱油指的是酱油样品，若是在步骤S5中执行，其中的酱油指的是待测酱油。在本实施例中，可以选用为日本insent公司的TS-5000Z电子舌。
实施例2
本实施例公开了一种基于电子舌的酱油滋味评价装置，如图2所示，包括：
酱油样品感官评分信息获取装置，用于针对于获取到的各酱油样品，获取多个具有感官经验的人员所作出的各味觉参数的感官评分信息；在本实施例中，可以获取20个酱油用品；针对每个酱油用品，获取到多个具有感官经验的人员所作出的各味觉参数的感官评分信息；其中，可以将各个酱油样品置于23±2℃的评价室内，由10名具有感官分析经验的评价人员(5男5女)组成评价小组，针对于每个酱油样品，每个评价人员都针对该酱油样品的6个味觉参数分别逐一进行感官评分。
酱油样品味觉参数值获取模块，用于获取电子舌针对各酱油样品采集到的各味觉参数值；其中电子舌为日本insent公司的TS-5000Z电子舌。其中每个酱油样品通过电子舌进行6次平行测定，针对于每次检测到各味觉参数值，取最后3次的平均值作为最终的味觉参数值。
味觉参数感官评价模型建立模块，用于根据各酱油样品的各味觉参数的感官评分以及各味觉参数值，采用偏最小二乘法分析酱油的各味觉参数的感官评分与各味觉参数值的相关性，从而建立酱油的各味觉参数感官评价模型：
F j＝K j+a jX 1+b jX 2+c jX 3+d jX 4+e jX 5+f jX 6；
j＝1,2,...,6；
其中F j表示味觉参数j的感官评价模型；味觉参数j＝1,2,...,6分别表示味觉参数鲜、酸、咸、苦、甜和饱满感；即F 1为味觉参数鲜的感官评价模型，F 2为味觉参数酸的感官评价模型，F 3为味觉参数咸的感官评价模型，F 4为味觉参数苦的感官评价模型，F 5为味觉参数甜的感官评价模型，F 6为味觉参数饱满感的感官评价模型；X 1至X 6分别对应表示酸、苦、鲜、饱满感、咸和甜味觉参数值；K j表示在味觉参数j感官评价模型中的常数；a j表示在味觉参数j感官评价模型中酸味觉参数值对应的权重；b j表示在味觉参数j感官评价模型中苦味觉参数值对应的权重；c j表示在味觉参数j感官评价模型中鲜味觉参数值对应的权重；d j表示在味觉参数j感官评价模型中饱满感味觉参数值对应的权重；e j表示在味觉参数j感官评价模型中咸味觉参数值对应的权重；f j表示在味觉参数j感官评价模型中甜味觉参数值对应的权重。
待测酱油味觉参数值获取模块，用于获取电子舌针对待测酱油采集到的各味觉参数值；
味觉参数感官评价模块，用于将待测酱油的各味觉参数值代入到酱油的各味觉参数感官评价模型中，得到各味觉参数的感官评分。
在本实施例中，酱油滋味评价装置还可以包括以下功能模块：
感官模型评价模块，用于通过相关系数R2和均方根误差RMSE值对各味觉参数感官评价模型进行评价。
在此需要说明的是，本实施例的装置仅以上述各功能模块的划分进行举例说明，在实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。
实施例3
本实施例公开了一种存储介质，存储有程序，所述程序被处理器执行时，实现如下操作：
针对于获取到的各酱油样品，获取多个具有感官经验的人员所作出的各味觉参数的感官评分信息；
获取电子舌针对各酱油样品采集到的各味觉参数值；
根据各酱油样品的各味觉参数的感官评分以及各味觉参数值，采用偏最小 二乘法分析酱油的各味觉参数的感官评分与各味觉参数值的相关性，从而建立酱油的各味觉参数感官评价模型；
获取电子舌针对待测酱油采集到的各味觉参数值；
将待测酱油的各味觉参数值代入到酱油的各味觉参数感官评价模型中，得到各味觉参数的感官评分。
本实施例中的存储介质可以是磁盘、光盘、计算机存储器、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、U盘、移动硬盘等介质。
实施例4
本实施例公开了一种计算设备，包括处理器以及用于存储处理器可执行程序的存储器，其特征在于：所述处理器执行存储器存储的程序时，实现如下操作：
针对于获取到的各酱油样品，获取多个具有感官经验的人员所作出的各味觉参数的感官评分信息；
获取电子舌针对各酱油样品采集到的各味觉参数值；
根据各酱油样品的各味觉参数的感官评分以及各味觉参数值，采用偏最小二乘法分析酱油的各味觉参数的感官评分与各味觉参数值的相关性，从而建立酱油的各味觉参数感官评价模型；
获取电子舌针对待测酱油采集到的各味觉参数值；
将待测酱油的各味觉参数值代入到酱油的各味觉参数感官评价模型中，得到各味觉参数的感官评分。
本实施例中所述的计算设备可以是台式电脑、笔记本电脑、智能手机、PDA手持终端、平板电脑或其他具有处理器功能的终端设备。
上述实施例为本发明较佳的实施方式，但本发明的实施方式并不受上述实施例的限制，其他的任何未背离本发明的精神实质与原理下所作的改变、修饰、替代、组合、简化，均应为等效的置换方式，都包含在本发明的保护范围之内。

Claims (10)

  1. 一种基于电子舌的酱油滋味评价方法，其特征在于，步骤如下：
    获取多个酱油样品；
    针对于各酱油样品，获取多个具有感官经验的人员所作出的各味觉参数的感官评分；各味觉参数包括酸、咸、苦、甜、鲜和饱满感；
    针对于各酱油样品，通过电子舌采集其中的各味觉参数值；
    根据上述获取到的各酱油样品的各味觉参数的感官评分以及各味觉参数值，采用偏最小二乘法分析酱油的各味觉参数的感官评分与各味觉参数值的相关性，从而建立酱油的各味觉参数感官评价模型；
    针对于待测的酱油，通过电子舌采集其中的各味觉参数值；然后将各味觉参数值分别代入到酱油的各味觉参数感官评价模型中，得到各味觉参数的感官评分。
  2. 根据权利要求1所述的基于电子舌的酱油滋味评价方法，其特征在于，所述酱油样品为经过预处理后的酱油样品，预处理指的是将酱油样品采用蒸馏水稀释到一定倍数。
  3. 根据权利要求2所述的基于电子舌的酱油滋味评价方法，其特征在于，通过电子舌采集酱油中各味觉参数值的步骤如下：
    步骤1、将电子舌的各传感器分别置于浸泡液中稳定90秒以初步清洗除去膜表面杂质，其中电子舌的鲜味传感器AAE、酸味传感器CA0、咸味传感器CT0置于的浸泡液为负极清洗液，电子舌的苦味传感器C00、甜味传感器GL1置于的浸泡液为正极清洗液，
    步骤2、将电子舌的各传感器分别置于第一份参比液和第二份参比液中清洗2分钟；
    步骤3、将电子舌的各传感器置于第三份参比液中稳定30秒，分别测得各电势值Vr i，i＝AAE,CA0,CT0,C00,GL1；Vr AAE、Vr CA0、Vr CT0、Vr C00和Vr GL1分别为 电子舌的鲜味传感器AAE、酸味传感器CA0、咸味传感器CT0、苦味传感器C00和甜味传感器GL1置于第三份参比液中稳定30秒后测得的电势差；
    步骤4、将电子舌的各传感器置于酱油溶液中稳定30秒，分别测得各电势值Vs i，i＝AAE,CA0,CT0,C00,GL1；Vs AAE、Vs CA0、Vs CT0、Vs C00和Vs GL1分别为电子舌的鲜味传感器AAE、酸味传感器CA0、咸味传感器CT0、苦味传感器C00和甜味传感器GL1置于酱油溶液中稳定30秒后测得的电势差；
    计算电势差V1 i＝Vs i-Vr i，i＝AAE,CA0,CT0,C00,GL1，得到酱油的鲜、酸、咸、苦和甜味觉参数值；
    步骤5、将电子舌的鲜味传感器AAE置于第四份参比溶液和第五份参比溶液分别清洗3秒；
    步骤6、将电子舌的鲜味传感器AAE置于第六份参比溶液稳定30秒，测得电势值Vr′ AAE；计算电势差V2＝Vr′ AAE-Vr AAE，作为饱满感味觉参数。
  4. 根据权利要求1所述的基于电子舌的酱油滋味评价方法，其特征在于，建立的各味觉参数感官评价模型为：
    F j＝K j+a jX 1+b jX 2+c jX 3+d jX 4+e jX 5+f jX 6；
    j＝1,2,...,6；
    其中F j表示味觉参数j的感官评价模型；味觉参数j＝1,2,...,6分别表示味觉参数鲜、酸、咸、苦、甜和饱满感；
    X 1至X 6分别对应表示酸、苦、鲜、饱满感、咸和甜味觉参数值；
    K j表示在味觉参数j感官评价模型中的常数；
    a j表示在味觉参数j感官评价模型中酸味觉参数值对应的权重；
    b j表示在味觉参数j感官评价模型中苦味觉参数值对应的权重；
    c j表示在味觉参数j感官评价模型中鲜味觉参数值对应的权重；
    d j表示在味觉参数j感官评价模型中饱满感味觉参数值对应的权重；
    e j表示在味觉参数j感官评价模型中咸味觉参数值对应的权重；
    f j表示在味觉参数j感官评价模型中甜味觉参数值对应的权重。
  5. 根据权利要求1所述的基于电子舌的酱油滋味评价方法，其特征在于，还包括如下步骤，在获取到各味觉参数感官评价模型后，通过相关系数R2和均方根误差RMSE值对各味觉参数感官评价模型进行评价。
  6. 根据权利要求1所述的基于电子舌的酱油滋味评价方法，其特征在于，还包括如下步骤：针对于待测酱油，在获取到各味觉参数的感官评分后，根据分值范围对其滋味特性进行评价；具体为：
    当某味觉参数的感官评分为0～1分时，将该味觉参数的滋味特性定性为无感觉；
    当某味觉参数的感官评分为1～3分时，将该味觉参数的滋味特性定性为阈值感；
    当某味觉参数的感官评分为3～5分时，将该味觉参数的滋味特性定性为微弱；
    当某味觉参数的感官评分为5～7分时，将该味觉参数的滋味特性定性为中等；
    当某味觉参数的感官评分为7～9分时，将该味觉参数的滋味特性定性为强烈。
  7. 根据权利要求1所述的基于电子舌的酱油滋味评价方法，其特征在于，针对于各酱油样品，将各酱油样品置于23±2℃的室内，然后由多个具有感官经验的人员对各酱油样品各味觉参数进行感官评分；在感官评分中采用定量描述分析法，以9点数字标度为评分标尺。
  8. 一种基于电子舌的酱油滋味评价装置，其特征在于，包括：
    酱油样品感官评分信息获取模块，用于针对于获取到的各酱油样品，获取多个具有感官经验的人员所作出的各味觉参数的感官评分信息；各味觉参数包括酸、咸、苦、甜、鲜和饱满感；
    酱油样品味觉参数值获取模块，用于获取电子舌针对各酱油样品采集到的各味觉参数值；
    味觉参数感官评价模型建立模块，用于根据各酱油样品的各味觉参数的感 官评分以及各味觉参数值，采用偏最小二乘法分析酱油的各味觉参数的感官评分与各味觉参数值的相关性，从而建立酱油的各味觉参数感官评价模型；
    待测酱油味觉参数值获取模块，用于获取电子舌针对待测酱油采集到的各味觉参数值；
    味觉参数感官评价模块，用于将待测酱油的各味觉参数值代入到酱油的各味觉参数感官评价模型中，得到各味觉参数的感官评分。
  9. 一种存储介质，存储有程序，其特征在于，所述程序被处理器执行时，实现如下操作：
    针对于获取到的各酱油样品，获取多个具有感官经验的人员所作出的各味觉参数的感官评分信息；
    获取电子舌针对各酱油样品采集到的各味觉参数值；
    根据各酱油样品的各味觉参数的感官评分以及各味觉参数值，采用偏最小二乘法分析酱油的各味觉参数的感官评分与各味觉参数值的相关性，从而建立酱油的各味觉参数感官评价模型；
    获取电子舌针对待测酱油采集到的各味觉参数值；
    将待测酱油的各味觉参数值代入到酱油的各味觉参数感官评价模型中，得到各味觉参数的感官评分。
  10. 一种计算设备，包括处理器以及用于存储处理器可执行程序的存储器，其特征在于：所述处理器执行存储器存储的程序时，实现如下操作：
    针对于获取到的各酱油样品，获取多个具有感官经验的人员所作出的各味觉参数的感官评分信息；
    获取电子舌针对各酱油样品采集到的各味觉参数值；
    根据各酱油样品的各味觉参数的感官评分以及各味觉参数值，采用偏最小二乘法分析酱油的各味觉参数的感官评分与各味觉参数值的相关性，从而建立酱油的各味觉参数感官评价模型；
    获取电子舌针对待测酱油采集到的各味觉参数值；
    将待测酱油的各味觉参数值代入到酱油的各味觉参数感官评价模型中，得到各味觉参数的感官评分。
PCT/CN2019/112052 2019-03-20 2019-10-18 基于电子舌的酱油滋味评价方法、装置、介质和计算设备 Ceased WO2020186746A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910211972.8 2019-03-20
CN201910211972.8A CN109991368B (zh) 2019-03-20 2019-03-20 基于电子舌的酱油滋味评价方法、装置、介质和计算设备

Publications (1)

Publication Number Publication Date
WO2020186746A1 true WO2020186746A1 (zh) 2020-09-24

Family

ID=67129674

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/112052 Ceased WO2020186746A1 (zh) 2019-03-20 2019-10-18 基于电子舌的酱油滋味评价方法、装置、介质和计算设备

Country Status (2)

Country Link
CN (1) CN109991368B (zh)
WO (1) WO2020186746A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117030810A (zh) * 2023-06-26 2023-11-10 江苏省农业科学院 一种菜用大豆鲜味口感的评价方法

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109991368B (zh) * 2019-03-20 2020-09-22 华南理工大学 基于电子舌的酱油滋味评价方法、装置、介质和计算设备
CN111475936B (zh) * 2020-04-03 2024-05-17 东北电力大学 一种基于味觉感知模型的味觉识别方法
CN111579724B (zh) * 2020-06-01 2022-07-12 中国标准化研究院 一种麻和辣阈上感觉敏感度快速分类方法、装置及应用
CN112348232A (zh) * 2020-10-15 2021-02-09 上海交通大学 一种基于bp神经网络预测食品感官鲜味强度的方法
CN113609775B (zh) * 2021-08-09 2024-04-23 上海太太乐食品有限公司 固态复合调味料鲜美度生津感感官评价分值的定量预报方法
CN117007645A (zh) * 2023-06-30 2023-11-07 江苏省农业科学院 一种菜用大豆籽粒甜味的评价方法
CN117007644A (zh) * 2023-06-30 2023-11-07 江苏省农业科学院 一种鲜食大豆籽粒食用品质的评价方法
CN118858548B (zh) * 2024-09-14 2025-01-03 浙江大学 基于生物感知的特异性数字化评价味觉信息的方法及系统
CN119251764B (zh) * 2024-09-26 2025-06-13 华南理工大学 基于监测宠物进食量的神经网络健康状况分析方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040191918A1 (en) * 2003-03-28 2004-09-30 Sandrine Isz Evaluation of bitterness of active drugs
CN103837587A (zh) * 2014-03-17 2014-06-04 上海应用技术学院 一种利用电子舌系统对杨梅汁味感快速品评的方法
CN106970191A (zh) * 2017-03-10 2017-07-21 北京工商大学 一种采用智舌系统对白酒原酒快速分级的方法
CN109991368A (zh) * 2019-03-20 2019-07-09 华南理工大学 基于电子舌的酱油滋味评价方法、装置、介质和计算设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103399050B (zh) * 2013-07-15 2015-02-25 浙江大学 一种基于口感信息快速评定人参掺假西洋参的方法
CN107727711A (zh) * 2017-10-12 2018-02-23 青岛啤酒股份有限公司 一种啤酒酒体饱满性的评价方法
CN107741439A (zh) * 2017-10-12 2018-02-27 青岛啤酒股份有限公司 一种啤酒酒体圆润性的评价方法
CN108303503A (zh) * 2018-01-05 2018-07-20 中国食品发酵工业研究院有限公司 葡萄酒味觉的评价方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040191918A1 (en) * 2003-03-28 2004-09-30 Sandrine Isz Evaluation of bitterness of active drugs
CN103837587A (zh) * 2014-03-17 2014-06-04 上海应用技术学院 一种利用电子舌系统对杨梅汁味感快速品评的方法
CN106970191A (zh) * 2017-03-10 2017-07-21 北京工商大学 一种采用智舌系统对白酒原酒快速分级的方法
CN109991368A (zh) * 2019-03-20 2019-07-09 华南理工大学 基于电子舌的酱油滋味评价方法、装置、介质和计算设备

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
HUANG, XINGYI ET AL.: "Quantitative Evaluation of Orange Juice Sensory Quality Using Electronic Tongue", MODERN FOOD SCIENCE AND TECHNOLOGY, vol. 30, no. 5, 30 May 2014 (2014-05-30), DOI: 20191230163759A *
WANG, DANDAN ET AL.: "Taste Characterization of Commercial Light Soy Sauce by Electronic Tongue Analysis", FOOD AND FERMENTATION INDUSTRIES, vol. 43, no. 6, 30 June 2017 (2017-06-30), DOI: 20191230163624Y *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117030810A (zh) * 2023-06-26 2023-11-10 江苏省农业科学院 一种菜用大豆鲜味口感的评价方法

Also Published As

Publication number Publication date
CN109991368B (zh) 2020-09-22
CN109991368A (zh) 2019-07-09

Similar Documents

Publication Publication Date Title
CN109991368B (zh) 基于电子舌的酱油滋味评价方法、装置、介质和计算设备
CN102222164A (zh) 一种食品感官质量评价方法及系统
CN104677875B (zh) 一种三维荧光光谱结合平行因子鉴别不同品牌白酒的方法
CN109490306B (zh) 一种基于色泽和气味数据融合的猪肉新鲜度检测方法
CN105427275B (zh) 大田环境麦穗计数方法及装置
Yang et al. A machine learning method for juice human sensory hedonic prediction using electronic sensory features
CN108760655A (zh) 一种苹果味觉图谱信息可视化方法
CN105588863A (zh) 基于味觉传感器阵列的牛肉味觉品质检测方法
CN110210680A (zh) 一种基于温度变化的鱼体新鲜度检测方法和装置
CN105606473B (zh) 一种基于机器视觉的红提葡萄硬度无损检测方法
CN103558167A (zh) 一种快速测定腌肉中氯化钠含量的方法
Wang et al. Electronic tongue for food sensory evaluation
CN104122308A (zh) 基于电子舌检测的差别度计算方法及茶叶品质鉴别方法
CN106295801B (zh) 一种基于果蝇算法优化广义回归神经网络算法的茶叶储存时间分类方法
CN118966484B (zh) 食品风味特征预测方法、装置、电子设备及存储介质
CN114970675A (zh) 基于特征选择的人工鼻冰箱食物新鲜度检测系统和方法
CN109991367A (zh) 基于电子舌的酱油理化成分检测方法、装置、介质和设备
Morin et al. Use of experienced panelists and the projective mapping task in comparison to trained panelists and naïve consumers
CN113504198A (zh) 一种苋菜红色素浓度检测方法、装置及存储介质
CN110648061A (zh) 农产品感官品质评价系统及方法
CN111461529B (zh) 用于生鲜水产品的品质协同评价方法及系统
Alejandrino et al. Bioimpedance spectroscopy tool with embedded hybrid PCA-SVM model for post-harvest carrot decay detection
CN106970191A (zh) 一种采用智舌系统对白酒原酒快速分级的方法
CN120892948A (zh) 基于多模态融合的烤鸡食用品质分级智能判定方法
CN106682695A (zh) 一种基于支持向量机的县域耕地自然质量评价方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19920497

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19920497

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 21.01.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19920497

Country of ref document: EP

Kind code of ref document: A1