CN117894385A - Vinegar fermentation detection method and system based on component analysis technology - Google Patents
Vinegar fermentation detection method and system based on component analysis technology Download PDFInfo
- Publication number
- CN117894385A CN117894385A CN202410288174.6A CN202410288174A CN117894385A CN 117894385 A CN117894385 A CN 117894385A CN 202410288174 A CN202410288174 A CN 202410288174A CN 117894385 A CN117894385 A CN 117894385A
- Authority
- CN
- China
- Prior art keywords
- vinegar
- sample
- index
- characteristic
- target
- 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.)
- Granted
Links
- 235000021419 vinegar Nutrition 0.000 title claims abstract description 275
- 239000000052 vinegar Substances 0.000 title claims abstract description 275
- 238000001514 detection method Methods 0.000 title claims abstract description 135
- 238000000855 fermentation Methods 0.000 title claims abstract description 127
- 230000004151 fermentation Effects 0.000 title claims abstract description 127
- 238000004458 analytical method Methods 0.000 title claims abstract description 50
- 238000005516 engineering process Methods 0.000 title claims abstract description 13
- 239000002994 raw material Substances 0.000 claims abstract description 61
- 238000000034 method Methods 0.000 claims abstract description 47
- 238000005259 measurement Methods 0.000 claims abstract description 39
- 238000012300 Sequence Analysis Methods 0.000 claims abstract description 16
- 230000007613 environmental effect Effects 0.000 claims abstract description 16
- 239000002245 particle Substances 0.000 claims description 66
- 230000001360 synchronised effect Effects 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000013075 data extraction Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 2
- 238000012731 temporal analysis Methods 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 6
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 239000012467 final product Substances 0.000 description 2
- 239000012535 impurity Substances 0.000 description 2
- 230000000813 microbial effect Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000003442 weekly effect Effects 0.000 description 2
- 102000004190 Enzymes Human genes 0.000 description 1
- 108090000790 Enzymes Proteins 0.000 description 1
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000003851 biochemical process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 235000019634 flavors Nutrition 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 235000011194 food seasoning agent Nutrition 0.000 description 1
- 230000035784 germination Effects 0.000 description 1
- 238000004949 mass spectrometry Methods 0.000 description 1
- 239000002207 metabolite Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 210000005253 yeast cell Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Chemical & Material Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Computing Systems (AREA)
- Distillation Of Fermentation Liquor, Processing Of Alcohols, Vinegar And Beer (AREA)
Abstract
The invention discloses a vinegar fermentation detection method and system based on a component analysis technology, and relates to the field of vinegar detection. The method comprises the following steps: collecting raw material information and basic environment information of target vinegar; searching in a vinegar fermentation detection warehouse by taking a raw material quality measurement result and an environmental temperature as indexes to obtain a first index influence factor; matching the first detection period based on the first index influencing factor; performing component analysis on Q vinegar samples of the target vinegar to obtain Q vinegar sample characteristic sequence sets; performing double-term time sequence analysis to obtain a first fermentation detection result; the stability is identified by a stability identifier, and a first stability factor is obtained; judging whether the first stability factor meets the preset stability factor, and if so, taking the first fermentation detection result as a target fermentation detection result. Solves the technical problem of poor reliability of the vinegar detection result in the prior art, and achieves the technical effect of improving the vinegar production quality.
Description
Technical Field
The invention relates to the field of vinegar detection, in particular to a vinegar fermentation detection method and system based on a component analysis technology.
Background
In the modern food industry, vinegar is an important seasoning, and quality control and fermentation detection in the production process are particularly important. Fermentation of vinegar is a complex biochemical process that is affected by a variety of factors, including the quality of the raw materials, the ambient temperature, etc., and basic environmental information. In the traditional vinegar fermentation process, the quality control often depends on manual experience and intuitive judgment, and a detection method and a standardized flow of a system are lacked. This results in poor reliability of the detection results of vinegar fermentation, thus making the quality fluctuation large, and it is difficult to ensure the consistency and stability of each batch of products. Meanwhile, the traditional fermentation process monitoring means are relatively backward, so that key parameter changes in the fermentation process cannot be mastered timely and accurately, and potential problems are difficult to early warn and intervene timely.
Disclosure of Invention
The embodiment of the application provides a vinegar fermentation detection method and a vinegar fermentation detection system based on a component analysis technology, which solve the technical problem of poor reliability of a vinegar detection result in the prior art.
In view of the above problems, the embodiment of the application provides a vinegar fermentation detection method and system based on a component analysis technology.
In a first aspect of the embodiment of the present application, there is provided a vinegar fermentation detection method based on a component analysis technique, the method comprising:
Collecting raw material information and basic environment information of target vinegar, wherein the basic environment information comprises an environment temperature, and the raw material information comprises a raw material quality measurement result;
searching in a vinegar fermentation detection library by taking the raw material quality measurement result and the environmental temperature as indexes to obtain a first index influence factor;
Matching a first detection period based on the first index influencing factor;
Sequentially carrying out component analysis on Q vinegar samples of target vinegar according to a preset characteristic index set according to a time sequence according to the first detection period to obtain Q vinegar sample characteristic sequence sets, wherein each vinegar sample characteristic sequence set comprises M vinegar characteristic sequences, and each vinegar characteristic sequence corresponds to one characteristic index in the preset characteristic index set;
performing double-term time sequence analysis on the Q vinegar sample feature sequence sets to obtain a first fermentation detection result of the target vinegar;
The stability of the Q vinegar sample feature sequence sets is identified by a stability identifier, and a first stability factor is obtained;
Judging whether the first stability factor meets a preset stability factor, and if so, taking the first fermentation detection result as a target fermentation detection result.
In a second aspect of the embodiment of the present application, there is provided a vinegar fermentation detection system based on a component analysis technique, the system comprising:
The information acquisition module is used for acquiring raw material information and basic environment information of the target vinegar, wherein the basic environment information comprises an environment temperature, and the raw material information comprises a raw material quality measurement result;
The retrieval module is used for retrieving in a vinegar fermentation detection library by taking the raw material quality measurement result and the environmental temperature as indexes to obtain a first index influence factor;
the matching module is used for matching a first detection period based on the first index influence factor;
The component analysis module is used for sequentially carrying out component analysis on Q vinegar samples of the target vinegar according to a preset characteristic index set according to the first detection period and the time sequence to obtain Q vinegar sample characteristic sequence sets, wherein each vinegar sample characteristic sequence set comprises M vinegar characteristic sequences, and each vinegar characteristic sequence corresponds to one characteristic index in the preset characteristic index set;
The time sequence analysis module is used for performing double-term time sequence analysis on the Q vinegar sample feature sequence sets to obtain a first fermentation detection result of the target vinegar;
the identification module is used for identifying the stability of the Q vinegar sample feature sequence sets by using a stability identifier to obtain a first stability factor;
And the judging module is used for judging whether the first stability factor meets a preset stability factor or not, and if so, taking the first fermentation detection result as a target fermentation detection result.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
And acquiring raw material information and basic environment information of the target vinegar to obtain a raw material quality measurement result and an environment temperature. And searching a vinegar fermentation detection library according to the raw material quality measurement result and the ambient temperature to obtain a first index influence factor, and matching the first detection period. And according to the period, sequentially carrying out component analysis on Q samples of the target vinegar to obtain a vinegar sample characteristic sequence set. And performing double-term time sequence analysis on the sample characteristic sequence sets to obtain a first fermentation detection result of the target vinegar. And then, the stability of the sample characteristic sequence set is identified by a stability identifier, and a first stability factor is obtained. And finally, judging whether the first stability factor meets the preset stability factor, and if so, taking the first fermentation detection result as a target fermentation detection result. Solves the technical problem of poor reliability of the vinegar detection result in the prior art, and achieves the technical effect of improving the vinegar production quality.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a vinegar fermentation detection method based on a component analysis technology according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a vinegar fermentation detection system based on a component analysis technology according to an embodiment of the present application.
Reference numerals illustrate: the system comprises an information acquisition module 11, a retrieval module 12, a matching module 13, a component analysis module 14, a time sequence analysis module 15, an identification module 16 and a judgment module 17.
Detailed Description
The embodiment of the application solves the technical problem of poor reliability of the vinegar detection result in the prior art by providing the vinegar fermentation detection method and the vinegar fermentation detection system based on the component analysis technology.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "comprises" and "comprising," along with any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the embodiment of the application provides a vinegar fermentation detection method based on a component analysis technology, wherein the method comprises the following steps:
Collecting raw material information and basic environment information of target vinegar, wherein the basic environment information comprises an environment temperature, and the raw material information comprises a raw material quality measurement result;
In the production process of vinegar, raw material information and basic environment information are key factors affecting the quality of the final product. In order to ensure the quality stability of the vinegar and the controllability of the fermentation process, accurate and comprehensive acquisition of the basic information is required. The quality measurement result of the raw material comprises the indexes of chemical component analysis (such as sugar, protein, fat and the like), microbial pollution, moisture content, impurity content and the like of the raw material. Fluctuations in ambient temperature may affect fermentation rate, microbial population balance, and metabolite production, thereby significantly affecting the flavor and quality of vinegar.
Searching in a vinegar fermentation detection library by taking the raw material quality measurement result and the environmental temperature as indexes to obtain a first index influence factor;
The vinegar fermentation detection library is a database system integrating a large amount of historical data, fermentation experience and scientific knowledge, can simulate and analyze fermentation processes of various raw materials and environmental conditions, and provides corresponding index influence factors. And searching in a vinegar fermentation detection warehouse by using the raw material quality measurement result and the environmental temperature to obtain a first index influence factor. The first index influencing factor is capable of quantifying the extent to which the feedstock and environmental factors influence the fermentation process.
Further, the method comprises the steps of:
obtaining quality measurement results of a plurality of sample raw materials, a plurality of sample environment temperatures and a plurality of sample index influence factors to construct a plurality of sample particles in the vinegar fermentation detection library;
Inputting the raw material quality measurement result and the ambient temperature into the vinegar fermentation detection warehouse to obtain target particles;
Based on the position of the target particle in the vinegar fermentation detection library, matching k sample particles closest to the target particle;
And analyzing based on the k sample particles to generate the first index influence factor.
In the process of constructing a vinegar fermentation detection library and generating a first index influence factor, raw material quality measurement results of a plurality of samples are required to be collected, wherein the raw material quality measurement results comprise data of chemical components, purity, impurity content and the like of raw materials, meanwhile, the corresponding environment temperature of each sample is recorded, and then the sample index influence factor is calculated through the collected data. The raw material quality measurement results, the ambient temperature and the index influence factors are combined to construct a plurality of sample particles in the vinegar fermentation detection warehouse. Each sample particle represents a specific fermentation condition and its corresponding set of influencing factors. When new raw material quality measurement results and environmental temperature data exist, the data are input into a vinegar fermentation detection warehouse, and target particles which represent specific states under the current production conditions are obtained. Next, the system searches through the existing sample particles to find k sample particles closest to the target particle, which provide information on the historical fermentation conditions and influence factors most similar to the target particle. Finally, a first index influencing factor is generated by a weighted average based on the index influencing factors of the k matched sample particles.
Further, the method further comprises:
taking a raw material quality measurement result as an x-axis of the vinegar fermentation detection warehouse and taking an ambient temperature as a y-axis of the vinegar fermentation detection warehouse, and constructing a frame of the vinegar fermentation detection warehouse;
inputting the quality measurement results of the plurality of sample raw materials and the environmental temperatures of the plurality of samples into a frame of the vinegar fermentation detection warehouse to obtain a plurality of initial sample particles;
And carrying out data identification on the initial sample particles by using a plurality of sample index influence factors to obtain a plurality of sample particles.
In constructing a vinegar fermentation test library, a two-dimensional framework can be created for efficient organization and management of data, wherein the raw material quality measurement result and the ambient temperature are respectively taken as an x-axis and a y-axis, and each point (x, y) in the coordinate system represents a specific combination of the raw material quality measurement result and the ambient temperature. A plurality of sample raw material quality measurement results and a plurality of sample environment temperatures are input into a framework of a vinegar fermentation detection warehouse, and each sample data form an initial sample particle, and the position of the initial sample particle in a coordinate system is determined by the raw material quality measurement results and the environment temperatures. For each initial sample particle, data identification is performed by using its corresponding sample index influence factor, for example, adding an additional dimension (such as color, size or label) in the coordinate system to represent the value of these influence factors. Upon completion of the identification, the initial sample particles are converted into sample particles with a richer information content, which particles are indicative of not only the raw materials and environmental conditions, but also the corresponding fermentation performance data.
Further, the method further comprises:
the identification information of the k sample particles is called to obtain k sample index influence factors;
Respectively calculating the inverse of the ratio of the distances from the k sample particles to the target particles to the sum of the distances from the k sample particles to the target particles to obtain k distance coefficients;
and weighting and calculating k sample index influence factors by using k distance coefficients, so as to obtain the first index influence factor.
The identification information of k sample particles closest to the target particles determined before is called from the vinegar fermentation detection library, and the identification information contains index influence factors of each sample particle, so that k sample index influence factors can be obtained. For each sample particle, calculating the ratio of the distance from the sample particle to the target particle to the sum of the distances from all k sample particles to the target particle, and taking the reciprocal of the ratio to obtain a distance coefficient. Sample particles with a larger distance coefficient indicate that they are closer to the target particle and will have a larger weight in the subsequent calculation. And finally, giving different weights to each sample index influence factor according to the corresponding distance coefficient, and carrying out weighted calculation on the k sample index influence factors by using the obtained k distance coefficients. The result of the weighted calculation is that the weighted average of all sample index influencing factors is the first index influencing factor.
Matching a first detection period based on the first index influencing factor;
In the vinegar fermentation process, the first index influence factor is a quantitative index for comprehensively evaluating the current fermentation condition. Based on this influencing factor, a corresponding first detection period can be adapted to ensure that monitoring and adjustment of the fermentation process can be performed in time. In general, when the first index influencing factor is higher, meaning that the current fermentation conditions may have a larger influence on the quality of the final product, for example, when the quality of the base raw material is poor, the first index influencing factor will be higher, thus requiring more frequent detection; conversely, when the influence factor is low, the detection frequency can be appropriately reduced. Specifically, several detection period thresholds are set, each corresponding to a different detection frequency, for example, three thresholds of high, medium and low may be set, and each corresponding to a different frequency such as daily detection, every other day detection and weekly detection. And comparing the calculated first index influence factor with a set detection period threshold value to determine the detection period which should be adopted under the current fermentation condition. If the impact factor is above a high threshold, selecting the highest frequency detection period (e.g., daily detection); if the impact factor is below the low threshold, selecting the lowest frequency detection period (e.g., weekly detection); if the impact factor is between the two thresholds, then a medium frequency detection period (e.g., alternate day detection) is selected.
Sequentially carrying out component analysis on Q vinegar samples of target vinegar according to a preset characteristic index set according to a time sequence according to the first detection period to obtain Q vinegar sample characteristic sequence sets, wherein each vinegar sample characteristic sequence set comprises M vinegar characteristic sequences, and each vinegar characteristic sequence corresponds to one characteristic index in the preset characteristic index set;
In the vinegar fermentation process, according to the determined first detection period, the target vinegar is subjected to periodic component analysis according to the set time sequence. Specifically, a set of characteristic indexes including a plurality of key characteristic indexes for evaluating vinegar samples including moisture, acidity, saccharifying enzyme activity, yeast cell number, germination rate, reducing sugar, alcohol degree, etc. is preset. Q samples of the target vinegar are sequentially collected in time sequence according to the first detection period, each sample representing the vinegar status at a specific point in time. Each collected vinegar sample is subjected to component analysis, and various characteristic indexes in the sample can be measured by adopting a method such as mass spectrometry analysis and the like. After each sample is analyzed, the obtained characteristic index data are arranged into a characteristic sequence. Each vinegar sample characteristic sequence set comprises M vinegar characteristic sequences, and each characteristic sequence corresponds to a specific characteristic index in a preset characteristic index set. Thus, for Q vinegar samples, Q sets of vinegar sample feature sequences will ultimately be obtained, each set reflecting the performance of the corresponding sample on a plurality of feature indicators.
Performing double-term time sequence analysis on the Q vinegar sample feature sequence sets to obtain a first fermentation detection result of the target vinegar;
After Q vinegar sample feature sequence sets are obtained, a two-term time sequence analysis is performed on the feature sequence sets to obtain a first fermentation detection result of the target vinegar. The double-term time sequence analysis is analysis in two directions, one is analysis on fermentation uniformity of a plurality of vinegar samples in the same time period; the other is to analyze the fermentation level of the whole sample at the last moment. And combining the results of the two analyses to obtain a first fermentation detection result of the target vinegar.
Further, performing a two-term time sequence analysis on the Q vinegar sample feature sequence sets to obtain a first fermentation detection result of the target vinegar, and the method further includes:
Carrying out simultaneous sequence deviation degree analysis on the Q vinegar sample feature sequence sets to obtain Q vinegar simultaneous sequence deviation degrees;
Extracting the vinegar sample characteristics of the last moment of the Q vinegar sample characteristic sequence sets, and carrying out concentrated trend analysis on Q vinegar sample characteristic index values obtained by extraction to obtain target vinegar sample characteristic index values;
And taking the Q vinegar synchronous sequence deviation degrees and the target vinegar sample characteristic index value as the first fermentation detection result.
The same-time sequence deviation degree analysis is performed on the Q vinegar sample characteristic sequence sets, which means that differences between characteristic index values of different samples at the same time point (i.e., same time sequence) are to be compared. By calculating the standard deviation of the characteristic index values of the samples at each moment, the dispersion degree of different samples in the same fermentation stage can be quantified. The vinegar sample characteristics at the last moment (namely at or near the end of fermentation) are extracted from the Q vinegar sample characteristic sequence sets. And carrying out concentrated trend analysis on the Q vinegar sample characteristic index values at the last time of extraction, such as calculating an average value, a median and the like, so as to obtain a target vinegar sample characteristic index value, wherein the characteristic index value reflects the typical characteristic performance of all samples at the end of fermentation. And integrating the Q vinegar synchronous sequence deviation degrees and the target vinegar sample characteristic index values to serve as a first fermentation detection result.
Further, the method further comprises:
Carrying out synchronous sequence data extraction on the Q vinegar sample feature sequence sets to obtain P synchronous sequence sample data sets, wherein each synchronous sequence sample data set comprises M vinegar feature index values;
Calculating the deviation degree of the vinegar characteristic indexes by traversing the P synchronous sequence sample data sets to obtain P index deviation degree sets, wherein each index deviation degree set comprises the deviation degree of M vinegar characteristic indexes in each synchronous sequence sample data set;
respectively carrying out average value processing on the P index deviation degree sets to obtain P simultaneous sequence deviation degrees;
And carrying out weighted calculation on the P pieces of the synchronous sequence deviation degree to obtain Q pieces of the synchronous sequence deviation degree of the vinegar.
And extracting data from the Q vinegar sample feature sequence sets according to the same time sequence points to form P simultaneous sample data sets. P represents different time points or phases in the time series, each simultaneous sample dataset containing M vinegar characteristic index values for all Q samples at that time point. Traversing the P simultaneous sample data sets, calculating the deviation degree of the M vinegar characteristic indexes in each data set, and calculating the average value of each characteristic index value relative to the indexes in all samples, wherein statistics such as standard deviation, absolute deviation and the like are used. Thus, P index deviation degree sets are obtained, and each set contains deviation degrees of M table vinegar characteristic indexes at corresponding time points. And carrying out mean value processing on the deviation degree in each index deviation degree set, namely calculating the mean value of all the characteristic index deviation degrees in each set to obtain a single simultaneous sequence deviation degree value which represents the overall level of all the characteristic index deviation degrees at the time point. P simultaneous sequence bias degrees are obtained, each bias degree corresponding to a specific time point or stage in the time sequence. And carrying out weighted calculation on the P pieces of the simultaneous sequence deviation degree to obtain the final Q pieces of the simultaneous sequence deviation degree of the edible vinegar.
Further, the method further comprises:
Calculating the average value of the characteristic index values of the Q vinegar samples to obtain the average value of the characteristic index values of the vinegar samples;
Taking the vinegar sample characteristic index mean value as an index, and searching among the Q vinegar sample characteristic index values according to a preset concentration step length to obtain a first vinegar sample characteristic index set mean value;
judging whether the concentration degree of the vinegar sample characteristic index mean value is larger than that of the first vinegar sample characteristic index set median value, if so, updating the vinegar sample characteristic index mean value into the first vinegar sample characteristic set median value according to a certain probability;
And continuing to search by taking the median value of the first vinegar sample index feature set as an index until the preset search times are met, and taking the median value of the first vinegar sample index feature set corresponding to the maximum value of the concentration degree in the search process as a target vinegar sample feature index value.
In order to determine a representative target vinegar sample characteristic index value during vinegar fermentation, an iterative search and comparison concentration method may be employed. Specifically, the average value of the characteristic index values of the Q vinegar samples is calculated, and the characteristic index average value of the vinegar samples is obtained. And taking the average value of the characteristic indexes of the vinegar samples as an index, and searching among the Q characteristic indexes of the vinegar samples according to a preset concentrated step length. The concentrated step length is the self-set distance moved during searching, namely the difference value from the characteristic index mean value of the vinegar sample. The purpose of the search is to find a more concentrated value, i.e. the value in the first vinegar sample characteristic index set, which has a higher concentration in the raw data than the current mean. And comparing the concentration of the characteristic index mean value of the vinegar sample with the concentration of the characteristic index mean value of the first vinegar sample. The concentration degree is the ratio of the number of index values in an area constructed by taking the characteristic index mean value of the vinegar sample as a center and taking the preset concentration step length as a radius to the area of the area, and reflects the density of the aggregation index values around the characteristic index mean value of the vinegar sample, and the larger the concentration degree is, the more representative the corresponding index value is. If the concentration of the value in the first vinegar sample characteristic index set is higher, updating the vinegar sample characteristic index mean value to the value in the higher concentration according to a certain probability. And taking the updated value in the index feature set of the first table vinegar sample as a new index, and continuing to search for the value in the next more set. And repeating the process, updating the index value every iteration, and comparing the concentration degree of the newly found concentration value with the concentration degree of the current index value until the preset search times are met. And after the iterative search is finished, taking the median value of the first vinegar sample index feature set corresponding to the maximum value of the concentration degree in the search process as a target vinegar sample feature index value.
The stability of the Q vinegar sample feature sequence sets is identified by a stability identifier, and a first stability factor is obtained;
In order to evaluate the stability of different sample feature sequence sets during vinegar fermentation, the stability identifier may be used for analysis. A stable identifier suitable for characteristics of vinegar fermentation data can be constructed based on the neural network model, and Q vinegar sample feature sequence sets are provided as input to the stable identifier. The stability identifier analyzes the data in each feature sequence set, searches for a stable pattern, trend, or periodic variation, and generates a first stability factor based on the analysis. The first stability factor was used to evaluate the stability of the vinegar fermentation process.
Judging whether the first stability factor meets a preset stability factor, and if so, taking the first fermentation detection result as a target fermentation detection result.
Before analysis of the fermentation process can be performed, a stabilization factor needs to be preset that reflects an acceptable level of stability during the fermentation process of the vinegar. And comparing the calculated first stability factor with a preset stability factor standard. If the first stability factor meets or exceeds a preset stability factor criterion, indicating that the stability of the vinegar sample characteristic sequence set is within an acceptable range, then the current fermentation process is deemed stable. If the first stability factor is below a preset criterion, this may mean that there is an unstable factor or potential problem in the fermentation process. If the first stability factor meets the preset stability factor, the first fermentation detection result obtained before can be used as a final target fermentation detection result.
In summary, the embodiment of the application has at least the following technical effects:
And acquiring raw material information and basic environment information of the target vinegar to obtain a raw material quality measurement result and an environment temperature. And searching a vinegar fermentation detection library according to the raw material quality measurement result and the ambient temperature to obtain a first index influence factor, and matching the first detection period. And according to the period, sequentially carrying out component analysis on Q samples of the target vinegar to obtain a vinegar sample characteristic sequence set. And performing double-term time sequence analysis on the sample characteristic sequence sets to obtain a first fermentation detection result of the target vinegar. And then, the stability of the sample characteristic sequence set is identified by a stability identifier, and a first stability factor is obtained. And finally, judging whether the first stability factor meets the preset stability factor, and if so, taking the first fermentation detection result as a target fermentation detection result. Solves the technical problem of poor reliability of the vinegar detection result in the prior art, and achieves the technical effect of improving the vinegar production quality.
Example two
Based on the same inventive concept as the vinegar fermentation detection method based on the component analysis technology in the foregoing embodiments, as shown in fig. 2, the present application provides a vinegar fermentation detection system based on the component analysis technology, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. Wherein, the system includes:
The information acquisition module 11 is used for acquiring raw material information and basic environment information of the target vinegar, wherein the basic environment information comprises an environment temperature, and the raw material information comprises a raw material quality measurement result;
The retrieval module 12 is used for retrieving in a vinegar fermentation detection library by taking the raw material quality measurement result and the environmental temperature as indexes to obtain a first index influence factor;
A matching module 13, wherein the matching module 13 is configured to match a first detection period based on the first index influence factor;
The component analysis module 14 is configured to sequentially perform component analysis on Q vinegar samples of the target vinegar according to a preset feature index set according to the first detection period and time sequence, so as to obtain Q vinegar sample feature sequence sets, where each vinegar sample feature sequence set includes M vinegar feature sequences, and each vinegar feature sequence corresponds to one feature index in the preset feature index set;
The time sequence analysis module 15 is used for performing double-term time sequence analysis on the Q vinegar sample feature sequence sets to obtain a first fermentation detection result of the target vinegar;
The identification module 16 is configured to identify stability of the Q vinegar sample feature sequence sets by using a stability identifier, so as to obtain a first stability factor;
The judging module 17 is configured to judge whether the first stability factor meets a preset stability factor, if yes, taking the first fermentation detection result as a target fermentation detection result.
Further, the retrieving module 12 is configured to perform the following method:
obtaining quality measurement results of a plurality of sample raw materials, a plurality of sample environment temperatures and a plurality of sample index influence factors to construct a plurality of sample particles in the vinegar fermentation detection library;
Inputting the raw material quality measurement result and the ambient temperature into the vinegar fermentation detection warehouse to obtain target particles;
Based on the position of the target particle in the vinegar fermentation detection library, matching k sample particles closest to the target particle;
And analyzing based on the k sample particles to generate the first index influence factor.
Further, the retrieving module 12 is configured to perform the following method:
taking a raw material quality measurement result as an x-axis of the vinegar fermentation detection warehouse and taking an ambient temperature as a y-axis of the vinegar fermentation detection warehouse, and constructing a frame of the vinegar fermentation detection warehouse;
inputting the quality measurement results of the plurality of sample raw materials and the environmental temperatures of the plurality of samples into a frame of the vinegar fermentation detection warehouse to obtain a plurality of initial sample particles;
And carrying out data identification on the initial sample particles by using a plurality of sample index influence factors to obtain a plurality of sample particles.
Further, the retrieving module 12 is configured to perform the following method:
the identification information of the k sample particles is called to obtain k sample index influence factors;
Respectively calculating the inverse of the ratio of the distances from the k sample particles to the target particles to the sum of the distances from the k sample particles to the target particles to obtain k distance coefficients;
and weighting and calculating k sample index influence factors by using k distance coefficients, so as to obtain the first index influence factor.
Further, the timing analysis module 15 is configured to perform the following method:
Carrying out simultaneous sequence deviation degree analysis on the Q vinegar sample feature sequence sets to obtain Q vinegar simultaneous sequence deviation degrees;
Extracting the vinegar sample characteristics of the last moment of the Q vinegar sample characteristic sequence sets, and carrying out concentrated trend analysis on Q vinegar sample characteristic index values obtained by extraction to obtain target vinegar sample characteristic index values;
And taking the Q vinegar synchronous sequence deviation degrees and the target vinegar sample characteristic index value as the first fermentation detection result.
Further, the timing analysis module 15 is configured to perform the following method:
Carrying out synchronous sequence data extraction on the Q vinegar sample feature sequence sets to obtain P synchronous sequence sample data sets, wherein each synchronous sequence sample data set comprises M vinegar feature index values;
Calculating the deviation degree of the vinegar characteristic indexes by traversing the P synchronous sequence sample data sets to obtain P index deviation degree sets, wherein each index deviation degree set comprises the deviation degree of M vinegar characteristic indexes in each synchronous sequence sample data set;
respectively carrying out average value processing on the P index deviation degree sets to obtain P simultaneous sequence deviation degrees;
And carrying out weighted calculation on the P pieces of the synchronous sequence deviation degree to obtain Q pieces of the synchronous sequence deviation degree of the vinegar.
Further, the timing analysis module 15 is configured to perform the following method:
Calculating the average value of the characteristic index values of the Q vinegar samples to obtain the average value of the characteristic index values of the vinegar samples;
Taking the vinegar sample characteristic index mean value as an index, and searching among the Q vinegar sample characteristic index values according to a preset concentration step length to obtain a first vinegar sample characteristic index set mean value;
judging whether the concentration degree of the vinegar sample characteristic index mean value is larger than that of the first vinegar sample characteristic index set median value, if so, updating the vinegar sample characteristic index mean value into the first vinegar sample characteristic set median value according to a certain probability;
And continuing to search by taking the median value of the first vinegar sample index feature set as an index until the preset search times are met, and taking the median value of the first vinegar sample index feature set corresponding to the maximum value of the concentration degree in the search process as a target vinegar sample feature index value.
It should be noted that the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
The specification and figures are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. The vinegar fermentation detection method based on the component analysis technology is characterized by comprising the following steps of:
Collecting raw material information and basic environment information of target vinegar, wherein the basic environment information comprises an environment temperature, and the raw material information comprises a raw material quality measurement result;
searching in a vinegar fermentation detection library by taking the raw material quality measurement result and the environmental temperature as indexes to obtain a first index influence factor;
Matching a first detection period based on the first index influencing factor;
Sequentially carrying out component analysis on Q vinegar samples of target vinegar according to a preset characteristic index set according to a time sequence according to the first detection period to obtain Q vinegar sample characteristic sequence sets, wherein each vinegar sample characteristic sequence set comprises M vinegar characteristic sequences, and each vinegar characteristic sequence corresponds to one characteristic index in the preset characteristic index set;
performing double-term time sequence analysis on the Q vinegar sample feature sequence sets to obtain a first fermentation detection result of the target vinegar;
The stability of the Q vinegar sample feature sequence sets is identified by a stability identifier, and a first stability factor is obtained;
Judging whether the first stability factor meets a preset stability factor, and if so, taking the first fermentation detection result as a target fermentation detection result.
2. The method of claim 1, wherein the method further comprises:
obtaining quality measurement results of a plurality of sample raw materials, a plurality of sample environment temperatures and a plurality of sample index influence factors to construct a plurality of sample particles in the vinegar fermentation detection library;
Inputting the raw material quality measurement result and the ambient temperature into the vinegar fermentation detection warehouse to obtain target particles;
Based on the position of the target particle in the vinegar fermentation detection library, matching k sample particles closest to the target particle;
And analyzing based on the k sample particles to generate the first index influence factor.
3. The method of claim 2, wherein the method further comprises:
taking a raw material quality measurement result as an x-axis of the vinegar fermentation detection warehouse and taking an ambient temperature as a y-axis of the vinegar fermentation detection warehouse, and constructing a frame of the vinegar fermentation detection warehouse;
inputting the quality measurement results of the plurality of sample raw materials and the environmental temperatures of the plurality of samples into a frame of the vinegar fermentation detection warehouse to obtain a plurality of initial sample particles;
And carrying out data identification on the initial sample particles by using a plurality of sample index influence factors to obtain a plurality of sample particles.
4. The method of claim 2, wherein the method further comprises:
the identification information of the k sample particles is called to obtain k sample index influence factors;
Respectively calculating the inverse of the ratio of the distances from the k sample particles to the target particles to the sum of the distances from the k sample particles to the target particles to obtain k distance coefficients;
and weighting and calculating k sample index influence factors by using k distance coefficients, so as to obtain the first index influence factor.
5. The method of claim 1, wherein the Q vinegar sample feature sequence sets are subjected to a two-term temporal analysis to obtain a first fermentation test result for the target vinegar, the method further comprising:
Carrying out simultaneous sequence deviation degree analysis on the Q vinegar sample feature sequence sets to obtain Q vinegar simultaneous sequence deviation degrees;
Extracting the vinegar sample characteristics of the last moment of the Q vinegar sample characteristic sequence sets, and carrying out concentrated trend analysis on Q vinegar sample characteristic index values obtained by extraction to obtain target vinegar sample characteristic index values;
And taking the Q vinegar synchronous sequence deviation degrees and the target vinegar sample characteristic index value as the first fermentation detection result.
6. The method of claim 5, wherein the method further comprises:
Carrying out synchronous sequence data extraction on the Q vinegar sample feature sequence sets to obtain P synchronous sequence sample data sets, wherein each synchronous sequence sample data set comprises M vinegar feature index values;
Calculating the deviation degree of the vinegar characteristic indexes by traversing the P synchronous sequence sample data sets to obtain P index deviation degree sets, wherein each index deviation degree set comprises the deviation degree of M vinegar characteristic indexes in each synchronous sequence sample data set;
respectively carrying out average value processing on the P index deviation degree sets to obtain P simultaneous sequence deviation degrees;
And carrying out weighted calculation on the P pieces of the synchronous sequence deviation degree to obtain Q pieces of the synchronous sequence deviation degree of the vinegar.
7. The method of claim 5, wherein the method further comprises:
Calculating the average value of the characteristic index values of the Q vinegar samples to obtain the average value of the characteristic index values of the vinegar samples;
Taking the vinegar sample characteristic index mean value as an index, and searching among the Q vinegar sample characteristic index values according to a preset concentration step length to obtain a first vinegar sample characteristic index set mean value;
judging whether the concentration degree of the vinegar sample characteristic index mean value is larger than that of the first vinegar sample characteristic index set median value, if so, updating the vinegar sample characteristic index mean value into the first vinegar sample characteristic set median value according to a certain probability;
And continuing to search by taking the median value of the first vinegar sample index feature set as an index until the preset search times are met, and taking the median value of the first vinegar sample index feature set corresponding to the maximum value of the concentration degree in the search process as a target vinegar sample feature index value.
8. A vinegar fermentation detection system based on a component analysis technique, for implementing the vinegar fermentation detection method based on a component analysis technique according to any one of claims 1 to 7, the system comprising:
The information acquisition module is used for acquiring raw material information and basic environment information of the target vinegar, wherein the basic environment information comprises an environment temperature, and the raw material information comprises a raw material quality measurement result;
The retrieval module is used for retrieving in a vinegar fermentation detection library by taking the raw material quality measurement result and the environmental temperature as indexes to obtain a first index influence factor;
the matching module is used for matching a first detection period based on the first index influence factor;
The component analysis module is used for sequentially carrying out component analysis on Q vinegar samples of the target vinegar according to a preset characteristic index set according to the first detection period and the time sequence to obtain Q vinegar sample characteristic sequence sets, wherein each vinegar sample characteristic sequence set comprises M vinegar characteristic sequences, and each vinegar characteristic sequence corresponds to one characteristic index in the preset characteristic index set;
The time sequence analysis module is used for performing double-term time sequence analysis on the Q vinegar sample feature sequence sets to obtain a first fermentation detection result of the target vinegar;
the identification module is used for identifying the stability of the Q vinegar sample feature sequence sets by using a stability identifier to obtain a first stability factor;
And the judging module is used for judging whether the first stability factor meets a preset stability factor or not, and if so, taking the first fermentation detection result as a target fermentation detection result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410288174.6A CN117894385B (en) | 2024-03-14 | 2024-03-14 | Vinegar fermentation detection method and system based on component analysis technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410288174.6A CN117894385B (en) | 2024-03-14 | 2024-03-14 | Vinegar fermentation detection method and system based on component analysis technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117894385A true CN117894385A (en) | 2024-04-16 |
| CN117894385B CN117894385B (en) | 2024-06-07 |
Family
ID=90642673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410288174.6A Active CN117894385B (en) | 2024-03-14 | 2024-03-14 | Vinegar fermentation detection method and system based on component analysis technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117894385B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116804668A (en) * | 2023-08-23 | 2023-09-26 | 国盐检测(天津)有限责任公司 | Salt iodine content detection data identification method and system |
| CN117057644A (en) * | 2023-07-31 | 2023-11-14 | 智慧互通科技股份有限公司 | Equipment production quality detection method and system based on characteristic matching |
| CN117151657A (en) * | 2023-10-30 | 2023-12-01 | 南通顺裕包装材料有限公司 | Plastic packaging material management method and system |
-
2024
- 2024-03-14 CN CN202410288174.6A patent/CN117894385B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117057644A (en) * | 2023-07-31 | 2023-11-14 | 智慧互通科技股份有限公司 | Equipment production quality detection method and system based on characteristic matching |
| CN116804668A (en) * | 2023-08-23 | 2023-09-26 | 国盐检测(天津)有限责任公司 | Salt iodine content detection data identification method and system |
| CN117151657A (en) * | 2023-10-30 | 2023-12-01 | 南通顺裕包装材料有限公司 | Plastic packaging material management method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117894385B (en) | 2024-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109597968B (en) | SMT big data-based solder paste printing performance influence factor analysis method | |
| CN107368700A (en) | Based on the microbial diversity interaction analysis system and method for calculating cloud platform | |
| CN108875118B (en) | Method and device for evaluating accuracy of prediction model of silicon content of blast furnace molten iron | |
| CN111370067A (en) | LC/GC-MS-oriented metabonomics data quality control method and system | |
| CN114611582B (en) | Method and system for analyzing substance concentration based on near infrared spectrum technology | |
| CN117894385B (en) | Vinegar fermentation detection method and system based on component analysis technology | |
| CN116738214B (en) | Data dimension reduction preprocessing method based on high-order tensor | |
| CN116579842B (en) | Credit data analysis method and system based on user behavior data | |
| CN117370326A (en) | Data evaluation method, device, electronic equipment and medium | |
| CN113933334B (en) | Locust honey authenticity identification method based on feature selection and machine learning algorithm | |
| CN114944198B (en) | Fusion method for data of computer processing acquisition equipment | |
| CN115983468A (en) | Big data-based information prediction analysis method and system | |
| CN111060633B (en) | Method for establishing grease waste judgment model in frying process based on characteristic flavor components and waste judgment method | |
| CN111143436A (en) | Data mining method for big data | |
| CN118294407B (en) | Near infrared spectrum modeling sample screening method | |
| CN114660108A (en) | Method for quickly identifying years of white spirit | |
| US20230288384A1 (en) | Method for determining small molecule components of a complex mixture, and associated apparatus and computer program product | |
| CN118365251A (en) | Chemical material warehouse management system based on Internet of things | |
| Kovačević et al. | Predicting the Specific Gravity of Must During Fermentation Using Machine Learning Models | |
| CN118691134A (en) | Fruit and vegetable freeze-drying control method and system based on multi-stage quality detection | |
| Brincoveanu | Analysis of time series data and optimization of coffee roasting processes using machine learning techniques | |
| Xu | Data Handling | |
| CN118113575A (en) | SVM-based process knowledge management system retrieval performance prediction method | |
| CN118126801A (en) | Intelligent recognition method and system for vinegar fermentation state | |
| CN117871459A (en) | Mutton crude fat content determination method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |