CN118037134B - Characteristic information extraction method and system for donkey-hide gelatin cake production process - Google Patents
Characteristic information extraction method and system for donkey-hide gelatin cake production process Download PDFInfo
- Publication number
- CN118037134B CN118037134B CN202410430365.1A CN202410430365A CN118037134B CN 118037134 B CN118037134 B CN 118037134B CN 202410430365 A CN202410430365 A CN 202410430365A CN 118037134 B CN118037134 B CN 118037134B
- Authority
- CN
- China
- Prior art keywords
- temperature
- donkey
- production data
- vector
- hide gelatin
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 154
- 108010010803 Gelatin Proteins 0.000 title claims abstract description 104
- 229920000159 gelatin Polymers 0.000 title claims abstract description 104
- 239000008273 gelatin Substances 0.000 title claims abstract description 104
- 235000019322 gelatine Nutrition 0.000 title claims abstract description 104
- 235000011852 gelatine desserts Nutrition 0.000 title claims abstract description 104
- 238000000605 extraction Methods 0.000 title claims description 14
- 239000013598 vector Substances 0.000 claims abstract description 94
- 238000000034 method Methods 0.000 claims abstract description 49
- 230000006870 function Effects 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 15
- 238000003756 stirring Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 4
- 239000000047 product Substances 0.000 description 8
- 230000000694 effects Effects 0.000 description 6
- 238000010438 heat treatment Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000012163 sequencing technique Methods 0.000 description 4
- 230000036541 health Effects 0.000 description 3
- 239000002994 raw material Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000002844 melting Methods 0.000 description 2
- 230000008018 melting Effects 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 239000011550 stock solution Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Manufacturing & Machinery (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of data processing, in particular to a method and a system for extracting characteristic information in a donkey-hide gelatin cake production process, wherein the method comprises the following steps: obtaining a production data vector of donkey-hide gelatin cakes in each batch; constructing corresponding instability coefficients according to the data values of the production data vectors of each quality of each batch; obtaining the corresponding dissimilarity coefficient according to the sequence constructed by the production data vector; acquiring local weights of each production data under different qualities based on the local weights; obtaining a difference significance index according to the normalized vector of the production data, and obtaining the global weight of the production data; and extracting characteristic information according to the global weight and the local weight. Therefore, the main factors are strictly controlled, and the quality of the donkey-hide gelatin cake is higher and more controllable.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a characteristic information extraction method and system in a donkey-hide gelatin cake production process.
Background
Donkey-hide gelatin cake is used as a traditional Chinese medicine health care product, and has a long history and a deep cultural background in China. The donkey-hide gelatin is used as a main raw material, is prepared by combining a plurality of auxiliary materials according to a specific formula and process, and is widely considered to have a plurality of health care effects of enriching blood, nourishing skin, regulating body functions and the like. Along with the improvement of the living standard and the enhancement of health consciousness of people, the market demand of the donkey-hide gelatin cake is increased year by year, and the production process and the quality control of the donkey-hide gelatin cake are promoted to be hot spots for research. However, the production process of donkey-hide gelatin cake is complex, and involves various raw materials and links, so how to ensure the stability and high quality of each batch of products becomes an important challenge for industry.
In the production process of the donkey-hide gelatin cake, factors such as raw material selection, proportion, processing conditions and the like have decisive influence on the quality of the final product. The characteristic information extraction technology provides a new view angle to solve the problem, and key factors affecting the quality of the donkey-hide gelatin cake are more accurately identified by analyzing production data, so that powerful support is provided for optimizing the production process and improving the quality of products. However, the existing feature extraction method has some limitations in the donkey-hide gelatin cake production process, and many methods only pay attention to a certain link of the production process, neglect other factors possibly important as well, and the one-sided analysis mode is difficult to comprehensively reflect the real situation of the production process, and is more likely to cause misjudgment of product quality. Therefore, there is an urgent need for a more comprehensive and efficient feature information extraction method, which can consider multiple factors in the production process and accurately evaluate their influence on the quality of donkey-hide gelatin cake. The method is not only beneficial to improving the intelligentized level of donkey-hide gelatin cake production, but also provides powerful technical support for ensuring the product quality of the donkey-hide gelatin cake and meeting the market demand.
Disclosure of Invention
In order to solve the technical problems, the application aims to provide a characteristic information extraction method and a characteristic information extraction system for a donkey-hide gelatin cake production process, and the adopted technical scheme is as follows:
In a first aspect, an embodiment of the present application provides a method for extracting feature information in a donkey-hide gelatin cake production process, where the method includes the following steps:
obtaining a production data vector of donkey-hide gelatin cakes in each batch;
dividing the donkey-hide gelatin cake into three qualities, and forming a temperature sequence for all temperature vectors in any one quality; acquiring a temperature variation set and a temperature stability set according to data in the temperature vector; acquiring a temperature dissimilarity coefficient according to the cosine similarity and the number of temperature vectors in the temperature sequence; acquiring an instability coefficient of temperature according to elements in the temperature variation set and the temperature stability set; obtaining local weight of the temperature under any quality according to the instability coefficient and the dissimilarity coefficient of the temperature; obtaining local weights of each production data under different qualities according to a method for obtaining the significance coefficient of the temperature;
Normalizing the temperature sequences with different qualities, and acquiring a difference significance index of the temperature according to the normalized temperature sequences with different qualities; acquiring the difference significance index of the rest production data according to the mode of acquiring the difference significance index of the temperature; acquiring global weights of each production data according to the difference significance indexes of all the production data;
and extracting characteristic information according to the global weight of all production data and the local weight under different qualities.
Preferably, the production data vector of the donkey-hide gelatin cake comprises a temperature vector, a humidity vector, a stirring vector and a pressure vector.
Preferably, the acquiring the temperature variation set and the temperature stability set according to the data in the temperature vector includes:
For the temperature vector, if the data values of the continuous moments exist in the temperature vector, the time corresponding to the continuous moments is the temperature duration time; the set of all the temperature duration is recorded as a temperature variation set;
Counting the temperature duration time corresponding to each temperature value, and adding the temperature duration time corresponding to each temperature value to be used as the total temperature duration time corresponding to the temperature value; the set of total duration of temperature is denoted as the temperature stability set.
Preferably, the obtaining the dissimilarity coefficient of the temperature according to the cosine similarity and the number of the temperature vectors in the temperature sequence includes:
Calculating cosine similarity of any two temperature vectors in the temperature sequence, calculating the same temperature vector, and accumulating all the cosine similarity as a first cosine similarity value;
the square of the number of temperature vectors in the temperature sequence is recorded as a first number;
The first number is differenced from the first cosine similarity value, and the exponential function value of the difference is recorded as the dissimilarity coefficient of the temperature.
Preferably, the obtaining the instability coefficient of the temperature according to the elements in the temperature variation set and the temperature stability set includes:
In the method, in the process of the invention, Indicates the number of elements in the temperature variation set of the a-th batch donkey-hide gelatin cake,/>Represents the temperature stability set of the donkey-hide gelatin cake of the a batch,/>Representing the variance of the temperature stability set of batch a of donkey-hide gelatin cake,/>Indicates the number of donkey-hide gelatin cake batches,/>Representing an exponential function based on a natural constant,/>Representing the coefficient of instability of the temperature,/>Is an adjustment parameter.
Preferably, the obtaining the local weight of the temperature under any quality according to the instability coefficient and the dissimilarity coefficient of the temperature includes:
Making the dissimilarity coefficient of the temperature and the value 1 different, and recording the sum of the difference and the instability coefficient of the temperature as the significance coefficient of the temperature;
The sum of the saliency coefficients of all production data is marked as a saliency total value, and the ratio of the saliency coefficient of each type of production data to the saliency total value is marked as a first ratio; the difference between the value 1 and the first ratio is taken as the local weight of the production data.
Preferably, normalizing the temperature sequences with different qualities, and obtaining a difference significance index of the temperature according to the normalized temperature sequences with different qualities includes:
the method for normalizing the temperature sequence comprises the following steps: normalizing each temperature vector in the temperature sequence;
The temperature vector normalization method comprises the following steps: accumulating all the element values in the temperature vector to obtain an element total value, calculating the ratio of each element value in the temperature vector to the element total value, marking the ratio as a normalized value of each element in the temperature vector, and replacing each element value of the temperature vector with the normalized value of the element to complete the normalization of the temperature vector;
the expression of the difference saliency coefficient is:
In the method, in the process of the invention, Represents the mth normalized vector,/>Represents the h normalized vector,/>Normalized temperature sequence representing the nth quality,/>Normalized temperature sequence representing quality z-Representation/>And/>The JS divergence of (c),Representing an exponential function based on a natural constant,/>Indicating a temperature difference significance index.
Preferably, the obtaining the global weight of each production data according to the difference significance index of all the production data specifically includes:
In the method, in the process of the invention, Representing the difference significance coefficient of the k-th class of production data,/>Representing the difference significance coefficient of the v-th class of production data,/>As a sign function,/>As a round-down function,/>A weight duty ratio coefficient representing the kth class of production data;
The accumulated value of the weight ratio coefficients of all types of production data is recorded as a weight total coefficient;
And taking the ratio of the weight duty ratio coefficient to the weight total coefficient of each type of production data as the global weight of each type of production data.
Preferably, the extracting feature information according to the global weight of all production data and the local weight under different qualities includes:
calculating the average value of each type of production data of the donkey-hide gelatin cake of each batch, and taking the product of the sum of the local weight and the global weight and the average value as the weighted value of each type of production data of each batch; constructing all weighted values into a production matrix;
And (3) reducing the dimension of the production matrix by using a PCA algorithm to obtain a load vector of the first main component, sequentially accumulating the load factors in the load vector from large to small, and taking the load factors sequentially accumulated from large to small as characteristic information when the accumulated value exceeds the preset proportion of the total value of all the load factors.
In a second aspect, an embodiment of the present application further provides a system for extracting feature information of a donkey-hide gelatin cake production process, where the system includes a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements the steps of the feature information extraction method of any one of the above donkey-hide gelatin cake production processes when executing the computer program.
The application has at least the following beneficial effects:
According to the method, through analyzing the production characteristics of the donkey-hide gelatin cake, the quality similarity significance index of each type of production data in the same quality donkey-hide gelatin cake is calculated by utilizing the characteristic that the production conditions of the same quality donkey-hide gelatin cake have higher similarity in the same type of data, and then the local weight of each type of production data in the same quality donkey-hide gelatin cake is calculated; the production data with larger influence on the quality of the donkey-hide gelatin cake is utilized, the characteristic of larger difference among the donkey-hide gelatin cakes with different quality is utilized, the difference significance index of each type of production data in the donkey-hide gelatin cakes with different quality is calculated, and then the global weight of each type of production data is calculated; and finally, weighting each production data according to the local weight and the global weight, and then reducing the dimension through PCA to determine factors which have main influence on the quality of the donkey-hide gelatin cake. In this way, the change of various factors in the production process between the same quality and different quality is considered, so that the influence of the factors on the quality of the donkey-hide gelatin cake is accurately evaluated, main influencing factors are determined, and in the subsequent donkey-hide gelatin cake production process, the main factors are strictly controlled, so that the quality of the donkey-hide gelatin cake is higher and more controllable.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart illustrating a method for extracting feature information in a donkey-hide gelatin cake production process according to an embodiment of the present application;
fig. 2 is a flowchart of an implementation of a method for extracting feature information in a donkey-hide gelatin cake production process according to an embodiment of the application.
Detailed Description
In order to further describe the technical means and effects adopted by the present application to achieve the preset purpose, the following detailed description refers to the specific implementation, structure, features and effects of a method and a system for extracting feature information in a donkey-hide gelatin cake production process according to the present application, which are described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
The following specifically describes a specific scheme of a method and a system for extracting characteristic information in a donkey-hide gelatin cake production process provided by the application with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for extracting feature information of a donkey-hide gelatin cake production process according to an embodiment of the application is shown, the method includes the following steps:
step S001, obtaining production data vectors of donkey-hide gelatin cakes in each batch.
In the donkey-hide gelatin cake production process, temperature data during donkey-hide gelatin heating and melting are collected through a temperature sensor in heating equipment, humidity data of a production environment are collected through a humidity sensor in a workshop environment, stirring speed data of a step of fusing auxiliary materials with donkey-hide gelatin stock solution are collected through a rotating speed sensor on stirring equipment, pressure data of a pressing step are collected through a pressure sensor on pressing equipment, and the four data are collectively called production data.
In this embodiment, the above production data are collected once per second, and parameters may be different in the production process of each batch of donkey-hide gelatin cake, so that the production time of each step is changed, and if the temperature, humidity, stirring speed and pressure are collected at fixed time intervals, the same type of production data of different batches of donkey-hide gelatin cakes will have different states at corresponding moments. Taking temperature data as an example, when the donkey-hide gelatin is melted by heating at a high temperature, the donkey-hide gelatin may be melted in 40 th minute and then the next step is performed, but when the temperature is lower, the donkey-hide gelatin is melted by heating, the donkey-hide gelatin may not be melted in 40 th minute, and at this time, the temperatures of two batches cannot be compared. So in order to eliminate this, instead of collecting data at fixed time intervals, data is collected every second until each step is finished, and then 1% of the time used in the current step is taken as a time interval, for example, in the donkey-hide gelatin heating and melting step, if the step is finished for 100 minutes in total, the time interval is 1 minute, and the temperature value is collected every one minute.
For each batch of donkey-hide gelatin cake, a vector is obtained in each step, which is a temperature vector, a humidity vector, a stirring speed vector and a pressure vector.
So far, the production data vector of the donkey-hide gelatin cake in the same batch is obtained.
Step S002, constructing the corresponding instability coefficient according to the data value of the production data vector of each quality of each batch; obtaining the corresponding dissimilarity coefficient according to the sequence constructed by the production data vector; based on this, local weights for each production data at different qualities are obtained.
According to industry evaluation standards, the quality of the produced donkey-hide gelatin cake is measured and divided into three quality grades of excellent, good and unqualified, and the donkey-hide gelatin cake with excellent quality is taken as an example:
Counting a plurality of batches of donkey-hide gelatin cakes with excellent quality, sequencing temperature vectors of all batches according to a time sequence to obtain a temperature sequence, sequencing humidity vectors of all batches according to a time sequence to obtain a humidity sequence, sequencing stirring speed vectors of all batches according to a time sequence to obtain a stirring speed sequence, and sequencing pressure vectors of all batches according to a time sequence to obtain a pressure sequence.
The corresponding production data of the donkey-hide gelatin cake with the same quality should have similarity, and in the production of different batches of donkey-hide gelatin cake, the higher the similarity is, the larger the influence on the quality of the donkey-hide gelatin cake is; the lower the similarity of the production data, the less the effect on the quality of the donkey-hide gelatin cake. Each type of production data has stability, which is helpful for controlling the data in the production process, if the data always fluctuates, the data is difficult to accurately control for production, so that the more stable the data is, the higher the controllability of the production process is, and the higher the consistency and reliability of the final finished product are.
The similarity of the production data is obtained by comparing the similarity of the same type of production data of donkey-hide gelatin cakes in different batches, and the production data is represented by vectors, so that the similarity of the production data is obtained by cosine similarity. The stability of the production data requires judgment of the time series time of the production data and the overall fluctuation frequency. If the data values of any one of the production data are the same, the time of the continuous moment is recorded as the data duration, all the data durations of each vector are counted to form a data fluctuation set, the sum of the data durations corresponding to the same data value in the same data fluctuation set is recorded as the total data duration, and the total data duration forms a data stability set.
In this embodiment, for example, a temperature vector is {1,1,2,1,1,1,3,4,6,6}, where {1,1} corresponds to a temperature duration of 2, {1,1} corresponds to a temperature duration of 3, {6,6} corresponds to a temperature duration of 2, where the temperature variation set is {2,3,2}, the total duration of the temperatures with a temperature value of 2 is 5, the total duration of the temperatures with a temperature value of 6 is 2, and the temperature stability set is {5,2}.
According to the cosine similarity of the vectors in the temperature sequence and the number of the vectors in the temperature sequence, the dissimilarity coefficient of the temperature is obtained, and the formula is as follows:
In the method, in the process of the invention, Representing the i-th vector in the temperature sequence,/>Represents the j-th vector in the temperature sequence,/>Representing cosine similarity function,/>Representing the number of vectors in the temperature sequence,/>Represents an exponential function with a base of a natural constant,The dissimilarity coefficient indicating temperature, t indicates that the production data is temperature data.
If the influence of temperature on the quality of the donkey-hide gelatin cake is larger, the similarity of temperature in the production data of different batches of donkey-hide gelatin cakes is higher, so that the cosine similarity is higherShould be closer to 1, thus/>Should be closer to 0, i.e. the dissimilarity coefficient with temperature/>And/>The closer to 1, the better, i.e., the smaller the dissimilarity factor, the better.
Obtaining a temperature instability coefficient according to the number of elements in the temperature fluctuation set and the variance of element values in the temperature stability set, wherein the formula is as follows:
In the method, in the process of the invention, Indicates the number of elements in the temperature variation set of the a-th batch donkey-hide gelatin cake,/>Represents the temperature stability set of the donkey-hide gelatin cake of the a batch,/>Representing the variance of the temperature stability set of batch a of donkey-hide gelatin cake,/>Indicates the number of donkey-hide gelatin cake batches,/>Representing an exponential function based on a natural constant,/>Representing the coefficient of instability of the temperature,/>Is an adjustment parameter to prevent the denominator from being 0.
The temperature is stable, so that the duration of a certain temperature is longer, that is, the proportion of a certain temperature in the temperature stability set is enough outstanding, so that the uniformity of data in the temperature stability set is broken, the variance is larger, and the frequency of overall temperature change is smaller, that is, the quantity of data in the temperature change set is smaller, so thatSmaller, i.e. coefficient of instability of temperature/>Smaller, and/>The smaller the better.
Obtaining a significance coefficient of the temperature according to the instability coefficient and the dissimilarity coefficient of the temperature, wherein the formula is as follows:
In the method, in the process of the invention, Representing the dissimilarity coefficient of temperature,/>Representing the coefficient of instability of the temperature,/>Representing the coefficient of significance of the temperature. Due to/>The range of values of (2) is/>And/>Smaller and better,/>And/>The closer to 1, the better, and thus the similarity index/>, of temperatureThe smaller the size, the closer to 0, the greater the effect of temperature on the quality of the donkey-hide gelatin cake.
The similarity significance index of humidity, stirring speed and pressure is obtained by calculating the similarity significance index of temperature. Since the calculation of the similarity significance index is not a calculation for one type of data value, the change trend, stability and similarity of the data are measured. Obtaining local weights of various production data according to the significance coefficients of different production data, wherein the formula is as follows:
In the method, in the process of the invention, Representing the significance coefficient of the nth class of production data,/>A significance coefficient representing production data of class v,Expressed at/>The local weight of the n-th class of production data under the quality is larger when the significance coefficient of each class of production data is smaller, so that the quality influence on the donkey-hide gelatin cake is larger, and the weight occupied by the class of production data is larger, thus/>The larger.
According to the local weights of the different production data of the donkey-hide gelatin cake with excellent quality, the local weights of the different production data of the donkey-hide gelatin cake with other quality are obtained
So far, the local weight of different production data under different qualities is obtained.
Step S003, the difference significance index is obtained according to the normalized vector of the production data, and the global weight of the production data is obtained.
According to the steps, the similarity of the donkey-hide gelatin cake with the same quality on the same type of production data is obtained, but if the similarity of the production data of one type of production data in the donkey-hide gelatin cake with all the quality is higher, the production data is not decisive for the quality of the donkey-hide gelatin cake. Therefore, it is necessary to continuously judge the difference of the donkey-hide gelatin cake with different quality on the same production data, and the larger the difference is, the more possibly the decisive influence on the quality of the donkey-hide gelatin cake is explained. Therefore, the difference significance coefficients of donkey-hide gelatin cakes with different qualities on the same production data are calculated.
Taking temperature data as an example, the normalized temperature vector of the donkey-hide gelatin cake with excellent quality forms a normalized temperature sequence with excellent quality, the normalized temperature vector of the donkey-hide gelatin cake with good quality forms a normalized temperature sequence with good quality, and the normalized temperature vector of the donkey-hide gelatin cake with unqualified quality forms a normalized temperature sequence with unqualified quality. The normalization is as follows:
In the method, in the process of the invention, Element value representing the r-th element in the vector,/>Representing the number of elements in a vector,/>Representing vectorsIs a function of the normalization of (a).
Obtaining a temperature difference significance index according to normalized temperature sequences of temperature data under different qualities, wherein the formula is as follows:
In the method, in the process of the invention, Represents the mth normalized vector,/>Represents the h normalized vector,/>Normalized temperature sequence representing the nth quality,/>Normalized temperature sequence representing quality z-Representation/>And/>The JS divergence of (c),Representing an exponential function based on a natural constant,/>Indicating a temperature difference significance index.
If the difference of the donkey-hide gelatin cake with different quality on the temperature data is larger, the difference between the two temperature vectors with different quality is also relatively more obvious, the value of JS divergence is larger, and thus the difference of the temperature is significant indexThe value of (2) will be smaller. If the difference of the donkey-hide gelatin cakes with different qualities on the temperature data is smaller, namely the similarity is larger, the value of JS divergence is closer to 0, so that the difference of the temperature is significant index/>The value of (2) will be greater. And because the index function reflects the index more obviously, the index/>, according to the difference of the temperature, can be obviously obtainedThe range of values of (2) to determine the temperature difference is concentrated between several qualities, i.e. if the difference significance index/>And is closer to 3, the difference between the three qualities of the temperature can be judged to be smaller; if the difference significance index/>And closer to 2, the large probability temperature is less differential between the at least two qualities; if the difference significance index/>The large probability temperature is large in the variability between the three qualities.
Obtaining the difference significance index of humidity, stirring speed and pressure according to the difference significance index mode of obtaining temperature、/>、/>. The more remarkable the difference is, the more likely the donkey-hide gelatin cake quality is affected mainly; the more likely the difference between more qualities is significant, the more production data having a major effect on the quality of donkey-hide gelatin cake should be given a higher weight, so that the global weight of each type of production data is obtained according to the difference significance index, the formula is as follows:
In the method, in the process of the invention, Representing the difference significance coefficient of the k-th class of production data,/>Representing the difference significance coefficient of the v-th class of production data,/>As a sign function,/>As a round-down function,/>A weight duty cycle representing the k-th class of production data,Weight ratio coefficient representing nth class production data,/>Representing global weights for the n-th class of production data.
Thus, global weights for each type of production data are obtained.
Step S004, extracting characteristic information according to the global weight of all production data and the local weight under different qualities.
And respectively calculating the average value of vectors of the production data of each class of donkey-hide gelatin cakes in each batch, wherein the average value of the vectors is the average value of all element values in the vectors, taking the product of the sum of local weight and global weight and the average value as the weighted value of each class of production data in each batch, constructing all weighted values as a production matrix, and listing the production matrix as a production data type.
Taking a production matrix as input, using a PCA algorithm to reduce the dimension to obtain a first principal component load vector, sorting the load factors in the load vector from large to small according to the absolute values of the load factors, accumulating from large to small, and when the accumulated value exceeds 70% of the sum of the absolute values of all the load factors, obtaining the load factors as characteristic information in the production process. The characteristic information includes data from most manufacturing processes. The PCA algorithm is a well-known technique and will not be described in detail herein.
Based on the same inventive concept as the above method, the embodiment of the application also provides a feature information extraction system of a donkey-hide gelatin cake production process, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to realize any one of the steps of the feature information extraction method of the donkey-hide gelatin cake production process.
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. 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.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing description of the preferred embodiments of the present application is not intended to be limiting, but rather, any modifications, equivalents, improvements, etc. that fall within the principles of the present application are intended to be included within the scope of the present application.
Claims (3)
1. The characteristic information extraction method of the donkey-hide gelatin cake production process is characterized by comprising the following steps of:
obtaining a production data vector of donkey-hide gelatin cakes in each batch;
Dividing the donkey-hide gelatin cake into three qualities, and forming a temperature sequence for all temperature vectors in any one quality; acquiring a temperature variation set and a temperature stability set according to data in the temperature vector; acquiring a temperature dissimilarity coefficient according to the cosine similarity and the number of temperature vectors in the temperature sequence; acquiring an instability coefficient of temperature according to elements in the temperature variation set and the temperature stability set; obtaining local weight of the temperature under any quality according to the instability coefficient and the dissimilarity coefficient of the temperature; acquiring local weights of each production data under different qualities according to a method for acquiring the local weights of the temperatures;
Normalizing the temperature sequences with different qualities, and acquiring a difference significance index of the temperature according to the normalized temperature sequences with different qualities; acquiring the difference significance index of the rest production data according to the mode of acquiring the difference significance index of the temperature; acquiring global weights of each production data according to the difference significance indexes of all the production data;
extracting characteristic information according to the global weight of all production data and the local weights under different qualities;
the acquiring the temperature variation set and the temperature stability set according to the data in the temperature vector comprises the following steps:
For the temperature vector, if the data values of the continuous moments exist in the temperature vector, the time corresponding to the continuous moments is the temperature duration time; the set of all the temperature duration is recorded as a temperature variation set;
counting the temperature duration time corresponding to each temperature value, and adding the temperature duration time corresponding to each temperature value to be used as the total temperature duration time corresponding to the temperature value; the set formed by the total duration of the temperature is recorded as a temperature stability set;
the obtaining the dissimilarity coefficient of the temperature according to the cosine similarity and the number of the temperature vectors in the temperature sequence comprises the following steps:
Calculating cosine similarity of any two temperature vectors in the temperature sequence, calculating the same temperature vector, and accumulating all the cosine similarity as a first cosine similarity value;
the square of the number of temperature vectors in the temperature sequence is recorded as a first number;
Taking the first quantity and the first cosine similarity value as differences, and recording the exponential function value of the differences as a dissimilarity coefficient of the temperature;
the obtaining the instability coefficient of the temperature according to the elements in the temperature variation set and the temperature stability set comprises the following steps:
In the method, in the process of the invention, Indicates the number of elements in the temperature variation set of the a-th batch donkey-hide gelatin cake,/>Represents the temperature stability set of the donkey-hide gelatin cake of the a batch,/>Representing the variance of the temperature stability set of batch a of donkey-hide gelatin cake,/>Indicates the number of donkey-hide gelatin cake batches,/>Representing an exponential function based on a natural constant,/>Representing the coefficient of instability of the temperature,/>Is an adjustment parameter;
the obtaining the local weight of the temperature under any quality according to the instability coefficient and the dissimilarity coefficient of the temperature comprises the following steps:
Making the dissimilarity coefficient of the temperature and the value 1 different, and recording the sum of the difference and the instability coefficient of the temperature as the significance coefficient of the temperature;
The sum of the saliency coefficients of all production data is marked as a saliency total value, and the ratio of the saliency coefficient of each type of production data to the saliency total value is marked as a first ratio; taking the difference value of the value 1 and the first ratio as the local weight of the production data;
normalizing the temperature sequences with different qualities, and acquiring a difference significance index of the temperature according to the normalized temperature sequences with different qualities, wherein the method comprises the following steps:
the method for normalizing the temperature sequence comprises the following steps: normalizing each temperature vector in the temperature sequence;
The temperature vector normalization method comprises the following steps: accumulating all the element values in the temperature vector to obtain an element total value, calculating the ratio of each element value in the temperature vector to the element total value, marking the ratio as a normalized value of each element in the temperature vector, and replacing each element value of the temperature vector with the normalized value of the element to complete the normalization of the temperature vector;
the expression of the difference saliency coefficient is:
In the method, in the process of the invention, Represents the mth normalized vector,/>Represents the h normalized vector,/>Normalized temperature sequence representing the nth quality,/>Normalized temperature sequence representing quality z-Representation/>And/>JS divergence of/>Representing an exponential function based on a natural constant,/>A difference significance index representing temperature;
The obtaining the global weight of each production data according to the difference significance index of all the production data specifically comprises the following steps:
In the method, in the process of the invention, Representing the difference significance coefficient of the k-th class of production data,/>Representing the difference significance coefficient of the v-th class of production data,/>As a sign function,/>As a round-down function,/>A weight duty ratio coefficient representing the kth class of production data;
The accumulated value of the weight ratio coefficients of all types of production data is recorded as a weight total coefficient;
Taking the ratio of the weight ratio coefficient of each type of production data to the weight total coefficient as the global weight of each type of production data;
the extracting the characteristic information according to the global weight of all production data and the local weight under different qualities comprises the following steps:
calculating the average value of each type of production data of the donkey-hide gelatin cake of each batch, and taking the product of the sum of the local weight and the global weight and the average value as the weighted value of each type of production data of each batch; constructing all weighted values into a production matrix;
And (3) reducing the dimension of the production matrix by using a PCA algorithm to obtain a load vector of the first main component, sequentially accumulating the load factors in the load vector from large to small, and taking the load factors sequentially accumulated from large to small as characteristic information when the accumulated value exceeds the preset proportion of the total value of all the load factors.
2. The method for extracting characteristic information of donkey-hide gelatin cake production process according to claim 1, wherein the donkey-hide gelatin cake production data vector comprises a temperature vector, a humidity vector, a stirring vector and a pressure vector.
3. A characteristic information extraction system of a donkey-hide gelatin cake production process, comprising a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor, when executing the computer program, realizes the steps of a characteristic information extraction method of a donkey-hide gelatin cake production process according to any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410430365.1A CN118037134B (en) | 2024-04-11 | 2024-04-11 | Characteristic information extraction method and system for donkey-hide gelatin cake production process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410430365.1A CN118037134B (en) | 2024-04-11 | 2024-04-11 | Characteristic information extraction method and system for donkey-hide gelatin cake production process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118037134A CN118037134A (en) | 2024-05-14 |
| CN118037134B true CN118037134B (en) | 2024-06-14 |
Family
ID=90989548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410430365.1A Active CN118037134B (en) | 2024-04-11 | 2024-04-11 | Characteristic information extraction method and system for donkey-hide gelatin cake production process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118037134B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118427881B (en) * | 2024-06-25 | 2024-10-01 | 大连爱柏斯化工股份有限公司 | Cobalt propionate synthesis related data protection method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116659589B (en) * | 2023-07-25 | 2023-10-27 | 澳润(山东)药业有限公司 | Donkey-hide gelatin cake preservation environment monitoring method based on data analysis |
| CN117408497B (en) * | 2023-12-14 | 2024-04-05 | 山东锦都食品有限公司 | Food processing material management and control method and system |
-
2024
- 2024-04-11 CN CN202410430365.1A patent/CN118037134B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| "阿胶类保健食品中阿胶成分和牛皮源成分检测及质量评价";王超 等;《食品与发酵工业》;20191231;第45卷(第1期);全文 * |
| Jinju Zhang等."Identification of donkey-hide gelatin and donkey-bone gelatin based on marker peptides".《LWT -FoodScienceandTechnology》.2023,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118037134A (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118037134B (en) | Characteristic information extraction method and system for donkey-hide gelatin cake production process | |
| CN109620152B (en) | MutifacolLoss-densenert-based electrocardiosignal classification method | |
| CN101484910B (en) | Clustering system, and defect kind judging device | |
| CN108959895B (en) | Electroencephalogram EEG (electroencephalogram) identity recognition method based on convolutional neural network | |
| Ollech et al. | A random forest-based approach to identifying the most informative seasonality tests | |
| Lauguico et al. | Lettuce life stage classification from texture attributes using machine learning estimators and feature selection processes | |
| Olesen et al. | Deep residual networks for automatic sleep stage classification of raw polysomnographic waveforms | |
| CN111048210A (en) | Method and device for evaluating disease risk based on fundus image | |
| Barhate et al. | Analysis of classifiers for prediction of type ii diabetes mellitus | |
| CN115969329B (en) | Sleep stage method, system, device and medium | |
| CN109325410B (en) | Electroencephalogram EEG (electroencephalogram) feature extraction method based on convolutional neural network | |
| CN111297327B (en) | Sleep analysis method, system, electronic equipment and storage medium | |
| CN113288157A (en) | Arrhythmia classification method based on depth separable convolution and improved loss function | |
| CN110766082B (en) | Plant leaf disease and insect pest degree classification method based on transfer learning | |
| CN113076347B (en) | Emotion-based push program screening system and method on mobile terminal | |
| CN111967616A (en) | Automatic time series regression method and device | |
| US20230200697A1 (en) | Automatic evolution method for brainwave database and automatic evolving system for detecting brainwave | |
| CN116763324A (en) | Single-channel electroencephalogram signal sleep stage method based on multiple scales and multiple attentions | |
| CN117000780A (en) | Self-adaptive cold-rolled strip multichannel shape forecasting method | |
| CN115670417A (en) | Health assessment method and system for running monitoring | |
| CN108182288A (en) | A kind of recommendation method based on artificial immunity | |
| CN114648270B (en) | Method and system for calculating safety inventory of life parts | |
| CN107016345A (en) | A kind of demand model construction method applied to Product Conceptual Design | |
| CN117877736B (en) | Intelligent ring abnormal health data early warning method based on machine learning | |
| CN115841367B (en) | Product recommendation method based on sleeping behaviors of user |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |