CN117928647A - Automatic quality detection method and system for food processing production line - Google Patents
Automatic quality detection method and system for food processing production line Download PDFInfo
- Publication number
- CN117928647A CN117928647A CN202410110153.5A CN202410110153A CN117928647A CN 117928647 A CN117928647 A CN 117928647A CN 202410110153 A CN202410110153 A CN 202410110153A CN 117928647 A CN117928647 A CN 117928647A
- Authority
- CN
- China
- Prior art keywords
- coefficient
- production
- quality
- threshold value
- stirring
- 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 145
- 235000013305 food Nutrition 0.000 title claims abstract description 76
- 238000001514 detection method Methods 0.000 title claims abstract description 61
- 238000012545 processing Methods 0.000 title claims abstract description 40
- 235000015203 fruit juice Nutrition 0.000 claims abstract description 58
- 238000011156 evaluation Methods 0.000 claims abstract description 55
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims abstract description 35
- 239000001301 oxygen Substances 0.000 claims abstract description 35
- 229910052760 oxygen Inorganic materials 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000010252 digital analysis Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 8
- 238000001914 filtration Methods 0.000 claims description 93
- 238000003756 stirring Methods 0.000 claims description 79
- 230000007613 environmental effect Effects 0.000 claims description 70
- 238000012856 packing Methods 0.000 claims description 61
- 238000002425 crystallisation Methods 0.000 claims description 46
- 230000008025 crystallization Effects 0.000 claims description 46
- 230000007547 defect Effects 0.000 claims description 46
- 235000013399 edible fruits Nutrition 0.000 claims description 36
- 235000011389 fruit/vegetable juice Nutrition 0.000 claims description 35
- 238000007254 oxidation reaction Methods 0.000 claims description 35
- 230000003647 oxidation Effects 0.000 claims description 33
- 229910001385 heavy metal Inorganic materials 0.000 claims description 28
- 244000005700 microbiome Species 0.000 claims description 28
- 239000000447 pesticide residue Substances 0.000 claims description 28
- 239000011148 porous material Substances 0.000 claims description 18
- 238000005259 measurement Methods 0.000 claims description 14
- 239000007788 liquid Substances 0.000 claims description 12
- 238000005516 engineering process Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000004806 packaging method and process Methods 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 9
- 230000002950 deficient Effects 0.000 claims description 8
- 238000005352 clarification Methods 0.000 claims description 7
- 238000007789 sealing Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 6
- 239000011521 glass Substances 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 4
- 238000002156 mixing Methods 0.000 claims description 4
- 238000002360 preparation method Methods 0.000 claims description 4
- 230000001954 sterilising effect Effects 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 239000004615 ingredient Substances 0.000 claims description 3
- 239000000126 substance Substances 0.000 abstract description 5
- 230000002411 adverse Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 4
- 238000012544 monitoring process Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 235000021581 juice product Nutrition 0.000 description 2
- 239000013618 particulate matter Substances 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 102000004190 Enzymes Human genes 0.000 description 1
- 108090000790 Enzymes Proteins 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 239000005415 artificial ingredient Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000003755 preservative agent Substances 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a quality automatic detection method and a system of a food processing production line, and relates to the technical field of food industry; the temperature and humidity, the oxygen concentration and the PM2.5 concentration of the production area are monitored in real time, the environment is ensured to meet the standard, and adverse effects on the product quality are prevented. Meanwhile, the appearance, chemical components and production parameter multi-aspect data are comprehensively collected, and the quality of the fruit juice product can be accurately assessed. And a digital analysis model is introduced to process the data, various coefficients are generated, and a scientific and quantized evaluation method is provided. By comparing the pre-warning information with a preset threshold value, early warning information can be timely generated to indicate potential problems, and a targeted decision scheme is provided, so that the production line can timely cope with potential quality risks.
Description
Technical Field
The invention relates to the technical field of food industry, in particular to a quality automatic detection method and system for a food processing production line.
Background
In the food processing industry, particularly juice processing lines, the quality of the product is affected by environmental conditions, production parameters and various data during the production process. Traditional juice production processes mainly rely on manual operation, lack of automatic monitoring and feedback mechanisms, are easily affected by human factors, and cause large fluctuation and instability in production. In addition, the traditional method generally detects the product quality only through a limited sampling mode, and cannot realize real-time monitoring of the whole process.
In juice production, environmental factors such as temperature and humidity, oxygen concentration, PM2.5 concentration, etc. directly affect the quality and safety of juice. In addition, factors such as appearance, pH value, microorganism content, heavy metal content, pesticide residue content, component proportion and the like of the fruit juice are also important indexes for evaluating the quality of the product. The production parameters such as stirring, filtering and packaging also have a direct influence on the quality of the juice.
Disclosure of Invention
(One) solving the technical problems
Aiming at the defects of the prior art, the invention provides a quality automatic detection method and system for a food processing production line, which are used for solving the problems in the background art.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme: an automatic quality detection method for food processing production line comprises the following steps,
Firstly, arranging a plurality of sensor devices and image acquisition devices in a plurality of production areas of a target fruit juice food, setting detection points, and determining the areas represented by the detection points and the edges of the represented areas; collecting real-time environmental data of a target fruit juice food in a plurality of production areas, specifically environmental temperature Wd, humidity Sd, oxygen concentration O 2 Nd and PM2.5 concentration data PM; establishing a first environmental data set;
step two, collecting appearance defects, pH value, microorganism content, heavy metal content, pesticide residue content and component proportion data and package detection data of target foods in a plurality of production processes in real time; establishing a second data set;
Step three, acquiring production parameter data in a plurality of production areas in real time; establishing a third production dataset;
Step four, a digital analysis model is established, and the first environmental data set, the second data set and the third production data set are processed, analyzed and calculated to obtain: real-time environmental coefficient Ssx, first defect coefficient Qxx, stirring coefficient Jbx, filtering coefficient GLx, quality coefficient ZLx and packing tightness coefficient Bzx;
Fifthly, comparing the real-time environment coefficient Ssx, the first defect coefficient Qxx, the stirring coefficient Jbx, the filtering coefficient GLx, the quality coefficient ZLx and the packing tightness coefficient Bzx with a first environment threshold value X1, a second appearance threshold value X2, a third stirring efficiency threshold value X3, a fourth filtering efficiency threshold value X4, a fifth quality threshold value X5 and a sixth packing threshold value X6 respectively to obtain corresponding evaluation results, and generating corresponding early warning information according to the corresponding evaluation results;
and step six, generating a corresponding decision scheme according to the corresponding early warning information.
Preferably, the first step includes:
S11, setting detection points in a plurality of production areas of fruit juice foods, including fruit preparation, juicing, filtering, clarifying, sterilizing, preserving and blending packaging areas, and arranging a plurality of sensor devices and image acquisition devices in the detection points;
S12, collecting real-time environment data in a plurality of detection points, marking corresponding time stamps on the real-time environment data generated in different production stages, and establishing a first environment data set;
The method comprises the steps of extracting ambient temperature Wd, humidity Sd, oxygen concentration O 2 Nd and PM2.5 concentration data PM in a first ambient data set, wherein the ambient temperature Wd is obtained through direct measurement of a temperature sensor, the humidity Sd is obtained through direct measurement of a humidity sensor, the oxygen concentration O 2 Nd is obtained through direct measurement of an oxygen concentration sensor, and the PM2.5 concentration data PM is obtained through direct measurement of a resistance sensor.
Preferably, the second step includes:
s21, arranging an image sensor or camera equipment, shooting images of target fruit juice foods in a production area in real time, extracting the images in each production area by utilizing an image identification technology, and identifying mildew features, oxidation features and fruit juice crystallization features of fruits by utilizing a texture and color space technology;
And analyzing and calculating the mildew point characteristics, the color change characteristics and the juice crystallization to obtain the product: mold formation coefficient Fm, oxidation coefficient Yh and crystallization coefficient JJ;
S22, disposing a pH sensor, a microorganism sensor, a heavy metal detection instrument, a pesticide residue detection instrument and a component sensor at a plurality of detection points of a production area, and collecting pH value, microorganism content Ws, heavy metal content ZJS, pesticide residue content NYc and component proportioning value CFpb in real time;
S23, installing a vacuum detection sensor in a packaging area, detecting sealing performance data of the juice package, and obtaining an air leakage value LQz; after pretreatment of the mildew coefficient Fm, the oxidation coefficient Yh, the crystallization coefficient JJ, the pH value, the microorganism content Ws, the heavy metal content ZJS, the pesticide residue content NYc, the component ratio value CFpb and the air leakage value LQz, a second data set is established.
Preferably, the mildew coefficient Fm and the oxidation coefficient Yh are obtained by the following steps: extracting a fruit mildew area mdmj in the image, a fruit oxidation blackening and grey hair area yhmj in the image and a surface area bmj of the extracted fruit; the mildew coefficient Fm and the oxidation coefficient Yh are calculated by the following formula:
The crystallization coefficient JJ is obtained by the following steps: extracting a crystallization area of juice in the glass bottle, separating the crystallization area from other areas in the image by adopting an image segmentation technology, measuring and obtaining the crystallization area jjmj, and measuring and calculating the juice area gzmj of the glass bottle; the crystallization coefficient JJ is obtained by the following formula:
Preferably, the third step includes: production parameters of the juice extraction and filtration clarification zone, including stirrer rotation rate jbsl, stirring time sj1, liquid stirring temperature jbwd, filtration rate glsl, filter pore size kj, number of filter pores slz and filtration time sj2, are collected and a third production dataset is established.
Preferably, the real-time environmental coefficient Ssx is generated by the following formula after cleaning, smoothing, filtering and dimensionless processing of the environmental temperature Wd, humidity Sd, oxygen concentration O 2 Nd and PM2.5 concentration data PM;
wherein Q 1 represents a target fruit juice food preset temperature threshold, Q 2 represents a target fruit juice food preset humidity threshold, Q 3 represents a target fruit juice food preset oxygen concentration threshold, Q 4 represents a target fruit juice food preset PM2.5 concentration threshold, w1, w2, w3, and w4 represent weight values, and 0< w1<1,0< w2<1,0< w3<1,0< w4<1, and w1+w2+w3+w4=1.0; a 1 denotes a first correction constant.
Preferably, the mildew coefficient Fm, the oxidation coefficient Yh and the crystallization coefficient JJ are subjected to generate the first defect coefficient Qxx by the following correlation formula:
Qxx＝w5*Fm+w6*Yh+w7*JJ+A2
Wherein w5, w6 and w7 represent preset scaling factors of the mildew coefficient Fm, the oxidation coefficient Yh and the crystallization coefficient JJ, respectively, and 0< w5<1,0< w6<1,0< w7<1, and w5+w6+w7=1.0; a 2 denotes a second correction constant;
The PH value, the microorganism content Ws, the heavy metal content ZJS, the pesticide residue content NYc and the component proportion value CFpb; after dimensionless treatment, the mass coefficient ZLx is calculated by the following formula:
Wherein: y 1 represents a target fruit juice food preset pH value threshold value, Y 2 represents a target fruit juice food preset microorganism content threshold value, Y 3 represents a target fruit juice food preset heavy metal content threshold value, Y 4 represents a target fruit juice food preset pesticide residue content threshold value, Y 5 represents a target fruit juice food preset ingredient proportioning threshold value, r1, r2, r3, r4 and r5 represent weight values, and 0< r1<1,0< r2<1,0< r3<1,0< r4<1,0< r5<1, and r1+r2+r3+r4+r5=1.0; ; a 3 denotes a third correction constant;
After the rotation rate jbsl of the stirrer, the stirring time sj1, the liquid stirring temperature jbwd, the filtration rate glsl, the filter pore size kj, the number of filter pores slz, and the filtration time sj2 were subjected to dimensionless processing, a stirring coefficient Jbx and a filtration coefficient GLx were obtained by calculation by the following formulas:
Wherein: e1, E2, E3, and E4 represent weight values, and e1+e2=1.0; e3+e4=1.0; and 0< e1<1,0< e2<1,0< e3<1,0< e4<1; ln represents a logarithmic operation;
The obtaining mode of the packing tightness coefficient Bzx is that the air leakage value LQz of the vacuum detection of the juice packing is obtained, the screw length Lwcd of the screw cap in the packing mode is obtained, and the packing tightness coefficient Bzx is obtained through calculation according to the following formula:
preferably, the fifth step includes:
s51, comparing the real-time environment coefficient Ssx with a first environment threshold X1 to obtain a first evaluation result, including: when the real-time environment coefficient Ssx is larger than the first environment threshold X1, the real-time environment of the production area is indicated to be unqualified, and first early warning information is generated; when the real-time environment coefficient Ssx is less than or equal to a first environment threshold value X1, representing that the real-time environment of the production area is qualified;
S52, comparing the first defect coefficient Qxx with a second appearance threshold X2 to obtain a second evaluation result, wherein the second evaluation result comprises: when the first defect coefficient Qxx is larger than the second appearance threshold value X2, the fruits are defective and unqualified, and second early warning information is generated; when the first defect coefficient Qxx is less than or equal to a second appearance threshold value X2, the fruit is qualified without defects;
s53, comparing the stirring coefficient Jbx with a third stirring efficiency threshold X3 to obtain a third evaluation result, including: when the stirring coefficient Jbx is smaller than a third stirring efficiency threshold X3, the stirring speed is not qualified, and third early warning information is generated; when the stirring coefficient Jbx is more than or equal to a third stirring efficiency threshold X3, the stirring rate is qualified;
S54, comparing the filtering coefficient GLx with a fourth filtering efficiency threshold X4 to obtain a fourth evaluation result, wherein the fourth evaluation result comprises: when the filtering coefficient GLx is smaller than the fourth filtering efficiency threshold value X4, the filtering rate is unqualified, and fourth early warning information is generated; when the filtering coefficient GLx is more than or equal to a fourth filtering efficiency threshold value X4, the filtering rate is qualified;
S55, comparing the quality coefficient ZLx with a fifth quality threshold X5 to obtain a fifth evaluation result, including: when the quality coefficient ZLx is larger than a fifth quality threshold X5, the quality is unqualified, and fifth early warning information is generated; when the quality coefficient ZLx is less than or equal to a fifth quality threshold X5, the quality is qualified;
S56, comparing the packing tightness coefficient Bzx with a sixth packing threshold X6 to obtain a sixth evaluation result, including: when the packing tightness coefficient Bzx is larger than a sixth packing threshold X6, the packing is unqualified, and sixth early warning information is generated; and when the packing tightness coefficient Bzx is less than or equal to a sixth packing threshold X6, the packing is qualified.
Preferably, the sixth step includes:
The first early warning information generates a first decision scheme comprising: adopting measures to adjust environmental parameters to enable the current environmental parameters to meet the requirements, and checking and maintaining temperature, humidity, oxygen concentration and PM2.5 concentration detection equipment;
The second early warning information generates a second decision scheme comprising: removing defective fruits from the production line, and ensuring that only fruits meeting quality standards enter the next stage of processing; checking the region causing fruit defects in the production process, and taking measures to improve and correct the region;
The third early warning information generates a third decision scheme comprising: adjusting the rotation rate, stirring time and liquid stirring temperature of the stirrer;
The fourth early warning information generates a fourth decision scheme comprising: checking whether the aperture of the filtering equipment is blocked, and cleaning and maintaining the filtering equipment;
The fifth early warning information generates a fifth decision scheme comprising: the control of the pH value, the microorganism content, the heavy metal content and the pesticide residue content is enhanced, the acceptable range is ensured, and the components are proportioned again, so that the component proportioning accords with a preset threshold value;
The sixth early warning information generates a second sixth strategy scheme, including: checking the thread length of the screw cap and improving the sealing process.
The automatic quality detection system of the food processing production line comprises a data acquisition module, a model building analysis module, an evaluation early warning module and a decision scheme generation module;
the data acquisition module comprises a first environmental data set acquisition unit, a second data set acquisition unit and a third production data set acquisition unit;
The first environmental data set acquisition unit is used for acquiring real-time environmental data of a target fruit juice food production area, including environmental temperature, humidity, oxygen concentration and PM2.5 concentration, and establishing a first environmental data set;
The second data set acquisition unit is used for adopting an image sensor or camera equipment to shoot images of target fruit juice foods in real time so as to identify appearance defects, mildewing, oxidation and crystallization characteristics; and collecting PH value, microorganism content, heavy metal content, pesticide residue content, component proportion data and package detection data; establishing a second data set;
The third production data set acquisition unit is used for acquiring production parameter data of the juicing and filtering clarification area in real time, wherein the production parameter data comprise the rotation rate of a stirrer, the stirring time, the liquid stirring temperature, the filtering rate, the filter pore diameter, the number of filter pores and the filtering time, and a third production data set is established;
the model building analysis module is used for building a digital analysis model, and processing, analyzing and calculating the first environment data set, the second data set and the third production data set to obtain: real-time environmental coefficient Ssx, first defect coefficient Qxx, stirring coefficient Jbx, filtering coefficient GLx, quality coefficient ZLx and packing tightness coefficient Bzx;
The evaluation early warning module is configured to compare the real-time environment coefficient Ssx, the first defect coefficient Qxx, the stirring coefficient Jbx, the filtering coefficient GLx, the quality coefficient ZLx and the packing tightness coefficient Bzx with the first environment threshold value X1, the second appearance threshold value X2, the third stirring efficiency threshold value X3, the fourth filtering efficiency threshold value X4, the fifth quality threshold value X5 and the sixth packing threshold value X6, respectively, to obtain corresponding evaluation results, and generate corresponding early warning information according to the corresponding evaluation results;
the decision scheme generation module is used for generating a corresponding decision scheme according to the corresponding early warning information.
(III) beneficial effects
The invention provides a quality automatic detection method and system for a food processing production line. The beneficial effects are as follows:
(1) According to the quality automatic detection method for the food processing production line, through deployment of the environment sensor, parameters such as the environment temperature, the humidity, the oxygen concentration and the PM2.5 concentration of a juice production area can be monitored in real time. This helps to know in time whether the production environment meets the standard, prevents the adverse effect of environmental factors on product quality. The method not only considers environmental parameters, but also collects various data such as appearance, chemical components, production parameters and the like of the fruit juice in real time, and establishes a comprehensive data set. This helps to more fully and accurately assess product quality. Introducing a digital analysis model, and generating real-time environment coefficients, defect coefficients, stirring coefficients, filtering coefficients, quality coefficients and packing tightness coefficients by processing, analyzing and calculating various data sets. This provides a scientific, quantitative way to evaluate product quality. By comparing the method with a preset threshold value, real-time early warning information can be generated, and possible problems are indicated. Accordingly, it provides a targeted decision scheme that enables the production line to quickly cope with potential quality risks, thereby improving product quality and safety. The method covers various aspects from environment to product appearance, chemical components, production parameters and the like, so that the quality management is more comprehensive, and the consistency and the high quality of the fruit juice product are improved.
(2) This quality automated inspection system of food processing production line, in this embodiment, data acquisition module includes three key parts: a first environmental data set acquisition unit, a second data set acquisition unit, and a third production data set acquisition unit. The units are respectively responsible for collecting real-time environment data, image characteristics and production parameter data to form a comprehensive data set, and provide a basis for subsequent analysis and decision. Next, the model building analysis module processes the first environmental dataset, the second dataset, and the third production dataset using a digital analysis model to obtain a real-time environmental coefficient Ssx, a first defect coefficient Qxx, a stirring coefficient Jbx, a filtration coefficient GLx, a quality coefficient ZLx, and a packing tightness coefficient Bzx. The coefficients reflect the states and performances of various aspects of the production line, and provide important basis for subsequent evaluation and early warning.
Then, the evaluation and early warning module compares the real-time environment coefficient Ssx, the first defect coefficient Qxx, the stirring coefficient Jbx, the filtering coefficient GLx, the quality coefficient ZLx and the packing tightness coefficient Bzx with corresponding thresholds according to the set thresholds (X1 to X6) to generate corresponding evaluation results. Once an anomaly is found, the system will generate corresponding pre-warning information, suggesting that a problem may exist in the production line.
And finally, the decision scheme generating module generates a specific decision scheme according to the evaluation result. These include adjusting environmental parameters, rejecting defective products, adjusting production parameters, etc. Each scheme is helpful for timely solving the problems in the production line, and ensures the product quality and the production efficiency.
Drawings
FIG. 1 is a schematic diagram showing steps of an automatic quality detecting method for a food processing line according to the present invention;
Fig. 2 is a schematic flow chart of an automatic quality detection system for a food processing line according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, the automatic quality detection method for a food processing line includes the following steps,
Firstly, arranging a plurality of sensor devices and image acquisition devices in a plurality of production areas of a target fruit juice food, setting detection points, and determining the areas represented by the detection points and the edges of the represented areas; collecting real-time environmental data of a target fruit juice food in a plurality of production areas, specifically environmental temperature Wd, humidity Sd, oxygen concentration O2Nd and PM2.5 concentration data PM; establishing a first environmental data set; sensor equipment and image acquisition equipment are deployed, the temperature, the humidity, the oxygen concentration and the PM2.5 concentration of the production environment are monitored in real time, environmental conditions are ensured to accord with the standard of product production, and the safety and the quality of fruit juice are improved. Rapid oxidation of pulp refers to the oxidation reaction caused by the contact of enzymes within the fruit with oxygen in the air. This reaction results in browning of the fruit surface, softening of the texture and poor mouthfeel. In order to reduce rapid oxidation of pulp, the temperature, humidity and oxygen concentration are detected, and after the real-time environmental data are detected, the temperature, humidity and oxygen concentration are adjusted for the environment which does not meet the production standard of the product, and measures such as reducing oxygen contact and controlling the temperature and the humidity are taken; PM2.5 particle concentration detection is used to improve air quality; high concentrations of PM2.5 particulates may deposit on the surface of juice products, affecting product hygiene and quality. By monitoring the concentration of particulate matter in the air, corresponding measures can be taken to reduce the contamination of the product by particulate matter.
Step two, collecting appearance defects, pH value, microorganism content, heavy metal content, pesticide residue content and component proportion data and package detection data of target foods in a plurality of production processes in real time; establishing a second data set; the comprehensive monitoring and data acquisition of the indexes of the product quality in multiple aspects are realized.
Step three, acquiring production parameter data in a plurality of production areas in real time; establishing a third production dataset; the key parameters in the production process can be monitored in real time, and the production efficiency and the product consistency can be improved.
Step four, a digital analysis model is established, and the first environmental data set, the second data set and the third production data set are processed, analyzed and calculated to obtain: real-time environmental coefficient Ssx, first defect coefficient Qxx, stirring coefficient Jbx, filtering coefficient GLx, quality coefficient ZLx and packing tightness coefficient Bzx; this provides a scientific, quantitative way to evaluate product quality.
Fifthly, comparing the real-time environment coefficient Ssx, the first defect coefficient Qxx, the stirring coefficient Jbx, the filtering coefficient GLx, the quality coefficient ZLx and the packing tightness coefficient Bzx with a first environment threshold value X1, a second appearance threshold value X2, a third stirring efficiency threshold value X3, a fourth filtering efficiency threshold value X4, a fifth quality threshold value X5 and a sixth packing threshold value X6 respectively to obtain corresponding evaluation results, and generating corresponding early warning information according to the corresponding evaluation results; the comparison of the coefficients and a preset threshold value ensures that the evaluation of the product quality is more accurate, and provides scientific basis for subsequent decisions.
And step six, generating a corresponding decision scheme according to the corresponding early warning information.
In the embodiment, by deploying the environmental sensor, the method can monitor parameters such as the environmental temperature, the humidity, the oxygen concentration, the PM2.5 concentration and the like of the juice production area in real time. This helps to know in time whether the production environment meets the standard, prevents the adverse effect of environmental factors on product quality. The method not only considers environmental parameters, but also collects various data such as appearance, chemical components, production parameters and the like of the fruit juice in real time, and establishes a comprehensive data set. This helps to more fully and accurately assess product quality. Introducing a digital analysis model, and generating real-time environment coefficients, defect coefficients, stirring coefficients, filtering coefficients, quality coefficients and packing tightness coefficients by processing, analyzing and calculating various data sets. This provides a scientific, quantitative way to evaluate product quality. By comparing the method with a preset threshold value, real-time early warning information can be generated, and possible problems are indicated. Accordingly, it provides a targeted decision scheme that enables the production line to quickly cope with potential quality risks, thereby improving product quality and safety. The method covers various aspects from environment to product appearance, chemical components, production parameters and the like, so that the quality management is more comprehensive, and consistency and high quality of the juice product are ensured.
Example 2, this example is illustrated in example 1, specifically, the first step includes:
S11, setting detection points in a plurality of production areas of fruit juice foods, including fruit preparation, juicing, filtering, clarifying, sterilizing, preserving and blending packaging areas, and arranging a plurality of sensor devices and image acquisition devices in the detection points;
S12, collecting real-time environment data in a plurality of detection points, marking corresponding time stamps on the real-time environment data generated in different production stages, and establishing a first environment data set;
the method comprises the steps of extracting ambient temperature Wd, humidity Sd, oxygen concentration O2Nd and PM2.5 concentration data PM in a first ambient data set, wherein the ambient temperature Wd is obtained through direct measurement of a temperature sensor, the humidity Sd is obtained through direct measurement of a humidity sensor, the oxygen concentration O2Nd is obtained through direct measurement of an oxygen concentration sensor, and the PM2.5 concentration data PM is obtained through direct measurement of a resistance sensor.
In this embodiment, detection points are set in different stages of fruit juice production, including fruit preparation, juicing, filtering and clarifying, sterilizing and preserving, blending and packaging, and other areas. Such deployment ensures comprehensive monitoring of the entire production process, facilitating real-time knowledge of the production environment at each stage. The first set of environmental data is created by marking the real-time environmental data generated at different production stages with corresponding time stamps. The labeling mode enables environmental data at different moments to be compared and analyzed, and is helpful for tracing and diagnosing potential problems. The collected ambient temperature, humidity, oxygen concentration and PM2.5 concentration data are directly obtained through corresponding sensor measurement. The direct measurement method ensures the accuracy and real-time performance of the data and avoids sampling errors and delays which may exist in the traditional means. The condition of the production environment can be more comprehensively known by collecting multi-dimensional environmental data such as the environmental temperature, the humidity, the oxygen concentration, the PM2.5 concentration and the like. This is critical to ensuring the quality of the environment during the juice production process and helps to improve the quality and safety of the product. The method is suitable for an automatic production line, the monitoring process is automated by the deployment of the sensor equipment and the image acquisition equipment, and the direct measurement of data is beneficial to timely adjusting production environment and parameters, so that the stability and efficiency of the production line are improved.
Embodiment 3, which is an explanation of embodiment 1, specifically, the step two includes:
s21, arranging an image sensor or camera equipment, shooting images of target fruit juice foods in a production area in real time, extracting the images in each production area by utilizing an image identification technology, and identifying mildew features, oxidation features and fruit juice crystallization features of fruits by utilizing a texture and color space technology;
And analyzing and calculating the mildew point characteristics, the color change characteristics and the juice crystallization to obtain the product: mold formation coefficient Fm, oxidation coefficient Yh and crystallization coefficient JJ;
S22, disposing a pH sensor, a microorganism sensor, a heavy metal detection instrument, a pesticide residue detection instrument and a component sensor at a plurality of detection points of a production area, and collecting pH value, microorganism content Ws, heavy metal content ZJS, pesticide residue content NYc and component proportioning value CFpb in real time;
S23, installing a vacuum detection sensor in a packaging area, detecting sealing performance data of the juice package, and obtaining an air leakage value LQz; after pretreatment of the mildew coefficient Fm, the oxidation coefficient Yh, the crystallization coefficient JJ, the pH value, the microorganism content Ws, the heavy metal content ZJS, the pesticide residue content NYc, the component ratio value CFpb and the air leakage value LQz, a second data set is established.
In this embodiment, an image of a target fruit juice food in a production area is captured in real time by using an image sensor or a camera device, and the mildew feature, oxidation feature and fruit juice crystallization feature of the fruit are extracted by using an image recognition technology. According to the method, visual information is acquired, so that appearance defects of the product, including mildew points, oxidization and crystallization, can be detected, and visual data support is provided for comprehensive evaluation of the quality of the product. The pH sensor, the microorganism sensor, the heavy metal detecting instrument, the pesticide residue detecting instrument and the component sensor are deployed at a plurality of detection points of the production area, and the pH value, the microorganism content, the heavy metal content, the pesticide residue content and the component proportioning value are collected in real time. Thus, the comprehensive detection of the multiple sensors covers multiple quality key indexes of the product, and more comprehensive quality monitoring is ensured. And installing a vacuum detection sensor in the packaging area, detecting sealing performance data of the juice package, and obtaining an air leakage value. This step helps to detect the quality of the package, prevents gas permeation from adversely affecting the product, and improves the safety and fresh-keeping effect of the package. And preprocessing each detection data including mildew coefficient, oxidation coefficient, crystallization coefficient, pH value, microorganism content, heavy metal content, pesticide residue content, component proportion value and air leakage value, and establishing a second data set. This enables the subsequent digital analysis model to make a comprehensive assessment of product quality in multiple dimensions.
Example 4, this example is an explanation of example 1, specifically, the mildew coefficient Fm and the oxidation coefficient Yh are obtained by: extracting a fruit mildew area mdmj in the image, a fruit oxidation blackening and grey hair area yhmj in the image and a surface area bmj of the extracted fruit; the mildew coefficient Fm and the oxidation coefficient Yh are calculated by the following formula:
When the juice contains high-concentration sugar, or artificial ingredients or preservatives are added, abnormal crystallization can be caused under improper temperature and humidity conditions, and abnormal stirring, filtering and packaging can be caused; the crystallization coefficient JJ is obtained by the following steps: extracting a crystallization area of juice in the glass bottle, separating the crystallization area from other areas in the image by adopting an image segmentation technology, measuring and obtaining the crystallization area jjmj, and measuring and calculating the juice area gzmj of the glass bottle; the crystallization coefficient JJ is obtained by the following formula:
In this embodiment, the mildew coefficient Fm is obtained by analyzing the image to accurately measure the mildew area in the fruit and comparing it with the total surface area. This helps real-time supervision product outward appearance defect, especially the condition of mildewing point, improves the outward appearance quality of product. The oxidation coefficient Yh is obtained by measuring the area of the oxidized region and comparing it with the total surface area. This helps to discover the oxidation condition of the fruit in time, and improves the freshness and taste of the product. The crystallization coefficient JJ adopts an image segmentation technology to separate a crystallization area from other areas in an image, then the area of the crystallization area is measured, and the crystallization area is compared with the total juice area to obtain the crystallization coefficient. This helps to monitor crystallization in the juice and provides important information on product quality.
Example 5, which is an explanation of example 1, specifically, the third step includes: production parameters of the juice extraction and filtration clarification zone, including stirrer rotation rate jbsl, stirring time sj1, liquid stirring temperature jbwd, filtration rate glsl, filter pore size kj, number of filter pores slz and filtration time sj2, are collected and a third production dataset is established.
In this embodiment, the third production dataset is obtained by detection of a rotation rate sensor, a timer or time sensor, a temperature sensor, a flow sensor, an aperture sensor, a counting sensor. By collecting and analyzing these production parameters, the digital analysis model is able to more fully evaluate the quality of the juice based on a combination of factors in the juicing and filtering clarification process. This helps to ensure stability and consistency during the production process, and to improve the efficiency and product quality of the juice production line
Example 6, which is an explanation of example 1, specifically, the real-time environmental coefficient Ssx is generated by the following formula after cleaning, smoothing, filtering and dimensionless treatment of the environmental temperature Wd, humidity Sd, oxygen concentration O 2 Nd and PM2.5 concentration data PM;
Wherein Q 1 represents a target fruit juice food preset temperature threshold, Q 2 represents a target fruit juice food preset humidity threshold, Q 3 represents a target fruit juice food preset oxygen concentration threshold, Q4 represents a target fruit juice food preset PM2.5 concentration threshold, w1, w2, w3, and w4 represent weight values, and 0< w1<1,0< w2<1,0< w3<1,0< w4<1, and w1+w2+w3+w4=1.0; a 1 denotes a first correction constant. The real-time environmental coefficient Ssx comprehensively considers the deviation between each environmental parameter and the preset threshold value, and performs proper weighting according to the weight value. The processing can more comprehensively and accurately evaluate the influence of the current environment on the fruit juice production, and provides a basis for subsequent quality evaluation and early warning.
Example 7, which is an explanation made in example 1, specifically, the mildew coefficient Fm, the oxidation coefficient Yh, and the crystallization coefficient JJ are subjected to the generation of the first defect coefficient Qxx by the following associated formulas:
Qxx＝w5*Fm+w6*Yh+w7*JJ+A2
Wherein w5, w6 and w7 represent preset scaling factors of the mildew coefficient Fm, the oxidation coefficient Yh and the crystallization coefficient JJ, respectively, and 0< w5<1,0< w6<1,0< w7<1, and w5+w6+w7=1.0; a 2 denotes a second correction constant;
The PH value, the microorganism content Ws, the heavy metal content ZJS, the pesticide residue content NYc and the component proportion value CFpb; after dimensionless treatment, the mass coefficient ZLx is calculated by the following formula:
Wherein: y 1 represents a target fruit juice food preset pH value threshold value, Y 2 represents a target fruit juice food preset microorganism content threshold value, Y 3 represents a target fruit juice food preset heavy metal content threshold value, Y 4 represents a target fruit juice food preset pesticide residue content threshold value, Y 5 represents a target fruit juice food preset ingredient proportioning threshold value, rl, r2, r3, r4 and r5 represent weight values, and 0< r1<1,0< r2<1,0< r3<1,0< r4<1,0< r5<1, and r1+r2+r3+r4+r5=1.0; ; a 3 denotes a third correction constant;
After the rotation rate jbsl of the stirrer, the stirring time sj1, the liquid stirring temperature jbwd, the filtration rate glsl, the filter pore size kj, the number of filter pores slz, and the filtration time sj2 were subjected to dimensionless processing, a stirring coefficient Jbx and a filtration coefficient GLx were obtained by calculation by the following formulas:
Wherein: e1, E2, E3, and E4 represent weight values, and e1+e2=1.0; e3+e4=1.0; and 0< e1<1,0< e2<1,0< e3<1,0< e4<1;1n represents a logarithmic operation;
The obtaining mode of the packing tightness coefficient Bzx is that the air leakage value LQz of the vacuum detection of the juice packing is obtained, the screw length Lwcd of the screw cap in the packing mode is obtained, and the packing tightness coefficient Bzx is obtained through calculation according to the following formula:
In this embodiment, the comprehensive evaluation of the first defect coefficient Qxx, the quality coefficient ZLx, the stirring coefficient Jbx, the filtering coefficient GLx and the packing tightness coefficient Bzx can help to monitor each link of the juice production line in real time, discover potential quality problems in advance, and generate early warning information and decision schemes, so as to ensure the production quality and safety of the juice.
The fifth step comprises the following steps:
S51, comparing the real-time environment coefficient Ssx with a first environment threshold X1 to obtain a first evaluation result, including: when the real-time environment coefficient Ssx is larger than the first environment threshold X1, the real-time environment of the production area is indicated to be unqualified, and first early warning information is generated; when the real-time environment coefficient Ssx is less than or equal to a first environment threshold value X1, the real-time environment of the production area is qualified, and early warning is not needed;
S52, comparing the first defect coefficient Qxx with a second appearance threshold X2 to obtain a second evaluation result, wherein the second evaluation result comprises: when the first defect coefficient Qxx is larger than the second appearance threshold value X2, the fruits are defective and unqualified, and second early warning information is generated; when the first defect coefficient Qxx is smaller than or equal to the second appearance threshold value X2, the fruits are qualified without defects, and early warning is not needed;
S53, comparing the stirring coefficient Jbx with a third stirring efficiency threshold X3 to obtain a third evaluation result, including: when the stirring coefficient Jbx is smaller than a third stirring efficiency threshold X3, the stirring speed is not qualified, and third early warning information is generated; when the stirring coefficient Jbx is more than or equal to a third stirring efficiency threshold X3, the stirring speed is qualified, and early warning is not needed;
S54, comparing the filtering coefficient GLx with a fourth filtering efficiency threshold X4 to obtain a fourth evaluation result, wherein the fourth evaluation result comprises: when the filtering coefficient GLx is smaller than the fourth filtering efficiency threshold value X4, the filtering rate is unqualified, and fourth early warning information is generated; when the filtering coefficient GLx is more than or equal to the fourth filtering efficiency threshold value X4, the filtering rate is qualified, and early warning is not needed;
S55, comparing the quality coefficient ZLx with a fifth quality threshold X5 to obtain a fifth evaluation result, including: when the quality coefficient ZLx is larger than a fifth quality threshold X5, the quality is unqualified, and fifth early warning information is generated; when the quality coefficient ZLx is smaller than or equal to a fifth quality threshold X5, the quality is qualified, and early warning is not needed;
s56, comparing the packing tightness coefficient Bzx with a sixth packing threshold X6 to obtain a sixth evaluation result, including: when the packing tightness coefficient Bzx is larger than a sixth packing threshold X6, the packing is unqualified, and sixth early warning information is generated; and when the packing tightness coefficient Bzx is less than or equal to a sixth packing threshold X6, the packing is qualified, and early warning is not needed. The evaluation and early warning mechanism is helpful for timely finding potential problems in the production process, and corresponding measures are taken to ensure the quality and safety of the juice
The sixth step comprises the following steps: the first early warning information generates a first decision scheme comprising: adopting measures to adjust environmental parameters to enable the current environmental parameters to meet the requirements, and checking and maintaining temperature, humidity, oxygen concentration and PM2.5 concentration detection equipment; ensuring the accuracy and normal operation.
The second early warning information generates a second decision scheme comprising: removing defective fruits from the production line, and ensuring that only fruits meeting quality standards enter the next stage of processing; checking the region causing fruit defects in the production process, and taking measures to improve and correct the region; to prevent similar problems from reoccurring.
The third early warning information generates a third decision scheme comprising: adjusting the rotation rate, stirring time and liquid stirring temperature of the stirrer; to improve stirring efficiency and uniformity.
The fourth early warning information generates a fourth decision scheme comprising: checking whether the aperture of the filtering equipment is blocked, and cleaning and maintaining the filtering equipment; ensuring that the filtration efficiency and rate meet the criteria.
The fifth early warning information generates a fifth decision scheme comprising: the control of the pH value, the microorganism content, the heavy metal content and the pesticide residue content is enhanced, the acceptable range is ensured, and the components are proportioned again, so that the component proportioning accords with a preset threshold value; ensuring the product quality to meet the requirements.
The sixth early warning information generates a second sixth strategy scheme, including: checking the thread length of the screw cap and improving the sealing process.
Embodiment 8, please refer to fig. 1, which includes a data acquisition module, a model building analysis module, an evaluation early warning module and a decision scheme generation module;
the data acquisition module comprises a first environmental data set acquisition unit, a second data set acquisition unit and a third production data set acquisition unit;
The first environmental data set acquisition unit is used for acquiring real-time environmental data of a target fruit juice food production area, including environmental temperature, humidity, oxygen concentration and PM2.5 concentration, and establishing a first environmental data set;
The second data set acquisition unit is used for adopting an image sensor or camera equipment to shoot images of target fruit juice foods in real time so as to identify appearance defects, mildewing, oxidation and crystallization characteristics; and collecting PH value, microorganism content, heavy metal content, pesticide residue content, component proportion data and package detection data; establishing a second data set;
The third production data set acquisition unit is used for acquiring production parameter data of the juicing and filtering clarification area in real time, wherein the production parameter data comprise the rotation rate of a stirrer, the stirring time, the liquid stirring temperature, the filtering rate, the filter pore diameter, the number of filter pores and the filtering time, and a third production data set is established;
the model building analysis module is used for building a digital analysis model, and processing, analyzing and calculating the first environment data set, the second data set and the third production data set to obtain: real-time environmental coefficient Ssx, first defect coefficient Qxx, stirring coefficient Jbx, filtering coefficient GLx, quality coefficient ZLx and packing tightness coefficient Bzx;
The evaluation early warning module is configured to compare the real-time environment coefficient Ssx, the first defect coefficient Qxx, the stirring coefficient Jbx, the filtering coefficient GLx, the quality coefficient ZLx and the packing tightness coefficient Bzx with the first environment threshold value X1, the second appearance threshold value X2, the third stirring efficiency threshold value X3, the fourth filtering efficiency threshold value X4, the fifth quality threshold value X5 and the sixth packing threshold value X6, respectively, to obtain corresponding evaluation results, and generate corresponding early warning information according to the corresponding evaluation results;
the decision scheme generation module is used for generating a corresponding decision scheme according to the corresponding early warning information.
In this embodiment, the data acquisition module includes three key parts: a first environmental data set acquisition unit, a second data set acquisition unit, and a third production data set acquisition unit. The units are respectively responsible for collecting real-time environment data, image characteristics and production parameter data to form a comprehensive data set, and provide a basis for subsequent analysis and decision. Next, the model building analysis module processes the first environmental dataset, the second dataset, and the third production dataset using a digital analysis model to obtain a real-time environmental coefficient Ssx, a first defect coefficient Qxx, a stirring coefficient Jbx, a filtration coefficient GLx, a quality coefficient ZLx, and a packing tightness coefficient Bzx. The coefficients reflect the states and performances of various aspects of the production line, and provide important basis for subsequent evaluation and early warning.
Then, the evaluation and early warning module compares the real-time environment coefficient Ssx, the first defect coefficient Qxx, the stirring coefficient Jbx, the filtering coefficient GLx, the quality coefficient ZLx and the packing tightness coefficient Bzx with the threshold according to the set threshold (X1 to X6) to generate a corresponding evaluation result. Once an anomaly is found, the system will generate corresponding pre-warning information, suggesting that a problem may exist in the production line.
And finally, the decision scheme generating module generates a specific decision scheme according to the evaluation result. These include adjusting environmental parameters, rejecting defective products, adjusting production parameters, etc. Each scheme is helpful for timely solving the problems in the production line, and ensures the product quality and the production efficiency.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A quality automatic detection method of a food processing production line is characterized by comprising the following steps of: comprises the steps of,
Firstly, arranging a plurality of sensor devices and image acquisition devices in a plurality of production areas of a target fruit juice food, setting detection points, and determining the areas represented by the detection points and the edges of the represented areas; collecting real-time environmental data of a target fruit juice food in a plurality of production areas, specifically environmental temperature Wd, humidity Sd, oxygen concentration O 2 Nd and PM2.5 concentration data PM; establishing a first environmental data set;
step two, collecting appearance defects, pH value, microorganism content, heavy metal content, pesticide residue content and component proportion data and package detection data of target foods in a plurality of production processes in real time; establishing a second data set;
Step three, acquiring production parameter data in a plurality of production areas in real time; establishing a third production dataset;
Step four, a digital analysis model is established, and the first environmental data set, the second data set and the third production data set are processed, analyzed and calculated to obtain: real-time environmental coefficient Ssx, first defect coefficient Qxx, stirring coefficient Jbx, filtering coefficient GLx, quality coefficient ZLx and packing tightness coefficient Bzx;
Fifthly, comparing the real-time environment coefficient Ssx, the first defect coefficient Qxx, the stirring coefficient Jbx, the filtering coefficient GLx, the quality coefficient ZLx and the packing tightness coefficient Bzx with a first environment threshold value X1, a second appearance threshold value X2, a third stirring efficiency threshold value X3, a fourth filtering efficiency threshold value X4, a fifth quality threshold value X5 and a sixth packing threshold value X6 respectively to obtain corresponding evaluation results, and generating corresponding early warning information according to the corresponding evaluation results;
and step six, generating a corresponding decision scheme according to the corresponding early warning information.
2. The automatic quality detection method for a food processing line according to claim 1, wherein: the first step comprises the following steps:
S11, setting detection points in a plurality of production areas of fruit juice foods, including fruit preparation, juicing, filtering, clarifying, sterilizing, preserving and blending packaging areas, and arranging a plurality of sensor devices and image acquisition devices in the detection points;
S12, collecting real-time environment data in a plurality of detection points, marking corresponding time stamps on the real-time environment data generated in different production stages, and establishing a first environment data set;
The method comprises the steps of extracting ambient temperature Wd, humidity Sd, oxygen concentration O 2 Nd and PM2.5 concentration data PM in a first ambient data set, wherein the ambient temperature Wd is obtained through direct measurement of a temperature sensor, the humidity Sd is obtained through direct measurement of a humidity sensor, the oxygen concentration O 2 Nd is obtained through direct measurement of an oxygen concentration sensor, and the PM2.5 concentration data PM is obtained through direct measurement of a resistance sensor.
3. The automatic quality detection method for a food processing line according to claim 2, wherein: the second step comprises the following steps:
s21, arranging an image sensor or camera equipment, shooting images of target fruit juice foods in a production area in real time, extracting the images in each production area by utilizing an image identification technology, and identifying mildew features, oxidation features and fruit juice crystallization features of fruits by utilizing a texture and color space technology;
And analyzing and calculating the mildew point characteristics, the color change characteristics and the juice crystallization to obtain the product: mold formation coefficient Fm, oxidation coefficient Yh and crystallization coefficient JJ;
S22, disposing a pH sensor, a microorganism sensor, a heavy metal detection instrument, a pesticide residue detection instrument and a component sensor at a plurality of detection points of a production area, and collecting pH value, microorganism content Ws, heavy metal content ZJS, pesticide residue content NYc and component proportioning value CFpb in real time;
S23, installing a vacuum detection sensor in a packaging area, detecting sealing performance data of the juice package, and obtaining an air leakage value LQz; after pretreatment of the mildew coefficient Fm, the oxidation coefficient Yh, the crystallization coefficient JJ, the pH value, the microorganism content Ws, the heavy metal content ZJS, the pesticide residue content NYc, the component ratio value CFpb and the air leakage value LQz, a second data set is established.
4. A method for automatically detecting the quality of a food processing line according to claim 3, wherein: the mildew coefficient Fm and the oxidation coefficient Yh are obtained in the following way: extracting a fruit mildew area mdmj in the image, a fruit oxidation blackening and grey hair area yhmj in the image and a surface area bmj of the extracted fruit; the mildew coefficient Fm and the oxidation coefficient Yh are calculated by the following formula:
The crystallization coefficient JJ is obtained by the following steps: extracting a crystallization area of juice in the glass bottle, separating the crystallization area from other areas in the image by adopting an image segmentation technology, measuring and obtaining the crystallization area jjmj, and measuring and calculating the juice area gzmj of the glass bottle; the crystallization coefficient JJ is obtained by the following formula:
5. The automatic quality inspection method for a food processing line according to claim 4, wherein: the third step comprises the following steps: production parameters of the juice extraction and filtration clarification zone, including stirrer rotation rate jbsl, stirring time sj1, liquid stirring temperature jbwd, filtration rate glsl, filter pore size kj, number of filter pores slz and filtration time sj2, are collected and a third production dataset is established.
6. The automatic quality inspection method for a food processing line according to claim 5, wherein: cleaning, smoothing, filtering and dimensionless processing the environmental temperature Wd, the humidity Sd, the oxygen concentration O 2 Nd and the PM2.5 concentration data PM, and generating a real-time environmental coefficient Ssx through the following formula;
wherein Q 1 represents a target fruit juice food preset temperature threshold, Q 2 represents a target fruit juice food preset humidity threshold, Q 3 represents a target fruit juice food preset oxygen concentration threshold, Q 4 represents a target fruit juice food preset PM2.5 concentration threshold, w1, w2, w3, and w4 represent weight values, and 0< w1<1,0< w2<1,0< w3<1,0< w4<1, and w1+w2+w3+w4=1.0; a 1 denotes a first correction constant.
7. The automatic quality inspection method for a food processing line according to claim 6, wherein: generating a first defect coefficient Qxx by performing the following correlation formula on a mildew coefficient Fm, an oxidation coefficient Yh and a crystallization coefficient JJ:
Qxx＝w5*Fm+w6*Yh+w7*JJ+A2
Wherein w5, w6 and w7 represent preset scaling factors of the mildew coefficient Fm, the oxidation coefficient Yh and the crystallization coefficient JJ, respectively, and 0< w5<1,0< w6<1,0< w7<1, and w5+w6+w7=1.0; a 2 denotes a second correction constant;
The PH value, the microorganism content Ws, the heavy metal content ZJS, the pesticide residue content NYc and the component proportion value CFpb; after dimensionless treatment, the mass coefficient ZLx is calculated by the following formula:
Wherein: y 1 represents a target fruit juice food preset pH value threshold value, Y 2 represents a target fruit juice food preset microorganism content threshold value, Y 3 represents a target fruit juice food preset heavy metal content threshold value, Y 4 represents a target fruit juice food preset pesticide residue content threshold value, Y 5 represents a target fruit juice food preset ingredient proportioning threshold value, r1, r2, r3, r4 and r5 represent weight values, and 0< r1<1,0< r2<1,0< r3<1,0< r4<1,0< r5<1, and r1+r2+r3+r4+r5=1.0; ; a 3 denotes a third correction constant;
After the rotation rate jbsl of the stirrer, the stirring time sj1, the liquid stirring temperature jbwd, the filtration rate glsl, the filter pore size kj, the number of filter pores slz, and the filtration time sj2 were subjected to dimensionless processing, a stirring coefficient Jbx and a filtration coefficient GLx were obtained by calculation by the following formulas:
Wherein: e1, E2, E3, and E4 represent weight values, and e1+e2=1.0; e3+e4=1.0; and 0< e1<1,0< e2<1,0< e3<1,0< e4<1; ln represents a logarithmic operation;
The obtaining mode of the packing tightness coefficient Bzx is that the air leakage value LQz of the vacuum detection of the juice packing is obtained, the screw length Lwcd of the screw cap in the packing mode is obtained, and the packing tightness coefficient Bzx is obtained through calculation according to the following formula:
8. the automatic quality inspection method for a food processing line according to claim 7, wherein: the fifth step comprises the following steps:
s51, comparing the real-time environment coefficient Ssx with a first environment threshold X1 to obtain a first evaluation result, including: when the real-time environment coefficient Ssx is larger than the first environment threshold X1, the real-time environment of the production area is indicated to be unqualified, and first early warning information is generated; when the real-time environment coefficient Ssx is less than or equal to a first environment threshold value X1, representing that the real-time environment of the production area is qualified;
S52, comparing the first defect coefficient Qxx with a second appearance threshold X2 to obtain a second evaluation result, wherein the second evaluation result comprises: when the first defect coefficient Qxx is larger than the second appearance threshold value X2, the fruits are defective and unqualified, and second early warning information is generated; when the first defect coefficient Qxx is less than or equal to a second appearance threshold value X2, the fruit is qualified without defects;
s53, comparing the stirring coefficient Jbx with a third stirring efficiency threshold X3 to obtain a third evaluation result, including: when the stirring coefficient Jbx is smaller than a third stirring efficiency threshold X3, the stirring speed is not qualified, and third early warning information is generated; when the stirring coefficient Jbx is more than or equal to a third stirring efficiency threshold X3, the stirring rate is qualified;
S54, comparing the filtering coefficient GLx with a fourth filtering efficiency threshold X4 to obtain a fourth evaluation result, wherein the fourth evaluation result comprises: when the filtering coefficient GLx is smaller than the fourth filtering efficiency threshold value X4, the filtering rate is unqualified, and fourth early warning information is generated; when the filtering coefficient GLx is more than or equal to a fourth filtering efficiency threshold value X4, the filtering rate is qualified;
S55, comparing the quality coefficient ZLx with a fifth quality threshold X5 to obtain a fifth evaluation result, including: when the quality coefficient ZLx is larger than a fifth quality threshold X5, the quality is unqualified, and fifth early warning information is generated; when the quality coefficient ZLx is less than or equal to a fifth quality threshold X5, the quality is qualified;
S56, comparing the packing tightness coefficient Bzx with a sixth packing threshold X6 to obtain a sixth evaluation result, including: when the packing tightness coefficient Bzx is larger than a sixth packing threshold X6, the packing is unqualified, and sixth early warning information is generated; and when the packing tightness coefficient Bzx is less than or equal to a sixth packing threshold X6, the packing is qualified.
9. The automatic quality inspection method for a food processing line according to claim 8, wherein: the sixth step comprises the following steps:
The first early warning information generates a first decision scheme comprising: adopting measures to adjust environmental parameters to enable the current environmental parameters to meet the requirements, and checking and maintaining temperature, humidity, oxygen concentration and PM2.5 concentration detection equipment;
The second early warning information generates a second decision scheme comprising: removing defective fruits from the production line, and ensuring that only fruits meeting quality standards enter the next stage of processing; checking the region causing fruit defects in the production process, and taking measures to improve and correct the region;
The third early warning information generates a third decision scheme comprising: adjusting the rotation rate, stirring time and liquid stirring temperature of the stirrer;
The fourth early warning information generates a fourth decision scheme comprising: checking whether the aperture of the filtering equipment is blocked, and cleaning and maintaining the filtering equipment;
The fifth early warning information generates a fifth decision scheme comprising: the control of the pH value, the microorganism content, the heavy metal content and the pesticide residue content is enhanced, the acceptable range is ensured, and the components are proportioned again, so that the component proportioning accords with a preset threshold value;
The sixth early warning information generates a second sixth strategy scheme, including: checking the thread length of the screw cap and improving the sealing process.
10. An automatic quality detection system for a food processing line, comprising a method for automatically detecting quality of a food processing line according to any one of claims 1 to 9, characterized in that: the system comprises a data acquisition module, a model building analysis module, an evaluation early warning module and a decision scheme generation module;
the data acquisition module comprises a first environmental data set acquisition unit, a second data set acquisition unit and a third production data set acquisition unit;
The first environmental data set acquisition unit is used for acquiring real-time environmental data of a target fruit juice food production area, including environmental temperature, humidity, oxygen concentration and PM2.5 concentration, and establishing a first environmental data set;
The second data set acquisition unit is used for adopting an image sensor or camera equipment to shoot images of target fruit juice foods in real time so as to identify appearance defects, mildewing, oxidation and crystallization characteristics; and collecting PH value, microorganism content, heavy metal content, pesticide residue content, component proportion data and package detection data; establishing a second data set;
The third production data set acquisition unit is used for acquiring production parameter data of the juicing and filtering clarification area in real time, wherein the production parameter data comprise the rotation rate of a stirrer, the stirring time, the liquid stirring temperature, the filtering rate, the filter pore diameter, the number of filter pores and the filtering time, and a third production data set is established;
the model building analysis module is used for building a digital analysis model, and processing, analyzing and calculating the first environment data set, the second data set and the third production data set to obtain: real-time environmental coefficient Ssx, first defect coefficient Qxx, stirring coefficient Jbx, filtering coefficient GLx, quality coefficient ZLx and packing tightness coefficient Bzx;
The evaluation early warning module is configured to compare the real-time environment coefficient Ssx, the first defect coefficient Qxx, the stirring coefficient Jbx, the filtering coefficient GLx, the quality coefficient ZLx and the packing tightness coefficient Bzx with the first environment threshold value X1, the second appearance threshold value X2, the third stirring efficiency threshold value X3, the fourth filtering efficiency threshold value X4, the fifth quality threshold value X5 and the sixth packing threshold value X6, respectively, to obtain corresponding evaluation results, and generate corresponding early warning information according to the corresponding evaluation results;
the decision scheme generation module is used for generating a corresponding decision scheme according to the corresponding early warning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410110153.5A CN117928647B (en) | 2024-01-26 | 2024-01-26 | Automatic quality detection method and system for food processing production line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410110153.5A CN117928647B (en) | 2024-01-26 | 2024-01-26 | Automatic quality detection method and system for food processing production line |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117928647A true CN117928647A (en) | 2024-04-26 |
| CN117928647B CN117928647B (en) | 2024-09-20 |
Family
ID=90768200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410110153.5A Active CN117928647B (en) | 2024-01-26 | 2024-01-26 | Automatic quality detection method and system for food processing production line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117928647B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103072740A (en) * | 2013-02-04 | 2013-05-01 | 广东省潮州市质量计量监督检测所 | Soft packaging bag |
| KR20190032166A (en) * | 2018-03-19 | 2019-03-27 | 박선민 | Food integrated logistics system |
| CN214437162U (en) * | 2021-01-27 | 2021-10-22 | 山东省食品药品检验研究院 | Centrifugal filtering device for food detection |
| CN113741601A (en) * | 2021-11-08 | 2021-12-03 | 伟龙食品有限公司 | Food processing data processing method and system and electronic equipment |
| CN115263502A (en) * | 2022-09-01 | 2022-11-01 | 潍柴动力股份有限公司 | PN filtering efficiency control method, device and system |
| CN115399631A (en) * | 2021-05-28 | 2022-11-29 | 佛山市顺德区美的电热电器制造有限公司 | Stirring control method, cooking equipment, control device and readable storage medium |
| CN116934359A (en) * | 2023-09-15 | 2023-10-24 | 深圳市金谷园实业发展有限公司 | Food safety full-flow supervision system based on Internet |
| CN117314477A (en) * | 2023-11-28 | 2023-12-29 | 深圳前海粤十信息技术有限公司 | Import cold chain food traceability system of traceing back carries out secondary |
-
2024
- 2024-01-26 CN CN202410110153.5A patent/CN117928647B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103072740A (en) * | 2013-02-04 | 2013-05-01 | 广东省潮州市质量计量监督检测所 | Soft packaging bag |
| KR20190032166A (en) * | 2018-03-19 | 2019-03-27 | 박선민 | Food integrated logistics system |
| CN214437162U (en) * | 2021-01-27 | 2021-10-22 | 山东省食品药品检验研究院 | Centrifugal filtering device for food detection |
| CN115399631A (en) * | 2021-05-28 | 2022-11-29 | 佛山市顺德区美的电热电器制造有限公司 | Stirring control method, cooking equipment, control device and readable storage medium |
| CN113741601A (en) * | 2021-11-08 | 2021-12-03 | 伟龙食品有限公司 | Food processing data processing method and system and electronic equipment |
| CN115263502A (en) * | 2022-09-01 | 2022-11-01 | 潍柴动力股份有限公司 | PN filtering efficiency control method, device and system |
| CN116934359A (en) * | 2023-09-15 | 2023-10-24 | 深圳市金谷园实业发展有限公司 | Food safety full-flow supervision system based on Internet |
| CN117314477A (en) * | 2023-11-28 | 2023-12-29 | 深圳前海粤十信息技术有限公司 | Import cold chain food traceability system of traceing back carries out secondary |
Non-Patent Citations (3)
| Title |
|---|
| 中国农业机械化科学研究院编: "农业机械设计手册", 30 April 1988, 机械工业出版社, pages: 753 - 754 * |
| 张家豪: "食品安全在线智能化检测关键技术的研究", 食安管理, 31 October 2022 (2022-10-31), pages 13 - 15 * |
| 谢尉扬等: "发电机严密性试验结果分析", 浙江电力, no. 3, 31 March 2000 (2000-03-31), pages 6 - 9 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117928647B (en) | 2024-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115018844B (en) | Plastic film quality evaluation method based on artificial intelligence | |
| CN109584225B (en) | Unsupervised defect detection method based on self-encoder | |
| CN110349153A (en) | The image method tobacco based on multi-feature fusion detection method of rate containing stalk | |
| CN115876258B (en) | Livestock and poultry breeding environment abnormity monitoring and alarming system based on multi-source data | |
| CN110473194A (en) | Fruit surface defect detection method based on more image block Threshold Segmentation Algorithms | |
| CN111007061A (en) | Pesticide residue detection method and system | |
| CN116843236A (en) | Food storage supervision system based on artificial intelligence | |
| EP3896650A1 (en) | Quality control system for series production | |
| CN118090730B (en) | Machine vision-based method and system for detecting maturity of pomegranate fermented black tea | |
| Syahrir et al. | Color grading in tomato maturity estimator using image processing technique | |
| CN117928647B (en) | Automatic quality detection method and system for food processing production line | |
| CN116165220B (en) | AOI (automated optical inspection) internal view detection device and method based on artificial intelligence | |
| WO2023226103A1 (en) | Leaf structure measurement method during threshing, redrying and air separation process and leaf outlet amount measurement method of air separator | |
| CN103743697A (en) | Method for monitoring tea production in real time by adopting near infrared spectrum | |
| CN111028250A (en) | Real-time intelligent cloth inspecting method and system | |
| Puchalski et al. | Image analysis for apple defect detection | |
| CN111007074B (en) | Rapid judgment method for blackening of 3104 tank body material after pasteurization | |
| CN117115142B (en) | Electronic element defect rapid detection method based on artificial intelligence | |
| Zhou et al. | Computer vision-based method for online measuring the moisture of iron ore green pellets in disc pelletizer | |
| CN117804551B (en) | Ginseng raw material cleaning quality control management system for ginsenoside extraction | |
| CN118128788B (en) | Semiconductor high temperature diffusion furnace fan filtration system based on accurate control | |
| CN118549370B (en) | Milk urea nitrogen detection system for milk cow health diagnosis | |
| Peng et al. | Maturity analysis of citrus based on machine vision and android mobile platform technology | |
| CN118362569A (en) | Intelligent detection method and system for packaging defects of prefabricated vegetable plastic packages | |
| CN115266746A (en) | Visual detection method for imaging appearance quality of small channel box |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240830 Address after: No. 11 Kechuang Road, High tech Industrial Development Zone, Shizheng Town, Pingyuan County, Meizhou City, Guangdong Province, China 514600 Applicant after: Guangdong Xingzhu Biotechnology Co.,Ltd. Country or region after: China Address before: No. 183-168, Liqiao Section, Longtang Road, Liqiao Town, Shunyi District, Beijing, 101300 Applicant before: China International Trade Union Heng Technology Development (Beijing) Co.,Ltd. Country or region before: China |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |