CN117752020A - Efficient continuous production method of fermented feed - Google Patents
Efficient continuous production method of fermented feed Download PDFInfo
- Publication number
- CN117752020A CN117752020A CN202311842767.4A CN202311842767A CN117752020A CN 117752020 A CN117752020 A CN 117752020A CN 202311842767 A CN202311842767 A CN 202311842767A CN 117752020 A CN117752020 A CN 117752020A
- Authority
- CN
- China
- Prior art keywords
- fermentation
- product
- component
- continuous production
- image data
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000010924 continuous production Methods 0.000 title claims abstract description 22
- 238000000855 fermentation Methods 0.000 claims abstract description 249
- 230000004151 fermentation Effects 0.000 claims abstract description 249
- 230000007246 mechanism Effects 0.000 claims description 36
- 230000004044 response Effects 0.000 claims description 13
- 239000002994 raw material Substances 0.000 claims description 10
- 238000003892 spreading Methods 0.000 claims description 9
- 230000007480 spreading Effects 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000000513 principal component analysis Methods 0.000 claims description 4
- 238000013136 deep learning model Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 8
- 239000000463 material Substances 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000000813 microbial effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000013598 vector Substances 0.000 description 3
- FERIUCNNQQJTOY-UHFFFAOYSA-N Butyric acid Chemical compound CCCC(O)=O FERIUCNNQQJTOY-UHFFFAOYSA-N 0.000 description 2
- KDLHZDBZIXYQEI-UHFFFAOYSA-N Palladium Chemical compound [Pd] KDLHZDBZIXYQEI-UHFFFAOYSA-N 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 235000016709 nutrition Nutrition 0.000 description 2
- 239000007858 starting material Substances 0.000 description 2
- 238000003756 stirring Methods 0.000 description 2
- YNHJECZULSZAQK-UHFFFAOYSA-N tetraphenylporphyrin Chemical compound C1=CC(C(=C2C=CC(N2)=C(C=2C=CC=CC=2)C=2C=CC(N=2)=C(C=2C=CC=CC=2)C2=CC=C3N2)C=2C=CC=CC=2)=NC1=C3C1=CC=CC=C1 YNHJECZULSZAQK-UHFFFAOYSA-N 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- GTZCNONABJSHNM-UHFFFAOYSA-N 5,10,15,20-tetraphenyl-21,23-dihydroporphyrin zinc Chemical compound [Zn].c1cc2nc1c(-c1ccccc1)c1ccc([nH]1)c(-c1ccccc1)c1ccc(n1)c(-c1ccccc1)c1ccc([nH]1)c2-c1ccccc1 GTZCNONABJSHNM-UHFFFAOYSA-N 0.000 description 1
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 241000894006 Bacteria Species 0.000 description 1
- 241000186000 Bifidobacterium Species 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 241000186660 Lactobacillus Species 0.000 description 1
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 1
- 244000046052 Phaseolus vulgaris Species 0.000 description 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- GEEDIXASGRLHHJ-UHFFFAOYSA-L [Fe](Cl)Cl.C1(=CC=CC=C1)C1=C2C=CC(C(=C3C=CC(=C(C=4C=CC(=C(C5=CC=C1N5)C5=CC=CC=C5)N4)C4=CC=CC=C4)N3)C3=CC=CC=C3)=N2 Chemical compound [Fe](Cl)Cl.C1(=CC=CC=C1)C1=C2C=CC(C(=C3C=CC(=C(C=4C=CC(=C(C5=CC=C1N5)C5=CC=CC=C5)N4)C4=CC=CC=C4)N3)C3=CC=CC=C3)=N2 GEEDIXASGRLHHJ-UHFFFAOYSA-L 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 description 1
- CVKFXBUVLBFHGO-UHFFFAOYSA-N cobalt 5,10,15,20-tetraphenyl-21,23-dihydroporphyrin Chemical compound [Co].c1cc2nc1c(-c1ccccc1)c1ccc([nH]1)c(-c1ccccc1)c1ccc(n1)c(-c1ccccc1)c1ccc([nH]1)c2-c1ccccc1 CVKFXBUVLBFHGO-UHFFFAOYSA-N 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- RKTYLMNFRDHKIL-UHFFFAOYSA-N copper;5,10,15,20-tetraphenylporphyrin-22,24-diide Chemical compound [Cu+2].C1=CC(C(=C2C=CC([N-]2)=C(C=2C=CC=CC=2)C=2C=CC(N=2)=C(C=2C=CC=CC=2)C2=CC=C3[N-]2)C=2C=CC=CC=2)=NC1=C3C1=CC=CC=C1 RKTYLMNFRDHKIL-UHFFFAOYSA-N 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 235000019634 flavors Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 208000028774 intestinal disease Diseases 0.000 description 1
- 229940039696 lactobacillus Drugs 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000050 nutritive effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 235000019629 palatability Nutrition 0.000 description 1
- 229910052763 palladium Inorganic materials 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000000741 silica gel Substances 0.000 description 1
- 229910002027 silica gel Inorganic materials 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Landscapes
- Apparatus Associated With Microorganisms And Enzymes (AREA)
Abstract
The invention discloses a high-efficiency continuous production method of fermented feed, and relates to the technical field of feed fermentation control. And (3) by arranging a first acquisition device on the fermentation bag, extracting granularity characteristics, uniformity characteristics, color characteristics and porosity characteristics of the fermentation component through image vision processing, and judging whether the fermentation component is converted into a first fermentation product. Further, the first fermentation product is monitored through the second collecting device, whether the second fermentation product is obtained is judged according to monitoring of volatile gas components in the fermentation process of the first fermentation product in the fermentation zone, and classification of the second fermentation product is automatically carried out. According to the technical scheme, the feed fermentation control effect is effectively improved, and the multi-stage feed fermentation process is monitored and accurately controlled in an omnibearing manner. In addition, the invention also discloses a control system for realizing the feed fermentation control method, and automatic and intelligent feed fermentation control is realized.
Description
Technical Field
The invention relates to the technical field of feed fermentation control, in particular to a high-efficiency continuous production method of fermented feed.
Background
The feed production plays an important role in modern agriculture, and the production of high-quality and differentiated feed products is an important foundation for the high-quality development of the current agriculture. Different from the traditional feed production, various microbial feeds are widely applied in the field of cultivation due to high nutritional value and excellent palatability, and the production of the microbial feeds is not separated from the participation of the fermentation process. The traditional fermentation mainly adopts stacked fermentation, trough fermentation and pool fermentation, the automation level is low, the fermentation process is completely dependent on the experience of staff, and because the fermentation process is not controllable, the fermentation process is extremely easy to be influenced by external factors, and the automation of feed fermentation and the accurate identification of the fermentation process are particularly important.
In the prior art, CN112126582A discloses a fodder fermentation self-detecting equipment, realizes fodder fermentation cycle sampling through mechanical structure's optimization to judge fodder fermentation progress and process, but this technical scheme does not consider the multiple stage of fodder fermentation, and the sample needs the manual work to detect and judges the fermentation process, and the degree of automation is lower. In general, most microbial feeds are multi-staged in fermentation process, and require multiple additions of starter or other microbial agents for production during the whole fermentation process, and the prior art lacks a control method for the whole fermentation process of the feed.
Disclosure of Invention
In order to solve the problems, the invention provides a high-efficiency continuous production method of fermented feed, which is characterized in that a first acquisition device is used for identifying the fermentation state of a fermentation component, a first fermentation product is accurately obtained, a second acquisition device is used for identifying the fermentation state of the first fermentation product, a second fermentation product is accurately obtained, and the fermented feed is divided into different types of feeds based on the characteristic identification of the second fermentation product. Furthermore, the invention also provides a control system for realizing the efficient continuous production method of the fermented feed, which is used for realizing the whole-process automatic production and integrated monitoring control of the feed.
The aim of the invention can be achieved by the following technical means:
a high-efficiency continuous production method of fermented feed comprises the following steps:
step 1: a first acquisition device is arranged on the fermentation belt, a second acquisition device is arranged in the plurality of fermentation areas, and the first acquisition device and the second acquisition device are both connected to the fermentation controller;
step 2: the batching mechanism conveys raw materials to the feeding mechanism according to a fermentation plan, and the feeding mechanism mixes the raw materials to obtain fermentation components and conveys the fermentation components to the fermentation belt;
step 3: the first acquisition device periodically acquires image data of the fermentation component and sends the image data to the fermentation controller;
step 4: the fermentation controller periodically extracts the characteristics of the image data, if the fermentation component is converted into a first fermentation product, the step 5 is carried out, otherwise, the step 3 is returned to;
step 5: the feeding mechanism conveys the first fermentation product to the fermentation zone, and the spreading mechanism uniformly spreads the first fermentation product in the fermentation zone;
step 6: the second acquisition device periodically acquires fermentation data in the fermentation area and sends the fermentation data to the fermentation controller;
step 7: if the fermentation data has the first characteristic, converting the first fermentation product into a second fermentation product, entering step 8, otherwise, returning to step 6;
step 8: extracting a second characteristic of fermentation data, and distributing a fermentation label to each fermentation zone based on the second characteristic, wherein any fermentation zone corresponds to a unique fermentation label to form a classification criterion;
step 9: the feeding mechanism obtains classification criteria, and conveys the second fermentation product in each fermentation zone to the feeding zone based on the classification criteria.
In the invention, the fermentation controller comprises image data characteristics corresponding to the first fermentation product under the fermentation component, and the image data characteristics form a training set and a testing set.
In the invention, in the step 3, after the image data of the fermentation component is input into the fermentation controller, the image data characteristics are extracted, and the similarity between the fermentation component and the first fermentation product is compared based on the deep learning model.
In the present invention, the image data features include granularity features, uniformity features, tint features, and porosity features.
In the invention, in the step 6, the specific volatile gas which is continuously released in the process of converting the first fermentation product into the second fermentation product is reacted with the second collecting device in a color reaction.
In the invention, the chromogenic reaction is a RGB lattice diagram of a 3X 3 array, and the fermentation data is the response difference value of a plurality of groups of RGB.
In the present invention, the first characteristic is a difference in the response of RGB corresponding to the second fermentation product under the fermentation component, and the second characteristic is a main component of the difference in the response of RGB corresponding to the second fermentation product under the fermentation component.
In the present invention, the principal component of the response difference of RGB is obtained by performing principal component analysis on the fermentation data, and the principal components are arranged from large to small in variance.
The implementation of the high-efficiency continuous production method of the fermented feed has the beneficial effects that: through the image data characteristic extraction of the first acquisition device, the feed can enter the next fermentation process at the most appropriate time point, and the granularity, uniformity, color and porosity of the fermentation components are accurately identified, so that the fineness of feed production is enhanced, and the nutritional value of the feed is enriched. In addition, through the second collection device extraction fermentation data, can judge the key node that first fermentation product changed into second fermentation product, and can combine fermentation data to classify second fermentation product, divide the fodder grade according to the effect of fodder fermentation. According to the technical scheme disclosed by the invention, the feed fermentation control system can realize high automation and intellectualization, accurately control the feed fermentation process, and adjust and optimize according to actual conditions.
Drawings
FIG. 1 is a flow chart of a process for the efficient continuous production of fermented feed of the present invention;
FIG. 2 is a schematic diagram of a control system for implementing the efficient continuous production process of fermented feed of the present invention;
FIG. 3 is a schematic diagram of a sensor array of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Example 1
According to the technical scheme disclosed by the invention, the related feed is understood to be a microbial feed, and lactobacillus, butyric acid bacteria and bifidobacteria with unique flavor and higher nutritive value are obtained by fermenting bean raw materials, so that the occurrence risk of intestinal diseases in the feeding process can be effectively reduced. As an aspect of the present application, to address automation in feed fermentation and production processes, and to precisely control the various stages of feed fermentation, the present application provides a specific embodiment of a high-efficiency continuous production method of fermented feed, comprising two implementation stages:
system configuration stage:
and (3) making a fermentation plan, wherein standard fermentation components can be generated based on the fermentation plan, and the specific implementation of the technical scheme is generated and configured according to the requirements of the fermentation plan.
The fermentation controller receives the fermentation plan and invokes image data features that are the decision criteria for the fermentation component under the fermentation plan to obtain the first fermentation product. In this embodiment, the fermentation controller includes image data features of the fermentation component corresponding to the first fermentation product, where the image data features form a training set and a testing set.
The fermentation controller receives a fermentation plan and invokes a first feature and a second feature, wherein the first feature is a judgment standard for obtaining a second fermentation product by a first fermentation product under the fermentation plan, and the judgment standard is understood as a response difference value of RGB (red, green and blue) of a corresponding second fermentation product under a fermentation component; the classification criterion of the second fermentation product under the fermentation plan based on the second characteristic is understood as a principal component of the response difference of RGB corresponding to the second fermentation product under the fermentation component, the principal component is obtained by performing principal component analysis on fermentation data, and the principal components are arranged according to the variance from large to small.
In this embodiment, the fermentation plan may be used as an input to the present solution, and the preferred fermentation plan is a configuration file, which is used to formulate the basic rules of the system implementation stage.
The system implementation stage:
a method for the efficient continuous production of fermented feed, see fig. 1, comprising the steps of:
step 1: a first acquisition device is arranged on the fermentation belt, a second acquisition device is arranged in the fermentation areas, and the first acquisition device and the second acquisition device are both connected to the fermentation controller. In this embodiment, a wireless sensor network is formed among the first collecting device, the second collecting devices and the fermentation controller, wherein a plurality of second collecting devices are arranged in any one fermentation area, and the second collecting devices are uniformly arranged in the fermentation area.
Further, data transmission is performed between the first acquisition device and the second acquisition device through the LoRa technology, so that communication interference in a narrow area is reduced.
Step 2: the batching mechanism conveys raw materials to the feeding mechanism according to a fermentation plan, and the feeding mechanism mixes the raw materials to obtain fermentation components and conveys the fermentation components to the fermentation belt. In this example, the fermentation component is a product of mixing and stirring multiple materials, and further comprises a starter necessary for fermenting the feed.
Step 3: the first acquisition device periodically acquires image data of the fermentation component and sends the image data to the fermentation controller, and after the image data of the fermentation component is input into the fermentation controller, the image data characteristics are extracted, and the similarity between the fermentation component and the first fermentation product is compared based on the deep learning model.
In this embodiment, the first acquisition device is provided with an automatic triggering system, so as to automatically capture images periodically within a specific time interval, and perform real-time image processing on the captured images, where the processing includes denoising, enhancement and feature analysis, so as to obtain corrected image data.
Step 4: and (3) periodically extracting the characteristics of the image data by the fermentation controller, if the fermentation controller recognizes that the fermentation component is a first fermentation product, entering a step (5), otherwise, returning to the step (3). In this embodiment, the image data features include granularity features, uniformity features, tint features, and porosity features.
Step 5: the feeding mechanism conveys the first fermentation product to the fermentation zone, and the spreading mechanism uniformly spreads the first fermentation product in the fermentation zone. In this embodiment, the fermentation area is a plurality of fermentation tanks, and the spreading mechanism can uniformly and hierarchically place the first fermentation product in the fermentation area through a plurality of layers of conveyor belts, and the thickness of the spreading is determined by a fermentation plan.
Step 6: the second acquisition device periodically acquires fermentation data in the fermentation area and sends the fermentation data to the fermentation controller, wherein the first fermentation product is continuously released specific volatile gas in the process of being converted into the second fermentation product, the specific volatile gas and the second acquisition device generate a color reaction, the color reaction is a RGB lattice diagram of a 3 multiplied by 3 array, and the fermentation data is a response difference value of a plurality of groups of RGB.
Step 7: if the fermentation data has the first characteristic, if the first fermentation product is converted into the second fermentation product, the step 8 is performed, otherwise, the step 6 is performed;
step 8: extracting a second characteristic of fermentation data, and distributing a fermentation label to each fermentation zone based on the second characteristic, wherein any fermentation zone corresponds to a unique fermentation label to form a classification criterion;
step 9: the feeding mechanism obtains classification criteria, and conveys the second fermentation product in each fermentation zone to the feeding zone based on the classification criteria.
Example two
When the first acquisition device acquires the image data on the fermentation zone, preprocessing an original image, wherein the original image is an RGB space, converting the RGB space into an HSV space for better extracting the characteristics of the image data, counting the distribution of each pixel point V, screening abnormal pixel points based on a 3 sigma principle, and carrying out normalization processing on the brightness V of each point to obtain corrected pixel values.
Based on color characteristics generated by the image data of the fermentation components, extracting a plurality of characteristic variables, and calculating the average value of each channel of RGBVariance->Slope ofWherein P is ij The gray value of one pixel of the (i, j) coordinate point, and N is the total number of pixels in the region. In this embodiment, the feature variables are hue histogram, hue variance, hue mean, hue slope, saturation mean, saturation variance, saturation slope, brightness mean, brightness variance, and brightness slope.
Converting the image data into a statistical moment of the gray histogram, wherein the preferred statistical moment in this embodiment is global texture feature of the gray histogram, average gray valueStandard deviation->Wherein z is i Is gray scale, p (z i ) Is the gray z i L is the number of all grayscales in the gray level histogram.
Calculating the frequency of the gray level co-occurrence matrix according to the gray level moment of inertia, the gray level entropy and the gray level correlation of the gray level co-occurrence matrix
Where θ is the direction of generating the gray level co-occurrence matrix, and θ is preferably 0 °, 45 °, 90 °, and 135 °, d is the distance of generating the gray level co-occurrence matrix, and the frequency F (i, j, d, θ) of the gray level co-occurrence matrix is used as the texture feature.
Two-dimensional discrete wavelet decomposition is performed on the color image, and Harr wavelet is selected as a basis function. This breaks the image into subbands of different frequencies, including high frequency subbands GD in the horizontal and vertical directions 2 And DG 2 From GD 2 And DG 2 Information is extracted from the sub-bands to calculate the feature variables, the high frequency sub-bands containing high frequency texture information in the image.
Further, for each subbandCalculating an inertia value K 1 And K 2 The inertia value will be used to evaluate the degree of uniformity of the distribution of the image, for subband GD 2 Calculate GD 2 Pixel mean value of subband mu GD 2 Calculate GD 2 Pixel standard deviation sigma GD of subband 2 Computing GD from mean and standard deviation 2 Inertia value K of subband 1 GD 2 The method comprises the steps of carrying out a first treatment on the surface of the For subband DG 2 Calculation of DG 2 Pixel mean value of subband mu DG 2 Calculation of DG 2 Pixel standard deviation sigma DG of subband 2 DG is calculated from the mean and standard deviation 2 Inertia value K of subband 2 DG 2 Obtaining K 1 And K 2 Two characteristic variables.
Will K 1 And K 2 Two characteristic variables are input into a neural network model, if K 1 And K 2 And if the two characteristic variables are successfully matched with the image data characteristics, judging that the fermentation component is converted into a first fermentation product.
Example III
The second acquisition device periodically acquires fermentation data in the fermentation area, and generates a first characteristic and a second characteristic based on the fermentation data, wherein the first characteristic is used for obtaining a judgment standard of a second fermentation product from a first fermentation product under the fermentation plan, and a classification standard of the second fermentation product under the fermentation plan is generated based on the second characteristic. In a preferred embodiment of the invention, the generation of fermentation data comprises the steps of:
step 101: A3X 3 sensor array was constructed, and a reference value g (R 1 ,G 1 ,B 1 ) And the color sensitive material of the second collecting device contacts the volatile gas component in the fermentation area to generate a 3X 3 group RGB channel image.
Step 102: the first acquisition device extracts the characteristic of the RGB channel image, which is the change value g (R 2 ,G 2 ,B 2 ) The response difference Δg (Δr, Δg, Δb) of RGB is calculated from the reference value of the color sensitive material, where Δr=isr 1 -R 2 One, Δg=i G 1 -G 2 One, Δb=ib 1 -B 2 And I. In the present embodimentIn an example, when the response difference of RGB meets the first characteristic, the fermentation process is stopped, and the second acquisition device stops acquiring fermentation data.
Step 103: calculating covariance matrix of RGB corresponding difference value, element C of covariance matrix C ij The covariance between the variable x and the variable y is represented, and the eigenvalue and eigenvector of the covariance matrix C are analyzed, so that the variance of the principal component is the eigenvalue and the direction of the principal component is the eigenvector.
Step 104: selecting n principal components from large to small, projecting the principal components onto the selected principal components, and for any sample x, projecting the projection values O onto the principal components y xy =△R x ·v yR2 +△Gx·v yG2 +△Bx·v yB2 Wherein vy R2 Feature vector v on channel R for y principal components yG2 Feature vector v on channel G for y principal components yB2 For the feature vectors of y principal components on channel B, ΔR x For the corresponding difference of the channels R corresponding to the sample x, deltaB x For the corresponding difference of channel B corresponding to sample x, ΔG x The corresponding difference for channel G corresponding to sample x.
Further, after the first n principal components are selected, the weights of the n principal components in the classification criterion need to be determined, the weights representing the contribution of each principal component to the classification. In the present embodiment, the larger the eigenvalue, the larger the contribution of the principal component to the data variance, and thus the higher the weight can be assigned.
Step 105: calculating a composite score for the second fermentation product, the composite score S y =w 1 ·O xy1 +w 2 ·O xy2 +…+w n ·O xyn According to S y The feeding means obtains a classification criterion based on which the second fermentation product in each fermentation zone is to be fed to the feeding zone, said classification criterion being based on the principal component analysis and the projection values.
Example IV
As a second aspect of the present application, in order to achieve a more efficient continuous production method of fermented feed, a preferred embodiment of the present application further provides a control system for achieving a efficient continuous production method of fermented feed, referring to fig. 2, including a fermentation belt, a fermentation controller, a dosing mechanism, a feeding mechanism, a spreading mechanism, a feeding mechanism, a first collecting device, and a second collecting device;
wherein, the fermentation zone is connected with the feeding mechanism and the fermentation zone and is used for conveying fermentation components. The batching mechanism is connected with the feeding mechanism and is provided with a storage area for various raw materials. The feeding mechanism mixes a plurality of raw materials through stirring, and a raw material bin is arranged on the feeding mechanism and controls the speed of conveying fermentation components to the fermentation belt according to a fermentation plan. The spreading mechanism is arranged in the fermentation area and used for spreading the fermentation components in the fermentation area according to a certain thickness. The feeding mechanism is connected with the fermentation areas and the feeding areas, one feeding area corresponding to any fermentation area is provided with a unique feeding mechanism, and the feeding mechanism also comprises a material moving module and a conveying module;
the transfer module is configured to transfer the second fermentation product within the fermentation zone onto the transport module. The conveying module conveys the second fermentation product to a feeding area through belt rolling;
the fermentation controller controls the fermentation belt, the batching mechanism, the feeding mechanism, the spreading mechanism, the feeding mechanism, the first acquisition device and the second acquisition device through the wireless sensor network. The first collecting device is arranged above the fermentation penetrating belt. The second collecting device is arranged in the fermentation area and consists of a color sensitive material and a silica gel plate.
In this embodiment, referring to fig. 3, the second collecting device is a sensor array, a plurality of sensor units form the sensor array, and a single color sensitive material and a silicone plate form one sensor unit.
In this embodiment, the color sensitive material is composed of tetraphenylporphyrin, copper tetraphenylporphyrin, zinc tetraphenylporphyrin, iron chloride tetraphenylporphyrin, palladium tetraphenylporphyrin, and cobalt tetraphenylporphyrin.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.
Claims (8)
1. The efficient continuous production method of the fermented feed is characterized by comprising the following steps of:
step 1: a first acquisition device is arranged on the fermentation belt, a second acquisition device is arranged in the plurality of fermentation areas, and the first acquisition device and the second acquisition device are both connected to the fermentation controller;
step 2: the batching mechanism conveys raw materials to the feeding mechanism according to a fermentation plan, and the feeding mechanism mixes the raw materials to obtain fermentation components and conveys the fermentation components to the fermentation belt;
step 3: the first acquisition device periodically acquires image data of the fermentation component and sends the image data to the fermentation controller;
step 4: the fermentation controller periodically extracts the characteristics of the image data, if the fermentation component is converted into a first fermentation product, the step 5 is carried out, otherwise, the step 3 is returned to;
step 5: the feeding mechanism conveys the first fermentation product to the fermentation zone, and the spreading mechanism uniformly spreads the first fermentation product in the fermentation zone;
step 6: the second acquisition device periodically acquires fermentation data in the fermentation area and sends the fermentation data to the fermentation controller;
step 7: if the fermentation data has the first characteristic, converting the first fermentation product into a second fermentation product, entering step 8, otherwise, returning to step 6;
step 8: extracting a second characteristic of fermentation data, and distributing a fermentation label to each fermentation zone based on the second characteristic, wherein any fermentation zone corresponds to a unique fermentation label to form a classification criterion;
step 9: the feeding mechanism obtains classification criteria, and conveys the second fermentation product in each fermentation zone to the feeding zone based on the classification criteria.
2. The method for efficient continuous production of fermented feed according to claim 1, wherein the fermentation controller includes image data features corresponding to the first fermentation product under the fermentation component, and the image data features constitute a training set and a test set.
3. The method for efficient continuous production of fermented feed according to claim 1, wherein in step 3, after the image data of the fermented component is inputted into the fermentation controller, the image data characteristics are extracted, and the similarity between the fermented component and the first fermentation product is compared based on the deep learning model.
4. A method for efficient continuous production of fermented feed according to claim 3, characterized in that the image data features include particle size features, uniformity features, colour features and porosity features.
5. The method for efficient continuous production of fermented feed according to claim 1, wherein in step 6, the first fermentation product is continuously released specific volatile gas during the conversion into the second fermentation product, and the specific volatile gas reacts with the second collecting device in a color reaction.
6. The method for efficient continuous production of fermented feed according to claim 5, wherein the chromogenic reaction is a 3 x 3 array of RGB dot patterns, and the fermentation data is a response difference of a plurality of groups of RGB.
7. The method for efficient continuous production of fermented feed according to claim 1, wherein the first characteristic is a difference in response to RGB of the corresponding second fermented product under the fermented component, and the second characteristic is a main component of the difference in response to RGB of the corresponding second fermented product under the fermented component.
8. The method for efficient continuous production of fermented feed according to claim 7, wherein the principal components of the response difference of RGB are obtained by principal component analysis of the fermentation data, and the principal components are arranged in a variance from large to small.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311842767.4A CN117752020A (en) | 2023-12-29 | 2023-12-29 | Efficient continuous production method of fermented feed |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311842767.4A CN117752020A (en) | 2023-12-29 | 2023-12-29 | Efficient continuous production method of fermented feed |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117752020A true CN117752020A (en) | 2024-03-26 |
Family
ID=90320060
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311842767.4A Pending CN117752020A (en) | 2023-12-29 | 2023-12-29 | Efficient continuous production method of fermented feed |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117752020A (en) |
-
2023
- 2023-12-29 CN CN202311842767.4A patent/CN117752020A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101193317B (en) | Method and device for automatic white balance processing of the image | |
CN101383008A (en) | Image classification method based on visual attention model | |
CN106815560A (en) | It is a kind of to be applied to the face identification method that self adaptation drives seat | |
CN107610087A (en) | A kind of tongue fur automatic division method based on deep learning | |
CN104331714B (en) | Platinum flotation grade evaluation method based on image data extraction and neural net model establishing | |
CN108739052A (en) | A kind of system and method for edible fungi growth parameter optimization | |
CN112893159B (en) | Coal gangue sorting method based on image recognition | |
CN104850854A (en) | Talc ore product sorting processing method and talc ore product sorting system | |
CN109598200B (en) | Intelligent image identification system and method for molten iron tank number | |
CN109447111A (en) | A kind of remote sensing supervised classification method based on subclass training sample | |
CN102855641A (en) | Fruit level classification system based on external quality | |
CN106645180A (en) | Method for checking defects of substrate glass, field terminal and server | |
CN111881864A (en) | Wisdom farming crops growth full-period full-dynamic monitoring management system | |
CN111680738A (en) | Screening device for apple quality detection and detection method thereof | |
CN117752020A (en) | Efficient continuous production method of fermented feed | |
CN107146258B (en) | Image salient region detection method | |
CN113743523B (en) | Building rubbish fine classification method guided by visual multi-feature | |
CN111797840A (en) | Self-adaptive camouflage effect on-line evaluation and system | |
Ji et al. | Apple color automatic grading method based on machine vision | |
CN106951824A (en) | The method and system of plant leaf color are extracted based on unmanned aerial vehicle remote sensing images | |
CN106824826A (en) | A kind of corn monoploid sorting system | |
CN114511850B (en) | Method for identifying size particle image of sunlight rose grape fruit | |
CN113470125B (en) | Method and system for carrying out color matching on patterns | |
CN111294588B (en) | Device and method for analyzing white pixel distribution in CMOS image sensor | |
CN108480232A (en) | Matrimony vine sorting technique based on shape and plumpness feature |
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 |