Intelligent thallus structure regulation and control method and system for edible fungus strain production
By monitoring and analyzing edible fungi bacteria images and growth environment data in real time, and dynamically adjusting growth regulation strategies, the problem of unstable quality in edible fungi production is solved, the survival rate and quality are improved, and production costs are reduced.
Patent Information
- Application Number
- CN202411018391.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-26
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The quality of edible fungi is uneven due to environmental factors during the production process, and it is difficult for the existing technology to effectively monitor and regulate, resulting in waste of inferior edible fungi and high production costs.
Real-time monitoring of edible fungi image data and growth environment data, analyze bacterial structure and spore concentration data through neural network, calculate bacterial structure difference and edible odor difference, and dynamically adjust growth regulation strategies, including transplantation and regulation of culture Basic components, optimize growth environment.
It improves the survival rate and quality of edible fungi, reduces the waste of manpower, material resources and financial resources, achieves the healthy growth and stable yield of edible fungi, and provides scientific growth status and regulatory needs decision-making support.
Smart Images

Figure CN119004017A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of edible fungus growth monitoring, and is a method and system for intelligently regulating bacterial structure for edible fungus strain production. Background Art
[0002] Edible fungi refer to fungal organisms that can be used as food. They usually have good nutritional value and edible properties, and are used as food by humans. Common edible fungi include mushrooms, shiitake mushrooms, oyster mushrooms, enoki mushrooms, etc. These edible fungi are of various types, delicious, and rich in nutrition. They are one of the important ingredients in people's daily diet. However, the production and cultivation process of edible fungi is easily affected by various environmental factors such as ambient temperature, humidity, ventilation, and light. The quality of the same batch of edible fungi will vary when they are picked. How to reduce the consumption of manpower, material resources and financial resources of inferior edible fungi while improving the overall yield rate of edible fungi is a difficult problem faced by the cultivation industry.
[0003] In the existing disclosed invention technologies, for example, the patent with publication number CN116649160A discloses an edible fungus strain production monitoring system and a monitoring method, which divides the edible fungus strain production base into n monitoring areas, collects historical strain growth data of the n monitoring areas; trains a machine learning model of the nth monitoring area based on the n historical strain growth data; uses the nth trained machine learning model to identify the growth photos of edible fungus strains in the nth monitoring area and outputs abnormal growth of strains in the i-th growth stage of the nth monitoring area; evaluates the growth environment data corresponding to the abnormal growth of strains in the i-th growth stage of the nth monitoring area, and generates a growth environment coefficient.
[0004] The above patent collects, processes and analyzes a large number of monitoring images. For inferior edible fungi, no judgment is made on the monitoring value, and abnormal growth monitoring of fungi is still carried out, which requires a lot of manpower, material resources and financial resources. Summary of the invention
[0005] The technical problem to be solved by the present invention is to solve the problem of uneven quality of edible fungi production in the prior art, and propose a method and system for intelligent control of fungal body structure for edible fungi strain production, aiming to improve the production yield of edible fungi.
[0006] In order to achieve the above-mentioned object, the technical solution of a method for intelligently controlling the bacterial structure of edible fungi strain production of the present invention comprises the following steps:
[0007] S1: Real-time monitoring and extraction of edible fungi bacterial image data throughout the growth cycle and the temperature, humidity, light, CO 2 Concentration data;
[0008] S2: performing image recognition preprocessing on the bacterial image data, and obtaining bacterial basic data and bacterial structure data of the edible fungi according to the bacterial image data analysis, and importing the bacterial structure data of the edible fungi into the bacterial structure difference calculation strategy to calculate the bacterial structure difference in real time;
[0009] S3: analyzing the spore types and spore concentration data of the air in the growth environment of the edible fungi, importing the spore concentration data into the edible fungi odor difference calculation strategy, and calculating the edible odor difference in real time;
[0010] S4: In the growth cycle of the edible fungi, a fixed unit time interval is set as an edible fungi growth regulation unit period; basic data of the edible fungi and spore types in the air of the growth environment of the edible fungi are extracted, and the survival probability of the edible fungi is calculated based on the data;
[0011] S5: Synchronously estimate and calculate the bacterial regulation demand of each edible fungus growth regulation unit period;
[0012] S6: Dynamically monitor the survival probability and bacterial regulation requirements of each edible fungus growth regulation unit period, implement corresponding bacterial regulation strategies, record and upload bacterial regulation results verification data to the edible fungus growth data management center.
[0013] Specifically, in S1, the edible fungus body image data includes: the edible fungus cap image data and the edible fungus gill image data;
[0014] In S2, the image recognition preprocessing of the bacterial image data and obtaining the bacterial structure data of the edible fungi according to the bacterial image data analysis includes the following specific steps:
[0015] The acquisition of the edible fungus cell structure data comprises the following specific steps:
[0016] S211: converting the image data of the edible mushroom cap into a grayscale image and inputting it into an input layer of the neural network, and establishing a two-dimensional coordinate system with the center of the edible mushroom cap as the coordinate origin;
[0017] S212: extract edge features from the edible mushroom cap image data through a convolutional layer, wherein the convolutional layer O 1 , O 2 , O 3 It is used to extract the plaque features and crack features in the cap image data. The convolution layer O 1 , O 2 , O 3 Each convolution layer includes 10 5×5 convolution kernels. 1 , O 2 , O 3The threshold segmentation processing of the plaque area and the crack area of the cap image data includes:
[0018] In the convolutional layer O i The threshold segmentation formula for the plaque area is r i,n (x n ,y n )∈R i ;
[0019] In the convolutional layer O i The threshold segmentation formula for the middle crack area is d i,n (x n ,y n )∈P i ;
[0020] Among them, r i,n (x n ,y n ) is the nth coordinate on the edge line of the plaque area of the ith convolutional layer (x n ,y n )’s pixel gradient grayscale value;
[0021] d i,n (x n ,y n ) is the nth coordinate on the edge line of the crack area of the i-th convolutional layer (x n ,y n )’s grayscale value;
[0022] x n is the horizontal coordinate of the nth pixel point in the two-dimensional plane coordinate system of the cap image data in S211;
[0023] y n is the ordinate of the nth pixel point in the two-dimensional plane coordinate system of the cap image data in S211;
[0024] R i The gray value set of all pixels in the plaque area extracted by the i-th convolutional layer;
[0025] P i The grayscale value set of all pixels in the crack area extracted by the i-th convolutional layer;
[0026] Step S212 also includes: extracting edge features from the gill image data of the edible fungi through a convolution layer, screening and identifying hyphae adhesion areas in the gill image data of the edible fungi, and performing convolution on the image data. 4 , O 5 , O 6 It is used to extract the adhesion features and hyphae spacing features in the gill image data. The convolution layer O 4 , O5 , O 6 Each convolutional layer includes 8 6×6 convolution kernels;
[0027] In the convolutional layer O i The threshold segmentation formula for hyphae adhesion is z i,g (x n ,y n )∈Q i ;
[0028] z i,g (x n ,y n ) is the gth coordinate on the edge line of the adhesion area of the i-th convolutional layer (x n ,y n )’s grayscale value;
[0029] Q i Extract the grayscale value set of all pixels in the adhesion area for the i-th convolutional layer.
[0030] Specifically, in S2, the acquisition of the edible fungus cell structure data further includes the following specific steps:
[0031] S213: Through sampling layer M 1 , M 2 , M 3 The plaque area, crack area and adhesion area in the cap image data output by the convolution layer are sampled and extracted respectively, and the edges of the plaque area, crack area and adhesion area are marked with different segmentation colors according to the total number of pixels in the plaque area, crack area and adhesion area;
[0032] S214: compressing the feature information of the plaque area, the crack area and the adhesion area into a one-dimensional vector at the same time, and finally outputting it through the output layer to complete the training of the neural network, wherein the fully connected layer is activated by a softmax function;
[0033] S215: extracting the plaque growth status data, crack trend data, adhesion degree data and hyphae spacing data output from the neural network model; the plaque growth status data includes: plaque area total data N 1 , plaque area data Grayscale mean data of plaque area The crack trend data includes: the total number of crack areas N 2 , the aspect ratio data of the crack area Rip depth data for the rip area The adhesion degree data includes: the total number of adhesion areas N 3 , Adhesion area data Grayscale mean data of the adhesion area
[0034] Specifically, in S2, the cell structure data of the edible fungus is imported into the cell structure difference calculation strategy to calculate the cell structure difference in real time, and the cell structure difference b 1 The calculation strategy is as follows:
[0035] b 1 =α 1 ×ln(C 1 +C 2 ) 2 +α 2 ×ln(C 3 +C 4 ) 2 ;
[0036] Among them, α 1 +α 2 =0.84; α 1 , α 2 They are the structural influence ratios of the cap area and gills of edible fungi;
[0037] C 1 , C 2 , C 3 , C 4 They are the difference in plaque growth, the difference in crack tendency, the difference in adhesion degree, and the difference in hyphae spacing;
[0038] The plaque growth difference C 1 and the gap trend difference C 2 The calculation strategy is as follows:
[0039]
[0040] Among them, v′, s′ 0 , h′ 0 They are the number of controllable plaque areas, the area of controllable plaque areas, and the mean grayscale value of controllable plaque areas of the target edible fungi;
[0041] v″,k″ 0 , l″ 0 are the controllable crack area number, controllable crack length-width ratio, and controllable crack depth of the target edible fungus; D is the radius of the cap;
[0042] The adhesion degree difference C 3 and hyphae interval difference C 4 The calculation strategy is as follows:
[0043]
[0044] Among them, v″′, s″′0 , h″′ 0 They are the number of controllable mycelium adhesion regions, the area of controllable mycelium adhesion regions, and the grayscale mean of controllable mycelium adhesion regions of the target edible fungi;
[0045] Indicates the nth 4 -1 and nth 4 The hyphal spacing between hyphae;
[0046] Indicates the nth 4 The nth 4 +1 hyphae spacing between hyphae;
[0047] represents the mean hyphae interval; N4 represents the total number of hyphae.
[0048] Specifically, in S3, the calculation strategy of the difference in the edible smell of the edible fungi is as follows:
[0049] b 2 =β 1 ×C 5 ;
[0050] Among them, β 1 =0.24; β 1 They are the influence ratio coefficients of edible odor difference on spore concentration data;
[0051] C 5 is the difference in edible smell of the spore concentration data, and the calculation strategy of the difference in edible smell of the spore concentration data is:
[0052] Among them, DW is the total number of edible fungus growth regulation unit periods in the target growth cycle of edible fungi;
[0053] nd dw is the spore concentration of the air in the growth environment of the edible fungi during the dwth edible fungi growth regulation unit period;
[0054] nd bz The spore concentration of the air in the growth environment of the target edible fungus.
[0055] Specifically, the S4 includes the following specific steps:
[0056] S41: in the growth cycle of the edible fungi, a fixed unit time interval is set as an edible fungi growth regulation unit period, and the target growth cycle of the edible fungi includes DW edible fungi growth regulation unit periods in total;
[0057] S42: extracting basic data of the edible fungi and spore types in the air of the growth environment of the edible fungi, wherein the basic data of the edible fungi include basic data of the cap and basic data of the gills;
[0058] S43: Calculate the survival probability of the edible fungus according to the basic data of the fungus, and the calculation formula of the survival probability λ is:
[0059] Among them, MJ dw ,ch dw are the mean values of the cap area and hypha length of edible fungi in the dwth edible fungi growth regulation unit period;
[0060] MJ bz ,ch bz are the mean values of cap area and hypha length of target edible fungi respectively;
[0061] μ 1 , μ 2 They are the coefficients of influence of regulation demand on the basic data of cap and the basic data of gills respectively.
[0062] Specifically, in S5, the mushroom control demand of each edible mushroom growth control unit period includes control prediction time data; the calculation strategy of the control prediction time is: Among them, tk dw is the bacterial regulation demand of the dwth edible fungus growth regulation unit period; ε 1 , ε 2 are the influence ratios of the control demand for the bacterial structure difference item and the edible smell difference item respectively; q 1 ,q 2 They are the target difference of the fungus body structure and the target difference of the edible smell.
[0063] Specifically, S6 includes the following specific steps:
[0064] S61: Dynamically monitor the survival probability of each edible fungus growth regulation unit period;
[0065] When the survival probability λ of edible fungi is less than or equal to the survival threshold within the unit period of edible fungi growth regulation, the edible fungi are transplanted and new edible fungi are sown, and the dynamic monitoring of edible fungi growth is resumed;
[0066] On the contrary, when the survival probability λ of the edible fungus is greater than the survival threshold, step S62 is executed;
[0067] S62: Extract the bacterial regulation demand tk for each edible fungus growth regulation unit period dw ;
[0068] When the bacteria regulate the demand tk dw When it is less than the threshold of human intervention in the bacterial structure, continue to enter the next edible fungus growth regulation unit period to monitor the growth of edible fungi;
[0069] When the bacteria regulate the demand tk dw When the threshold of human intervention in the bacterial structure is greater than or equal to the threshold, the bacterial structure difference term in the calculation formula of the edible mushroom bacterial regulation demand is extracted respectively. and food smell difference Select the regulatory strategy and execute the corresponding bacterial regulatory strategy.
[0070] Specifically, S6 also includes the following specific steps:
[0071] S63: Select the difference item of the bacterial structure of edible fungi Select regulatory strategies;
[0072] When the bacterial structure difference When growing mushrooms, spray antibiotics on their caps and increase ventilation;
[0073] On the contrary, it is not necessary to regulate the bacterial structure to determine whether the edible fungi are edible;
[0074] S64: Select the difference item of edible fungus odor Select regulatory strategies;
[0075] When the food smell difference When optimizing the composition of the culture medium, add nutrients that are conducive to producing edible odor, including amino acids and proteins, and adjust the fertilization method;
[0076] On the contrary, it is not necessary to regulate the edible smell when judging edible fungi;
[0077] S65: Record and upload the bacterial regulation results verification data to the edible fungus growth data management center.
[0078] In addition, the present invention provides an intelligent control system for the bacterial structure of edible fungi production, which includes the following modules:
[0079] Edible fungus growth data extraction module, bacterial structure difference calculation module, edible odor difference calculation module, edible fungus survival probability calculation module, bacterial regulation demand estimation module, bacterial regulation strategy execution module;
[0080] The edible fungus growth data extraction module is used to monitor and extract the edible fungus bacterial image data of the edible fungus species in the entire growth cycle and the temperature, humidity, light, CO2 content of the growth environment in real time. 2 Concentration data;
[0081] The bacterial structure difference calculation module is used to perform image recognition preprocessing on the bacterial image data, and obtain the bacterial structure data of the edible fungi according to the bacterial image data analysis, and import the bacterial structure data of the edible fungi into the bacterial structure difference calculation strategy to calculate the bacterial structure difference in real time;
[0082] The edible odor difference calculation module is used to analyze the spore types and spore concentration data of the air in the growth environment of the edible fungi, import the spore types and spore concentration data into the edible odor difference calculation strategy of the edible fungi, and calculate the edible odor difference in real time;
[0083] The edible fungus survival probability calculation module is used to extract the basic data of the edible fungus and the spore types in the air of the growth environment of the edible fungus, and calculate the survival probability of the edible fungus based on the data;
[0084] The bacterial cell regulation demand estimation module is used to estimate and calculate the bacterial cell regulation demand of each edible fungus growth regulation unit period;
[0085] The bacterial cell regulation strategy execution module is used to dynamically monitor the bacterial cell regulation demand within each edible fungus growth regulation unit period, execute the corresponding bacterial cell regulation strategy, and record and upload the bacterial cell regulation result verification data to the edible fungus growth data management center.
[0086] A storage medium stores instructions, and when a computer reads the instructions, the computer executes any one of the above-mentioned methods for intelligent control of bacterial structure for production of edible fungi.
[0087] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any one of the above-mentioned methods for intelligently regulating bacterial structure for the production of edible fungi is implemented.
[0088] Compared with the prior art, the technical effects of the present invention are as follows:
[0089] 1. The present invention can detect abnormal situations in time and take corresponding control strategies by real-time monitoring of edible fungi image data and growth environment data, which helps to ensure the healthy growth and stable yield of edible fungi.
[0090] 2. The present invention gives priority to calculating the survival probability of edible fungi. For inferior edible fungi, the strategy of transplanting edible fungi and sowing new edible fungi is implemented. According to the changes in different time periods and growth environment, the bacterial regulation strategy is dynamically adjusted, which is beneficial to improving the survival rate and quality of edible fungi and reducing the waste of manpower, material and financial resources.
[0091] 3. Based on real-time calculation results such as bacterial structure data and edible odor difference, the present invention can more scientifically estimate the growth status and regulation requirements of edible fungi and provide reliable data support for decision-making. BRIEF DESCRIPTION OF THE DRAWINGS
[0092] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.
[0093] in:
[0094] Figure 1 A schematic diagram of a process of an intelligent control method of bacterial cell structure for edible fungus strain production according to the present invention;
[0095] Figure 2 The present invention is a schematic diagram of the structure of an intelligent control system for bacterial structure used in the production of edible fungi. DETAILED DESCRIPTION
[0096] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.
[0097] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0098] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0099] Embodiment 1:
[0100] like Figure 1 As shown, a method for intelligently controlling the bacterial structure of edible fungi strain production according to an embodiment of the present invention is as follows: Figure 1 As shown, the specific steps are as follows:
[0101] S1: Real-time monitoring and extraction of edible fungi bacterial image data throughout the growth cycle and the temperature, humidity, light, CO 2 Concentration and other data;
[0102] In S1, the edible fungus body image data includes: the cap image data and the gill image data of the edible fungus.
[0103] S2: performing image recognition preprocessing on the bacterial image data, and obtaining bacterial basic data and bacterial structure data of the edible fungi according to the bacterial image data analysis, and importing the bacterial structure data of the edible fungi into the bacterial structure difference calculation strategy to calculate the bacterial structure difference in real time;
[0104] In S2, the image recognition preprocessing of the bacterial image data and obtaining the bacterial structure data of the edible fungi according to the bacterial image data analysis includes the following specific steps:
[0105] The acquisition of the edible fungus cell structure data comprises the following specific steps:
[0106] S211: converting the image data of the edible mushroom cap into a grayscale image and inputting it into an input layer of the neural network, and establishing a two-dimensional coordinate system with the center of the edible mushroom cap as the coordinate origin;
[0107] S212: extract edge features from the edible mushroom cap image data through a convolutional layer, wherein the convolutional layer O 1 , O 2 , O 3 It is used to extract the plaque features and crack features in the cap image data. The convolution layer O 1 , O 2 , O 3 Each convolution layer includes 10 5×5 convolution kernels. 1 , O 2 , O 3 The threshold segmentation processing of the plaque area and the crack area of the cap image data includes:
[0108] In the convolutional layer O i The threshold segmentation formula for the plaque area is r i,n (x n ,y n )∈R i ;
[0109] In the convolutional layer O i The threshold segmentation formula for the middle crack area is d i,n (x n ,y n )∈P i ;
[0110] Among them, r i,n (x n ,y n ) is the nth coordinate on the edge line of the plaque area of the ith convolutional layer (xn ,y n )’s pixel gradient grayscale value;
[0111] d i,n (x n ,y n ) is the nth coordinate on the edge line of the crack area of the i-th convolutional layer (x n ,y n )’s grayscale value;
[0112] x n is the horizontal coordinate of the nth pixel point in the two-dimensional plane coordinate system of the cap image data in S211;
[0113] y n is the ordinate of the nth pixel point in the two-dimensional plane coordinate system of the cap image data in S211;
[0114] R i The gray value set of all pixels in the plaque area extracted by the i-th convolutional layer;
[0115] P i The grayscale value set of all pixels in the crack area extracted by the i-th convolutional layer;
[0116] Step S212 also includes: extracting edge features from the gill image data of the edible fungi through a convolution layer, screening and identifying hyphae adhesion areas in the gill image data of the edible fungi, and performing convolution on the image data. 4 , O 5 , O 6 It is used to extract the adhesion features and hyphae spacing features in the gill image data. The convolution layer O 4 , O 5 , O 6 Each convolutional layer includes 8 6×6 convolution kernels;
[0117] In the convolutional layer O i The threshold segmentation formula for hyphae adhesion is z i,g (x n ,y n )∈Q i ;
[0118] z i,g (x n ,y n ) is the gth coordinate on the edge line of the adhesion area of the i-th convolutional layer (x n ,y n )’s grayscale value;
[0119] Q i Extract the grayscale value set of all pixels in the adhesion area for the i-th convolutional layer.
[0120] In S2, the acquisition of the edible fungus cell structure data also includes the following specific steps:
[0121] S213: Through sampling layer M 1 , M 2 , M 3 The plaque area, crack area and adhesion area in the cap image data output by the convolution layer are sampled and extracted respectively, and the edges of the plaque area, crack area and adhesion area are marked with different segmentation colors according to the total number of pixels in the plaque area, crack area and adhesion area;
[0122] S214: compressing the feature information of the plaque area, the crack area and the adhesion area into a one-dimensional vector at the same time, and finally outputting it through the output layer to complete the training of the neural network, wherein the fully connected layer is activated by a softmax function;
[0123] S215: extracting the plaque growth status data, crack trend data, adhesion degree data and hyphae spacing data output from the neural network model; the plaque growth status data includes: plaque area total data N 1 , plaque area data Grayscale mean data of plaque area The crack trend data includes: the total number of crack areas N 2 , the aspect ratio data of the crack area Rip depth data for the rip area The adhesion degree data includes: the total number of adhesion areas N 3 , Adhesion area data Grayscale mean data of the adhesion area
[0124] In S2, the bacterial structure data of the edible fungi is imported into the bacterial structure difference calculation strategy to calculate the bacterial structure difference in real time, and the bacterial structure difference b 1 The calculation strategy is as follows:
[0125] b 1 =α 1 ×ln(C 1 +C 2 ) 2 +α 2 ×ln(C 3 +C 4 ) 2 ;
[0126] Among them, α 1 +α 2 =0.84; α 1 , α2 They are the structural influence ratios of the cap area and gills of edible fungi;
[0127] C 1 , C 2 , C 3 , C 4 They are the difference in plaque growth, the difference in crack tendency, the difference in adhesion degree, and the difference in hyphae spacing;
[0128] The plaque growth difference C 1 and the gap trend difference C 2 The calculation strategy is as follows:
[0129]
[0130] Among them, v′, s′ 0 , h′ 0 are the number of controllable plaque areas, the area of controllable plaque areas, and the grayscale mean of controllable plaque areas of the target edible fungi; D is the radius of the cap;
[0131] v″,k″ 0 , l″ 0 They are the number of controllable crack areas, controllable crack length-width ratio, and controllable crack depth of the target edible fungi;
[0132] The adhesion degree difference C 3 and hyphae interval difference C 4 The calculation strategy is as follows:
[0133]
[0134] Among them, v″′, s″′ 0 , h″′ 0 They are the number of controllable mycelium adhesion regions, the area of controllable mycelium adhesion regions, and the grayscale mean of controllable mycelium adhesion regions of the target edible fungi;
[0135] Indicates the nth 4 -1 and nth 4 The hyphal spacing between hyphae;
[0136] Indicates the nth 4 The nth 4 +1 hyphae spacing between hyphae;
[0137] represents the mean hyphae interval; N4 represents the total number of hyphae.
[0138] S3: analyzing the spore types and spore concentration data of the air in the growth environment of the edible fungi, importing the spore concentration data into the edible fungi odor difference calculation strategy, and calculating the edible odor difference in real time;
[0139] In S3, the calculation strategy of the difference in the edible smell of the edible fungi is as follows:
[0140] b 2 =β 1 ×C 5 ;
[0141] Among them, β 1 =0.24; β 1 They are the influence ratio coefficients of edible odor difference on spore concentration data;
[0142] C 5 is the difference in edible smell of the spore concentration data, and the calculation strategy of the difference in edible smell of the spore concentration data is:
[0143] Among them, DW is the total number of edible fungus growth regulation unit periods in the target growth cycle of edible fungi;
[0144] nd dw is the spore concentration of the air in the growth environment of the edible fungi during the dwth edible fungi growth regulation unit period;
[0145] nd bz The spore concentration of the air in the growth environment of the target edible fungus.
[0146] S4: In the growth cycle of the edible fungi, a fixed unit time interval is set as an edible fungi growth regulation unit period; basic data of the edible fungi and spore types in the air of the growth environment of the edible fungi are extracted, and the survival probability of the edible fungi is calculated based on the data;
[0147] The S4 comprises the following specific steps:
[0148] S41: in the growth cycle of the edible fungi, a fixed unit time interval is set as an edible fungi growth regulation unit period, and the target growth cycle of the edible fungi includes DW edible fungi growth regulation unit periods in total;
[0149] S42: extracting basic data of the edible fungi and spore types in the air of the growth environment of the edible fungi, wherein the basic data of the edible fungi include basic data of the cap and basic data of the gills;
[0150] S43: Calculate the survival probability of the edible fungus according to the basic data of the fungus, and the calculation formula of the survival probability λ is:
[0151] Among them, MJ dw ,ch dw are the mean values of the cap area and hypha length of edible fungi in the dwth edible fungi growth regulation unit period;
[0152] MJ bz ,ch bz are the mean values of cap area and hypha length of target edible fungi respectively;
[0153] μ 1 , μ 2 They are the coefficients of influence of regulation demand on the basic data of cap and the basic data of gills respectively.
[0154] S5: Synchronously estimate and calculate the bacterial regulation demand of each edible fungus growth regulation unit period;
[0155] In S5, the mushroom control demand of each edible mushroom growth control unit period includes control prediction time data; the calculation strategy of the control prediction time is: Among them, tk dw is the bacterial regulation demand of the dwth edible fungus growth regulation unit period; ε 1 , ε 2 are the influence ratios of the control demand for the bacterial structure difference item and the edible smell difference item respectively; q 1 ,q 2 They are the target difference of the bacterial structure and the target difference of the edible fungi smell;
[0156] S6: Dynamically monitor the survival probability and bacterial regulation requirements of each edible fungus growth regulation unit period, implement corresponding bacterial regulation strategies, record and upload bacterial regulation results verification data to the edible fungus growth data management center.
[0157] S6 includes the following specific steps:
[0158] S61: Dynamically monitor the survival probability of each edible fungus growth regulation unit period;
[0159] When the survival probability λ of edible fungi is less than or equal to the survival threshold within the unit period of edible fungi growth regulation, the edible fungi are transplanted and new edible fungi are sown, and the dynamic monitoring of edible fungi growth is resumed;
[0160] On the contrary, when the survival probability λ of the edible fungus is greater than the survival threshold, step S62 is executed;
[0161] S62: Extract the bacterial regulation demand tk for each edible fungus growth regulation unit period dw ;
[0162] When the bacteria regulate the demand tk dw When it is less than the threshold of human intervention in the bacterial structure, continue to enter the next edible fungus growth regulation unit period to monitor the growth of edible fungi;
[0163] When the bacteria regulate the demand tk dw When the threshold of human intervention in the bacterial structure is greater than or equal to the threshold, the bacterial structure difference term in the calculation formula of the edible mushroom bacterial regulation demand is extracted respectively. and food smell difference Select the regulatory strategy and execute the corresponding bacterial regulatory strategy.
[0164] S6 also includes the following specific steps:
[0165] S63: Select the difference item of the bacterial structure of edible fungi Select regulatory strategies;
[0166] When the bacterial structure difference When growing mushrooms, spray antibiotics on their caps and increase ventilation;
[0167] On the contrary, it is not necessary to regulate the bacterial structure to determine whether the edible fungi are edible;
[0168] S64: Select the difference item of edible fungus odor Select regulatory strategies;
[0169] When the food smell difference When optimizing the composition of the culture medium, add nutrients that are conducive to producing edible odor, including amino acids and proteins, and adjust the fertilization method;
[0170] On the contrary, it is not necessary to regulate the edible smell when judging edible fungi;
[0171] S65: Record and upload the bacterial regulation results verification data to the edible fungus growth data management center.
[0172] Embodiment 2:
[0173] like Figure 2 As shown, a method system for intelligently controlling the bacterial structure of edible fungi strain production according to an embodiment of the present invention is as follows: Figure 2 As shown, it includes the following modules:
[0174] Edible fungus growth data extraction module, bacterial structure difference calculation module, edible odor difference calculation module, edible fungus survival probability calculation module, bacterial regulation demand estimation module, bacterial regulation strategy execution module;
[0175] The edible fungus growth data extraction module is used to monitor and extract the edible fungus bacterial image data and the temperature, humidity, light, CO2 of the growth environment in real time during the entire growth cycle of the edible fungus species. 2 Concentration and other data;
[0176] The bacterial structure difference calculation module is used to perform image recognition preprocessing on the bacterial image data, and obtain the bacterial structure data of the edible fungi according to the bacterial image data analysis, and import the bacterial structure data of the edible fungi into the bacterial structure difference calculation strategy to calculate the bacterial structure difference in real time;
[0177] The edible odor difference calculation module is used to analyze the spore types and spore concentration data of the air in the growth environment of the edible fungi, import the spore types and spore concentration data into the edible odor difference calculation strategy of the edible fungi, and calculate the edible odor difference in real time;
[0178] The edible fungus survival probability calculation module is used to extract the basic data of the edible fungus and the spore types in the air of the growth environment of the edible fungus, and calculate the survival probability of the edible fungus based on the data;
[0179] The bacterial cell regulation demand estimation module is used to estimate and calculate the bacterial cell regulation demand of each edible fungus growth regulation unit period;
[0180] The bacterial cell regulation strategy execution module is used to dynamically monitor the bacterial cell regulation demand within each edible fungus growth regulation unit period, execute the corresponding bacterial cell regulation strategy, and record and upload the bacterial cell regulation result verification data to the edible fungus growth data management center.
[0181] Embodiment three:
[0182] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;
[0183] The processor executes the above-mentioned method for intelligent control of bacterial structure for edible fungus production by calling the computer program stored in the memory.
[0184] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement a method for intelligent control of bacterial structure for edible fungus strain production provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.
[0185] Embodiment 4:
[0186] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;
[0187] When the computer program runs on a computer device, the computer device executes the above-mentioned method for intelligent control of bacterial structure for the production of edible fungi.
[0188] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.
[0189] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0190] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.
[0191] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0192] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0193] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0194] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0195] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0196] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0197] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0198] In summary, compared with the prior art, the technical effects of the present invention are as follows:
[0199] 1. The present invention can detect abnormal situations in time and take corresponding control strategies by real-time monitoring of edible fungi image data and growth environment data, which helps to ensure the healthy growth and stable yield of edible fungi.
[0200] 2. The present invention gives priority to calculating the survival probability of edible fungi. For inferior edible fungi, the strategy of transplanting edible fungi and sowing new edible fungi is implemented. According to the changes in different time periods and growth environment, the bacterial regulation strategy is dynamically adjusted, which is beneficial to improving the survival rate and quality of edible fungi and reducing the waste of manpower, material and financial resources.
[0201] 3. Based on real-time calculation results such as bacterial structure data and edible odor difference, the present invention can more scientifically estimate the growth status and regulation requirements of edible fungi and provide reliable data support for decision-making.
[0202] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. A method for intelligently controlling the bacterial structure of edible fungi strain production, characterized in that: The method comprises the following specific steps: S1: Real-time monitoring and extraction of the image data of edible fungi during the entire growth cycle and the temperature, humidity, light, and CO2 concentration data of the growth environment; S2: performing image recognition preprocessing on the bacterial image data, and obtaining bacterial basic data and bacterial structure data of the edible fungi according to the bacterial image data analysis, and importing the bacterial structure data of the edible fungi into the bacterial structure difference calculation strategy to calculate the bacterial structure difference in real time; S3: analyzing the spore types and spore concentration data of the air in the growth environment of the edible fungi, importing the spore concentration data into the edible fungi odor difference calculation strategy, and calculating the edible odor difference in real time; S4: In the growth cycle of the edible fungi, a fixed unit time interval is set as an edible fungi growth regulation unit period; basic data of the edible fungi and spore types in the air of the growth environment of the edible fungi are extracted, and the survival probability of the edible fungi is calculated based on the data; S5: Synchronously estimate and calculate the bacterial regulation demand of each edible fungus growth regulation unit period; S6: Dynamically monitor the survival probability and bacterial regulation requirements of each edible fungus growth regulation unit period, implement corresponding bacterial regulation strategies, record and upload bacterial regulation results verification data to the edible fungus growth data management center.
2. The method for intelligently controlling the bacterial structure of edible fungi strain production according to claim 1, characterized in that: In S1, the edible fungus body image data includes: the edible fungus cap image data and the edible fungus gill image data; In S2, the image recognition preprocessing of the bacterial image data and obtaining the bacterial structure data of the edible fungi according to the bacterial image data analysis includes the following specific steps: The acquisition of the edible fungus cell structure data comprises the following specific steps: S211: converting the image data of the edible mushroom cap into a grayscale image and inputting it into an input layer of the neural network, and establishing a two-dimensional coordinate system with the center of the edible mushroom cap as the coordinate origin; S212: extract edge features from the cap image data of the edible mushrooms through convolution layers, wherein the convolution layers O1, O2, and O3 are used to extract plaque features and crack features from the cap image data, and each of the convolution layers O1, O2, and O3 includes 10 5×5 convolution kernels. The threshold segmentation processing of the plaque area and the crack area of the cap image data in the convolution layers O1, O2, and O3 includes: In the convolutional layer O i The threshold segmentation formula for the plaque area is r i,n (x n ,y n )∈R i ; In the convolutional layer O i The threshold segmentation formula for the middle crack area is d i,n (x n ,y n )∈P i ; Among them, r i,n (x n ,y n ) is the nth coordinate on the edge line of the plaque area of the ith convolutional layer (x n ,y n )’s pixel gradient grayscale value; d i,n (x n ,y n ) is the nth coordinate on the edge line of the crack area of the i-th convolutional layer (x n ,y n )’s grayscale value; x n is the horizontal coordinate of the nth pixel point in the two-dimensional plane coordinate system of the cap image data in S211; y n is the ordinate of the nth pixel point in the two-dimensional plane coordinate system of the cap image data in S211; R i The gray value set of all pixels in the plaque area extracted by the i-th convolutional layer; P i The grayscale value set of all pixels in the crack area extracted by the i-th convolutional layer; Step S212 also includes: extracting edge features from the gill image data of the edible fungi through a convolution layer, screening and identifying hyphae adhesion areas in the gill image data of the edible fungi, and the convolution layers O4, O5, and O6 are used to extract adhesion features and hyphae spacing features in the gill image data, and each of the convolution layers O4, O5, and O6 includes 8 6×6 convolution kernels; In the convolutional layer O i The threshold segmentation formula for hyphae adhesion is z i,g (x n ,y n )∈Q i ; z i,g (x n ,y n ) is the gth coordinate on the edge line of the adhesion area of the i-th convolutional layer (x n ,y n )’s grayscale value; Q i Extract the grayscale value set of all pixels in the adhesion area for the i-th convolutional layer.
3. The method for intelligently controlling the bacterial structure for producing edible fungi according to claim 2, characterized in that: In S2, the acquisition of the edible fungus cell structure data also includes the following specific steps: S213: sampling and extracting the plaque area, the crack area and the adhesion area in the cap image data output by the convolution layer through the sampling layers M1, M2 and M3 respectively, and marking the edges of the plaque area, the crack area and the adhesion area with different segmentation colors according to the total number of pixels in the plaque area, the crack area and the adhesion area; S214: compressing the feature information of the plaque area, the crack area and the adhesion area into a one-dimensional vector at the same time, and finally outputting it through the output layer to complete the training of the neural network, wherein the fully connected layer is activated by a softmax function; S215: extracting the plaque growth status data, crack trend data, adhesion degree data and hyphae spacing data output from the neural network model; the plaque growth status data includes: plaque area total data N1, plaque area data Plaque area grayscale mean data The crack trend data includes: the total number of crack areas data N2, the length-to-width ratio data of the crack areas Rip depth data for the rip area The adhesion degree data includes: the total number of adhesion regions data N3, the area data of the adhesion regions Grayscale mean data of the adhesion area 4. The method for intelligently controlling the bacterial structure for producing edible fungi according to claim 3, characterized in that: In S2, the cell structure data of the edible fungi is imported into the cell structure difference calculation strategy to calculate the cell structure difference in real time. The calculation strategy of the cell structure difference b1 is as follows: b1=α1×ln(C1+C2) 2 +α2×ln(C3+C4) 2 ; Among them, α1+α2=0.84; α1 and α2 are the structural influence coefficients of the cap area and gills of edible fungi respectively; C1, C2, C3, and C4 are the difference in plaque growth, the difference in crack tendency, the difference in adhesion degree, and the difference in hyphae spacing, respectively; The calculation strategy of the plaque growth difference C1 and the crack trend difference C2 is as follows: Among them, v′, s′0, and h′0 are the number of controllable plaque areas, the area of controllable plaque areas, and the grayscale mean of the controllable plaque areas of the target edible fungi, respectively; v″, k″0, l″0 are the controllable crack area number, controllable crack length-width ratio, and controllable crack depth of the target edible fungus, respectively; D is the cap radius; The calculation strategy of the adhesion degree difference C3 and hyphae spacing difference C4 is as follows: Among them, v″′, s″′0, h″′0 are the number of controllable mycelium adhesion regions, the area of controllable mycelium adhesion regions, and the grayscale mean of controllable mycelium adhesion regions of the target edible fungi respectively; represents the hyphae interval between the n4-1th and n4th hyphae; represents the hyphae interval between the n4th and n4+1th hyphae; represents the mean hyphae interval; N4 represents the total number of hyphae.
5. The method for intelligently controlling the bacterial structure for producing edible fungi according to claim 4, characterized in that: In S3, the calculation strategy of the difference in the edible smell of the edible fungi is as follows: b2 = β1 × C5; Among them, β1=0.24; β1 is the influence ratio of edible odor difference of spore concentration data; C5 is the difference in edible smell of the spore concentration data, and the calculation strategy of the difference in edible smell of the spore concentration data is: Among them, DW is the total number of edible fungus growth regulation unit periods in the target growth cycle of edible fungi; nd dw is the spore concentration of the air in the growth environment of the edible fungi during the dwth edible fungi growth regulation unit period; nd bz The spore concentration of the air in the growth environment of the target edible fungus.
6. The method for intelligently controlling the bacterial structure for producing edible fungi according to claim 5, characterized in that: The S4 comprises the following specific steps: S41: in the growth cycle of the edible fungi, a fixed unit time interval is set as an edible fungi growth regulation unit period, and the target growth cycle of the edible fungi includes DW edible fungi growth regulation unit periods in total; S42: extracting basic data of the edible fungi and spore types in the air of the growth environment of the edible fungi, wherein the basic data of the edible fungi include basic data of the cap and basic data of the gills; S43: Calculate the survival probability of the edible fungus according to the basic data of the fungus, and the calculation formula of the survival probability λ is: Among them, MJ dw ,ch dw are the mean values of the cap area and hypha length of edible fungi in the dwth edible fungi growth regulation unit period; MJ bz ,ch bz are the mean values of cap area and hypha length of target edible fungi respectively; μ1 and μ2 are the coefficients of influence of regulation demand on cap basic data and gill basic data respectively.
7. The method for intelligently controlling the bacterial structure for producing edible fungi according to claim 6, characterized in that: In S5, the mushroom control demand of each edible mushroom growth control unit period includes control prediction time data; the calculation strategy of the control prediction time is: Among them, tk dw is the bacterial regulation demand in the dwth edible fungus growth regulation unit period; ε1 and ε2 are the control demand influence ratios of the bacterial structure difference item and the edible odor difference item respectively; q1 and q2 are the target difference of the bacterial structure and the target difference of the edible fungus respectively.
8. The method for intelligently controlling the bacterial structure for producing edible fungi according to claim 7, characterized in that: S6 includes the following specific steps: S61: Dynamically monitor the survival probability of each edible fungus growth regulation unit period; When the survival probability λ of edible fungi is less than or equal to the survival threshold within the unit period of edible fungi growth regulation, the edible fungi are transplanted and new edible fungi are sown, and the dynamic monitoring of edible fungi growth is resumed; On the contrary, when the survival probability λ of the edible fungus is greater than the survival threshold, step S62 is executed; S62: Extract the bacterial regulation demand tk for each edible fungus growth regulation unit period dw ; When the bacteria regulate the demand tk dw When it is less than the threshold of human intervention in the bacterial structure, continue to enter the next edible fungus growth regulation unit period to monitor the growth of edible fungi; When the bacteria regulate the demand tk dw When the threshold of human intervention in the bacterial structure is greater than or equal to the threshold, the bacterial structure difference term in the calculation formula of the edible mushroom bacterial regulation demand is extracted respectively. and food smell difference Select the regulatory strategy and execute the corresponding bacterial regulatory strategy.
9. The method for intelligently controlling the bacterial structure for producing edible fungi according to claim 8, characterized in that: S6 also includes the following specific steps: S63: Select the difference item of the bacterial structure of edible fungi Select regulatory strategies; When the bacterial structure difference When growing mushrooms, spray antibiotics on their caps and increase ventilation; On the contrary, it is not necessary to regulate the bacterial structure to determine whether the edible fungi are edible; S64: Select the difference item of edible fungus odor Select regulatory strategies; When the food smell difference When optimizing the composition of the culture medium, add nutrients that are conducive to producing edible odor, including amino acids and proteins, and adjust the fertilization method; On the contrary, it is not necessary to regulate the edible smell when judging edible fungi; S65: Record and upload the bacterial regulation results verification data to the edible fungus growth data management center.
10. A bacterial structure intelligent control system for edible fungus strain production, which is used to implement a bacterial structure intelligent control method for edible fungus strain production as claimed in any one of claims 1 to 9, characterized in that: The system includes the following modules: Edible fungus growth data extraction module, bacterial structure difference calculation module, edible odor difference calculation module, edible fungus survival probability calculation module, bacterial regulation demand estimation module, bacterial regulation strategy execution module; The edible fungus growth data extraction module is used to monitor and extract the edible fungus body image data of the edible fungus species in the entire growth cycle and the temperature, humidity, light, and CO2 concentration data of the growth environment in real time; The bacterial structure difference calculation module is used to perform image recognition preprocessing on the bacterial image data, and obtain the bacterial structure data of the edible fungi according to the bacterial image data analysis, and import the bacterial structure data of the edible fungi into the bacterial structure difference calculation strategy to calculate the bacterial structure difference in real time; The edible odor difference calculation module is used to analyze the spore types and spore concentration data of the air in the growth environment of the edible fungi, import the spore types and spore concentration data into the edible odor difference calculation strategy of the edible fungi, and calculate the edible odor difference in real time; The edible fungus survival probability calculation module is used to extract the basic data of the edible fungus and the spore types in the air of the growth environment of the edible fungus, and calculate the survival probability of the edible fungus based on the data; The bacterial cell regulation demand estimation module is used to estimate and calculate the bacterial cell regulation demand of each edible fungus growth regulation unit period; The bacterial cell regulation strategy execution module is used to dynamically monitor the bacterial cell regulation demand within each edible fungus growth regulation unit period, execute the corresponding bacterial cell regulation strategy, and record and upload the bacterial cell regulation result verification data to the edible fungus growth data management center.
Citation Information
Patent Citations
Edible mushroom strain production monitoring system and monitoring method
CN116649160A
Cited By
Intelligent control method and system for edible mushrooms under dynamic conveying
CN120167293A
