CN113711843A - System and method for optimizing growth parameters of edible fungi - Google Patents
System and method for optimizing growth parameters of edible fungi Download PDFInfo
- Publication number
- CN113711843A CN113711843A CN202111119016.0A CN202111119016A CN113711843A CN 113711843 A CN113711843 A CN 113711843A CN 202111119016 A CN202111119016 A CN 202111119016A CN 113711843 A CN113711843 A CN 113711843A
- Authority
- CN
- China
- Prior art keywords
- growth
- edible fungi
- edible
- sensor
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 241000233866 Fungi Species 0.000 title claims abstract description 136
- 230000012010 growth Effects 0.000 title claims abstract description 89
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000002474 experimental method Methods 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims abstract description 23
- 238000004519 manufacturing process Methods 0.000 claims abstract description 23
- 238000010801 machine learning Methods 0.000 claims abstract description 18
- 230000011218 segmentation Effects 0.000 claims abstract description 16
- 238000004891 communication Methods 0.000 claims abstract description 14
- 230000006870 function Effects 0.000 claims abstract description 4
- 238000012544 monitoring process Methods 0.000 claims abstract description 4
- 230000007613 environmental effect Effects 0.000 claims description 52
- 239000000758 substrate Substances 0.000 claims description 40
- 238000012706 support-vector machine Methods 0.000 claims description 15
- 239000002689 soil Substances 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000008635 plant growth Effects 0.000 claims description 4
- 235000001674 Agaricus brunnescens Nutrition 0.000 claims description 3
- 239000003415 peat Substances 0.000 claims description 2
- 239000010902 straw Substances 0.000 claims description 2
- 244000025254 Cannabis sativa Species 0.000 claims 1
- 210000003608 fece Anatomy 0.000 claims 1
- 244000144972 livestock Species 0.000 claims 1
- 239000010871 livestock manure Substances 0.000 claims 1
- 244000144977 poultry Species 0.000 claims 1
- 241000392443 Pleurotus citrinopileatus Species 0.000 description 13
- 239000001963 growth medium Substances 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000012803 optimization experiment Methods 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000002932 luster Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000013433 optimization analysis Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
- A01G18/00—Cultivation of mushrooms
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N99/00—Subject matter not provided for in other groups of this subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Mining & Mineral Resources (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Mycology (AREA)
- Environmental Sciences (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a system and a method for optimizing production parameters of edible fungi, belonging to the technical field of edible fungi cultivation. The system comprises a computer, a display connected with the computer, a sensor based on a Modbus communication protocol and a camera; the sensor based on the Modbus communication protocol is an environment sensor, the camera is used for monitoring the growth condition of the edible fungi, and the sensor based on the Modbus communication protocol and the camera are connected with the computer through the Ethernet; the computer is provided with an edible fungus growth model analysis system with image processing and machine learning functions, the system can collect sensor experiment records, observe the growth vigor of edible fungi through a camera to generate an edible fungus growth model, and find the optimal edible fungus area and growth environment parameters in the model by using a fine segmentation algorithm. The invention has the advantages of finer analysis granularity, more detailed result data and small acquisition error, improves the accuracy of experimental analysis results, saves manpower and reduces cost.
Description
The application is a divisional application of a patent application named as a system and a method for optimizing growth parameters of edible fungi, wherein the application date of the original application is 2018, 06 and 01, and the application number is 201810558867.7.
Technical Field
The invention relates to a system and a method for optimizing growth parameters of edible fungi, belonging to the technical field of edible fungi cultivation.
Background
China is a large edible fungus producing country, and produces over 600 million tons of various edible fungi every year, which greatly enriches the material life of people, in recent years, along with the rapid improvement of income level and the rapid enhancement of consumption capacity, the demand of people on edible fungi is continuously increased, but due to insufficient production capacity, the price is still high. At present, the occupied amount of people in China is only 5 kilograms per year, and the number of people is less than one fourth of that of people in developed countries. Therefore, on the basis of industrial cultivation, the yield of the edible fungi in a single bottle can be improved by using which method to find the optimal cultivation environment and the optimal substrate, so that the total yield of the edible fungi is improved, and the market demand is better met.
The culture environment and the substrate selection of the same edible fungus directly influence the yield and quality of the mature edible fungus, so that how to obtain the highest yield of the edible fungus in a single bottle mainly focuses on the growth environment and the substrate selection of the edible fungus, and how to find out more optimal environment configuration and substrate selection for experimental analysis according to the growth environment and the substrate selection is particularly important. The growth environment parameters of the edible fungi are at least dozens of items, the data acquisition of CO2, temperature, humidity, EC, color and luster, area and the like of a complete experiment of the edible fungi is thousands or even tens of thousands, the data acquisition is huge, the analysis is difficult, the correlation of another environment parameter item can be found out frequently according to a single environment parameter item, the comprehensive correlation in the growth process of the edible fungi is difficult to calculate and analyze by integrating all the items, and the fine difference and the optimization are difficult to find out in a large amount of acquired data manually.
In the process of optimizing the growth experiment of the edible fungi, an experimenter usually arranges an environment sensor in the front, generally, one experiment sets dozens of environment parameters including the type of the edible fungi matrix, collects a plurality of records and usually needs manual copying; measuring the diameter or height of the strain and estimating the area; after the growth of the edible fungi is finished, repeating the steps to carry out a plurality of experiments; after a plurality of experiments are finished, generally artificially comparing results, determining better growth environment parameters in the experiments, and the process is shown in fig. 1.
The following problems are easily caused with the above conventional practice:
1. manual recording is time consuming, labor consuming and inefficient. The manual copying of the sensor data and the manual measurement of the area of the edible fungi need to be repeated, and much manpower and time are consumed.
2. The acquisition error is large. The acquisition time interval of manual acquisition is relatively large, the interval of different environmental parameters can be several minutes in the same acquisition, the time interval of different batches of acquisition cannot be too short, and for example, the acquisition of all the environmental parameters once in several minutes is difficult to achieve.
3. The analysis particle size is rough. After a period of time of experiment, only approximate magnitude of various environmental parameters in the whole experiment process can be obtained, and the magnitude of which time period cannot be achieved, particularly the magnitude of which granularity is minute.
4. The analysis result is inaccurate. After a plurality of experiments are finished, the correlation of various environmental parameters cannot be measured through manual estimation and comparison of experimental results, so that an optimal analysis result cannot be found.
Disclosure of Invention
The invention provides a system and a method for optimizing edible fungus production parameters, aiming at the problems of difficult manual comparison difference, huge workload, low comparison efficiency, rough statistical result, difficult optimization experiment, inaccurate optimizing result and the like in the process of searching for the optimal culture environment and the optimal substrate based on the precondition of the maximum yield of edible fungi.
By the system and the method provided by the invention, the automation rate of edible fungus optimization growth model analysis is improved, an optimal report is generated, complicated manual operation is omitted, the accuracy of an analysis result is improved, errors are effectively reduced, and the experiment optimization cost is reduced, so that the yield and the quality of edible fungi are improved.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for optimizing production parameters of edible fungi is based on a system for optimizing the production parameters of the edible fungi, and comprises the following steps: the Modbus communication system comprises a computer, a display connected with the computer, a sensor based on a Modbus communication protocol and a camera; the sensor based on the Modbus communication protocol is an environment sensor, the camera is used for monitoring the growth condition of the edible fungi, and the sensor based on the Modbus communication protocol and the camera are both connected with the computer through the Ethernet; an edible fungus growth model analysis system with image processing and machine learning functions is installed in a computer, the system can collect sensor experiment records, observe the growth vigor of edible fungi through a camera to generate an edible fungus growth model, and find the optimal edible fungus area and growth environment parameters in the model by using a fine segmentation algorithm; the method for optimizing the production parameters of the edible fungi comprises the following steps:
(1) when edible fungi are produced, the system for optimizing the production parameters of the edible fungi is adopted, the parameter configuration and the acquisition time interval of the environmental sensor and the camera are set, and the type of the substrate of the edible fungi is adopted to monitor the growth process of the edible fungi; the environmental parameters collected by the environmental sensor comprise: CO22Concentration, ambient temperature, humidity, soil conductivity, O2Concentration, pH and substrate temperature; the collection time interval is 1-30 min; the substrate for edible fungus growth is prepared from organic substances such as crop straw, mushroom dregs, peat, sawdust and animal and fowl excrements through fermenting or high-temp treating, and proportionally mixingCombining;
(2) the computer is connected with the sensor and the camera through software, and automatically acquires sensing data and a plant growth state image;
(3) sketching and calculating result parameters such as the growth area, the color and the like of the edible fungi by an image processing algorithm;
(4) after the growth of the edible fungi is finished, changing environmental parameters, and repeating the steps for a plurality of experiments;
(5) the method comprises the following steps of taking environmental parameters of a plurality of experiments as characteristics, taking the area, color, weight and average score of the edible fungi as labels, sending the labels into a machine learning algorithm for learning and generating an edible fungi growth model, and specifically comprises the following steps: taking the growth environment parameters and initialization settings of the edible fungi as characteristic parameters of a machine learning SVM algorithm, taking the results of the matching processing of the area, color or area color of the edible fungi analyzed by an image processing algorithm as labels, and learning and training by using the SVM algorithm to obtain an edible fungi growth model; the initialization setting includes: what substrate, collection time interval;
(6) and searching the optimal or maximum growth environment parameter of the edible fungus area in the model by using a fine segmentation algorithm to generate a curve report, thereby providing an optimal multi-factor growth curve for researchers.
Optionally, the edible fungus growth model is as follows: z ═ f (a, b, c, …), a ∈ A { (A)i}，b∈B＝{Bi}，c∈C＝{Ci…; wherein z represents the area or color of the edible fungi; f represents a functional relationship; a, b, c, … represents an environmental parameter, such as CO2Concentration, ambient temperature, humidity, soil conductivity, O2Concentration, pH or substrate temperature; a is equal to A ═ A [ ]iIn this, A, B, C … is a collection space of discrete points on the time axis of an environmental parameter, such as CO2Concentration collection space, ambient temperature collection space, humidity collection space, soil conductivity collection space, O2Concentration, pH or substrate temperature, Ai being an environmental parameter over time.
Optionally, if the requirements are met, a result is generated, and if the requirements are not met, experimental analysis iteration can be performed according to the report.
Optionally, the edible fungus growth environment parameters and the initialization settings are used as characteristic parameters of a machine learning algorithm, the edible fungus area or color analyzed by the image processing algorithm or the result of area color fitting processing is used as a label, and an SVM algorithm is used for learning and training to obtain the edible fungus growth model.
Optionally, the edible fungus growth environmental parameter comprises CO2、EC、O2Temperature, humidity, pH and substrate temperature, the initialization settings include substrate and acquisition time interval.
Optionally, the fine segmentation algorithm includes dividing a set space of a single environmental factor into two subspaces in the edible fungus growth model, and searching an optimal value in each subspace; taking the better of the two, subdividing the subspace into two next-level subspaces, repeating the steps, iterating for multiple times to find a more optimal area or color result value until a stable optimal value is obtained; and performing the segmented optimization on all the environmental parameters to finally obtain the optimal multi-factor growth model.
Optionally, the fine segmentation optimization algorithm includes the following steps:
1) learning and training a large amount of complete edible fungus growth data through a machine learning SVM (support vector machine) algorithm to obtain an edible fungus growth model;
2) each independent environment factor space is divided into two subspaces: α 1 ═ a0～Ai/2},α2＝{Ai/2+1～Ai},β1＝{B0～Bi/2},β2＝{Bi/2+1～Bi},γ1＝{C0～Ci/2},γ2＝{Ci/2+1～Ci… finding the optimal solution in each spatial combination; α 1 ═ a0～Ai/2 α 1 is a subspace of space A, Ai, Bi, Ci denote an environmental parameter, e.g., CO2Concentration, ambient temperature, humidity, soil conductivity, O2Concentration, pH or substrate temperature;
3) repeating the previous step on the space corresponding to the optimal solution, and iterating for multiple times to find a better area or color result value until a stable maximum value is obtained;
4) finally obtaining the space { ai, bi, ci … } of the maximum value as an optimal multi-factor growth model; ai, bi, ci … show that the environmental data for a certain time slice corresponding to the maximum edible fungus area or the optimal color can be obtained.
Optionally, the fruiting chamber is provided with a first culture bottle and a second culture bottle; two indoor temperature sensors, two indoor humidity sensors and two CO sensors are arranged2Sensor, O2The device comprises a sensor, a first in-bottle substrate temperature sensor and a second in-bottle substrate temperature sensor; the first culture bottle is a deep culture bottle, and the second culture bottle is a shallow culture bottle; the first bottle inner matrix temperature sensor is positioned in the deep culture bottle, and the second bottle inner matrix temperature sensor is positioned in the shallow culture bottle.
The invention relates to a method for training a growth model by combining environmental parameters, image processing area and/or color of edible fungi.
The invention has the advantages that:
(1) the analysis granularity is finer. Since the analysis prediction is performed based on the acquisition time interval setting, the shorter the acquisition time interval setting is, the production environment parameter such as CO is2The finer the magnitude of the optimum for a certain period of time.
(2) As a more mature machine learning algorithm is used for guidance, the optimization experiment is in a better direction, and result data are more detailed.
(3) The acquisition error is small. The system and the method adopt automatic acquisition, the time interval is small, the same acquisition is carried out, the interval of different environmental parameters is in millisecond level, and the acquisition time interval of different batches can also be in second level.
(4) The accuracy of the experimental analysis result is improved. The system and the method can find out more optimal environmental parameter configuration than the prior experiment and the edible fungus growth result which is not present in the prior experiment and has larger possible area by generating the edible fungus growth model by machine learning and searching the model by a fine segmentation optimization searching algorithm.
(5) The labor is saved, and the cost is reduced. The whole analysis process is completely automated, and the condition of screening by manpower can be completely replaced. Besides the consumption of electric energy, the system does not need any extra expenditure, and the cost of the experiment is reduced to a great extent.
The invention is further illustrated by the following figures and detailed description of the invention, which are not meant to limit the scope of the invention.
Drawings
FIG. 1 is a flow chart of a conventional method for optimizing the growth of edible fungi.
FIG. 2 is a schematic structural diagram of the edible mushroom production parameter optimizing system of the present invention.
FIG. 3 is a flow chart of the method for optimizing production parameters of edible fungi.
FIG. 4 is a sensor and polling time arrangement.
Fig. 5 is a camera configuration.
FIG. 6-1 and FIG. 6-2 are image processing comparisons, FIG. 6-1: before treatment, FIG. 6-2: and (5) after treatment.
FIG. 7 is the history data of the environmental change experiment during the fruiting process of Pleurotus citrinopileatus.
FIG. 8 is a history curve of the environmental change experiment during the fruiting process of Pleurotus citrinopileatus.
Fig. 9 shows the statistical results.
FIG. 10 is a diagram of a fine segmentation algorithm.
Fig. 11 is an analysis parameter set.
Detailed Description
As shown in FIG. 2, which is a physical frame diagram of the present invention, the system for optimizing production parameters of edible fungi of the present invention comprises a computer server, a display connected to the server, and a sensor based on Modbus communication protocol, wherein the sensor based on Modbus communication protocol is an environmental sensor, such as CO2The device comprises a sensor, an EC sensor (soil conductivity sensor), a temperature sensor, a humidity sensor and the like, and is used for aligning the edible fungi for experiments by arranging a high-definition camera. High definition digtal camera is used for monitoring domestic fungus's growth condition, based on Modbus communication protocol's sensor and make a video recordingThe heads are all connected with a computer through Ethernet; the computer is provided with an edible fungus growth model analysis system with an image processing algorithm and a machine learning algorithm, the system can collect sensor experiment records, observe the growth vigor of edible fungi through a camera to generate an edible fungus growth model, and find the optimal edible fungus area and growth environment parameters in the model by using a fine segmentation algorithm.
The specific flow chart of the present invention is shown in fig. 3, and sequentially includes: (1) setting an experimental environment sensor, a camera, acquisition time and the like, and during the production of edible fungi, setting parameter configuration and acquisition time intervals of the environment sensor and the camera, and adopting a substrate of the edible fungi and the like by adopting the edible fungi production parameter optimizing system shown in figure 2; (2) starting an experiment, acquiring sensor data and image data, connecting a computer with a sensor and a camera through software, and automatically acquiring the sensor data and a plant growth state image; (3) processing the edible fungus image, and sketching and calculating result parameters such as the growth area, the color and the like of the edible fungus by an image processing algorithm; (4) whether a plurality of experiments are finished or not, if not, returning to the step (1) to continue the experiments, and changing environmental parameters including CO after the edible fungi grow2Concentration, ambient temperature, humidity, EC, O2Concentration, pH, substrate temperature, etc., repeating the above steps for several experiments; (5) the method comprises the steps of generating a model through machine learning, wherein environmental parameters of a plurality of experiments are used as characteristics, and the area or color of the edible fungi are used as labels and are sent to a machine learning (SVM) algorithm for learning and generating an edible fungi growth model; (6) and fine segmentation optimization is carried out, a report is generated, an optimal or maximum edible fungus area and growth environment parameters are searched in the model by using a fine segmentation algorithm, and a curve report is generated. (7) If the experiment requirement is met, entering into the step (8) to output a result; if the condition is not satisfied, returning to the step (1) to continue the experiment, and then carrying out experiment analysis iteration according to the report.
Taking Pleurotus citrinopileatus as an example, the optimization analysis of growth parameters is realized by means of computer technology, and the method comprises the following steps:
(1) setting parameter configuration and acquisition time interval acquired by environment sensor and edible fungus camera before experimenter starts experiment and adoptingA matrix for edible fungus. As shown in FIG. 4, the fruiting chamber 2 (culture chamber 2) is provided with two culture bottles, a deep culture bottle and a shallow culture bottle, and is provided with an indoor temperature sensor 1, an indoor temperature sensor 2, an indoor humidity sensor 1, an indoor humidity sensor 2, CO2Sensor 1, CO2Sensor 2, O2A sensor, an in-bottle (substrate) temperature sensor 1 (deep culture bottle), an in-bottle (substrate) temperature sensor 2 (shallow culture bottle), 9 environmental sensors in total; the data acquisition time interval (polling time) was 1 minute. As shown in fig. 5, the camera is mounted so as to be aligned with the culture flask. The matrix type is Pleurotus citrinopileatus Yunnan No. 1.
(2) The device is connected with a sensor and a camera through software, and automatically acquires sensing data and a plant growth state image.
(3) The image of Pleurotus citrinopileatus growth obtained at a time is sketched and result parameters (average result of more than two culture bottles) such as growth area, color and the like of the edible fungi are calculated by an image processing algorithm of a computer edible fungi growth model analysis system, for example, fig. 6-1 is an image before processing, fig. 6-2 is an image after processing, and the result after processing is shown in table 1.
TABLE 1 acquisition of sensor data and calculation results
The computer acquires indoor temperature (1), indoor humidity (2) and O according to the acquisition time interval2、CO2(2) Temperature in bottle (2), temperature in bottle (1), indoor temperature (2), CO2(1) After the environmental parameters are calculated, the area (positive position) (average) of pleurotus citrinopileatus, the red mean (positive position) (average) of pleurotus citrinopileatus, the green mean (positive position) (average) of pleurotus citrinopileatus, the blue mean (positive position) (average) of pleurotus citrinopileatus, the maturity (positive position) (average) of pleurotus citrinopileatus and the like are sketched and calculated by an image processing algorithm, and part of historical data are shown in fig. 7.
Drawing to obtain the statistical result of the Pleurotus citrinopileatus fruiting process environment change experiment shown in FIG. 8 according to the collected data, wherein the statistical result includes CO2(1)、CO2(2)、O2The variation curves of indoor temperature (1), indoor temperature (2), indoor humidity (1), indoor humidity (2), temperature in the bottle (1), temperature in the bottle (2) and pleurotus citrinopileatus area (normal position) (average).
(4) After the edible fungi grow, changing environmental parameters (without changing collection time interval) including CO2Concentration, ambient temperature, humidity, O2Concentration, pH, substrate temperature, etc., the above procedure was repeated for several experiments. The environmental parameters may vary within the following ranges: ambient CO2The concentration is 600-3000ppm, the ambient temperature is 10-25 ℃, the ambient humidity is 45-100 percent, the pH value of the substrate is 4.5-8.0, and O2The concentration is 28000-35000 ppm, and the substrate temperature is 11-18 ℃.
(5) And (3) taking the environmental parameters of a plurality of experiments as characteristics, and taking the area or color of the edible fungi as a label to be sent to an SVM algorithm for learning and generating an edible fungi growth model. The method for training the growth model by combining the environmental parameters of the edible fungi, the image processing area and the color comprises the following steps: growing edible fungus with environmental parameters (such as CO)2、EC、O2Temperature, humidity, pH, substrate temperature and the like), initializing and setting (how to plant the substrate and acquisition time interval) as characteristic parameters of machine learning, labeling the area or color analyzed by the edible fungus image or the result of area color fitting processing, training the labeled area or color fitting processing, and obtaining a growth model by utilizing an SVM algorithm.
(6) And searching the optimal (maximum) edible fungus area and growth environment parameters in the model by using a fine segmentation algorithm.
The fine segmentation optimization algorithm comprises the following specific steps:
1) learning and training a large amount of complete edible fungus growth data through a machine learning SVM (support vector machine) algorithm to obtain an edible fungus growth model z ═ f (a, b, c, …), a ∈ A ═ A { (A)i}，b∈B＝{Bi}，c∈C＝{Ci…; wherein a, b, c, … represents an environmental parameter, such as CO2Concentration, ambient temperature, humidity, EC value (soil conductivity), O2Concentration, pH or substrate temperature, etc.; z represents the area or color of the edible fungi, and f represents the functional relation. a is equal to A ═ A [ ]iThe symbol, A, B, C … is a collection space of discrete points on the time axis of an environmental parameter, such as CO2Concentration volume, ambient temperature volume, humidity volume, EC value (soil conductivity) volume, O2Concentration space, pH or substrate temperature space, etc., AiIs an environmental parameter at a time;
2) each independent factor space is divided into two subspaces: α 1 ═ a0～Ai/2},α2＝{Ai/2+1～Ai},β1＝{B0～Bi/2},β2＝{Bi/2+1～Bi},γ1＝{C0～Ci/2},γ2＝{Ci/2+1～Ci… finding the optimal solution in each spatial combination; α 1 ═ a0～Ai/2 α 1 is a subspace of space A, Ai, Bi, Ci denote certain environmental parameters, such as CO2Concentration, ambient temperature, humidity, EC value (soil conductivity), O2Concentration, pH or substrate temperature, etc.;
3) repeating the previous step on the space corresponding to the optimal solution, and iterating for multiple times to find a better area or color result value until a stable maximum value is obtained;
4) and finally obtaining the space { ai, bi, ci … } of the maximum value as the optimal multi-factor growth model. ai, bi, ci … show that the environmental data for a certain time slice corresponding to the maximum edible fungus area or the optimal color can be obtained.
As shown in FIG. 9, the optimal growth curve of Pleurotus citrinopileatus is predicted by the above experiment, the temperature of culture medium is 15-18 deg.C, oxygen content is 20.8%, and environmental CO is present2600-1300ppm, the environmental temperature is 14-18 ℃, the environmental humidity is 45% -100%, and the culture time is 72 h.
As shown in fig. 10, any point on the graph can be represented by x, y, and assuming that the model function is z ═ f (x, y) after training, first, x, y is calculated by a set of intervals 20, the set is { [0,0], [0,20], [0,40], [20,0], [20,20], [20,40], [40,0], [40,20], [40,40] } (upper left corner is [0,0]), and as a result [20,20], that is, z1 value of point 9 is maximum, then, a set of intervals 10 is calculated around point 9, and finally, the value of [30,10], that is, z2 value of a point is larger than z1, and then, the calculation is performed in turn, and no larger value is calculated around C, that is, C > B > a >9, C is the searched area value, and x, y corresponding to the value is the optimal parameter of the finally found growth environment.
As shown in fig. 11, is a generated curve report. In which the CO is changed according to FIG. 112Temperature, etc., such as CO2Is substantially constant in the statistical results of FIG. 8, the next experiment can be analyzed according to FIG. 11 to report that CO starts2The concentration of the culture medium is stabilized at the concentration of 500-700ppm, and after the culture medium is cultured for a certain period, the culture medium is stabilized to the concentration of about 1200ppm, so that the area growth rate is relatively well accelerated.
If the requirements are met, a result is generated, and if the requirements are not met, experimental analysis iteration can be performed according to the report.
Claims (8)
1. A method for optimizing production parameters of edible fungi is characterized in that the method is based on a system for optimizing the production parameters of the edible fungi: the Modbus communication system comprises a computer, a display connected with the computer, a sensor based on a Modbus communication protocol and a camera; the sensor based on the Modbus communication protocol is an environment sensor, the camera is used for monitoring the growth condition of the edible fungi, and the sensor based on the Modbus communication protocol and the camera are both connected with the computer through the Ethernet; an edible fungus growth model analysis system with image processing and machine learning functions is installed in a computer, the system can collect sensor experiment records, observe the growth vigor of edible fungi through a camera to generate an edible fungus growth model, and find the optimal edible fungus area and growth environment parameters in the model by using a fine segmentation algorithm; the method for optimizing the production parameters of the edible fungi comprises the following steps:
(1) when edible fungi are produced, the system for optimizing the production parameters of the edible fungi is adopted, the parameter configuration and the acquisition time interval of the environmental sensor and the camera are set, and the type of the substrate of the edible fungi is adopted to monitor the growth process of the edible fungi; the environmental parameters collected by the environmental sensor comprise: CO22Concentration, ambient temperature, humidity, soil conductivity, O2Concentration, pH and substrate temperature; the collection time interval is 1-30 min; the substrate for edible fungus growth is generally adoptedOrganic matters such as crop straw, mushroom residue, grass peat, sawdust and livestock and poultry manure are fermented or treated at high temperature and then mixed according to a certain proportion;
(2) the computer is connected with the sensor and the camera through software, and automatically acquires sensing data and a plant growth state image;
(3) sketching and calculating result parameters such as the growth area, the color and the like of the edible fungi by an image processing algorithm;
(4) after the growth of the edible fungi is finished, changing environmental parameters, and repeating the steps for a plurality of experiments;
(5) the method comprises the following steps of taking environmental parameters of a plurality of experiments as characteristics, taking the area, color, weight and average score of the edible fungi as labels, sending the labels into a machine learning algorithm for learning and generating an edible fungi growth model, and specifically comprises the following steps: taking the growth environment parameters and initialization settings of the edible fungi as characteristic parameters of a machine learning SVM algorithm, taking the results of the matching processing of the area, color or area color of the edible fungi analyzed by an image processing algorithm as labels, and learning and training by using the SVM algorithm to obtain an edible fungi growth model; the initialization setting includes: what substrate, collection time interval;
(6) and searching the optimal or maximum growth environment parameter of the edible fungus area in the model by using a fine segmentation algorithm to generate a curve report, thereby providing an optimal multi-factor growth curve for researchers.
2. The method for optimizing edible fungus production parameters according to claim 1, wherein the edible fungus growth model is: z ═ f (a, B, c, …), a ∈ a ═ { Ai }, B ∈ B { [ B } ]i}，c∈C＝{Ci…; wherein z represents the area or color of the edible fungi; f represents a functional relationship; a, b, c, … represents an environmental parameter, such as CO2Concentration, ambient temperature, humidity, soil conductivity, O2Concentration, pH or substrate temperature; a is equal to A ═ A [ ]iIn this, A, B, C … is a collection space of discrete points on the time axis of an environmental parameter, such as CO2Concentration collection space, ambient temperature collection space, humidity collection space, soil conductivity collection space, O2Concentration space, pH or substrate temperature space, AiIs an environmental parameter of a time.
3. The method for optimizing edible fungus production parameters according to claim 2, wherein: if the requirements are met, a result is generated, and if the requirements are not met, experimental analysis iteration can be performed according to the report.
4. The method for optimizing edible fungus production parameters according to claim 2, wherein: and taking the growth environment parameters of the edible fungi and the initialization setting as characteristic parameters of a machine learning algorithm, taking the area or color of the edible fungi analyzed by the image processing algorithm or the result of the area color fitting processing as a label, and learning and training by utilizing an SVM algorithm to obtain an edible fungi growth model.
5. The method for optimizing edible fungus production parameters according to claim 4, wherein: the edible fungus growth environment parameters comprise CO2、EC、O2Temperature, humidity, pH and substrate temperature, the initialization settings include substrate and acquisition time interval.
6. The method for optimizing edible fungus production parameters according to claim 2, wherein: the fine segmentation algorithm comprises the steps that in an edible fungus growth model, a set space of a single environmental factor is divided into two subspaces, and an optimal value is searched in each subspace; taking the better of the two, subdividing the subspace into two next-level subspaces, repeating the steps, iterating for multiple times to find a more optimal area or color result value until a stable optimal value is obtained; and performing the segmented optimization on all the environmental parameters to finally obtain the optimal multi-factor growth model.
7. The method of claim 2, wherein the fine segmentation optimization algorithm comprises the steps of:
1) learning and training a large amount of complete edible fungus growth data through a machine learning SVM (support vector machine) algorithm to obtain an edible fungus growth model;
2) each independent environment factor space is divided into two subspaces: α 1 ═ a0～Ai/2},α2＝{Ai/2+1～Ai},β1＝{B0～Bi/2},β2＝{Bi/2+1～Bi},γ1＝{C0～Ci/2},γ2＝{Ci/2+1～Ci… finding the optimal solution in each spatial combination; α 1 ═ a0～Ai/2α 1 is a subspace of space A, Ai，BiAnd Ci represents an environmental parameter, such as CO2Concentration, ambient temperature, humidity, soil conductivity, O2Concentration, pH or substrate temperature;
3) repeating the previous step on the space corresponding to the optimal solution, and iterating for multiple times to find a better area or color result value until a stable maximum value is obtained;
4) finally obtaining the space { ai, bi, ci … } of the maximum value as an optimal multi-factor growth model; ai, bi, ci … show that the environmental data for a certain time slice corresponding to the maximum edible fungus area or the optimal color can be obtained.
8. The method for optimizing production parameters of edible fungi according to claim 1, wherein the fruiting chamber is provided with a first culture bottle and a second culture bottle; two indoor temperature sensors, two indoor humidity sensors and two CO sensors are arranged2Sensor, O2The device comprises a sensor, a first in-bottle substrate temperature sensor and a second in-bottle substrate temperature sensor; the first culture bottle is a deep culture bottle, and the second culture bottle is a shallow culture bottle; the first bottle inner matrix temperature sensor is positioned in the deep culture bottle, and the second bottle inner matrix temperature sensor is positioned in the shallow culture bottle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111119016.0A CN113711843B (en) | 2018-06-01 | 2018-06-01 | System and method for optimizing growth parameters of edible fungi |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810558867.7A CN108739052A (en) | 2018-06-01 | 2018-06-01 | A kind of system and method for edible fungi growth parameter optimization |
| CN202111119016.0A CN113711843B (en) | 2018-06-01 | 2018-06-01 | System and method for optimizing growth parameters of edible fungi |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810558867.7A Division CN108739052A (en) | 2018-06-01 | 2018-06-01 | A kind of system and method for edible fungi growth parameter optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113711843A true CN113711843A (en) | 2021-11-30 |
| CN113711843B CN113711843B (en) | 2022-07-26 |
Family
ID=64002243
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810558867.7A Pending CN108739052A (en) | 2018-06-01 | 2018-06-01 | A kind of system and method for edible fungi growth parameter optimization |
| CN202111119016.0A Active CN113711843B (en) | 2018-06-01 | 2018-06-01 | System and method for optimizing growth parameters of edible fungi |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810558867.7A Pending CN108739052A (en) | 2018-06-01 | 2018-06-01 | A kind of system and method for edible fungi growth parameter optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN108739052A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114971933A (en) * | 2022-05-25 | 2022-08-30 | 连云港银丰食用菌科技有限公司 | Edible mushroom preservation method and system |
| CN116649159A (en) * | 2023-08-01 | 2023-08-29 | 江苏慧岸信息科技有限公司 | Edible fungus growth parameter optimizing system and method |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109613947B (en) * | 2018-11-15 | 2020-12-15 | 西北农林科技大学 | Embedded facility light environment optimization regulation and control system integrating illumination frequency and duty ratio |
| CN109557966A (en) * | 2018-12-30 | 2019-04-02 | 盐城爱菲尔菌菇装备科技股份有限公司 | A kind of TT&C system and method for edible fungi growth environment |
| CN109874584A (en) * | 2019-03-19 | 2019-06-14 | 广州辰轩农业科技有限公司 | A kind of fruit tree growing way monitoring system based on deep learning convolutional neural networks |
| CN112930926A (en) * | 2021-01-28 | 2021-06-11 | 电凯(常州)新能源技术研究院有限公司 | Plant production parameter optimization method based on deep learning |
| CN115152528B (en) * | 2022-06-28 | 2024-07-02 | 江苏国耳生物科技有限公司 | Growth progress monitoring system and method for edible fungus bag growth |
| CN115127617A (en) * | 2022-07-21 | 2022-09-30 | 湖南博立农业科技发展有限公司 | Intelligent management and control system for edible fungus bionic planting |
| WO2024023343A1 (en) | 2022-07-28 | 2024-02-01 | Mushlabs Gmbh | Method and system for fungal culture and characteristics prediction of mycelium derived products |
| CN116720633B (en) * | 2023-08-11 | 2023-10-27 | 安徽农业大学 | Method for optimizing edible fungus breeding growth parameters |
| CN116797601B (en) * | 2023-08-24 | 2023-11-07 | 西南林业大学 | Image recognition-based Huashansong growth dynamic monitoring method and system |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201000564Y (en) * | 2006-09-01 | 2008-01-02 | 上海农业信息有限公司 | Edible fungus cultivation monitoring apparatus |
| CN103226348A (en) * | 2013-03-29 | 2013-07-31 | 湖北亿瑞生物科技有限公司 | Centralized remote environment control system and method for edible mushroom houses |
| CN103438932A (en) * | 2013-08-20 | 2013-12-11 | 解波 | System for monitoring edible fungi cultivation environment |
| CN103476042A (en) * | 2013-09-03 | 2013-12-25 | 吉林大学 | Wireless temperature sensor optimizing arrangement method in environment monitoring system |
| CN203422649U (en) * | 2013-07-23 | 2014-02-05 | 无锡百盛传感网络有限公司 | Environment parameter acquisition control system used in edible fungi growing sheds |
| CN104090542A (en) * | 2014-06-20 | 2014-10-08 | 广西小草信息产业有限责任公司 | Intelligent management system for edible medicinal fungus cultivation |
| CN105867495A (en) * | 2016-06-03 | 2016-08-17 | 福建省远山惠民生物有限公司 | Industrialized edible mushroom fruiting system and method remotely controlled by time parameters |
| CN105961034A (en) * | 2016-07-01 | 2016-09-28 | 北京蘑宿科技有限责任公司 | Edible fungus cultivation machine, cultivation monitoring system and method |
| CN205830457U (en) * | 2016-07-01 | 2016-12-28 | 北京蘑宿科技有限责任公司 | A kind of cultivating edible machine |
| CN106651149A (en) * | 2016-12-01 | 2017-05-10 | 厦门迈信物联科技股份有限公司 | Plant growth behavior analyzing method |
| JP2017153436A (en) * | 2016-03-03 | 2017-09-07 | 有限会社新潟システム制御 | Mushroom-sorting apparatus |
| CN206593595U (en) * | 2017-02-15 | 2017-10-27 | 河南瑞远物联网科技有限公司 | A kind of pleurotus eryngii growing way monitoring system based on image procossing |
| CN107622361A (en) * | 2017-10-31 | 2018-01-23 | 江苏天舒电器股份有限公司 | A kind of mathematical modeling and its control method for edible mushroom greenhouse-environment |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103869796A (en) * | 2014-03-31 | 2014-06-18 | 常熟理工学院 | Edible mushroom producing environment monitoring method and system |
| CN107341734A (en) * | 2017-06-06 | 2017-11-10 | 浙江大学 | A kind of method for building up of the protected crop seedling growth forecast model based on physiological parameter |
-
2018
- 2018-06-01 CN CN201810558867.7A patent/CN108739052A/en active Pending
- 2018-06-01 CN CN202111119016.0A patent/CN113711843B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201000564Y (en) * | 2006-09-01 | 2008-01-02 | 上海农业信息有限公司 | Edible fungus cultivation monitoring apparatus |
| CN103226348A (en) * | 2013-03-29 | 2013-07-31 | 湖北亿瑞生物科技有限公司 | Centralized remote environment control system and method for edible mushroom houses |
| CN203422649U (en) * | 2013-07-23 | 2014-02-05 | 无锡百盛传感网络有限公司 | Environment parameter acquisition control system used in edible fungi growing sheds |
| CN103438932A (en) * | 2013-08-20 | 2013-12-11 | 解波 | System for monitoring edible fungi cultivation environment |
| CN103476042A (en) * | 2013-09-03 | 2013-12-25 | 吉林大学 | Wireless temperature sensor optimizing arrangement method in environment monitoring system |
| CN104090542A (en) * | 2014-06-20 | 2014-10-08 | 广西小草信息产业有限责任公司 | Intelligent management system for edible medicinal fungus cultivation |
| JP2017153436A (en) * | 2016-03-03 | 2017-09-07 | 有限会社新潟システム制御 | Mushroom-sorting apparatus |
| CN105867495A (en) * | 2016-06-03 | 2016-08-17 | 福建省远山惠民生物有限公司 | Industrialized edible mushroom fruiting system and method remotely controlled by time parameters |
| CN205830457U (en) * | 2016-07-01 | 2016-12-28 | 北京蘑宿科技有限责任公司 | A kind of cultivating edible machine |
| CN105961034A (en) * | 2016-07-01 | 2016-09-28 | 北京蘑宿科技有限责任公司 | Edible fungus cultivation machine, cultivation monitoring system and method |
| CN106651149A (en) * | 2016-12-01 | 2017-05-10 | 厦门迈信物联科技股份有限公司 | Plant growth behavior analyzing method |
| CN206593595U (en) * | 2017-02-15 | 2017-10-27 | 河南瑞远物联网科技有限公司 | A kind of pleurotus eryngii growing way monitoring system based on image procossing |
| CN107622361A (en) * | 2017-10-31 | 2018-01-23 | 江苏天舒电器股份有限公司 | A kind of mathematical modeling and its control method for edible mushroom greenhouse-environment |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114971933A (en) * | 2022-05-25 | 2022-08-30 | 连云港银丰食用菌科技有限公司 | Edible mushroom preservation method and system |
| CN114971933B (en) * | 2022-05-25 | 2024-01-16 | 连云港银丰食用菌科技有限公司 | Preservation method and system for edible fungi |
| CN116649159A (en) * | 2023-08-01 | 2023-08-29 | 江苏慧岸信息科技有限公司 | Edible fungus growth parameter optimizing system and method |
| CN116649159B (en) * | 2023-08-01 | 2023-11-07 | 江苏慧岸信息科技有限公司 | Edible fungus growth parameter optimizing system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108739052A (en) | 2018-11-06 |
| CN113711843B (en) | 2022-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113711843B (en) | System and method for optimizing growth parameters of edible fungi | |
| CN108346142B (en) | Plant growth state identification method based on plant illumination image | |
| CN116649159B (en) | Edible fungus growth parameter optimizing system and method | |
| CN114677033B (en) | Laboratory cultivation data full-period flow intelligent monitoring analysis management system | |
| CN117455062A (en) | Crop yield prediction algorithm based on multi-source heterogeneous agricultural data | |
| CN115349316B (en) | Soil quality improvement and monitoring system and soil improvement method | |
| CN108427862B (en) | Nondestructive measurement method for biomass of multi-variety cotton in whole growth period based on image analysis | |
| CN116776290A (en) | Tobacco big data model construction method | |
| CN115575583A (en) | Artificial intelligence-based microbial fertilizer production quality evaluation system | |
| CN112036397B (en) | Embedded cucumber leaf image recognition device based on deep learning | |
| CN107766880B (en) | Photosynthetic bacteria fermentation process key parameter soft measurement method based on BA-LSSVM | |
| US20230309464A1 (en) | Method and apparatus for automated crop recipe optimization | |
| Jackson et al. | Robust Ensemble Machine Learning for Precision Agriculture | |
| CN108038586A (en) | A kind of water environment evaluation method and system of culture of Chinese mitten crab | |
| CN117371602A (en) | Fish growth trend prediction method | |
| CN117313920A (en) | Intelligent grape planting environment monitoring system | |
| Araneta et al. | Controlled Environment for Spinach Cultured Plant with Health Analysis using Machine Learning | |
| CN116818002A (en) | Intelligent agricultural planting monitoring system based on big data | |
| CA3127938A1 (en) | Holding tank monitoring system based on wireless sensor network and monitoring method | |
| Feng et al. | A real-time monitoring and control system for crop | |
| CN113988465A (en) | Banana plant nutrition judgment method based on machine learning | |
| CN212276431U (en) | Embedded cucumber leaf image recognition device based on deep learning | |
| Pabitha et al. | A digital footprint in enhancing agricultural practices with improved production using machine learning | |
| AU2021100096A4 (en) | Ai-based crop recommendation system for smart farming towards agriculture 5.0 | |
| CN111178391B (en) | Method for constructing parallel data set in product industry by using incremental singular value decomposition method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |