CN116830943A - Intelligent greenhouse crop growth environment adjusting method and system - Google Patents
Intelligent greenhouse crop growth environment adjusting method and system Download PDFInfo
- Publication number
- CN116830943A CN116830943A CN202310528210.7A CN202310528210A CN116830943A CN 116830943 A CN116830943 A CN 116830943A CN 202310528210 A CN202310528210 A CN 202310528210A CN 116830943 A CN116830943 A CN 116830943A
- Authority
- CN
- China
- Prior art keywords
- environment
- parameter set
- parameters
- historical
- growth
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000005286 illumination Methods 0.000 claims abstract description 45
- 238000005457 optimization Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 14
- 230000033228 biological regulation Effects 0.000 claims abstract description 9
- 230000007613 environmental effect Effects 0.000 claims description 75
- 238000004458 analytical method Methods 0.000 claims description 64
- 238000012549 training Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 6
- 230000007423 decrease Effects 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 2
- 238000011161 development Methods 0.000 abstract description 7
- 230000006870 function Effects 0.000 description 35
- 230000000694 effects Effects 0.000 description 10
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000005265 energy consumption Methods 0.000 description 4
- 240000008067 Cucumis sativus Species 0.000 description 3
- 235000010799 Cucumis sativus var sativus Nutrition 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000004141 dimensional analysis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
-
- 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
- A01G9/00—Cultivation in receptacles, forcing-frames or greenhouses; Edging for beds, lawn or the like
- A01G9/24—Devices or systems for heating, ventilating, regulating temperature, illuminating, or watering, in greenhouses, forcing-frames, or the like
-
- 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
- A01G9/00—Cultivation in receptacles, forcing-frames or greenhouses; Edging for beds, lawn or the like
- A01G9/24—Devices or systems for heating, ventilating, regulating temperature, illuminating, or watering, in greenhouses, forcing-frames, or the like
- A01G9/246—Air-conditioning systems
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Environmental Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Marine Sciences & Fisheries (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Animal Husbandry (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Mining & Mineral Resources (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Agronomy & Crop Science (AREA)
- Greenhouses (AREA)
Abstract
The application provides an intelligent regulation method and system for greenhouse crop growth environment, which relate to the technical field of intelligent regulation and comprise the following steps: acquiring current temperature parameters, humidity parameters and illumination parameters of greenhouse crops as a current environment parameter set, acquiring an adjustment feasible region according to the environment parameter set in a preset historical time range, constructing an adaptability function according to cost and growth conditions, setting constraint conditions to perform environment parameter optimization to obtain an optimal environment parameter set, wherein the growth conditions of the greenhouse crops are acquired based on image processing identification, and the environment parameters in the growth environment are adjusted by adopting the optimal environment parameter set. The application solves the technical problems that the traditional greenhouse crop growth environment adjusting method depends on manual adjustment and is easily influenced by subjective factors, so that the efficiency is low, the cost is high, and meanwhile, the development requirements of modern agriculture on high efficiency and intelligence cannot be met.
Description
Technical Field
The application relates to the technical field of intelligent regulation, in particular to an intelligent regulation method and system for greenhouse crop growth environment.
Background
With the advancement of technology, greenhouse planting is becoming more and more important as an efficient agricultural planting mode, and in the greenhouse planting process, environmental parameter control is one of key factors affecting crop growth and yield. The traditional control method is usually manually adjusted, has low efficiency and high cost, is easily influenced by subjective factors, and cannot meet the development requirements of modern agriculture on high efficiency and intelligence, so that the research on a method capable of intelligently adjusting the growth environment of greenhouse crops becomes particularly important.
Disclosure of Invention
The embodiment of the application provides an intelligent greenhouse crop growth environment adjusting method and system, which are used for solving the technical problems that the traditional greenhouse crop growth environment adjusting method depends on manual adjustment and is easily influenced by subjective factors, so that the efficiency is low, the cost is high, and meanwhile, the development requirements of modern agriculture on high efficiency and intelligence cannot be met.
In view of the above problems, the embodiment of the application provides an intelligent greenhouse crop growth environment adjusting method and system.
In a first aspect, an embodiment of the present application provides a method for intelligently adjusting a greenhouse crop growth environment, where the method includes: acquiring current temperature parameters, humidity parameters and illumination parameters in the growing environment of greenhouse crops as a current environment parameter set; acquiring an adjustment feasible region for adjusting the environmental parameters currently according to the environmental parameter set of the growth environment in a preset historical time range; constructing an adaptability function according to the cost of adjusting the environmental parameters in the growing environment and the growing condition of the greenhouse crops after the environmental parameters are adjusted; setting constraint conditions according to the current environment parameter set, and optimizing environment parameters in the adjustable feasible domain based on the fitness function and the constraint conditions to obtain an optimal environment parameter set, wherein the growth condition of the greenhouse crops is obtained based on image processing identification; and adjusting the environmental parameters in the growth environment by adopting the optimal environmental parameter set.
In a second aspect, an embodiment of the present application provides an intelligent greenhouse crop growth environment adjustment system, the system comprising: the environment parameter set acquisition module is used for acquiring current temperature parameters, humidity parameters and illumination parameters in the growing environment of greenhouse crops and taking the current temperature parameters, humidity parameters and illumination parameters as a current environment parameter set; the adjustable feasible region acquisition module is used for acquiring an adjustable feasible region for adjusting the environmental parameters currently according to the environmental parameter set of the growth environment in the preset historical time range; the fitness function construction module is used for constructing a fitness function according to the cost of adjusting the environmental parameters in the growing environment and the growing condition of the greenhouse crops after the environmental parameters are adjusted; the environment parameter optimizing module is used for setting constraint conditions according to the current environment parameter set, optimizing the environment parameters in the adjustable feasible region based on the fitness function and the constraint conditions to obtain an optimal environment parameter set, wherein the growth condition of the greenhouse crops is obtained based on image processing identification; and the environment parameter adjusting module is used for adjusting the environment parameters in the growth environment by adopting the optimal environment parameter set.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
acquiring current temperature parameters, humidity parameters and illumination parameters in a growing environment of greenhouse crops as a current environment parameter set, acquiring an adjustment feasible region according to an environment parameter set of the growing environment in a preset history time range, constructing a fitness function according to the cost of adjusting the environment parameters in the growing environment and the growing condition of the greenhouse crops after the environment parameters are adjusted, setting constraint conditions, optimizing the environment parameters, and acquiring an optimal environment parameter set, wherein the growing condition of the greenhouse crops is acquired based on image processing identification, and the environment parameters in the growing environment are adjusted by adopting the optimal environment parameter set.
The method solves the technical problems that the traditional greenhouse crop growth environment adjusting method is manually adjusted and is easily influenced by subjective factors, so that the efficiency is low, the cost is high, meanwhile, the development requirements of modern agriculture on high efficiency and intelligence cannot be met, the environmental parameters are automatically acquired, and a feasible region and fitness function are constructed and adjusted according to historical data, so that the environmental parameters are optimized, the growth environment of greenhouse crops is effectively adjusted, the production cost is reduced, and meanwhile, the technical effect of intelligent production is realized.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly described below. It is apparent that the figures in the following description relate only to some embodiments of the present disclosure and are not limiting of the present disclosure.
FIG. 1 is a schematic flow chart of an intelligent regulation method for the growth environment of greenhouse crops according to the embodiment of the application;
FIG. 2 is a schematic diagram of a process for obtaining a feasible region for adjustment in an intelligent adjustment method for the growth environment of greenhouse crops according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of obtaining an optimal environmental parameter set in an intelligent regulation method for greenhouse crop growth environment according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an intelligent greenhouse crop growth environment regulating system according to an embodiment of the present application.
Reference numerals illustrate: the system comprises an environment parameter set acquisition module 10, an adjustment feasible region acquisition module 20, an fitness function construction module 30, an environment parameter optimizing module 40 and an environment parameter adjustment module 50.
Detailed Description
The intelligent greenhouse crop growth environment adjusting method solves the technical problems that the traditional greenhouse crop growth environment adjusting method is manually adjusted and is easily affected by subjective factors, so that the efficiency is low, the cost is high, meanwhile, the development requirements of modern agriculture are not met, the environment parameters are automatically acquired, a feasible region and a fitness function are constructed and adjusted according to historical data, the environment parameters are optimized, the growth environment of greenhouse crops is effectively adjusted, the production cost is reduced, and meanwhile, the intelligent production is realized.
Example 1
As shown in fig. 1, the embodiment of the application provides an intelligent greenhouse crop growth environment adjusting method, which comprises the following steps:
step S100: acquiring current temperature parameters, humidity parameters and illumination parameters in the growing environment of greenhouse crops as a current environment parameter set;
specifically, temperature, humidity and illumination sensors are deployed in a greenhouse, the sensors transmit data to a central processing system through wireless connection, data of the parameters are monitored and collected in real time, the obtained temperature, humidity and illumination data are integrated together to form a current environmental parameter set, and the set is used as a basis for analysis and adjustment of subsequent steps. The current environmental condition in the clear greenhouse is realized so as to carry out corresponding adjustment according to the crop requirements.
Step S200: acquiring an adjustment feasible region for adjusting the environmental parameters currently according to the environmental parameter set of the growth environment in a preset historical time range;
further, as shown in fig. 2, step S200 of the present application further includes:
step S210: acquiring a plurality of historical environment parameter sets of the growth environment in a preset historical time range, and acquiring a historical temperature parameter set, a historical humidity parameter set and a historical illumination parameter set;
step S220: performing error compensation on the historical temperature parameters, the historical humidity parameters and the historical illumination parameters in the historical temperature parameter set, the historical humidity parameter set and the historical illumination parameter set according to a preset proportion to obtain a plurality of historical temperature parameter ranges, a plurality of historical illumination parameter ranges and a plurality of historical humidity parameter ranges;
step S230: and randomly generating temperature parameters, humidity parameters and illumination parameters in the historical temperature parameter ranges, the historical illumination parameter ranges and the historical humidity parameter ranges respectively, and combining to obtain a plurality of environment parameter sets to obtain the adjustment feasible region.
Specifically, the historical environmental parameter data is analyzed to determine a viable range of current environmental parameter adjustments, with a historical time range, such as the last days, weeks, or months, being preset based on the growth cycle of the crop and the availability of the data. A plurality of historical environmental parameter sets within a preset historical time range are extracted from a database or a storage system, including records of temperature, humidity and illumination parameters over a period of time. The extracted historical environmental parameter data are classified according to temperature, humidity and illumination, and are respectively integrated into a historical temperature parameter set, a historical humidity parameter set and a historical illumination parameter set, wherein the historical temperature parameter set, the historical humidity parameter set and the historical illumination parameter set are used for determining the change condition of each environmental parameter in a historical time range.
A suitable preset proportion, for example + -10%, is set according to the crop growth requirements and practical experience. The ratio is used for performing error compensation on the historical environment parameters, and the error compensation range of each historical parameter is calculated according to the preset ratio for the historical temperature parameter set, the historical humidity parameter set and the historical illumination parameter set, for example, if the historical temperature parameter is 20 degrees, the error compensation is performed according to the preset ratio of +/-10%, and the adjusted range is [18,22 ]. And respectively acquiring a plurality of historical temperature parameter ranges, a plurality of historical illumination parameter ranges and a plurality of historical humidity parameter ranges according to the error compensation result, wherein the parameter ranges are used for constructing an adjustment feasible region and providing references for environmental parameter adjustment.
The temperature parameter, the illumination parameter and the humidity parameter are randomly generated in each of the historical temperature parameter range, the historical illumination parameter range and the historical humidity parameter range, and are randomly combined to form a plurality of environment parameter sets which represent various environment conditions which can occur in the adjustable feasible region. An adjustable feasible region consisting of a plurality of environment parameter sets provides a search space for subsequent environment parameter optimization, and in the feasible region, the system performs optimization according to a fitness function and constraint conditions to find the optimal environment parameter set.
Step S300: constructing an adaptability function according to the cost of adjusting the environmental parameters in the growing environment and the growing condition of the greenhouse crops after the environmental parameters are adjusted;
specifically, cost factors including energy consumption, water resource consumption, labor cost and the like are determined, wherein the energy consumption comprises heating, refrigerating, lighting and the like, and the factors are quantized into a cost index for measuring the economic effect of environmental parameter adjustment;
the images are processed and analyzed by using a camera or other image acquisition equipment to identify the growth conditions of the crops, such as leaf area, stem thickness, inflorescence quantity and the like, and the information is used for more accurately evaluating the growth effect of the environmental parameter adjustment. Determining growth effect factors including crop growth speed, growth period, yield index and the like, and quantifying the factors into a growth effect index for measuring the influence of environmental parameter adjustment on crop growth.
The cost index and the growth effect index are integrated into one fitness function, the fitness function is used for minimizing the cost index and maximizing the growth effect index, and the fitness function can be adjusted and optimized according to actual conditions so as to meet the requirements of different crops and greenhouse conditions.
The fitness function is as follows:
wherein Y is fitness, W K 、W S And W is C Is given by weight, K A To adjust the formation of the environment parameter setBook, K B For the cost of the current set of environmental parameters,to adjust the size score of the jth greenhouse crop in the growing environment after the environmental parameter set, T is the detected number of greenhouse crops, S B Average size score of greenhouse crops in said growing environment under said current set of environmental parameters, +.>To adjust the color score of the jth greenhouse crop in the growing environment after the environmental parameter set, C B The average color score, color score and size score of the greenhouse crops in the growing environment under the current environmental parameter set are obtained through image processing identification.
Step S400: setting constraint conditions according to the current environment parameter set, and optimizing environment parameters in the adjustable feasible domain based on the fitness function and the constraint conditions to obtain an optimal environment parameter set, wherein the growth condition of the greenhouse crops is obtained based on image processing identification;
further, as shown in fig. 3, step S400 of the present application further includes:
step S410: setting the fitness larger than 0 as a constraint condition, and discarding if the environment parameter set does not meet the constraint condition in the optimizing process;
step S420: randomly selecting an environment parameter set in the adjustable feasible domain as a first environment parameter set and temporarily serving as an optimal solution;
step S430: acquiring a first fitness of the first environment parameter set according to the fitness function;
step S440: randomly selecting an environment parameter set in the adjustable feasible domain again to serve as a second environment parameter set, and obtaining second fitness according to the fitness function;
step S450: judging whether the second fitness is larger than the first fitness, if so, replacing the second environment parameter set with the second environment parameter set as an optimal solution, if not, randomly generating random numbers in 0,1, judging whether the random numbers are smaller than a probability value, if so, taking the second environment parameter set as the optimal solution, and if not, taking the first environment parameter set as the optimal solution, wherein the probability value is reduced along with the increase of iteration times;
step S460: continuing to perform iterative optimization until the first optimizing iteration times are reached, and adding the new environment parameter set into the tabu table when the adaptability of the new environment parameter set obtained by iteration is smaller than or equal to the adaptability of the optimal solution;
step S470: and continuing to perform iterative optimization until the second optimizing iteration times are reached, and outputting a final optimal solution to obtain the optimal environment parameter set.
Specifically, according to the current environmental parameter set, constraint conditions are set, and in order to ensure that the environmental parameter set has positive influence on greenhouse crop growth, constraint conditions with a fitness greater than 0 are set. In the optimizing process, calculating the fitness value of each environment parameter set according to the fitness function, if the environment parameter set with the fitness not more than 0 is met, namely the constraint condition is not met, discarding the environment parameter set without consideration.
In the adjustable feasible domain, randomly selecting an environment parameter set as an initial solution, wherein the initial solution comprises a temperature parameter, a humidity parameter and an illumination parameter, taking the initial solution as a starting point of an optimizing process, and temporarily taking the selected initial solution as an optimal solution for comparison and updating of a subsequent optimizing process.
Substituting the first environment parameter set into the fitness function, and calculating a fitness value, namely first fitness, of the fitness function, wherein the first fitness reflects the fitness of the initial solution to the growth of greenhouse crops and is used as a reference for subsequent optimization. And randomly selecting one environment parameter set again in the adjustable feasible region as a second environment parameter set, comparing the second environment parameter set with the first environment parameter set, substituting the second environment parameter set into the fitness function, and calculating the fitness value, namely a second fitness, reflecting the fitness of the second environment parameter set to the growth of greenhouse crops.
And comparing the first fitness with the second fitness, and if the second fitness is larger than the first fitness, replacing a second environment parameter set corresponding to the second fitness as an optimal solution. If the second fitness is not greater than the first fitness, generating a random number in a [0,1] interval, and comparing the random number with a preset probability value, wherein the probability value is reduced along with the increase of iteration times so as to reduce the possibility of receiving a suboptimal solution in later iterations, and the probability value is calculated by the following formula:
wherein Y is 2 For a second fitness, Y 1 For the first fitness, N is a constant that decreases as the number of iterations increases.
If the random number is smaller than the probability value, the second environment parameter set is used as an optimal solution, otherwise, the first environment parameter set is still used as the optimal solution.
The first optimizing iteration times are equivalent to the optimizing of the first stage, in the stage, a better environment parameter set is continuously and iteratively searched, whether the solution with lower fitness is accepted as an optimal solution is judged according to the probability value, optimizing efficiency is improved, and local optimum is jumped out. In the iterative process, when the fitness of a new environment parameter set is smaller than or equal to that of the current optimal solution, the new environment parameter set is added into a tabu table, wherein the tabu table is a strategy for avoiding repeated searching and trapping in the local optimal solution, and records the searched suboptimal solutions so as to avoid repeated searching on the solutions in subsequent iterations.
The second optimizing iteration times are equivalent to the optimizing of the second stage, in the stage, iteration is continued, probability values and tabu tables are adjusted, solutions with low fitness are directly abandoned and tabu is carried out, optimizing precision is improved, and the found optimal solutions are output and serve as an optimal environment parameter set.
Further, step S430 of the present application further includes:
step S431: acquiring T crop images of T greenhouse crops in the growth environment under the first environment parameter set;
step S432: constructing a growth condition analysis model based on greenhouse crop growth monitoring data in historical time in a plurality of growth environments, wherein the growth condition analysis model comprises a size analysis unit and a color analysis unit;
step S433: respectively inputting the T crop images into the growth condition analysis model to obtain T size scores and T color scores;
step S434: acquiring greenhouse environment cost under the first environment parameter set;
step S435: inputting the T size scores, the T color scores and the greenhouse environment cost into the fitness function to obtain the first fitness.
Specifically, under a first set of environmental parameters, T greenhouse crops within a growing environment are captured by a camera or other image capturing device mounted within the greenhouse, where T is the number of greenhouse crops, e.g., 30 greenhouse crops within the growing environment, and each of them is image captured.
Greenhouse crop growth monitoring data is collected over a plurality of historical time periods within the growing environment, including characteristics of greenhouse crop size, color, growth rate, etc. Constructing a growth condition analysis model based on a convolutional neural network by adopting the collected data, wherein the model comprises a size analysis unit and a color analysis unit, and the size analysis unit is used for analyzing the size characteristics of greenhouse crops, such as plant height, leaf length, leaf width and the like; the color analysis unit is used for analyzing color characteristics of greenhouse crops, such as leaf colors, flower colors and the like. The growth analysis model is trained using historical data and validated to ensure that the model can accurately analyze the growth of greenhouse crops.
Respectively inputting the obtained T crop images into a growth condition analysis model, wherein in the model, a size analysis unit performs size characteristic analysis on the T crop images, and calculates a size score for each crop image based on the size characteristics such as plant height, leaf length and width; the color analysis unit performs color feature analysis on the T input crop images, and calculates a color score for each crop image based on color features such as leaf color, flower color, and the like.
Factors influencing the greenhouse environment cost include energy consumption (such as electric power, water resources and the like), equipment maintenance cost, labor cost and the like, and cost calculation is performed according to the energy consumption, the equipment maintenance cost and the like under the first environment parameter set, so that the greenhouse environment cost under the environment parameter set is obtained. Substituting the T size scores, the T color scores and the greenhouse environment cost into the fitness function, and calculating to obtain a fitness value corresponding to the first environment parameter set, namely the first fitness.
Further, step S432 of the present application further includes:
step S4321: acquiring a historical crop image set, a historical size scoring set and a historical color scoring set based on greenhouse crop growth monitoring data in historical time in a plurality of growth environments;
step S4322: constructing the size analysis unit and the color analysis unit based on a convolutional neural network;
step S4323: performing supervision training, verification and testing on the size analysis unit by adopting the historical crop image set and the historical size grading set, updating network parameters until a first convergence condition is reached, and obtaining the size analysis unit;
step S4324: and performing supervision training, verification and testing on the color analysis unit by adopting the historical crop image set and the historical color grading set, updating network parameters until reaching a second convergence condition, obtaining the color analysis unit, and obtaining the growth condition analysis model.
Specifically, greenhouse crop growth monitoring data under different growth environments is collected, including crop images, size scores and color scores, wherein the size scores and the color scores are obtained by one skilled in the art from the crop images, e.g., in case of cucumber, the size scores may be based on the length and thickness of the cucumber, and the color scores may be based on the color and surface texture of the cucumber. The collected crop images, size scores, and color scores are categorized and ranked to form a set of historical crop images, a set of historical size scores, and a set of historical color scores.
The size analysis unit and the color analysis unit are constructed using convolutional neural networks (Convolutional Neural Networks, CNN), which is a deep learning technique suitable for image processing and recognition tasks. Based on the convolutional neural network, a network structure of an analysis unit is constructed, wherein the network structure comprises a convolutional layer, an activation function, a pooling layer, a full-connection layer and the like, the size analysis unit and the color analysis unit can share a part of the convolutional layer, and a size score and a color score are respectively output in the following full-connection layer.
The historical crop image set and the historical size scoring set are randomly divided into a training set, a verification set and a test set according to a certain proportion, for example, 70% training set, 15% verification set and 15% test set. And taking the crop images in the training set as input and the corresponding historical size scores as output targets, training a size analysis unit by using a supervised learning method, and continuously updating network parameters in the training process to minimize the prediction error. After training, the performance of the size analysis unit is evaluated by using the verification set, and super parameters such as a network structure, a learning rate and the like are adjusted according to the verification result so as to improve the performance of the model.
Setting a first convergence condition, such as the training loss being less than a certain threshold, the validation loss no longer falling significantly or reaching a maximum training period, etc., and stopping the training process when the convergence condition is met. The final performance of the dimensional analysis unit is evaluated using the test set, and the test results are used as an estimate of the model's performance on unknown data.
In the same way, the historical crop image set and the historical color scoring set are adopted to construct the color analysis unit, and for the sake of brevity of the description, details are omitted here. And integrating the size analysis unit and the color analysis unit to obtain the growth condition analysis model.
Step S500: and adjusting the environmental parameters in the growth environment by adopting the optimal environmental parameter set.
In particular, control devices related to temperature, humidity and lighting adjustment, such as heaters, refrigeration devices, humidity controllers, lighting systems, etc., are connected to the central control system. According to the optimal environment parameter set, corresponding control instructions are generated for each control device, the control device adjusts the output of each control device according to the received instructions so as to change the temperature, humidity and illumination conditions in the temperature chamber and adjust the temperature, humidity and illumination conditions to parameters in the optimal environment parameter set, and an environment which is more favorable for the growth and development of crops is created while the cost is controlled.
In summary, the intelligent greenhouse crop growth environment adjusting method and system provided by the embodiment of the application have the following technical effects:
acquiring current temperature parameters, humidity parameters and illumination parameters in a growing environment of greenhouse crops as a current environment parameter set, acquiring an adjustment feasible region according to an environment parameter set of the growing environment in a preset history time range, constructing a fitness function according to the cost of adjusting the environment parameters in the growing environment and the growing condition of the greenhouse crops after the environment parameters are adjusted, setting constraint conditions, optimizing the environment parameters, and acquiring an optimal environment parameter set, wherein the growing condition of the greenhouse crops is acquired based on image processing identification, and the environment parameters in the growing environment are adjusted by adopting the optimal environment parameter set.
The method solves the technical problems that the traditional greenhouse crop growth environment adjusting method is manually adjusted and is easily influenced by subjective factors, so that the efficiency is low, the cost is high, meanwhile, the development requirements of modern agriculture on high efficiency and intelligence cannot be met, the environmental parameters are automatically acquired, and a feasible region and fitness function are constructed and adjusted according to historical data, so that the environmental parameters are optimized, the growth environment of greenhouse crops is effectively adjusted, the production cost is reduced, and meanwhile, the technical effect of intelligent production is realized.
Example two
Based on the same inventive concept as the intelligent regulation method of greenhouse crop growth environment in the foregoing embodiments, as shown in fig. 4, the present application provides an intelligent regulation system of greenhouse crop growth environment, the system comprising:
the environment parameter set acquisition module 10 is used for acquiring current temperature parameters, humidity parameters and illumination parameters in the growing environment of greenhouse crops, and the current temperature parameters, the humidity parameters and the illumination parameters are used as a current environment parameter set;
the adjustable feasible region acquisition module 20 is used for acquiring an adjustable feasible region for adjusting the environmental parameters currently according to the environmental parameter set of the growth environment in a preset historical time range;
the fitness function construction module 30 is used for constructing a fitness function according to the cost of adjusting the environmental parameters in the growing environment and the growing condition of the greenhouse crops after the environmental parameters are adjusted;
the environment parameter optimizing module 40 is configured to set constraint conditions according to the current environment parameter set, and perform environment parameter optimizing in the adjustable feasible domain based on the fitness function and the constraint conditions to obtain an optimal environment parameter set, where the growth condition of the greenhouse crop is obtained based on image processing identification;
an environmental parameter adjustment module 50, wherein the environmental parameter adjustment module 50 is configured to adjust environmental parameters within the growth environment using the optimal set of environmental parameters.
Further, the system further comprises:
the historical environment parameter acquisition module is used for acquiring a plurality of historical environment parameter sets of the growing environment in a preset historical time range and acquiring a historical temperature parameter set, a historical humidity parameter set and a historical illumination parameter set;
the error compensation module is used for carrying out error compensation on the historical temperature parameter, the historical humidity parameter and the historical illumination parameter in the historical temperature parameter set, the historical humidity parameter set and the historical illumination parameter set according to a preset proportion to obtain a plurality of historical temperature parameter ranges, a plurality of historical illumination parameter ranges and a plurality of historical humidity parameter ranges;
the environment parameter acquisition module is used for randomly generating temperature parameters, humidity parameters and illumination parameters in the historical temperature parameter ranges, the historical illumination parameter ranges and the historical humidity parameter ranges respectively, combining the temperature parameters, the humidity parameters and the illumination parameters to obtain a plurality of environment parameter sets, and obtaining the adjustable feasible region.
Further, the system further comprises:
constructing a fitness function, wherein the fitness function is as follows:
wherein Y is fitness, W K 、W S And W is C Is given by weight, K A To adjust the cost of the post-environmental parameter set, K B For the cost of the current set of environmental parameters,to adjust the size score of the jth greenhouse crop in the growing environment after the environmental parameter set, T is the detected number of greenhouse crops, S B Average size score of greenhouse crops in said growing environment under said current set of environmental parameters, +.>To adjust the color score of the jth greenhouse crop in the growing environment after the environmental parameter set, C B The average color score, color score and size score of the greenhouse crops in the growing environment under the current environmental parameter set are obtained through image processing identification.
Further, the system further comprises:
the discarding module is used for setting the fitness larger than 0 as a constraint condition, and discarding if the environment parameter set does not meet the constraint condition in the optimizing process;
the temporary optimal solution acquisition module is used for randomly selecting an environment parameter set in the adjustable feasible domain, and taking the environment parameter set as a first environment parameter set and temporarily taking the environment parameter set as an optimal solution;
the first fitness obtaining module is used for obtaining the first fitness of the first environment parameter set according to the fitness function;
the second fitness obtaining module is used for randomly selecting an environment parameter set in the adjustable feasible domain again to serve as a second environment parameter set, and obtaining second fitness according to the fitness function;
the second fitness judging module is used for judging whether the second fitness is larger than the first fitness, if so, replacing the second environment parameter set with the second fitness as an optimal solution, if not, randomly generating a random number in 0,1, judging whether the random number is smaller than a probability value, if so, taking the second environment parameter set as the optimal solution, and if not, taking the first environment parameter set as the optimal solution, wherein the probability value is reduced along with the increase of iteration times;
the first iterative optimization module is used for continuing iterative optimization until the first optimization iteration times are reached, and adding the new environment parameter set into the tabu table when the adaptation degree of the new environment parameter set obtained by iteration is smaller than or equal to the adaptation degree of the optimal solution;
and the second iterative optimization module is used for continuing iterative optimization until reaching the second optimization iteration times, and outputting the final optimal solution to obtain the optimal environment parameter set.
Further, the system further comprises:
the crop image acquisition module is used for acquiring T crop images of T greenhouse crops in the growth environment under the first environment parameter set;
the analysis model construction module is used for constructing a growth condition analysis model based on greenhouse crop growth monitoring data in historical time in a plurality of growth environments, wherein the growth condition analysis model comprises a size analysis unit and a color analysis unit;
the scoring acquisition module is used for respectively inputting the T crop images into the growth condition analysis model to obtain T size scores and T color scores;
the greenhouse environment cost acquisition module is used for acquiring the greenhouse environment cost under the first environment parameter set;
and the first fitness output module is used for inputting the T size scores, the T color scores and the greenhouse environment cost into the fitness function to obtain the first fitness.
Further, the system further comprises:
the historical information acquisition module is used for acquiring a historical crop image set, a historical size scoring set and a historical color scoring set based on greenhouse crop growth monitoring data in historical time in a plurality of growth environments;
the analysis unit construction module is used for constructing the size analysis unit and the color analysis unit based on the convolutional neural network;
the size analysis unit training module is used for performing supervision training, verification and testing on the size analysis unit by adopting the historical crop image set and the historical size scoring set, updating network parameters until a first convergence condition is reached, and obtaining the size analysis unit;
and the color analysis unit training module is used for performing supervision training, verification and test on the color analysis unit by adopting the historical crop image set and the historical color grading set, updating network parameters until reaching a second convergence condition, obtaining the color analysis unit and obtaining the growth condition analysis model.
Further, the system further comprises:
the probability value is calculated by:
wherein Y is 2 For a second fitness, Y 1 For the first fitness, N is a constant that decreases as the number of iterations increases.
The foregoing detailed description of a method for intelligently adjusting the growth environment of greenhouse crops will be clear to those skilled in the art, and the device disclosed in this embodiment is relatively simple in description, and the relevant points refer to the description of the method section because the device disclosed in the embodiment corresponds to the method disclosed in the embodiment.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. An intelligent greenhouse crop growth environment adjusting method is characterized by comprising the following steps:
acquiring current temperature parameters, humidity parameters and illumination parameters in the growing environment of greenhouse crops as a current environment parameter set;
acquiring an adjustment feasible region for adjusting the environmental parameters currently according to the environmental parameter set of the growth environment in a preset historical time range;
constructing an adaptability function according to the cost of adjusting the environmental parameters in the growing environment and the growing condition of the greenhouse crops after the environmental parameters are adjusted;
setting constraint conditions according to the current environment parameter set, and optimizing environment parameters in the adjustable feasible domain based on the fitness function and the constraint conditions to obtain an optimal environment parameter set, wherein the growth condition of the greenhouse crops is obtained based on image processing identification;
and adjusting the environmental parameters in the growth environment by adopting the optimal environmental parameter set.
2. The method of claim 1, wherein obtaining a temperature parameter range, a humidity parameter range, and an illumination parameter range within the growth environment, in combination with an environmental parameter set of the growth environment within a preset historical time range, obtains an adjustment feasible region for adjusting environmental parameters currently, comprising:
acquiring a plurality of historical environment parameter sets of the growth environment in a preset historical time range, and acquiring a historical temperature parameter set, a historical humidity parameter set and a historical illumination parameter set;
performing error compensation on the historical temperature parameters, the historical humidity parameters and the historical illumination parameters in the historical temperature parameter set, the historical humidity parameter set and the historical illumination parameter set according to a preset proportion to obtain a plurality of historical temperature parameter ranges, a plurality of historical illumination parameter ranges and a plurality of historical humidity parameter ranges;
and randomly generating temperature parameters, humidity parameters and illumination parameters in the historical temperature parameter ranges, the historical illumination parameter ranges and the historical humidity parameter ranges respectively, and combining to obtain a plurality of environment parameter sets to obtain the adjustment feasible region.
3. The method of claim 1, wherein the fitness function is constructed based on the cost of adjusting the environmental parameters in the growing environment and the adjusted growth of the greenhouse crop, as follows:
wherein Y is fitness, W K 、W S And W is C Is given by weight, K A To adjust the cost of the post-environmental parameter set, K B For the currentThe cost of the set of environmental parameters,to adjust the size score of the jth greenhouse crop in the growing environment after the environmental parameter set, T is the detected number of greenhouse crops, S B Average size score of greenhouse crops in said growing environment under said current set of environmental parameters, +.>To adjust the color score of the jth greenhouse crop in the growing environment after the environmental parameter set, C B The average color score, color score and size score of the greenhouse crops in the growing environment under the current environmental parameter set are obtained through image processing identification.
4. A method according to claim 3, wherein setting constraints according to the current set of environmental parameters, and performing environmental parameter optimization in the regulatory feasible region based on the fitness function and constraints, comprises:
setting the fitness larger than 0 as a constraint condition, and discarding if the environment parameter set does not meet the constraint condition in the optimizing process;
randomly selecting an environment parameter set in the adjustable feasible domain as a first environment parameter set and temporarily serving as an optimal solution;
acquiring a first fitness of the first environment parameter set according to the fitness function;
randomly selecting an environment parameter set in the adjustable feasible domain again to serve as a second environment parameter set, and obtaining second fitness according to the fitness function;
judging whether the second fitness is larger than the first fitness, if so, replacing the second environment parameter set with the second environment parameter set as an optimal solution, if not, randomly generating random numbers in 0,1, judging whether the random numbers are smaller than a probability value, if so, taking the second environment parameter set as the optimal solution, and if not, taking the first environment parameter set as the optimal solution, wherein the probability value is reduced along with the increase of iteration times;
continuing to perform iterative optimization until the first optimizing iteration times are reached, and adding the new environment parameter set into the tabu table when the adaptability of the new environment parameter set obtained by iteration is smaller than or equal to the adaptability of the optimal solution;
and continuing to perform iterative optimization until the second optimizing iteration times are reached, and outputting a final optimal solution to obtain the optimal environment parameter set.
5. The method of claim 4, wherein obtaining a first fitness of the first set of environmental parameters according to the fitness function comprises;
acquiring T crop images of T greenhouse crops in the growth environment under the first environment parameter set;
constructing a growth condition analysis model based on greenhouse crop growth monitoring data in historical time in a plurality of growth environments, wherein the growth condition analysis model comprises a size analysis unit and a color analysis unit;
respectively inputting the T crop images into the growth condition analysis model to obtain T size scores and T color scores;
acquiring greenhouse environment cost under the first environment parameter set;
inputting the T size scores, the T color scores and the greenhouse environment cost into the fitness function to obtain the first fitness.
6. The method of claim 5, wherein constructing a growth analysis model based on greenhouse crop growth monitoring data over a historical time in a plurality of growth environments comprises:
acquiring a historical crop image set, a historical size scoring set and a historical color scoring set based on greenhouse crop growth monitoring data in historical time in a plurality of growth environments;
constructing the size analysis unit and the color analysis unit based on a convolutional neural network;
performing supervision training, verification and testing on the size analysis unit by adopting the historical crop image set and the historical size grading set, updating network parameters until a first convergence condition is reached, and obtaining the size analysis unit;
and performing supervision training, verification and testing on the color analysis unit by adopting the historical crop image set and the historical color grading set, updating network parameters until reaching a second convergence condition, obtaining the color analysis unit, and obtaining the growth condition analysis model.
7. The method of claim 4, wherein the probability value is calculated by:
wherein Y is 2 For a second fitness, Y 1 For the first fitness, N is a constant that decreases as the number of iterations increases.
8. An intelligent greenhouse crop growth environment regulation system, the system comprising:
the environment parameter set acquisition module is used for acquiring current temperature parameters, humidity parameters and illumination parameters in the growing environment of greenhouse crops and taking the current temperature parameters, humidity parameters and illumination parameters as a current environment parameter set;
the adjustable feasible region acquisition module is used for acquiring an adjustable feasible region for adjusting the environmental parameters currently according to the environmental parameter set of the growth environment in the preset historical time range;
the fitness function construction module is used for constructing a fitness function according to the cost of adjusting the environmental parameters in the growing environment and the growing condition of the greenhouse crops after the environmental parameters are adjusted, wherein the growing condition of the greenhouse crops is acquired based on image processing identification;
the environment parameter optimizing module is used for setting constraint conditions according to the current environment parameter set, and optimizing the environment parameters in the adjustable range based on the fitness function and the constraint conditions to obtain an optimal environment parameter set;
and the environment parameter adjusting module is used for adjusting the environment parameters in the growth environment by adopting the optimal environment parameter set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310528210.7A CN116830943A (en) | 2023-05-11 | 2023-05-11 | Intelligent greenhouse crop growth environment adjusting method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310528210.7A CN116830943A (en) | 2023-05-11 | 2023-05-11 | Intelligent greenhouse crop growth environment adjusting method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116830943A true CN116830943A (en) | 2023-10-03 |
Family
ID=88162382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310528210.7A Pending CN116830943A (en) | 2023-05-11 | 2023-05-11 | Intelligent greenhouse crop growth environment adjusting method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116830943A (en) |
-
2023
- 2023-05-11 CN CN202310528210.7A patent/CN116830943A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110685868A (en) | Wind turbine generator fault detection method and device based on improved gradient elevator | |
| CN104914720B (en) | Electronic nose intelligence baking control system and control method with autolearn feature | |
| CN112987666B (en) | Power plant unit operation optimization regulation and control method and system | |
| CN111654874A (en) | Wireless sensor network anomaly detection method | |
| CN107219759B (en) | Greenhouse environment control method and device | |
| CN106408132A (en) | Method and device of crop yield prediction based on plantation device | |
| US20210256428A1 (en) | Controller for controlling a technical system, and method for configuring the controller | |
| CN116545954B (en) | Communication gateway data transmission method and system based on internet of things | |
| CN112527037B (en) | Greenhouse environment regulation and control method and system with environment factor prediction function | |
| CN110119169A (en) | A kind of tomato greenhouse temperature intelligent early warning system based on minimum vector machine | |
| CN115529987B (en) | Air port regulating and controlling method, device, equipment and storage medium for crop facility | |
| CN111553806B (en) | Self-adaptive crop management system and method based on low-power-consumption sensor and Boost model | |
| CN110119767A (en) | A kind of cucumber green house temperature intelligent detection device based on LVQ neural network | |
| CN106296434A (en) | A kind of Grain Crop Yield Prediction method based on PSO LSSVM algorithm | |
| CN114372408A (en) | Short-term power load prediction method and device based on chaotic sparrow search algorithm | |
| CN110097473A (en) | A kind of collecting method, device and the equipment in crops life complete period | |
| CN113221447A (en) | Soil humidity prediction method for optimizing BP neural network based on improved genetic algorithm | |
| CN116830943A (en) | Intelligent greenhouse crop growth environment adjusting method and system | |
| CN116757354A (en) | Tobacco redrying section key parameter screening method based on multilayer perceptron | |
| CN113344243B (en) | Wind speed prediction method and system for optimizing ELM (ELM) based on improved Harris eagle algorithm | |
| CN114637351A (en) | Greenhouse environment regulation and control method and system for facility crops | |
| CN117469774B (en) | Air conditioning system regulation and control method and device, electronic equipment and storage medium | |
| CN109491345A (en) | A kind of research method based on quality control of key procedures | |
| CN113552806B (en) | Breeding house environment parameter analysis method based on fuzzy control algorithm | |
| CN117313555B (en) | GRU humidity prediction method based on self-adaptive OATS-AJSA |
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 |