CN110083190B - Green pepper greenhouse environment intelligent monitoring system based on subtraction clustering classifier - Google Patents

Green pepper greenhouse environment intelligent monitoring system based on subtraction clustering classifier Download PDF

Info

Publication number
CN110083190B
CN110083190B CN201910320161.1A CN201910320161A CN110083190B CN 110083190 B CN110083190 B CN 110083190B CN 201910320161 A CN201910320161 A CN 201910320161A CN 110083190 B CN110083190 B CN 110083190B
Authority
CN
China
Prior art keywords
green pepper
greenhouse
yield
neural network
prediction
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.)
Active
Application number
CN201910320161.1A
Other languages
Chinese (zh)
Other versions
CN110083190A (en
Inventor
马从国
姜仲秋
汪超
梁欢
丁晓红
马海波
周恒瑞
王建国
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
WEIHAI GEMHO DIGITAL MINE TECHNOLOGY CO.,LTD.
Original Assignee
Huaiyin Institute of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huaiyin Institute of Technology filed Critical Huaiyin Institute of Technology
Priority to CN201910320161.1A priority Critical patent/CN110083190B/en
Publication of CN110083190A publication Critical patent/CN110083190A/en
Application granted granted Critical
Publication of CN110083190B publication Critical patent/CN110083190B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/0285—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks and fuzzy logic
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/048—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators using a predictor
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
    • G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D27/00—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00
    • G05D27/02—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00 characterised by the use of electric means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/20—Pc systems
    • G05B2219/25—Pc structure of the system
    • G05B2219/25252—Microprocessor
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/20—Pc systems
    • G05B2219/26—Pc applications
    • G05B2219/2614—HVAC, heating, ventillation, climate control

Abstract

The invention discloses a green pepper greenhouse environment intelligent monitoring system based on a subtraction clustering classifier, which is characterized by comprising the following steps of: the intelligent monitoring system consists of a green pepper greenhouse environment parameter detection platform based on a wireless sensor network and an intelligent green pepper greenhouse yield early warning system; the invention provides an intelligent green pepper greenhouse environment monitoring system based on a subtractive clustering classifier, which effectively solves the problems that only green pepper greenhouse environment parameters can be obtained by monitoring the green pepper greenhouse environment parameters by equipment in the prior art, and the green pepper greenhouse yield cannot be pre-warned according to the green pepper greenhouse environment temperature and illumination.

Description

Green pepper greenhouse environment intelligent monitoring system based on subtraction clustering classifier
Technical Field
The invention relates to the technical field of agricultural greenhouse automation equipment, in particular to an intelligent green pepper greenhouse environment monitoring system based on a subtractive clustering classifier.
Background
The green pepper fruits are thick, crisp and tender in meat and rich in nutrition, can be cultivated in both the south and the north of China, and have an important position in vegetable production, the yield of the green pepper fruits is second to that of tomatoes in solanaceae vegetables, and the green pepper fruits are one of the favorite vegetables of the masses all the year round. The green pepper is strong in production seasonality, so that the contradiction between light and busy seasons supplied by the market is prominent, the rotting loss in the busy season is serious, the supply quantity in the light season is insufficient, and the requirements of people are difficult to meet. The green pepper is also called sweet pepper and vegetable pepper, is an annual herbaceous plant of the genus green pepper of the family solanaceae, and is native to the tropical region of central and south america. The green pepper cultivation in autumn and winter in the greenhouse can meet the market supply of the vegetables in the off season before the New year's day and the spring festival, the yield per mu is generally 120 plus 1800kg, and the yield per mu can reach 1.2 ten thousand yuan. The naturally discolored red peppers in the green peppers in the solar greenhouse have thick fruit pulp, tender texture, good taste, easy color matching and unique quality, and the retail price is higher than that of the same green peppers by more than 30 percent. Domestic experts research the relationship between green pepper growth and illuminance in a dispute, research the change of the external form and the physiological index of green peppers under weak light such as heavy waves and the like, research the influence of illumination intensity on the photosynthetic property and the growth and development of the green peppers such as Chenyinhua and the like, research the influence of different sun-shading treatments of a sunlight greenhouse on the color and the yield of the green peppers by using a Yangyi greenhouse system, test the illumination intensity and the illumination time of different sun-shading treatments by using a sunlight greenhouse intelligent system, and perform related analysis on the color change time, the quantity, the yield and the selling price of the green peppers, and research results show that the color change of the green peppers is closely related to the illumination intensity and the illumination time, when fruits develop to enter a color change stage, the comprehensive characters of the sun-shading treatment outside a black sun-shading net is the best, the economic benefit is 27.. The green pepper greenhouse intelligent control is a high and new agricultural technology, has the advantages of energy conservation, labor saving, environmental friendliness and the like, can improve the yield of red green peppers in the greenhouse without additionally adding chemical input products, and obviously improves the economic benefit. Through setting up different illumination and handling, become red optimum illumination intensity and illumination time through adjusting greenhouse green pepper to through sunlight greenhouse intelligent control sunshade, light filling system, time, quantity, output, the selling price that greenhouse green pepper becomes red are showing differently, improve the output that greenhouse green pepper becomes red, satisfy market demand. The green pepper greenhouse sun-shading treatment can obviously improve the color change rate of green peppers in a sunlight greenhouse, but the yield is reduced in different degrees, the weight of a single fruit is also influenced to a certain extent, and the number of the fruits with more strict sun-shading is smaller, the yield is lower, but the weight of the single fruit is increased. The prediction of the green pepper yield is an important component of agricultural production and vegetable management and control, and has important significance for making regulation and control policies and providing auxiliary decisions by agricultural departments. The effective prediction of the regional per capita vegetable occupation and the single green pepper yield can provide scientific reference for government to make and implement agricultural economic policies, optimal allocation of agricultural economic resources, reasonable adjustment of agricultural structures and the like, and is beneficial to the healthy development of agricultural economy.
Disclosure of Invention
The invention provides an intelligent green pepper greenhouse environment monitoring system based on a subtractive clustering classifier, which effectively solves the problem that in the prior art, only green pepper greenhouse environment parameters can be obtained by monitoring the green pepper greenhouse environment parameters only by equipment, but the green pepper greenhouse yield cannot be pre-warned according to the green pepper greenhouse environment temperature and illumination.
The invention is realized by the following technical scheme:
an intelligent green pepper greenhouse environment monitoring system is composed of a green pepper greenhouse environment parameter detection platform based on a wireless sensor network and an intelligent green pepper greenhouse yield early warning system, wherein the green pepper greenhouse environment parameter detection platform based on the wireless sensor network is used for detecting, adjusting and monitoring green pepper greenhouse environment factor parameters; the green pepper greenhouse yield intelligent early warning system comprises a greenhouse green pepper yield prediction subsystem, a green pepper greenhouse temperature prediction subsystem, a green pepper greenhouse illumination prediction subsystem, a greenhouse green pepper yield environmental parameter correction model and a least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier, and early warning is carried out on the yield of a green pepper greenhouse according to the historical yield of the green pepper greenhouse and the influence of the temperature and illumination of the green pepper greenhouse on the green pepper greenhouse yield.
The invention further adopts the technical improvement scheme that:
the green pepper greenhouse environment parameter detection platform based on the wireless sensor network is composed of detection nodes, control nodes and a field monitoring terminal, and the green pepper greenhouse environment parameter detection platform is constructed in a self-organizing manner through a wireless communication module NRF 2401. The detection nodes are respectively composed of a sensor group module, a single chip microcomputer and a wireless communication module NRF2401, the sensor group module is responsible for detecting the microclimate environment parameters of the green pepper greenhouse such as temperature, humidity, wind speed and illuminance, the sampling intervals are controlled by the single chip microcomputer and are sent to the field monitoring end through the wireless communication module NRF 2401; the control node controls the adjusting equipment of the green pepper greenhouse environment parameters; the field monitoring end is composed of an industrial control computer, the green pepper greenhouse environment parameter detection of the detection nodes is managed, intelligent early warning is carried out on green pepper greenhouse yield, and a green pepper greenhouse environment parameter detection platform based on a wireless sensor network is shown in figure 1.
The invention further adopts the technical improvement scheme that:
the green pepper greenhouse yield intelligent early warning system comprises a greenhouse green pepper yield prediction subsystem, a green pepper greenhouse temperature prediction subsystem, a green pepper greenhouse illumination prediction subsystem, a greenhouse green pepper yield environmental parameter correction model and a least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier; the structure of the green pepper greenhouse yield intelligent early warning system is shown in figure 2.
The invention further adopts the technical improvement scheme that:
the greenhouse green pepper yield prediction subsystem comprises a greenhouse green pepper yield Empirical Mode (EMD) decomposition model, a plurality of least square support vector machine (LS-SVM) yield prediction models and a plurality of LS-SVM yield prediction model values which are subjected to equal weight addition to obtain a green pepper yield prediction value; the greenhouse green pepper yield historical data are used as input of an Empirical Mode Decomposition (EMD) model for greenhouse green pepper yield, the EMD model for greenhouse green pepper yield decomposes the greenhouse green pepper yield historical data into a low-frequency trend part and a plurality of high-frequency fluctuation parts, the low-frequency trend part and the high-frequency fluctuation parts of the greenhouse green pepper yield historical data are respectively used as input of a plurality of least square support vector machines (LS-SVM) yield prediction models, the plurality of LS-SVM yield prediction models respectively predict components of the low-frequency trend part and the high-frequency fluctuation parts of the greenhouse green pepper yield historical data, and the values of the least square support vector machines (LS-SVM) yield prediction models are subjected to equal weight addition to obtain a greenhouse green pepper yield prediction value.
The invention further adopts the technical improvement scheme that:
the green pepper greenhouse temperature prediction subsystem comprises a green pepper greenhouse temperature subtraction cluster classifier, a plurality of HRFNN recurrent neural network temperature prediction models and an ANFIS neural network temperature prediction fusion model; the method comprises the steps that a plurality of detection point temperature values of a green pepper greenhouse are used as input of a green pepper greenhouse temperature subtraction cluster classifier, the green pepper greenhouse temperature subtraction cluster classifier divides the plurality of detection point temperature values of the green pepper greenhouse into a plurality of types, each type of green pepper greenhouse temperature value is respectively used as input of a plurality of HRFNN recurrent neural network temperature prediction models, the plurality of HRFNN recurrent neural network temperature prediction models respectively predict the plurality of types of green pepper greenhouse temperature values, the predicted values of the plurality of HRFNN recurrent neural network temperature prediction models are used as input of an ANFIS neural network temperature prediction fusion model, and the ANFIS neural network temperature prediction fusion model realizes fusion of the predicted values of the plurality of HRN recurrent neural network temperature prediction models to obtain a green pepper greenhouse temperature predicted value.
The invention further adopts the technical improvement scheme that:
the green pepper greenhouse illumination prediction subsystem comprises a green pepper greenhouse illumination subtraction cluster classifier, a plurality of ANFIS neural network illumination prediction models and an HRFNN recurrent neural network illumination prediction fusion model; the green pepper greenhouse illumination prediction method comprises the steps that a plurality of detection point illumination values of a green pepper greenhouse are used as input of a green pepper greenhouse illumination subtraction cluster classifier, the green pepper greenhouse illumination subtraction cluster classifier divides the plurality of detection point illumination values of the green pepper greenhouse into a plurality of types, each type of green pepper greenhouse illumination value is respectively used as input of a plurality of ANFIS neural network illumination prediction models, the plurality of ANFIS neural network illumination prediction models respectively predict the illumination values of the plurality of types of green pepper greenhouses, the prediction values of the plurality of ANFIS neural network illumination prediction models are used as input of an HRFNN recurrent neural network illumination prediction fusion model, and the HRFNN recurrent neural network illumination prediction fusion model realizes fusion of the prediction values of the plurality of ANFIS neural network illumination prediction models to obtain a green pepper greenhouse illumination prediction value.
The invention further adopts the technical improvement scheme that:
the greenhouse green pepper yield environment parameter correction model consists of 4 differential operators S and a GRNN neural network, wherein the 4 differential operators S are averagely divided into 2 groups, and each group of 2 differential operators S is connected in series to respectively form a differential loop 1 and a differential loop 2; the output of the green pepper yield prediction subsystem of the greenhouse is used as the input of an A end of a GRNN neural network, the output of the green pepper greenhouse temperature prediction subsystem is used as the input of a differential circuit 1 and the input of a B end of the GRNN neural network, the output of the connecting ends of 2 differential operators S of the differential circuit 1 is the input of a D end of the GRNN neural network, and the output of the differential circuit 1 is the input of a C end of the GRNN neural network; the output of the green pepper greenhouse illumination prediction subsystem is used as the input of a differential circuit 2 and the input of an E end of a GRNN neural network, the output of a connecting end of 2 differential operators S of the differential circuit 2 is the input of an I end of the GRNN neural network, and the output of the differential circuit 2 is the input of an F end of the GRNN neural network; the GRNN neural network is composed of 7 input end nodes of A, B, C, D, E, F and I, 13 intermediate nodes and 1 output end node, the greenhouse green pepper yield environment parameter correction model realizes correction of the influence degree of greenhouse temperature and illuminance on green pepper yield, reflects the influence of actual value changes of the greenhouse temperature and illuminance on the greenhouse green pepper yield, and improves the accuracy of greenhouse green pepper yield prediction.
The invention further adopts the technical improvement scheme that:
the least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier outputs the size of a greenhouse green pepper yield predicted value, green pepper type and green pepper greenhouse area according to a greenhouse green pepper yield environment parameter correction model as the input of the least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier, and the output of the least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier divides the greenhouse green pepper yield into five greenhouse green pepper yield grades, namely greenhouse green pepper high yield, greenhouse green pepper relatively high yield, greenhouse green pepper medium yield, greenhouse green pepper low yield and greenhouse green pepper very low yield.
Compared with the prior art, the invention has the following obvious advantages:
firstly, decomposing an original greenhouse green pepper yield historical data sequence into components of different frequency bands through an Empirical Mode Decomposition (EMD), wherein each component displays different characteristic information hidden in the original sequence. To reduce the non-stationarity of the sequence. The data relevance of the high-frequency part is not strong, the frequency is higher, the fluctuation component of the original sequence is represented, and the periodicity and the randomness are certain, and the periodicity is consistent with the periodicity change of the green pepper yield of the greenhouse; the low frequency component represents the variation trend of the original sequence. Therefore, the EMD can gradually decompose fluctuation components, period components and trend components of the green pepper yield of the greenhouse, each decomposed component contains the same deformation information, mutual interference among different characteristic information is reduced to a certain extent, and the decomposed component change curve is smoother than the original green pepper yield deformation sequence curve. Therefore, EMD can effectively analyze greenhouse green pepper yield deformation data under the multi-factor combined action, and each component obtained through decomposition is beneficial to better prediction of a plurality of least square support vector machine (LS-SVM) yield prediction models. And respectively establishing an ANFIS network prediction model for each component, reconstructing a phase space for each component in order to avoid problems of randomness of selection of input dimension of the extreme learning machine, loss of component information and the like, and finally overlapping the equal weight of prediction results of each component to obtain a final fusion prediction result. Example researches show that the provided fusion prediction result has higher prediction precision.
According to the characteristics of green pepper greenhouse temperature and illuminance difference, a green pepper greenhouse temperature and illuminance subtraction cluster classifier is constructed to classify the temperature and illuminance sample parameters of a plurality of detection points of a green pepper greenhouse, a plurality of HRFNN recurrent neural network temperature prediction models and ANFIS neural network temperature prediction fusion models related to temperature are designed, and a plurality of ANFIS neural network illuminance prediction models and HRFNN recurrent neural network illuminance prediction fusion models related to illumination are designed; the method respectively predicts the temperature and illuminance sample parameters of a plurality of detection points of the green pepper greenhouse, extracts relatively homogeneous data with similar causes from massive data, and respectively establishes a prediction model which has stronger pertinence and can reflect the green pepper greenhouse temperature and illuminance at any time stage, thereby improving the accuracy of temperature and illuminance prediction.
The HRFNN recurrent neural network structure leads a static network to have dynamic characteristics by introducing internal variables into a fuzzy rule layer; the activation degree of each rule of the network at the K moment not only comprises the activation degree value calculated by current input, but also comprises the contribution of all rule activation degree values at the previous moment, so that the accuracy of network identification is improved, and the dynamic identification of the green pepper greenhouse temperature and illumination can be better completed. The HRFNN recurrent neural network is a typical dynamic recurrent neural network, the feedback connection of the HRFNN recurrent neural network is composed of a group of 'structure' units and used for memorizing the past state of a hidden layer, and the HRFNN recurrent neural network and the network input are used as the input of the hidden layer unit at the next moment.
The greenhouse green pepper yield environment parameter correction model consists of 4 differential operators S and a GRNN neural network, wherein the 4 differential operators S are averagely divided into 2 groups, and each group of 2 differential operators S is connected in series to respectively form a differential loop 1 and a differential loop 2; the temperature, the temperature primary change rate and the temperature secondary change rate which affect the green pepper greenhouse yield are respectively formed by connecting 2 differential operators S in series to form a differential loop 1, the illuminance change primary change rate and the illuminance secondary change rate which affect the green pepper greenhouse yield are respectively formed by connecting 2 differential operators S in series to form a differential loop 2, and the illuminance, the illuminance change primary change rate and the illuminance secondary change rate which affect the green pepper greenhouse yield are introduced into GRNN neural network training to form a new input vector.
And fifthly, the GRNN adopted in the greenhouse green pepper yield environment parameter correction model has stronger nonlinear mapping capability, flexible network structure and high fault tolerance and robustness, and is suitable for greenhouse green pepper yield environment parameter correction. The GRNN has stronger advantages in approximation capability and learning speed than the RBF network, the network finally converges on an optimized regression surface with more sample size accumulation, and when the sample data is less, the network can also process unstable data, and the prediction effect is better. The GRNN network model has the advantages of strong generalization capability, high prediction precision and stable algorithm, has high convergence speed, few adjustment parameters, difficulty in falling into local minimum values and the like, is high in prediction network operation speed, and has a good application prospect in greenhouse green pepper yield environment parameter correction.
Sixthly, the least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier outputs the size of a greenhouse green pepper yield predicted value, the green pepper type and the green pepper greenhouse area as the input of the least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier according to the greenhouse green pepper yield environment parameter correction model, the output of the least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier divides the greenhouse green pepper yield into five greenhouse green pepper yield grades of high greenhouse green pepper yield, medium greenhouse green pepper yield, low greenhouse green pepper yield and very low greenhouse green pepper yield, and the scientificity and reliability of greenhouse green pepper yield early warning are improved.
Drawings
FIG. 1 is a green pepper greenhouse environment parameter detection platform based on a wireless sensor network according to the invention;
FIG. 2 is an intelligent early warning system for green pepper greenhouse yield according to the present invention;
FIG. 3 is a functional diagram of a detection node according to the present invention;
FIG. 4 is a functional diagram of a control node according to the present invention;
FIG. 5 is a functional diagram of the site monitoring software of the present invention;
FIG. 6 is a plan layout view of an intelligent detection platform for green pepper greenhouse environmental parameters.
Detailed Description
The technical scheme of the invention is further described by combining the attached drawings 1-6:
1. design of overall system function
The invention discloses an intelligent greenhouse environment monitoring system, which can detect green pepper greenhouse environment factor parameters and early warn green pepper greenhouse yield according to the influence of environment factors on green pepper greenhouse yield. The green pepper greenhouse environment parameter detection platform based on the wireless sensor network comprises a detection node 1 for green pepper greenhouse environment parameters and a control node 2 for adjusting the green pepper greenhouse environment parameters, wherein the detection node 1, the control node 2 and a field monitoring terminal 3 are in wireless communication by respectively adopting NRF2401 and MSP430 series microprocessors; the detection node 1 and the control node 2 are installed in a monitored green pepper greenhouse environment area to form a network in a self-organizing mode, and finally, information interaction is carried out with the on-site monitoring terminal 3. The detection node 1 sends the detected green pepper greenhouse environment parameters to the field monitoring terminal 3 and performs primary processing on the sensor data; the field monitoring terminal 3 transmits control information to the detection node 1 and the control node 2. The whole system structure is shown in figure 1.
2. Design of detection node
A large number of detection nodes 1 based on a wireless sensor network are adopted as green pepper greenhouse environment parameter sensing terminals, and the mutual information interaction between the field monitoring terminals 3 is realized through the detection nodes 1 and the control nodes 2 through a self-organizing wireless network. The detection node 1 comprises a sensor for collecting the green pepper greenhouse environment temperature, humidity, wind speed and illuminance parameters, a corresponding signal conditioning circuit, an MSP430 microprocessor and an NRF2401 wireless transmission module; the software of the detection node mainly realizes wireless communication and acquisition and pretreatment of green pepper greenhouse environment parameters. The software is designed by adopting a C language program, so that the compatibility degree is high, the working efficiency of software design and development is greatly improved, and the reliability, readability and transportability of program codes are enhanced. The structure of the detection node is shown in fig. 3.
3. Design of control node
The control node 2 is provided with 4D/A conversion circuits on an output path to realize the output quantity regulation of temperature, humidity, wind speed and illuminance, a relay control circuit, an MSP430 microprocessor and a wireless communication module interface, and realizes the control of green pepper greenhouse environment control equipment, and the control node is shown in figure 4.
4. Software design of field monitoring terminal
The field monitoring terminal 3 is an industrial control computer, the field monitoring terminal 3 mainly acquires green pepper greenhouse environment parameters and gives an early warning for green pepper greenhouse yield, and information interaction with the detection node 1 and the control node 2 is realized, the field monitoring terminal 3 mainly has the functions of communication parameter setting, data analysis and data management and a green pepper greenhouse yield intelligent early warning system, and the green pepper greenhouse yield intelligent early warning system comprises a greenhouse green pepper yield prediction subsystem, a green pepper greenhouse temperature prediction subsystem, a green pepper greenhouse illumination prediction subsystem, a greenhouse green pepper yield environment parameter correction model and a least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier; the management software selects Microsoft Visual + +6.0 as a development tool, calls the Mscomm communication control of the system to design a communication program, and the functions of the field monitoring end software are shown in figure 5.
(1) Green pepper yield prediction subsystem design for greenhouse
The greenhouse green pepper yield prediction subsystem comprises a greenhouse green pepper yield Empirical Mode (EMD) decomposition model, a plurality of least square support vector machine (LS-SVM) yield prediction models and a plurality of LS-SVM yield prediction model values which are subjected to equal weight addition to obtain a green pepper yield prediction value;
A. empirical Mode Decomposition (EMD) model for green pepper yield in greenhouse
Empirical Mode Decomposition (EMD) of green pepper yield in greenhouse is a self-adaptive signal screening method, and has the characteristics of simple and intuitive calculation and based on experience and self-adaptation. The method can screen trends with different characteristics existing in the yield information of the green pepper historical data step by step to obtain a plurality of high-frequency fluctuation parts (IMF) and low-frequency trend parts. The IMF component decomposed by the empirical mode decomposition of the green pepper yield in the greenhouse comprises components of different frequency sections of information from high to low, and the frequency resolution contained in each frequency section is changed along with the information, so that the green pepper yield analysis method has the characteristic of self-adaptive multi-resolution analysis. The purpose of empirical mode decomposition of greenhouse green pepper yield is to extract the historical data information of greenhouse green pepper yield more accurately. The empirical mode decomposition method for greenhouse green pepper yield aims at the steps of the screening process of historical greenhouse green pepper yield data, and comprises the following steps:
firstly, determining all local extreme points of greenhouse green pepper yield historical data information, and then connecting left and right local extreme points by using three sample lines to form an upper envelope line.
Secondly, local minimum value points of greenhouse green pepper yield historical data information of the three spline lines are connected to form a lower envelope line, and the upper envelope line and the lower envelope line should envelop all data points.
③, the average of the upper and lower envelope is m1(t), obtaining:
x(t)-m1(t)＝h1(t) (1)
x (t) is the original signal of the historical data information of green pepper yield in the greenhouse, if h1(t) is an IMF, then h1(t) is the first IMF component of x (t). Note c1(t)＝h1k(t), then c1(t) is the first component of signal x (t) that satisfies the IMF condition.
④, mixing c1(t) separating from x (t) to obtain:
r1(t)＝x(t)-c1(t) (2)
will r is1(t) repeating the steps (1) to (3) as the original data to obtain the 2 nd component c satisfying the IMF condition of x (t)2. The cycle is repeated n times to obtain n components of the signal x (t) satisfying the IMF condition. Therefore, the empirical mode decomposition model for the green pepper yield of the greenhouse decomposes the historical data information of the green pepper yield of the greenhouse into a low-frequency trend part and a plurality of high-frequency fluctuation parts.
B. Multi-least squares support vector machine (LS-SVM) yield prediction model
The yield prediction model of a plurality of least squares support vector machines (LS-SVM) has stronger generalization capability and global capability, overcomes the defects of poor generalization capability, overfitting, easy falling into local optimum and the like of other machine learning methods, and is an extension to a standard support vector machineThe model adopts a sum of squares error loss function to replace an insensitive loss function of a standard support vector machine, and simultaneously realizes the conversion of inequality constraints in a standard SVM algorithm into equal constraints. Therefore, the least square support vector machine (LS-SVM) model simplifies the quadratic programming problem into solving a linear equation set, obviously reduces the complexity of solving and improves the calculation speed. Let green pepper yield historical data in greenhouse train sample set D { (x)i,yi)|i＝1,2,…,n}，xiAnd yiInput and output sample data, respectively, and n is the number of samples, which can map the input samples from the original space to the high-dimensional feature space. Introducing a Lagrange equation, converting the optimization problem with constraint conditions into the optimization problem without constraint conditions, and obtaining a linear regression equation of a least square support vector machine (LS-SVM) yield prediction model as follows:
Figure GDA0002570338140000101
in the solving process, in order to avoid solving a complex nonlinear mapping function, a Radial Basis Function (RBF) is introduced to replace dot product operation in a high-dimensional space, so that the calculated amount can be greatly reduced, and the RBF is easy to realize the optimization process of the SVM because the center of each basis function of the RBF corresponds to the support vector one by one, and the support vector and the weight can be obtained through an algorithm. Therefore, the least squares support vector machine (LS-SVM) model is:
Figure GDA0002570338140000102
the output of a least square support vector machine (LS-SVM) yield prediction model is a prediction value of greenhouse green pepper yield historical data in low-frequency and high-frequency states, each intermediate node corresponds to a support vector, x1,x2,…xnFor the low-frequency and high-frequency information of the greenhouse green pepper yield historical data after mode decomposition, αiIs the network weight.
(2) Green pepper greenhouse temperature prediction subsystem design
The green pepper greenhouse temperature prediction subsystem comprises a green pepper greenhouse temperature subtraction cluster classifier, a plurality of HRFNN recurrent neural network temperature prediction models and an ANFIS neural network temperature prediction fusion model.
A. Green pepper greenhouse temperature subtraction clustering classifier
Compared with other clustering methods, the green pepper greenhouse temperature subtractive clustering does not need to determine the clustering number in advance, the position and the clustering number of the green pepper greenhouse temperature clustering center can be quickly determined according to the green pepper greenhouse temperature sample data density, and each green pepper greenhouse temperature data point is used as the characteristic of a potential clustering center, so that the green pepper greenhouse temperature clustering result is independent of the dimension of the problem. Therefore, the green pepper greenhouse temperature subtraction clustering algorithm is a rule automatic extraction method suitable for modeling based on green pepper greenhouse temperature data. Setting N green pepper greenhouse temperature data points (X) in m-dimensional space1,X2,…XN) Each data point Xi＝(xi,1,xi,2,…,xi,m) Are all candidates for cluster centers, i-1, 2, …, N, data point XiThe density function of (a) is defined as:
Figure GDA0002570338140000111
in the formula, the radius raIs a positive number, raAn influence neighborhood of the point is defined, and data points outside the radius contribute very little to the density index of the point and are generally ignored. Calculate each point XiSelecting the density value with the highest density index Dc1As the first cluster center Xc1(ii) a And then correcting the density value to eliminate the influence of the existing cluster center. The density value is corrected according to the following formula:
Figure GDA0002570338140000112
wherein D isc1Is the highest density value corresponding to the initial clustering center, and the corrected radius rbIs set to avoid second polyThe centroid is too close to the previous centroid and is generally set to rb＝ηraAnd 1.25 is not less than η is not more than 1.5 after the density index of each data point is corrected, when D isckAnd Dc1And when the following formula is satisfied, the clustering center corresponding to the density index is the Kth clustering center. This process is repeated until a new cluster center XckCorresponding density index DckAnd Dc1Terminating clustering when the following equation is satisfied:
Dck/Dc1＜ (7)
the expression is a threshold value set in advance according to actual conditions.
The basic idea of the online clustering method provided by the invention is that if the distance from a green pepper greenhouse temperature point to the center of a group is less than a clustering radius raThen the point belongs to this group and when new data is obtained, the group and the center of the group change accordingly. With the continuous increase of the input green pepper greenhouse temperature spatial data, the algorithm of the invention obtains better input space division by dynamically adjusting the green pepper greenhouse temperature clustering center and the clustering number in real time, and comprises the following steps:
step 1: green pepper greenhouse temperature data normalization processing, input data each dimension clustering radius raAnd setting parameters such as threshold values.
Step 2: c clustering centers are obtained by carrying out subtractive clustering on green pepper greenhouse temperature data sets and v is storedi(i ═ 1,2, …, c) and its corresponding density value D (v)i)。
And step 3: when the k-th data in the newly added online green pepper greenhouse temperature data set arrives, calculating xk(k-1, 2, …, M) to i cluster centers viDistance d ofki＝||xk-viIf d | |ki＞raGo to step 4; if d iski≤raGo to step 5.
And 4, step 4: calculating x from equation (6)kDensity value of D (x)k) And D (x)k) >. sup.x, green pepper greenhouse temperature datakIf the cluster does not belong to any existing cluster, a cluster is newly created, the number c of clusters in the space is input to c +1, and the process returnsAnd 3. step 3.
And 5: determining a data point x according to a minimum distance criterionkBelonging to the nearest cluster subset, and further comparing the new data xkThe density value of (2) and the density value of the cluster center, if D (x)k)＞D(vi) Then data xkCloser to its nearest cluster center, xkReplacing the original clustering center as a new clustering center of the subset; if D (x)k)≤D(vi) If so, keeping the clustering result unchanged, and judging whether the newly added data group is finished. If yes, go to step 6; otherwise, returning to the step 3.
Step 6: calculating a clustering center viAnd vjIf min | | vi-vj||≤(0.5-0.7)raAnd D (v)i)＞D(vj) Then, the cluster subset v is indicatediAnd vjCan be combined into a cluster with v as the centeri(ii) a Otherwise, keeping the clustering result unchanged.
The green pepper greenhouse temperature subtractive clustering realizes classification of green pepper greenhouse temperature historical data, and each green pepper greenhouse temperature is input into a corresponding HRFNN recurrent neural network prediction model to predict a future greenhouse temperature value.
B. Multiple HRFNN recurrent neural network temperature prediction model
The input of the HRFNN recurrent neural network temperature prediction models is historical data of greenhouse temperatures of various green peppers, and the output of the input of the HRFNN recurrent neural network temperature prediction models is a predicted value of the greenhouse temperatures of various green peppers. The HRFNN recurrent neural network prediction model is a multi-input single-output network topological structure, and a network consists of 4 layers: an input layer, a membership function layer, a rule layer, and an output layer. The network comprises n input nodes, wherein each input node corresponds to m condition nodes, m represents a rule number, nm rule nodes and 1 output node. Layer I introduces the input into the network; the second layer fuzzifies the input, and the adopted membership function is a Gaussian function; the third layer corresponds to fuzzy reasoning; layer iv corresponds to the defuzzification operation. By using
Figure GDA0002570338140000131
Representing the input and output of the ith node of the kth layer, respectively, the signal transfer process inside the network and the input-output relationship between the layers can be described as follows. Layer I: an input layer, each input node of the layer being directly connected to an input variable, the input and output of the network being represented as:
Figure GDA0002570338140000132
in the formula
Figure GDA0002570338140000133
And
Figure GDA0002570338140000134
for the input and output of the ith node of the network input layer, N represents the number of iterations. Layer II: the membership function layer, the nodes of the layer fuzzify the input variables, each node represents a membership function, a Gaussian function is adopted as the membership function, and the input and output of the network are expressed as:
Figure GDA0002570338140000135
in the formula mijAnd σijRespectively representing the mean center and width value of the j term Gaussian function of the ith linguistic variable of the II layer, wherein m is the number of all linguistic variables corresponding to the input node. Layer III: the fuzzy inference layer, namely the rule layer, adds dynamic feedback to ensure that the network has better learning efficiency, and the feedback link introduces an internal variable hkAnd selecting a sigmoid function as an activation function of the internal variable of the feedback link. The inputs and outputs of the network are represented as:
Figure GDA0002570338140000141
in the formula of omegajkIs the connection weight of the recursion part, the neuron of the layer represents the front part of the fuzzy logic rule, the node of the layer is corresponding to the second partThe output of the layer and the feedback of the third layer perform Π's operation,
Figure GDA0002570338140000142
is the output of the third layer, and m represents the number of rules in a full connection. The feedback link mainly calculates the value of the internal variable and the activation strength of the corresponding membership function of the internal variable. The activation strength is related to the rule node matching degree of the layer 3. The internal variables introduced by the feedback link comprise two types of nodes: and the receiving node and the feedback node. The carrying node calculates an internal variable by using weighted summation to realize the defuzzification function; the result of fuzzy inference of hidden rules represented by internal variables. And the feedback node adopts a sigmoid function as a fuzzy membership function to realize the fuzzification of the internal variable. A fourth layer: the deblurring layer, i.e., the output layer. The layer node performs a summation operation on the input quantities. The inputs and outputs of the network are represented as:
Figure GDA0002570338140000143
in the formula lambdajIs the connection weight of the output layer. The HRFNN recurrent neural network prediction model has the performance approaching a highly nonlinear dynamic system, the training error and the testing error of the recurrent neural network added with internal variables are respectively obviously reduced, and the HRFNN recurrent neural network temperature prediction model of the patent trains the weight of the neural network by adopting a gradient descent algorithm added with cross validation. The HRFNN recurrent neural network temperature prediction model introduces internal variables in a feedback link, performs weighted summation on output quantities of the rule layer, performs defuzzification output as feedback quantities, and uses the feedback quantities and the output quantities of the membership function layer as input of the rule layer at the next moment. The network output comprises the activation intensity of the rule layer and output historical information, the capability of the HRFNN recurrent neural network temperature prediction model for adapting to a nonlinear dynamic system is enhanced, and the HRFNN recurrent neural network temperature prediction model can accurately predict green pepper greenhouse temperature parameters.
C. ANFIS neural network temperature prediction fusion model
The ANFIS neural network temperature prediction fusion model is an Adaptive Fuzzy Inference System ANFIS based on a neural network, also called an Adaptive neural-Fuzzy Inference System (Adaptive neural-Fuzzy Inference System), and organically combines the neural network and the Adaptive Fuzzy Inference System, thereby not only playing the advantages of the neural network and the Adaptive Fuzzy Inference System, but also making up the respective defects. The fuzzy membership function and the fuzzy rule in the ANFIS neural network temperature prediction fusion model are obtained by learning known historical data of a large number of green pepper greenhouse temperatures, and the ANFIS neural network temperature prediction fusion model has the greatest characteristic of being based on a data modeling method instead of being based on experience or intuition and is given arbitrarily. The input of the ANFIS neural network temperature prediction fusion model is the predicted value of the greenhouse temperature of the multi-type green pepper, and the main operation steps of the ANFIS neural network temperature prediction fusion model are as follows:
and on the layer 1, fuzzifying the input predicted values of the greenhouse temperatures of the various green peppers, wherein the corresponding output of each node can be represented as:
Figure GDA0002570338140000151
the formula n is the number of each input membership function, and the membership function adopts a Gaussian membership function.
And 2, realizing rule operation, outputting the applicability of the rule, and multiplying the rule operation of the ANFIS neural network temperature prediction fusion model by adopting multiplication.
Figure GDA0002570338140000152
And 3, normalizing the applicability of each rule:
Figure GDA0002570338140000153
and 4, at the layer 4, the transfer function of each node is a linear function and represents a local linear model, and the output of each self-adaptive node i is as follows:
Figure GDA0002570338140000154
and 5, a single node of the layer is a fixed node, and the output of the ANFIS neural network model is calculated as follows:
Figure GDA0002570338140000161
the condition parameters determining the shape of the membership function and the conclusion parameters of the inference rule in the ANFIS neural network temperature prediction fusion model can be trained through a learning process. The parameters are adjusted by an algorithm combining a linear least square estimation algorithm and gradient descent. In each iteration of the ANFIS neural network temperature prediction fusion model, firstly, input signals are transmitted to the layer 4 along the network in the forward direction, and conclusion parameters are adjusted by adopting a least square estimation algorithm; the signal continues to propagate forward along the network to the output layer (i.e., layer 5). The ANFIS neural network temperature prediction fusion model reversely propagates the obtained error signals along the network, and the condition parameters are updated by a gradient method. By adjusting the given condition parameters in the ANFIS neural network temperature prediction fusion model in the mode, the global optimum point of the conclusion parameters can be obtained, so that the dimension of a search space in a gradient method can be reduced, and the convergence speed of the ANFIS neural network temperature prediction fusion model parameters can be increased. The ANFIS neural network temperature prediction fusion model is a multi-type green pepper greenhouse temperature prediction value, and the output of the ANFIS neural network temperature prediction fusion model is used as a fusion value of the multi-type green pepper greenhouse temperature prediction values.
(3) Green pepper greenhouse illumination prediction subsystem design
The green pepper greenhouse illumination prediction subsystem comprises a green pepper greenhouse illumination subtraction cluster classifier, a plurality of ANFIS neural network illumination prediction models and an HRFNN recurrent neural network illumination prediction fusion model.
A. Green pepper greenhouse illuminance subtraction clustering classifier
The illuminance values of a plurality of detection points of the green pepper greenhouse are used as the input of the green pepper greenhouse illuminance subtraction cluster classifier, the green pepper greenhouse illuminance subtraction cluster classifier divides the illuminance values of the plurality of detection points of the green pepper greenhouse into a plurality of types, and the design method of the green pepper greenhouse illuminance subtraction cluster classifier can refer to the design method of the green pepper greenhouse temperature subtraction cluster classifier.
B. Illuminance prediction model for multiple ANFIS neural networks
The light intensity value of each type of green pepper greenhouse is respectively used as the input of a plurality of ANFIS neural network light intensity prediction models, the plurality of ANFIS neural network light intensity prediction models respectively predict the light intensity values of the plurality of types of green pepper greenhouse, and the design method of the plurality of ANFIS neural network light intensity prediction models can refer to the design method of the ANFIS neural network temperature prediction fusion model.
C. HRFNN recurrent neural network illuminance prediction fusion model
The predicted values of the plurality of ANFIS neural network illuminance prediction models are used as the input of the HRFNN recurrent neural network illuminance prediction fusion model, the HRFNN recurrent neural network illuminance prediction fusion model realizes the fusion of the predicted values of the plurality of ANFIS neural network illuminance prediction models to obtain green pepper greenhouse illuminance predicted values, and the HRFNN recurrent neural network illuminance prediction fusion model design can refer to the method for designing the plurality of HRFNN recurrent neural network temperature prediction models.
(4) Design of green pepper yield environmental parameter correction model for greenhouse
The greenhouse green pepper yield environment parameter correction model consists of 4 differential operators S and a GRNN neural network, wherein the 4 differential operators S are averagely divided into 2 groups, and each group of 2 differential operators S is connected in series to respectively form a differential loop 1 and a differential loop 2; the output of the green pepper yield prediction subsystem of the greenhouse is used as the input of an A end of a GRNN neural network, the output of the green pepper greenhouse temperature prediction subsystem is used as the input of a differential circuit 1 and the input of a B end of the GRNN neural network, the output of the connecting ends of 2 differential operators S of the differential circuit 1 is the input of a D end of the GRNN neural network, and the output of the differential circuit 1 is the input of a C end of the GRNN neural network; the output of the green pepper greenhouse illumination prediction subsystem is used as the input of a differential circuit 2 and the input of an E end of a GRNN neural network, and the output of the connecting end of 2 differential operators S of the differential circuit 2 is an I end of the GRNN neural networkThe output of the differential loop 2 is the input of the F end of the GRNN neural network; the GRNN neural network consists of 7 input end nodes of A, B, C, D, E, F and I, 13 intermediate nodes and 1 output end node, a differential operator is called in MATLAB, the greenhouse green pepper yield environmental parameter correction model realizes correction of the influence degree of greenhouse temperature and illumination on green pepper yield, reflects the influence of actual change of greenhouse temperature and illumination on greenhouse green pepper yield, and improves the accuracy of greenhouse green pepper yield prediction; the GRNN Neural network is a local approximation network GRNN (generalized Regression Neural network), is established on the basis of mathematical statistics, has a clear theoretical basis, determines a network structure and a connection value after a learning sample is determined, and only needs to determine a smooth parameter and a variable in the training process. The learning of the GRNN neural network completely depends on data samples, has stronger advantages than the BRF network in approximation capability and learning speed, has strong nonlinear mapping and flexible network structure and high fault tolerance and robustness, and is particularly suitable for fast approximation of functions and processing unstable data. The artificial adjustment parameters of GRNN are few, and the learning of the network completely depends on data samples, so that the network can reduce the influence of artificial subjective assumption on the prediction result to the maximum extent. The GRNN neural network has strong prediction capability under a small sample, has the characteristics of high training speed, strong robustness and the like, and is basically not disturbed by multiple collinearity of input data. The GRNN neural network constructed by the method comprises an input layer, a mode layer, a summation layer and an output layer, wherein an input vector X of the GRNN network is an n-dimensional vector, and a network output vector Y is a k-dimensional vector X ═ X1,x2,…,xn}TAnd Y ═ Y1,y2,…,yk}T. The number of neurons in the mode layer is equal to the number m of training samples, each neuron corresponds to a training sample one by one, and the transfer function p of the neurons in the mode layeriComprises the following steps:
pi＝exp{-[(x-xi)T(x-xi)]/2σ},(i＝1,2,…,m) (17)
the neuron outputs in the above formula enter a summation layer for summation, and the summation layer functions are divided into two types, which are respectively:
Figure GDA0002570338140000181
Figure GDA0002570338140000182
wherein, yijThe jth element value in the vector is output for the ith training sample. According to the GRNN neural network prediction model algorithms, the estimated value of the jth element of the network output vector Y is:
yj＝sNj/sD,(j＝1,2,…k) (20)
the GRNN neural network model is established on the basis of mathematical statistics, and the output result of the network can be converged to an optimal regression surface. The GRNN has strong prediction capability and high learning speed, is mainly used for solving the problem of function approximation, has high parallelism in the aspect of structure, and realizes a greenhouse green pepper yield environment parameter correction model.
(5) Least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier
The least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier outputs the size of a greenhouse green pepper yield predicted value, green pepper type and green pepper greenhouse area according to a greenhouse green pepper yield environment parameter correction model as the input of the least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier, and the output of the least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier divides the greenhouse green pepper yield into five greenhouse green pepper yield grades, namely greenhouse green pepper high yield, greenhouse green pepper relatively high yield, greenhouse green pepper medium yield, greenhouse green pepper low yield and greenhouse green pepper very low yield. The method is characterized in that different types of green peppers are quantized into different numbers to serve as the input of a least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier, for example, the number of the capsicum frutescens is 1, the number of the capsicum frutescens is 2, the number of the capsicum frutescens is 3, the number of the capsicum frutescens is 4, and the like. The output of the least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier is a value between 0 and 1, the output is more than 0.8 and less than or equal to 1 for high greenhouse green pepper yield, more than 0.6 and less than or equal to 0.8 for relatively high greenhouse green pepper yield, more than 0.4 and less than or equal to 0.6 for medium greenhouse green pepper yield, more than 0.2 and less than or equal to 0.4 for low greenhouse green pepper yield, and less than or equal to 0.2 and more than or equal to 0 for very low greenhouse green pepper yield, and the design method of the least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier can refer to the design method of a plurality of LS-SVM yield prediction models of the LS-SVM.
5. Design example of green pepper greenhouse environment parameter intelligent detection platform
According to the situation of green pepper greenhouse environment, the system is provided with a plane arrangement installation diagram of a detection node 1, a control node 2 and a field monitoring terminal 3, wherein the detection node 1 is arranged in the detected green pepper greenhouse environment in a balanced manner, the whole system is arranged in a plane manner as shown in fig. 6, and the collection of green pepper greenhouse environment parameters and the intelligent early warning of green pepper greenhouse yield are realized through the system.
The technical means disclosed in the invention scheme are not limited to the technical means disclosed in the above embodiments, but also include the technical scheme formed by any combination of the above technical features. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and such improvements and modifications are also considered to be within the scope of the present invention.

Claims (5)

1. The utility model provides a green pepper greenhouse environment intelligent monitoring system based on subtraction cluster classifier which characterized in that: the intelligent monitoring system consists of a green pepper greenhouse environment parameter detection platform based on a wireless sensor network and an intelligent green pepper greenhouse yield early warning system; the green pepper greenhouse yield intelligent early warning system comprises a greenhouse green pepper yield prediction subsystem, a green pepper greenhouse temperature prediction subsystem, a green pepper greenhouse illumination prediction subsystem, a greenhouse green pepper yield environmental parameter correction model and a least square support vector machine greenhouse green pepper yield grade classifier, and early warning on the yield of a green pepper greenhouse is realized according to the historical yield of the green pepper greenhouse and the influence of the temperature and illumination of the green pepper greenhouse on the green pepper greenhouse yield;
the greenhouse green pepper yield prediction subsystem comprises a greenhouse green pepper yield Empirical Mode (EMD) decomposition model, a plurality of least square support vector machine (LS-SVM) yield prediction models and a plurality of LS-SVM yield prediction model values which are subjected to equal weight addition to obtain a green pepper yield prediction value; the greenhouse green pepper yield historical data are used as input of an Empirical Mode Decomposition (EMD) model for greenhouse green pepper yield, the EMD model for greenhouse green pepper yield decomposes the greenhouse green pepper yield historical data into a low-frequency trend part and a plurality of high-frequency fluctuation parts, the low-frequency trend part and the high-frequency fluctuation parts of the greenhouse green pepper yield historical data are respectively used as input of a plurality of least square support vector machine (LS-SVM) yield prediction models, the plurality of LS-SVM yield prediction models respectively predict components of the low-frequency trend part and the high-frequency fluctuation parts of the greenhouse green pepper yield historical data, and the values of the plurality of LS-SVM yield prediction models are subjected to equal weight addition to obtain a greenhouse green pepper yield prediction value;
the green pepper greenhouse temperature prediction subsystem comprises a green pepper greenhouse temperature subtraction cluster classifier, a plurality of HRFNN recurrent neural network temperature prediction models and an ANFIS neural network temperature prediction fusion model; the method comprises the following steps that a plurality of detection point temperature values of a green pepper greenhouse are used as input of a green pepper greenhouse temperature subtraction cluster classifier, the green pepper greenhouse temperature subtraction cluster classifier divides the plurality of detection point temperature values of the green pepper greenhouse into a plurality of types, each type of green pepper greenhouse temperature value is respectively used as input of a plurality of HRFNN recurrent neural network temperature prediction models, the plurality of HRFNN recurrent neural network temperature prediction models respectively predict the plurality of types of green pepper greenhouse temperature values, the predicted values of the plurality of HRFNN recurrent neural network temperature prediction models are used as input of an ANFIS neural network temperature prediction fusion model, and the ANFIS neural network temperature prediction fusion model realizes fusion of the predicted values of the plurality of HRN recurrent neural network temperature prediction models to obtain a green pepper greenhouse temperature predicted value;
the green pepper greenhouse illumination prediction subsystem comprises a green pepper greenhouse illumination subtraction cluster classifier, a plurality of ANFIS neural network illumination prediction models and an HRFNN recurrent neural network illumination prediction fusion model; the green pepper greenhouse illumination prediction method comprises the steps that a plurality of detection point illumination values of a green pepper greenhouse are used as input of a green pepper greenhouse illumination subtraction cluster classifier, the green pepper greenhouse illumination subtraction cluster classifier divides the plurality of detection point illumination values of the green pepper greenhouse into a plurality of types, each type of green pepper greenhouse illumination value is respectively used as input of a plurality of ANFIS neural network illumination prediction models, the plurality of ANFIS neural network illumination prediction models respectively predict the illumination values of the plurality of types of green pepper greenhouses, the prediction values of the plurality of ANFIS neural network illumination prediction models are used as input of an HRFNN recurrent neural network illumination prediction fusion model, and the HRFNN recurrent neural network illumination prediction fusion model realizes fusion of the prediction values of the plurality of ANFIS neural network illumination prediction models to obtain a green pepper greenhouse illumination prediction value;
the greenhouse green pepper yield environment parameter correction model consists of 4 differential operators S and a GRNN neural network, wherein the 4 differential operators S are averagely divided into 2 groups, and each group of 2 differential operators S is connected in series to respectively form a differential loop 1 and a differential loop 2; the output of the green pepper yield prediction subsystem of the greenhouse is used as the input of an A end of a GRNN neural network, the output of the green pepper greenhouse temperature prediction subsystem is used as the input of a differential circuit 1 and the input of a B end of the GRNN neural network, the output of the connecting ends of 2 differential operators S of the differential circuit 1 is the input of a D end of the GRNN neural network, and the output of the differential circuit 1 is the input of a C end of the GRNN neural network; the output of the green pepper greenhouse illumination prediction subsystem is used as the input of a differential circuit 2 and the input of an E end of a GRNN neural network, the output of a connecting end of 2 differential operators S of the differential circuit 2 is the input of an I end of the GRNN neural network, and the output of the differential circuit 2 is the input of an F end of the GRNN neural network; the GRNN neural network consists of 7 input end nodes of A, B, C, D, E, F and I, 13 intermediate nodes and 1 output end node, and the greenhouse green pepper yield environmental parameter correction model realizes correction of the influence degree of greenhouse temperature and illuminance on green pepper yield, reflects the influence of actual change of the greenhouse temperature and illuminance on the greenhouse green pepper yield, and improves the accuracy of greenhouse green pepper yield prediction;
the size of a greenhouse green pepper yield predicted value output by the greenhouse green pepper yield environment parameter correction model, the green pepper type and the green pepper greenhouse area serve as the input of a least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier, and the output of the least square support vector machine (LS-SVM) greenhouse green pepper yield grade classifier divides the greenhouse green pepper yield into five greenhouse green pepper yield grades, namely greenhouse green pepper high yield, greenhouse green pepper relatively high yield, greenhouse green pepper medium yield, greenhouse green pepper low yield and greenhouse green pepper very low yield.
2. The green pepper greenhouse environment intelligent monitoring system based on the subtractive clustering classifier according to claim 1, wherein: the green pepper greenhouse environment parameter detection platform based on the wireless sensor network realizes detection, adjustment and monitoring of green pepper greenhouse environment factor parameters, and comprises detection nodes, control nodes and a field monitoring terminal, wherein the detection nodes, the control nodes and the field monitoring terminal are constructed into an intelligent green pepper greenhouse environment parameter detection platform through a wireless communication module NRF2401 in a self-organizing manner.
3. The green pepper greenhouse environment intelligent monitoring system based on the subtractive cluster classifier according to claim 2, wherein: the detection nodes are respectively composed of a sensor group module, a single chip microcomputer and a wireless communication module NRF2401, the sensor group module is responsible for detecting the microclimate environment parameters of the green pepper greenhouse such as temperature, humidity, wind speed and illuminance, the sampling intervals are controlled by the single chip microcomputer, and the parameters are sent to the field monitoring end through the wireless communication module NRF 2401.
4. The green pepper greenhouse environment intelligent monitoring system based on the subtractive cluster classifier according to claim 2, wherein: the control node controls the adjusting equipment for the green pepper greenhouse environment parameters.
5. The green pepper greenhouse environment intelligent monitoring system based on the subtractive cluster classifier according to claim 2, wherein: the field monitoring end is composed of an industrial control computer, and realizes management of green pepper greenhouse environment parameters detected by the detection nodes and intelligent early warning of green pepper greenhouse yield.
CN201910320161.1A 2019-04-19 2019-04-19 Green pepper greenhouse environment intelligent monitoring system based on subtraction clustering classifier Active CN110083190B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910320161.1A CN110083190B (en) 2019-04-19 2019-04-19 Green pepper greenhouse environment intelligent monitoring system based on subtraction clustering classifier

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910320161.1A CN110083190B (en) 2019-04-19 2019-04-19 Green pepper greenhouse environment intelligent monitoring system based on subtraction clustering classifier

Publications (2)

Publication Number Publication Date
CN110083190A CN110083190A (en) 2019-08-02
CN110083190B true CN110083190B (en) 2020-08-25

Family

ID=67415873

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910320161.1A Active CN110083190B (en) 2019-04-19 2019-04-19 Green pepper greenhouse environment intelligent monitoring system based on subtraction clustering classifier

Country Status (1)

Country Link
CN (1) CN110083190B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110580021B (en) * 2019-09-10 2020-09-25 淮阴工学院 Granary environmental safety intelligent monitoring system based on field bus
CN110929753B (en) * 2019-10-18 2024-03-19 江苏大学 Green pepper identification method based on color image
CN111010390A (en) * 2019-12-12 2020-04-14 重庆工商大学 Self-adaptive calling method and system based on multi-protocol heterogeneous Internet of things
CN111523646B (en) * 2020-04-23 2023-06-23 国家开放大学 Intelligent perception network and management method for remote education learning center based on Internet of things
CN113219871B (en) * 2021-05-07 2022-04-01 淮阴工学院 Curing room environmental parameter detecting system

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101795090A (en) * 2009-01-19 2010-08-04 原子能委员会 Method of forecasting the electrical production of a photovoltaic device
WO2017136489A1 (en) * 2016-02-03 2017-08-10 Caspo, Llc Smart cooking system that produces and uses hydrogen fuel
CN108138555A (en) * 2015-02-23 2018-06-08 奈克森能量无限责任公司 Method, system and the equipment of predicting reservoir property

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101719231A (en) * 2008-10-09 2010-06-02 西南石油大学 Dynamic differential simulation forecasting method and data processing handheld device applying same
CN101480143B (en) * 2009-01-21 2010-11-03 华中科技大学 Method for predicating single yield of crops in irrigated area
CN103984980B (en) * 2014-01-28 2017-12-19 中国农业大学 The Forecasting Methodology of temperature extremal in a kind of greenhouse
CN205247189U (en) * 2015-12-22 2016-05-18 天津宏宝派农业科技发展有限公司 Wisdom farming system based on thing networking
CN106225846A (en) * 2016-08-29 2016-12-14 孟玲 Greenhouse monitoring system
CN106408433A (en) * 2016-11-22 2017-02-15 河南工业大学 Grain yield prediction method and grain yield prediction device based on differential processing
CN107016453A (en) * 2016-12-08 2017-08-04 中国农业大学 A kind of aquaculture dissolved oxygen prediction method and device
WO2018117890A1 (en) * 2016-12-21 2018-06-28 Schlumberger Technology Corporation A method and a cognitive system for predicting a hydraulic fracture performance
CN108091111B (en) * 2017-11-20 2018-11-13 淮阴工学院 A kind of oil truck oil and gas leakage intelligent early-warning system
CN108537371A (en) * 2018-03-27 2018-09-14 深圳春沐源控股有限公司 A kind of production forecast method and device
CN108934613B (en) * 2018-09-25 2021-08-06 邻家健康科技(厦门)有限公司 Automatic sprinkling irrigation system of solar photovoltaic vegetable planting greenhouse
CN109583301B (en) * 2018-10-29 2021-08-31 广东奥博信息产业股份有限公司 Method and device for predicting optimal external planting conditions in crop growth process

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101795090A (en) * 2009-01-19 2010-08-04 原子能委员会 Method of forecasting the electrical production of a photovoltaic device
CN108138555A (en) * 2015-02-23 2018-06-08 奈克森能量无限责任公司 Method, system and the equipment of predicting reservoir property
WO2017136489A1 (en) * 2016-02-03 2017-08-10 Caspo, Llc Smart cooking system that produces and uses hydrogen fuel

Also Published As

Publication number Publication date
CN110083190A (en) 2019-08-02

Similar Documents

Publication Publication Date Title
CN110083190B (en) Green pepper greenhouse environment intelligent monitoring system based on subtraction clustering classifier
CN110084417B (en) Intelligent strawberry greenhouse environment parameter monitoring system based on GRNN neural network
CN110119766B (en) Green pepper greenhouse temperature intelligent early warning device of multi-combination intelligent model
CN110163254B (en) Cucumber greenhouse output intelligent prediction device based on recurrent neural network
CN110119086B (en) Tomato greenhouse environmental parameter intelligent monitoring device based on ANFIS neural network
Pandith et al. Performance evaluation of machine learning techniques for mustard crop yield prediction from soil analysis
Benmouiza et al. Forecasting hourly global solar radiation using hybrid k-means and nonlinear autoregressive neural network models
CN110109193B (en) Intelligent eggplant greenhouse temperature detection device based on DRNN neural network
Zhang et al. A novel agricultural commodity price forecasting model based on fuzzy information granulation and MEA-SVM model
CN110119169B (en) Tomato greenhouse temperature intelligent early warning system based on minimum vector machine
CN110647979B (en) Greenhouse environment multi-parameter intelligent monitoring system based on Internet of things
CN110705757B (en) Multi-point temperature sensor intelligent monitoring system based on field bus network
CN107169621A (en) A kind of Dissolved Oxygen in Water Forecasting Methodology and device
CN110119767B (en) Intelligent cucumber greenhouse temperature detection device based on LVQ neural network
CN112906735A (en) Domestic fungus environment big data detecting system
CN113281465A (en) Livestock and poultry house breeding environment harmful gas detection system
CN113219871B (en) Curing room environmental parameter detecting system
CN110147825B (en) Strawberry greenhouse temperature intelligent detection device based on empirical mode decomposition model
CN113301127B (en) Livestock feed detection system
CN110119165B (en) Aquaculture pond dissolved oxygen detection device
CN112911533B (en) Temperature detection system based on remove end App
CN113283642A (en) Poultry feed detection and formula system
CN113255739A (en) Fish feed detection and formula system
CN112906856A (en) Livestock and poultry house ambient temperature detection system based on cloud platform
Jasti et al. Crop Intelligent: Weather based Crop Selection using Machine Learning

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
TR01 Transfer of patent right

Effective date of registration: 20211117

Address after: 264200 No. 10-7, Futian Road, torch high tech Industrial Development Zone, Weihai City, Shandong Province

Patentee after: WEIHAI GEMHO DIGITAL MINE TECHNOLOGY CO.,LTD.

Address before: 223005 Jiangsu Huaian economic and Technological Development Zone, 1 East Road.

Patentee before: HUAIYIN INSTITUTE OF TECHNOLOGY

TR01 Transfer of patent right