CN112906856A - Livestock and poultry house ambient temperature detection system based on cloud platform - Google Patents

Livestock and poultry house ambient temperature detection system based on cloud platform Download PDF

Info

Publication number
CN112906856A
CN112906856A CN202110041246.3A CN202110041246A CN112906856A CN 112906856 A CN112906856 A CN 112906856A CN 202110041246 A CN202110041246 A CN 202110041246A CN 112906856 A CN112906856 A CN 112906856A
Authority
CN
China
Prior art keywords
neural network
livestock
temperature
poultry house
output
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
Application number
CN202110041246.3A
Other languages
Chinese (zh)
Inventor
马从国
周大森
叶文芊
周恒瑞
柏小颖
葛红
马海波
丁晓红
张利兵
李亚洲
金德飞
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.)
Huaiyin Institute of Technology
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 CN202110041246.3A priority Critical patent/CN112906856A/en
Publication of CN112906856A publication Critical patent/CN112906856A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • 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
    • G01—MEASURING; TESTING
    • G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
    • G01K13/00—Thermometers specially adapted for specific purposes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F13/38—Information transfer, e.g. on bus
    • G06F13/42—Bus transfer protocol, e.g. handshake; Synchronisation
    • G06F13/4282—Bus transfer protocol, e.g. handshake; Synchronisation on a serial bus, e.g. I2C bus, SPI bus
    • G06F13/4286—Bus transfer protocol, e.g. handshake; Synchronisation on a serial bus, e.g. I2C bus, SPI bus using a handshaking protocol, e.g. RS232C link
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • G06F18/24137—Distances to cluster centroïds
    • G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
    • 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
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/10—Detection; Monitoring
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/30—Control
    • G16Y40/35—Management of things, i.e. controlling in accordance with a policy or in order to achieve specified objectives

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Environmental & Geological Engineering (AREA)
  • Toxicology (AREA)
  • Neurology (AREA)
  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • Housing For Livestock And Birds (AREA)

Abstract

The invention discloses a cloud platform-based livestock and poultry house environment temperature detection system which consists of a livestock and poultry house environment parameter acquisition and control platform and a livestock and poultry house environment temperature big data processing subsystem and realizes the functions of acquisition, processing and prediction of livestock and poultry house breeding environment parameters; the invention effectively solves the problems that the existing livestock and poultry breeding environment temperature detection system cannot accurately detect and predict the livestock and poultry breeding environment temperature according to the characteristics of nonlinearity, large hysteresis, complex dynamic change and the like of the breeding environment temperature change, so that the effective management of the livestock and poultry breeding environment temperature is greatly influenced, and the temperature parameter is not managed, so that the breeding benefit of livestock and poultry houses is greatly influenced.

Description

Livestock and poultry house ambient temperature detection system based on cloud platform
Technical Field
The invention relates to the technical field of automatic equipment for detecting the environmental temperature of a livestock and poultry house, in particular to a system for detecting the environmental temperature of the livestock and poultry house based on a cloud platform.
Background
The temperature and humidity are important environmental factors influencing the growth of livestock and poultry, and when the temperature and humidity in the environment are too high, bacteria in the environment can grow wantonly, so that the resistance of the livestock and poultry is reduced; when the temperature and the humidity of the environment are too low, water vapor in the air cannot effectively adsorb dust and bacteria, and diseases such as respiratory tract diseases of livestock and poultry are easy to obtain, and death can be caused in serious cases.
The illumination plays an important role in the production performance of the livestock, and under the appropriate illumination intensity, the illumination not only has a growth promoting effect on the livestock, but also has a positive effect on the propagation and fattening of the livestock. The detection terminal obtains the sunlight irradiation data through the illumination intensity sensor, and the high resolution of the detection terminal can be utilized to detect the light intensity change in a large range in the breeding environment. Most of practitioners in livestock breeding industry in China take families or small and medium-sized enterprises as main units. Compared with developed countries, the method has the advantages of low informatization degree, low technical input cost, high labor input cost and the like in the breeding production. With the coming of the agricultural information era, the intellectualization degree of livestock breeding can be effectively improved by combining the modern information technology with the traditional breeding industry. The livestock and poultry house environment temperature detection system based on the cloud platform realizes detection of the livestock and poultry house environment parameters and prediction of the temperature, and improves the economic benefit and efficiency of livestock and poultry breeding.
Disclosure of Invention
The invention provides a livestock and poultry house environment temperature detection system based on a cloud platform, which effectively solves the problems that the existing livestock and poultry breeding environment temperature detection system cannot accurately detect and predict the livestock and poultry breeding environment temperature according to the characteristics of nonlinearity, large hysteresis, complex dynamic change and the like of breeding environment temperature change, so that the effective management of the livestock and poultry breeding environment temperature is greatly influenced, and the temperature parameter is not managed, so that the breeding benefit of the livestock and poultry house is greatly influenced.
The invention is realized by the following technical scheme:
a livestock and poultry house environment temperature detection system based on a cloud platform is composed of a livestock and poultry house environment parameter acquisition and control platform and a livestock and poultry house environment temperature big data processing subsystem, wherein the livestock and poultry house environment parameter detection system platform is composed of a detection node, a control node, a gateway node, a field monitoring end, a mobile end APP and a cloud platform, the detection node and the control node are responsible for detecting and controlling the livestock and poultry house environment parameters, the livestock and poultry house environment parameters are uploaded to the cloud platform through the gateway node, and a breeding manager can check livestock and poultry breeding environment data of the cloud platform in real time from the mobile end APP, so that the remote monitoring and intelligent regulation and control functions of the livestock and poultry house breeding environment parameters are realized; the structure diagram of the livestock and poultry house environment parameter acquisition and control platform is shown in figure 1.
The invention further adopts the technical improvement scheme that:
the big data processing subsystem of the temperature of the environment of the livestock and poultry house comprises a temperature detection unit and a temperature grade classifier, the output of a plurality of temperature sensors is respectively the input of a plurality of corresponding beat Delay lines TDL (tapped Delay line) of the temperature detection unit, the trapezoidal fuzzy number of the temperature detection unit in the nursery period, the trapezoidal fuzzy number of the temperature in the growing period and the trapezoidal fuzzy number of the temperature in the fattening period output by the temperature detection unit in different growth stages of the livestock and poultry are taken as the input of 3 corresponding beat Delay lines TDL (tapped Delay line) of the temperature classifier, the trapezoidal fuzzy number output by the temperature classifier represents the temperature suitability grade of the livestock and poultry house, and the big data processing subsystem of the temperature of the environment of the livestock and poultry house is shown in figure 2.
The invention further adopts the technical improvement scheme that:
the temperature detection unit consists of a plurality of beat Delay lines TDL (tapped Delay line), a plurality of NARX neural network temperature models, a DRNN neural network model, a FLNN neural network model, an ANFIS neural network model, 3 integration loops and a GMDH neural network model, wherein 2 integration operators S are connected in series to form an integration loop, the output of the connecting end of 2 integration operators of each integration loop is used as 1 corresponding input of the GMDH neural network model, and the output of each integration loop is used as 1 corresponding input of the GMDH neural network model; the outputs of the plurality of temperature sensors are respectively used as the inputs of a plurality of corresponding beat delay lines TDL, the temperature sensor value output by each beat delay line TDL for a period of time is respectively used as the input of a corresponding NARX neural network temperature model, the outputs of the plurality of NARX neural network temperature models are respectively used as the inputs of a DRNN neural network model, a FLNN neural network model and an ANFIS neural network model, the outputs of the DRNN neural network model, the FLNN neural network model and the ANFIS neural network model are respectively used as the input of each corresponding integration loop and 1 corresponding input of the GMDH neural network model, the output of the GMDH neural network model is a trapezoidal fuzzy number representing the magnitude of a plurality of temperature sensor values in a period of time of animal house environment, the trapezoidal fuzzy number is [ a, b, c, d ], [ a, b, c, d ] constitutes a trapezoidal fuzzy number which is formed by the temperature detection unit and outputs a plurality of temperature sensor values in a period of time, a. b, c and d respectively represent the minimum value, the maximum value and the maximum value of the environment temperature of the livestock and poultry house, and the temperature detection unit converts the temperature sensor values of a plurality of periods of time into temperature trapezoidal fuzzy values.
The invention further adopts the technical improvement scheme that:
the temperature grade classifier consists of 3 beat Delay lines TDL (tapped Delay line), 3 dynamic recursive wavelet neural networks, 3 self-associative neural networks and RBF neural network classifiers, wherein the temperature detection unit respectively takes the temperature trapezoidal fuzzy number in the nursery period, the temperature trapezoidal fuzzy number in the growing period and the temperature trapezoidal fuzzy number in the fattening period output in different growth stages of livestock and poultry as the corresponding 1 st, 2 nd and 3 rd input of the temperature classifier according to beat Delay lines TDL (tapped Delay line), the temperature trapezoidal fuzzy of the livestock and poultry shed in a period of time output by the 3 beat Delay lines TDL is respectively taken as the corresponding 1 st, 2 nd and 3 rd input of the self-associative neural networks, the output of the 3 self-associative neural networks is respectively taken as the corresponding 1 st, 2 nd recursive wavelet neural networks and 3 rd input of the dynamic recursive wavelet neural networks, the output of the 1 st dynamic recursive neural network is respectively taken as the input of the 2 nd dynamic recursive wavelet neural network and the RBF neural network classifier The 2 nd dynamic recursive wavelet neural network output is respectively used as the 3 rd dynamic recursive wavelet neural network input and the corresponding input of an RBF neural network classifier, the 3 rd dynamic recursive wavelet neural network is used as the corresponding input of the RBF neural network classifier, and numbers 1-5 representing different livestock and poultry types are used as 1 corresponding input of the RBF neural network classifier, wherein the number 1 represents a live pig, the number 2 represents a chicken, the number 3 represents a beef cattle, the number 4 represents a sheep, the number 5 represents a pigeon, and the trapezoidal fuzzy number output by the RBF neural network classifier represents the temperature suitability level; .
The invention further adopts the technical improvement scheme that:
according to the engineering practice of the livestock and poultry house temperature on the livestock and poultry growth suitability, the RBF neural network classifier divides the influence degree of the livestock and poultry house environment temperature on the livestock and poultry growth process into 5 suitability grades, the 5 suitability grades are respectively generally suitable, relatively suitable, very suitable, unsuitable and very unsuitable and respectively correspond to 5 different trapezoidal fuzzy numbers, a corresponding relation table of the 5 trapezoidal fuzzy numbers and the 5 suitability grades is constructed, the similarity between the trapezoidal fuzzy number output by the RBF neural network classifier and the 5 trapezoidal fuzzy numbers representing the 5 suitability grades is calculated, and the suitability grade corresponding to the trapezoidal fuzzy number with the maximum similarity is determined as the livestock and poultry house environment temperature suitability grade.
Compared with the prior art, the invention has the following obvious advantages:
the FLNN function connection neural network model is composed of an input layer and an output layer, and has no hidden layer, so that compared with the traditional neural network, the FLNN function connection neural network model has smaller network calculation amount and higher training speed. The method can avoid updating the weight of the hidden layer, only needs to adjust the weight of the output layer, has higher convergence speed and less on-line calculation amount, simultaneously expands the temperature parameter input variable of the livestock and poultry breeding environment, can improve the network resolution capability of the FLNN function connection neural network model, and improves the accuracy of detecting the environment temperature of the livestock and poultry house.
The GMDH neural network model is mainly a process of continuously generating active neurons, screening the neurons by an external criterion, and combining the screened neurons strongly to generate the next layer of neurons until the model with the optimal complexity is selected. Firstly, a model result of definite function analytic expression can be obtained, the self-organizing GMDH neural network model integrates the ideas of neural network and statistical modeling, and a result of function expression can be given, even a multivariable high-order regression equation which is difficult to achieve by other modeling methods; self-organizing control is carried out in the modeling process without any initial assumption, the GMDH neural network model allows hundreds of input variables, then a large number of models to be selected are generated layer by layer through a large number of variables, an algorithm searches for input items which have substantial influence on the explained variables according to data drive, an optimal network structure is generated through self-organization, and the influence of subjective factors of a modeler is reduced as much as possible; and optimal complexity and high-precision prediction are achieved, GMDH can make decisions from approximate, uncertain and even contradictory knowledge environments through the optimal complex characteristics of the network model, over-fitting and under-fitting of the model structure are avoided, GMDH is closer to the real situation of the livestock and poultry house environment temperature change system through the network model, and accordingly the livestock and poultry house environment temperature has higher prediction reliability.
The NARX neural network is utilized to build a dynamic recursive network of the model by introducing a delay module and outputting feedback, the NARX neural network introduces input and output vector delay feedback into network training to form a new input vector, and the NARX neural network has good nonlinear mapping capability, the input of the NARX neural network not only comprises original livestock house environment temperature input data, but also comprises trained temperature output data, and the generalization capability of the network is improved, so that the NARX neural network has better prediction accuracy and self-adaption capability in livestock house environment temperature prediction compared with the traditional static neural network.
Fourth, the temperature of the environment of the livestock and poultry house has the characteristics of nonlinearity, large hysteresis, complex dynamic change and the like, and a sensor for measuring the environment temperature of the livestock and poultry house is easily interfered, so that the environment temperature measurement of the livestock and poultry house often contains large noise. On the other hand, the measured temperatures of the poultry house environment are more than the number of its independent variables, i.e. there is redundant information in these measured temperatures. The self-association neural network can utilize redundant information to inhibit measurement noise of the livestock and poultry house environment temperature information through compression and decompression processes of the livestock and poultry house environment temperature information. In the big data processing process of the environment of the livestock and poultry house, the measured temperature is preprocessed by using the auto-associative neural network, so that the accuracy of the environment temperature of the livestock and poultry house can be greatly improved.
Fifth, the invention animal house environment temperature suitability degree grade classification scientificity and reliability, the RBF neural network classifier of the patent classifies the animal house environment temperature suitability degree grade, the animal house environment temperature suitability degree grade is according to the size of the trapezoid fuzzy number of the animal house environment temperature suitable animal growth grade, according to the engineering practice experience of the animal house environment temperature control, the dynamic quantification of the temperature of the animal house in the conservation period, the growth period and the fattening period to the size of the animal growth influence is to be the suitability degree grade through the RBF neural network classifier, the animal house environment temperature is divided into five conditions through the trapezoid fuzzy number, the 5 suitability degrees of the animal house environment temperature are respectively the general suitable, more suitable, unsuitable and less suitable corresponding to 5 different trapezoid fuzzy numbers, the similarity of the trapezoid fuzzy number output by the RBF neural network classifier and the 5 trapezoid fuzzy numbers representing the 5 suitability degrees is calculated, and the suitability grade corresponding to the trapezoidal fuzzy number of the similarity is determined as the suitability grade of the environment temperature of the livestock and poultry house, so that the dynamic performance and scientific classification of the suitability grade of the environment temperature of the livestock and poultry house are realized.
Sixth, because the invention introduces the first and second variable quantity of the temperature parameter predicted value of the animal house through 3 integral loops, the GMDH neural network model is applied in the time series prediction of the nonlinear parameter and the detected parameter is converted into the trapezoidal fuzzy number according to the predicted value of the detected parameter and the influence of the variable quantity, thus having better prediction precision and self-adaptive ability and improving the generalization ability of the GMDH neural network model.
Drawings
FIG. 1 is a table for collecting and controlling environmental parameters of a poultry house according to the present invention;
FIG. 2 is a big data processing subsystem of the environment temperature of the livestock and poultry house of the invention;
FIG. 3 is a temperature class classifier of the present invention;
FIG. 4 is a detection node of the present invention;
FIG. 5 is a control node of the present invention;
FIG. 6 is a gateway node of the present invention;
fig. 7 is the site monitoring software of the present invention.
Detailed Description
The technical solution of the present invention is further described with reference to the accompanying drawings 1-7:
design of overall system function
The system consists of a livestock and poultry house environment parameter acquisition and control platform and a livestock and poultry house environment temperature big data processing subsystem, wherein the livestock and poultry house environment parameter acquisition and control platform comprises detection nodes, control nodes, gateway nodes, a field monitoring end, a cloud platform and a mobile end App of the livestock and poultry house environment parameters, and the detection nodes, the control nodes and the gateway nodes are communicated by constructing a CAN communication network; the detection node sends the detected environment parameters of the livestock and poultry house to an on-site monitoring end through an RS232 interface of the gateway node, and the on-site monitoring end manages sensor data and predicts temperature; the gateway node realizes bidirectional transmission of the livestock and poultry house environmental parameters between the NB-IoT module and the cloud platform and between the cloud platform and the mobile terminal App through the 5G network, and bidirectional transmission of the livestock and poultry house environmental parameters between the gateway node and the field monitoring terminal is realized through the RS232 interface. Remove App end and provide real-time animal poultry house environmental data for managers, warning management, historical data's inquiry satisfies the convenient visual of animal poultry house environmental data information, and all data that come from the sensor collection of detecting node have all been uploaded to the database of cloud platform in, and managers looks over current animal poultry house environmental parameter through removing end App accessible long-range. The cloud platform realizes the functions of user management, livestock and poultry house environment data management, real-time monitoring, alarming and the like. The cloud platform is mainly responsible for processing, storing, analyzing and displaying the received environment information of the livestock and poultry house. The cloud platform and the user are interacted mainly through a webpage end and a mobile equipment end, the efficient interaction between the cloud platform and the user is realized to the maximum extent through complete functions of the webpage end and convenient and fast operation of the mobile end, and the user management provides management operation of registering an account number, logging in the account number and changing account number information for a manager; the data management provides the operations of historical data query and data classification management for users; the real-time monitoring function processes the parameters into visualized data, and the change of the data can be presented in a mode of easy analysis of a histogram or a line graph. The structure of the livestock and poultry house environment parameter acquisition and control platform is shown in figure 1.
Second, design of detection node
The detection node consists of a sensor, a conditioning circuit, an STM32 single chip microcomputer and a CAN bus interface, is mainly used for collecting and detecting the environmental parameters of each livestock and poultry house by a temperature sensor, a humidity sensor, an illumination intensity sensor and a wind speed sensor in the livestock and poultry environment, and the real-time interaction of the information between the detection node and the gateway node is realized through the CAN bus interface of the detection node and the CAN bus interface of the gateway node by the environmental data information.
Control node design
The control node is composed of a CAN bus interface, an STM32 single chip microcomputer, a temperature control device, a humidity control device, a light illumination control device and an air speed control device, and the stability of each factor data of the livestock and poultry house breeding environment is regulated and controlled by adjusting the operation of the devices for heat supply, humidity supply and ventilation. After the microprocessor of the control node receives the set values of the environmental parameters sent by the cloud platform management personnel, the work of the temperature control device, the humidity control device, the wind speed control device and the illuminance control device is controlled through the relay, and the regulation and control of the environment of the livestock and poultry house are completed. The control node and the gateway node are in bidirectional data communication through a CAN bus interface, and in order to achieve that the environment of the livestock and poultry house is always in a suitable environment, the running state and the running efficiency of the equipment are dynamically adjusted.
Fourth, gateway node design
The gateway node comprises a CAN bus interface, an NB-IoT module, an STM32 single chip microcomputer and an RS232 interface, bidirectional transmission of data between the detection node and the field control monitoring terminal and between the control node and the field control monitoring terminal is achieved through the CAN bus interface and the RS232 interface, and bidirectional transmission between the mobile terminal APP, the detection node, the control node and the field monitoring terminal is achieved through the CAN bus interface, the NB-IoT module and the RS232 interface.
Fifthly, field monitoring terminal software design
The field monitoring end is an industrial control computer, mainly realizes acquisition of parameters of the livestock and poultry house and prediction of the environmental temperature of the livestock and poultry house, realizes information interaction with the gateway node, and has the main functions of communication parameter setting, data analysis and data management and a big data processing subsystem of the environmental temperature of the livestock and poultry house. The big data processing subsystem of the environment temperature of the livestock and poultry house comprises a temperature detection unit and a temperature grade classifier. The structure of the big data processing subsystem for the environment temperature of the livestock and poultry house is shown in figure 2. 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 7. The big data processing subsystem of the temperature of the environment of the livestock and poultry house comprises a temperature detection unit and a temperature grade classifier, the output of a plurality of temperature sensors is respectively the input of a plurality of corresponding beat Delay lines TDL (tapped Delay line) of the temperature detection unit, the trapezoidal fuzzy number of the temperature detection unit in the nursery period, the trapezoidal fuzzy number of the temperature in the growing period and the trapezoidal fuzzy number of the temperature in the fattening period output by the temperature detection unit in different growth stages of the livestock and poultry are taken as the input of 3 corresponding beat Delay lines TDL (tapped Delay line) of the temperature classifier, the trapezoidal fuzzy number output by the temperature classifier represents the temperature suitability grade of the livestock and poultry house, and the temperature detection unit and the temperature grade classifier are characterized as follows:
1. temperature sensing unit design
The temperature detection unit consists of a plurality of beat Delay lines TDL (tapped Delay line), a plurality of NARX neural network temperature models, a DRNN neural network model, a FLNN neural network model, an ANFIS neural network model, 3 integration loops and a GMDH neural network model, wherein 2 integration operators S are connected in series to form an integration loop, the output of the connecting end of 2 integration operators of each integration loop is used as 1 corresponding input of the GMDH neural network model, and the output of each integration loop is used as 1 corresponding input of the GMDH neural network model; the outputs of the plurality of temperature sensors are respectively used as the inputs of a plurality of corresponding beat delay lines TDL, the temperature sensor value output by each beat delay line TDL for a period of time is respectively used as the input of a corresponding NARX neural network temperature model, the outputs of the plurality of NARX neural network temperature models are respectively used as the inputs of a DRNN neural network model, a FLNN neural network model and an ANFIS neural network model, the outputs of the DRNN neural network model, the FLNN neural network model and the ANFIS neural network model are respectively used as the input of each corresponding integration loop and 1 corresponding input of the GMDH neural network model, the output of the GMDH neural network model is a trapezoidal fuzzy number representing the magnitude of a plurality of temperature sensor values in a period of time of animal house environment, and the trapezoidal fuzzy numbers are [ a, b, c, d ], [ a, b, c, d ] form a trapezoidal fuzzy number which forms a plurality of temperature sensor values output by the temperature detection unit within a period of time, a. b, c and d respectively represent the minimum value, the maximum value and the maximum value of the environment temperature of the livestock and poultry house, and the temperature detection unit converts a period of time temperature sensor values into a temperature trapezoidal fuzzy value;
A. NARX neural network temperature model design
And the outputs of the plurality of NARX neural network temperature models are used as the inputs of the DRNN neural network model, the FLNN function connection type neural network model and the ANFIS neural network model, and the outputs of the DRNN neural network model, the FLNN function connection type neural network model and the ANFIS neural network model are respectively used as the input of each corresponding integral loop and 1 corresponding input of the GMDH neural network model. The NARX neural network temperature model (Nonlinear Auto-Regression with External input neural network) is a dynamic feedforward neural network, the NARX neural network temperature model is a Nonlinear autoregressive network with External input, the NARX neural network temperature model has a dynamic characteristic of multistep time delay and is connected with a plurality of layers of a closed network through feedback, and the recurrent neural network of the NARX neural network temperature model is a dynamic neural network which is widely applied in a Nonlinear dynamic system and has the performance generally superior to that of a full recurrent neural network. Before application, the delay order and the number of hidden layer neurons of the input and output are generally determined in advance, the output of the NARX neural network temperature model depends not only on the past output y (t-n), but also on the input temperature vector X (t) and the delay order of the input temperature vector, and the like, wherein the input temperature signal is transmitted to the hidden layer through a time epitaxial layer, the hidden layer processes the input temperature signal and then transmits the processed input temperature signal to the output layer, the output layer linearly weights the hidden layer output signal to obtain a final neural network output signal, and the time epitaxial layer delays a signal fed back by the network and a signal output by the input layer and then transmits the final neural network output signal to the hidden layer. The NARX neural network temperature model has the characteristics of nonlinear mapping capability, good robustness, adaptability and the like, and is suitable for predicting the temperature of the livestock and poultry breeding environment. x (t) represents the external input of the neural network temperature model, namely the value of the temperature sensor of the environment of the livestock and poultry breeding environment; m represents the delay order of the external input; y (t) is the output of the neural network, namely the predicted value of the environment temperature of the livestock and poultry breeding environment in the next time period; n is the output delay order; s is the number of hidden layer neurons; the output of the jth implicit element can be found as:
Figure BDA0002895444100000091
in the above formula, wjiAs a connection weight between the ith input and the jth implicit neuron, bjIs the bias value of the jth implicit neuron, and the output y (t +1) of the network has the value:
y(t+1)＝f[y(t),y(t-1),…,y(t-n),x(t),x(t-1),…,x(t-m+1)；W] (2)
B. DRNN neural network design
And the outputs of the plurality of NARX neural network temperature models are used as the inputs of the DRNN neural network model, the FLNN function connection type neural network model and the ANFIS neural network model, and the outputs of the DRNN neural network model, the FLNN function connection type neural network model and the ANFIS neural network model are respectively used as the input of each corresponding integral loop and 1 corresponding input of the GMDH neural network model. The output of the DRNN neural network model is used as the input of a corresponding integral loop and 1 corresponding input of the GMDH neural network model, the DRNN neural network model is a dynamic regression neural network with feedback and the capability of adapting to time-varying characteristics, the network can more directly and vividly change the dynamic change performance of detection parameters of the livestock and poultry breeding environment, the DRNN neural network model can more accurately control the temperature of the livestock and poultry breeding environment, the network structure of the DRNN neural network model is a 3-layer network structure of n-2n +1-1, and the hidden layer of the DRNN neural network model is a dynamic regression layer. Let I ═ I1(t),I2(t),…,In(t)]Inputting vectors for DRNN neural network model, wherein Ii(t) is the input of the ith neuron of the input layer of the DRNN neural network model at the t moment, and the output of the jth neuron of the regression layer is Xj(t)，Sj(t) is the sum of the j-th regression neuron inputs, f (-) is a function of S, and O (t) is the output of the DRNN neural network model. The output layer output of the DRNN neural network model is:
Figure BDA0002895444100000101
C. FLNN function connection type neural network model design
The outputs of the plurality of NARX neural network temperature models are respectively used as the inputs of the DRNN neural network model, the FLNN neural network model and the ANFIS neural network model, and the outputs of the DRNN neural network model, the FLNN neural network model and the ANFIS neural network model are respectively used as the input of each corresponding integration loop and 1 corresponding input of the GMDH neural network model. The output of the parameter measurement sensor is used as the input of the corresponding beat delay line TDL, the parameter measurement sensor value of each beat delay line TDL output for a period of time is respectively used as the input of the corresponding FLNN function connection type neural network model, and the outputs of the plurality of FLNN function connection type neural network models are respectively used as the input of the plurality of DRNN neural network model models. The FLNN functional connection neural network is a functional neural network model, and the function of functional connection in the model is to multiply each component of an input mode of detection parameters of the livestock and poultry breeding environment by the whole mode vector, and the result is to generate a product of the original mode vector. The FLNN function connection type neural network carries out nonlinear expansion on the detection parameter input mode of the livestock and poultry breeding environment in advance, a high-order item is introduced into the FLNN function connection type neural network, and the detection parameter input mode of the livestock and poultry breeding environment is mapped to a larger mode space through the nonlinear expansion of the detection parameter input mode of the livestock and poultry breeding environment, so that the mode expression of the detection parameter input signal of the livestock and poultry breeding environment is enhanced, and the network structure of the FLNN function connection type neural network model is greatly simplified. Although the detection parameter information of the livestock and poultry breeding environment input by the FLNN function connection type neural network model is not increased, the enhancement of the FLNN function connection type neural network model brings simplification of the network structure of the FLNN function connection type neural network model and improvement of the learning speed, the supervised learning can be realized by using a single-layer network, and the method has great advantages compared with a multi-layer forward neural network. The FLNN function connection type neural network model realizes supervised learning by using a single-layer network, and the solving process can be completed by the following self-adaptive supervised learning algorithm. The learning algorithm of the FLNN functional type connected neural network model may be represented by the following equation:
Figure BDA0002895444100000111
weight adjustment:
Figure BDA0002895444100000112
wherein: fi(k)、
Figure BDA0002895444100000113
ei(k) And wn(k) Respectively the expected output, the estimated output, the error and the nth connection weight of the functional network in the kth step of the ith input mode; alpha is a learning factor and affects stability and convergence rate. The method is characterized in that the FLNN function connection neural network model adopts a function expansion mode to expand the input of detection parameters of the original livestock and poultry breeding environment, so that the input of the detection parameters of the original livestock and poultry breeding environment is converted into another space, and the enhanced mode is used as the input of a network input layer of the FLNN function connection neural network model, so that the nonlinear problem is better solved through the method; the FLNN function connection neural network model is composed of an input layer and an output layer, and has no hidden layer, so that compared with the traditional neural network, the FLNN function connection neural network model has smaller network calculation amount and higher training speed. The method can avoid updating the weight of the hidden layer, only needs to adjust the weight of the output layer, has higher convergence speed and less on-line calculation amount, simultaneously expands the input variable of the detection parameters of the livestock and poultry breeding environment, and can improve the network resolution capability of the FLNN function connection neural network model.
D. ANFIS neural network model design
The outputs of the plurality of NARX neural network temperature models are respectively used as the inputs of the DRNN neural network model, the FLNN neural network model and the ANFIS neural network model, and the outputs of the DRNN neural network model, the FLNN neural network model and the ANFIS neural network model are respectively used as the input of each corresponding integration loop and 1 corresponding input of the GMDH neural network model. The ANFIS neural network 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 are obtained by learning known historical data of a large number of livestock and poultry house environment temperatures, and the ANFIS neural network model is mainly characterized by a data-based modeling method instead of being given arbitrarily based on experience or intuition. The input of the ANFIS neural network model is an NARX neural network output value, the output of the ANFIS neural network model is a livestock and poultry house environment temperature predicted value again, and the main operation steps are as follows:
on the layer 1, animal house numerical values of input NARX neural network output values are fuzzified, and the corresponding output of each node can be represented as:
Figure BDA0002895444100000121
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 model by adopting multiplication.
Figure BDA0002895444100000122
And 3, normalizing the applicability of each rule:
Figure BDA0002895444100000123
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 BDA0002895444100000124
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 BDA0002895444100000131
the condition parameters determining the shape of the membership function and the conclusion parameters of the inference rule in the ANFIS neural network 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, firstly, an input signal is transmitted along the network in the forward direction until the layer 4, a least square estimation algorithm is adopted to adjust conclusion parameters, and the signal is continuously transmitted along the network in the forward direction until the output layer. The ANFIS neural network 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 model in this way, the global optimum point of the conclusion parameters can be obtained, so that the dimension of the search space in the gradient method can be reduced, and the convergence rate of the ANFIS neural network model parameters can be increased. The ANFIS neural network model output is a fused value of a plurality of NARX neural network output values.
E. GMDH neural network model design
The output of the DRNN neural network model, the FLNN neural network model and the ANFIS neural network model is respectively used as the input of each corresponding integral loop and 1 corresponding input of the GMDH neural network model, the output of the GMDH neural network model is a trapezoidal fuzzy number representing the magnitude of a plurality of temperature sensor values in the environment of the livestock and poultry house in a period of time, and the trapezoidal fuzzy number is [ a, b, c, d ]]，[a，b，c，d]Trapezoidal fuzzy values of a plurality of temperature sensor values output by the temperature detection unit in a period of time are formed, and a, b, c and d respectively represent the environment temperature of the livestock and poultry houseThe temperature detection unit converts the temperature sensor values over a period of time into temperature trapezoidal fuzzy values. The GMDH neural network model (GMDH) is an algorithm for self-organizing data mining, if the GMDH neural network model has m input variables x1,x2,…,xmAnd the output is Y. The goal of GMDH is to establish a functional relationship f where the coefficients of the input-to-output relationship are to be fixed and the form is known, which can be approximated by applying a polynomial expanded by a volterra series:
Figure BDA0002895444100000141
the GMDH neural network model is mainly used for processing small sample data and building an animal house environment parameter prediction model by automatically searching the correlation among variables in the sample. Firstly, a first generation intermediate candidate model is generated according to an initial model of a reference function, then a plurality of items are screened from the first generation intermediate candidate model and are added with a calculation rule to generate a second generation intermediate candidate model, and the process is repeated until an optimal livestock and poultry house environment parameter prediction model is obtained, so that the GMDH neural network model can adaptively establish a high-order polynomial model with an explanation capacity on a dependent variable according to an independent variable. Let RjMaximum number of neurons in layer j, xklIs the kth dimension, y, of the l input samplejklPredicting a value of the kth input sample for the kth neuron in the jth layer of the network,
Figure BDA0002895444100000142
the root mean square of the threshold value of the kth neuron in the jth layer of the network is obtained, and Y is a predicted value of the network. The GMDH neural network model adopts a self-adaptive multilayer iteration method to construct a network structure, selects a network optimal model through a minimum deviation criterion, and constructs nonlinear mapping between input and output based on a Kolmogorov-Gabor polynomial. Data preprocessing divides a data set into a training set and a testing set; input quantities are paired, and a local polynomial model is identified, so that a competition model set is generated, and a selection criterion value is calculated asInputting by one layer until the optimal complexity model is selected. The learning evolution process of the GMDH neural network model is as follows: setting the maximum number R of neurons in each layer of the networkjAnd the number of initial variables d of the network0A network minimum deviation criterion is selected. Constructing an initial network only containing layer 1 neurons according to the dimension of the input data. Calculating threshold value root mean square of each neuron in sequence
Figure BDA0002895444100000143
For the j-th layer of the network, the layers are ordered from large to small
Figure BDA0002895444100000144
Before RjAn
Figure BDA0002895444100000145
The selected neurons are retained, and the remaining neurons are unselected. For selected neurons, find the minimum
Figure BDA0002895444100000146
And is minimum with the upper layer
Figure BDA0002895444100000147
Make a comparison if
Figure BDA0002895444100000148
Is less than
Figure BDA0002895444100000149
Executing the step (iv) otherwise executing the step (v). And generating a next layer of neurons according to the currently selected neurons. And fifthly, finishing the network construction.
2. Temperature class classifier design
The temperature grade classifier consists of 3 beat Delay lines TDL (tapped Delay line), 3 dynamic recursive wavelet neural networks, 3 self-associative neural networks and RBF neural network classifiers, wherein the temperature detection unit respectively takes the temperature trapezoidal fuzzy number in the nursery period, the temperature trapezoidal fuzzy number in the growing period and the temperature trapezoidal fuzzy number in the fattening period output in different growth stages of livestock and poultry as the corresponding 1 st, 2 nd and 3 rd input of the temperature classifier according to beat Delay lines TDL (tapped Delay line), the temperature trapezoidal fuzzy of the livestock and poultry shed in a period of time output by the 3 beat Delay lines TDL is respectively taken as the corresponding 1 st, 2 nd and 3 rd input of the self-associative neural networks, the output of the 3 self-associative neural networks is respectively taken as the corresponding 1 st, 2 nd recursive wavelet neural networks and 3 rd input of the dynamic recursive wavelet neural networks, the output of the 1 st dynamic recursive neural network is respectively taken as the input of the 2 nd dynamic recursive wavelet neural network and the RBF neural network classifier The 2 nd dynamic recursive wavelet neural network output is respectively used as the 3 rd dynamic recursive wavelet neural network input and the corresponding input of an RBF neural network classifier, the 3 rd dynamic recursive wavelet neural network is used as the corresponding input of the RBF neural network classifier, and numbers 1-5 representing different livestock and poultry types are used as 1 corresponding input of the RBF neural network classifier, wherein the number 1 represents a live pig, the number 2 represents a chicken, the number 3 represents a beef cattle, the number 4 represents a sheep, the number 5 represents a pigeon, and the trapezoidal fuzzy number output by the RBF neural network classifier represents the temperature suitability level. The design process of the temperature grade classifier is as follows:
A. self-associative neural network design
The temperature detection unit respectively takes the temperature trapezoidal fuzzy numbers in the nursery period, the growth period and the fattening period output in different growth stages of livestock and poultry as the input of corresponding 1 st, 2 nd and 3 rd beat Delay lines TDL (tapped Delay line) of the temperature classifier, the temperature trapezoidal fuzzy numbers in the livestock and poultry house output for a period of time according to the beat Delay lines TDL are respectively taken as the input of corresponding 1 st, 2 nd and 3 rd self-association neural networks, and the temperature trapezoidal fuzzy numbers output by the 3 self-association neural networks are respectively taken as the input of corresponding 1 st, 2 nd and 3 rd dynamic recursive wavelet neural networks. An Auto-associative neural network (AANN), a feedforward neural network of a special structure, includes an input layer, a number of hidden layers, and an output layer. The method comprises the steps of firstly compressing input data information of the trapezoidal fuzzy number of the environment temperature of the livestock and poultry house through an input layer, a mapping layer and a bottleneck layer, extracting a most representative low-dimensional subspace reflecting the system structure of the trapezoidal fuzzy number of the environment temperature of the livestock and poultry house from a high-dimensional parameter space input by a network, effectively filtering noise and measurement errors in the input data of the trapezoidal fuzzy number of the environment temperature of the livestock and poultry house, decompressing the data of the trapezoidal fuzzy number of the environment temperature of the livestock and poultry house through the bottleneck layer, the demapping layer and the output layer, and restoring the compressed information to each parameter value, so that reconstruction of the input data of the trapezoidal fuzzy number of the environment temperature of each livestock and poultry house is realized. In order to achieve the purpose of information compression, the number of nodes of a bottleneck layer of a self-associative neural network is obviously smaller than that of an input layer, and in order to prevent the formation of simple single mapping between the input layer and the output layer, except that a linear function is adopted as an excitation function of the output layer, non-linear excitation functions are adopted in other layers. In essence, the first layer of the hidden layer of the self-associative neural network is called as a mapping layer, and the node transfer function of the mapping layer can be an S-shaped function or other similar nonlinear functions; the second layer of the hidden layer is called a bottleneck layer, the dimension of the bottleneck layer is the minimum in the network, the transfer function of the bottleneck layer can be linear or nonlinear, the bottleneck layer avoids the mapping relation that the output and the input are equal, which is easy to realize, one-to-one, and the bottleneck layer enables the network to encode and compress the trapezoidal fuzzy number signals of the environment temperature of the livestock and poultry house to obtain a correlation model of the data of the input temperature sensor, and the correlation model is decoded and decompressed behind the bottleneck layer to generate an estimated value of the trapezoidal fuzzy number input signals of the environment temperature of the livestock and poultry house; the third layer or the last layer of the hidden layer is called a demapping layer, the node transfer function of the demapping layer is a generally nonlinear S-shaped function, and the self-associative neural network is trained by an error back propagation algorithm.
B. Dynamic recursive wavelet neural network prediction model design
The outputs of the 3 self-associative neural networks are respectively used as the inputs of the 1 st, the 2 nd and the 3 rd dynamic recursive wavelet neural networks, the output of the 1 st dynamic recursive wavelet neural network is respectively used as the input of the 2 nd dynamic recursive wavelet neural network and the corresponding input of the RBF neural network classifier, and the output of the 2 nd dynamic recursive wavelet neural network is divided intoThe wavelet function is taken as an excitation function of a neuron on the basis of a wavelet Neural network WNN (wavelet Neural networks) theory and is combined with an artificial Neural network to provide a feedforward type network, and the expansion and contraction, translation factors and connection weight of wavelets in the wavelet Neural network are adaptively adjusted in the optimization process of an error energy function. Let the input signal of the wavelet neural network be represented as an input one-dimensional vector xi(i ═ 1,2, …, n), the output signal is denoted yk(k is 1,2, …, m), and the calculation formula of the predicted value of the output layer of the wavelet neural network prediction model is as follows:
Figure BDA0002895444100000171
in the formula omegaijInputting the connection weight between the i node of the layer and the j node of the hidden layer,
Figure BDA0002895444100000172
as wavelet basis functions, bjIs a shift factor of the wavelet basis function, ajScale factor, omega, of wavelet basis functionsjkThe connection weight between the node of the hidden layer j and the node of the output layer k. The dynamic recursive wavelet neural network prediction model is different from a common static wavelet neural network in that the dynamic recursive wavelet neural network prediction model is provided with two associated layer nodes which play a role in storing the internal state of a network, a self-feedback loop with fixed gain is added on the two associated layer nodes, and the memory performance of time sequence characteristic information is enhanced, so that the tracking precision of the breeding yield evolution track of the livestock and poultry house is enhanced to ensure better prediction precision; the first associated layer node is used for storing the state of the phase point of the hidden layer node at the previous moment and transmitting the state to the hidden layer node at the next moment; the second correlation layer node is used for storing the state of the phase point of the output layer node at the previous moment and transmitting the state to the hidden layer node at the next moment; feedback of neurons in hidden and output layersThe information can influence the dynamic processing capacity of the prediction of the dynamic recursive wavelet neural network prediction model, and the two associated layers belong to the state feedback in the dynamic recursive wavelet neural network prediction model to form the special dynamic memory performance of the recursion of the dynamic recursive wavelet neural network prediction model, so that the accuracy and the dynamic performance of the dynamic recursive wavelet neural network prediction model for predicting the environment temperature of the livestock and poultry house are improved; a group of connection weights are added between the first association layer node and the output layer node of the dynamic recursive wavelet neural network prediction model to enhance the dynamic approximation capability of the dynamic recursive wavelet neural network prediction model for predicting the environment temperature of the livestock house and improve the prediction precision of the environment temperature of the livestock house. The correction algorithm of the weight and the threshold of the dynamic recursive wavelet neural network livestock and poultry house environment temperature prediction model in the patent adopts a gradient correction method to update the network weight and the wavelet basis function parameters, so that the output of the dynamic recursive wavelet neural network livestock and poultry house environment temperature prediction model is continuously close to the expected output.
C. RBF neural network classifier design
The outputs of the 3 self-associative neural networks are respectively used as the inputs of the 1 st, the 2 nd and the 3 rd dynamic recursive wavelet neural networks, the output of the 1 st dynamic recursive wavelet neural network is respectively used as the input of the 2 nd dynamic recursive wavelet neural network and the corresponding input of an RBF neural network classifier, the output of the 2 nd dynamic recursive wavelet neural network is respectively used as the input of the 3 rd dynamic recursive wavelet neural network and the corresponding input of the RBF neural network classifier, the 3 rd dynamic recursive wavelet neural network is used as the corresponding input of the RBF neural network classifier, and the numbers 1-5 representing different livestock and poultry types are used as the 1 corresponding input of the RBF neural network classifier, wherein the number 1 represents a live pig, the number 2 represents a chicken, the number 3 represents a beef cattle, the number 4 represents a sheep, the number 5 represents a pigeon, and the trapezoidal fuzzy number output by the RBF neural network classifier represents the temperature suitability grade; the radial basis vector of the RBF neural network classifier is H ═ H1,h2,…,hp]T，hpFor basis functions, a commonly used radial basis function in a radial basis function neural network is a gaussian function, and its expression is:
Figure BDA0002895444100000181
wherein X is the time sequence output of 2 outputs of the beat-to-beat delay line TDL, C is the coordinate vector of the central point of the Gaussian basis function of the neuron in the hidden layer, and deltajThe width of the Gaussian base function of the jth neuron of the hidden layer; the output connection weight vector of the network is wijThe output expression of the RBF neural network classifier is as follows:
Figure BDA0002895444100000182
the trapezoidal fuzzy number output by the RBF neural network classifier represents the level value of the environment temperature suitability of the livestock and poultry house; according to the engineering practice of the livestock and poultry house temperature on the livestock and poultry growth suitability, the RBF neural network classifier divides the influence degree of the livestock and poultry house environment temperature on the livestock and poultry growth process into 5 suitability grades, the 5 suitability grades are respectively generally suitable, relatively suitable, very suitable, unsuitable and very unsuitable and respectively correspond to 5 different trapezoidal fuzzy numbers, a corresponding relation table of the 5 trapezoidal fuzzy numbers and the 5 suitability grades is constructed, the similarity between the trapezoidal fuzzy number output by the RBF neural network classifier and the 5 trapezoidal fuzzy numbers representing the 5 suitability grades is calculated, the suitability grade corresponding to the trapezoidal fuzzy number with the maximum similarity is determined as the livestock and poultry house environment temperature suitability grade, and the corresponding relation between the livestock and poultry house temperature on the livestock and poultry growth suitability and the trapezoidal fuzzy numbers is shown as table 1.
TABLE 1 corresponding relationship table of environment temperature suitability grade and trapezoidal fuzzy number of livestock and poultry house
Serial number Suitability rating Fuzzy number of trapezoid
1 Is generally suitable for (0.0，0.05，0.15，0.3)
2 Is relatively suitable (0.1，0.15，0.3，0.4)
3 Is very suitable for (0.3，0.35，0.45，0.7)
4 Is not suitable for (0.6，0.75，0.8，0.9)
5 Is very unsuitable for (0.8，0.85，0.9，1.0)
Fifth, design example of livestock and poultry house environment temperature detection system based on cloud platform
According to the actual condition of the livestock and poultry house big data detection system, a plane layout installation diagram of detection nodes, gateway nodes and a field monitoring end of the livestock and poultry house parameter acquisition platform is arranged in the system, sensors of the detection nodes are evenly arranged in all directions of the livestock and poultry house according to detection requirements, and the acquisition of the parameters of the livestock and poultry house is 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 (6)

1. The utility model provides a livestock and poultry house ambient temperature detecting system based on cloud platform which characterized in that: the detection system consists of an animal house environment parameter acquisition and control platform and an animal house environment temperature big data processing subsystem, and realizes the functions of acquiring, processing and predicting the animal house breeding environment parameters;
the livestock and poultry house environment temperature big data processing subsystem comprises a temperature detection unit and a temperature grade classifier, the outputs of a plurality of temperature sensors are respectively the inputs of a plurality of corresponding beat delay lines TDL of the temperature detection unit, the trapezoidal fuzzy number of the temperatures of the livestock and poultry in the nursery period, the trapezoidal fuzzy number of the temperatures in the growing period and the trapezoidal fuzzy number of the temperatures of the fattening period output by the temperature detection unit in different growth stages of the livestock and poultry are used as the inputs of the corresponding beat delay lines TDL of the temperature classifier, and the trapezoidal fuzzy number output by the temperature classifier represents the temperature suitability grade of the livestock and poultry house.
2. The system for detecting the environmental temperature of the livestock and poultry house based on the cloud platform as claimed in claim 1, wherein: the temperature detection unit comprises a beat delay line TDL, a NARX neural network temperature model, a DRNN neural network model, an FLNN neural network model, an ANFIS neural network model, integral loops and a GMDH neural network model, wherein 2 integral operators S are connected in series to form one integral loop, the output of the connecting end of 2 integral operators of each integral loop is used as the corresponding input of the GMDH neural network model, and the output of each integral loop is used as the corresponding input of the GMDH neural network model; the temperature sensor output is respectively used as the input of a plurality of corresponding beat delay lines TDL, the temperature sensor value of a period of time output by each beat delay line TDL is respectively used as the input of a corresponding NARX neural network temperature model, the output of the NARX neural network temperature model is respectively used as the input of a DRNN neural network model, a FLNN neural network model and an ANFIS neural network model, the output of the DRNN neural network model, the FLNN neural network model and the ANFIS neural network model are respectively used as the input of each corresponding integration loop and the corresponding input of the GMDH neural network model, the output of the GMDH neural network model is a trapezoidal fuzzy number representing the magnitude of a plurality of temperature sensor values in a period of time of livestock and poultry house environment and is output as a temperature detection unit, and the temperature detection unit converts the temperature sensor values of a period of time into temperature trapezoidal fuzzy values.
3. The system for detecting the environmental temperature of the livestock and poultry house based on the cloud platform as claimed in claim 1 or 2, wherein: the temperature grade classifier comprises a beat delay line TDL, a dynamic recursive wavelet neural network, a self-associative neural network and a RBF neural network classifier, wherein the temperature trapezoidal fuzzy number, the growth period temperature trapezoidal fuzzy number and the fattening period temperature trapezoidal fuzzy number output by the temperature detection unit at different growth stages of the livestock and poultry are respectively used as the input of the corresponding beat delay line TDL of the temperature classifier, the livestock and poultry house temperature trapezoidal fuzzy number output by the beat delay line TDL for a period of time is respectively used as the input of the corresponding self-associative neural network, and the output of the self-associative neural network is respectively used as the input of the corresponding dynamic recursive wavelet neural network.
4. The livestock and poultry house environment temperature detection system based on the cloud platform as claimed in claim 3, wherein: the 1 st dynamic recursive wavelet neural network output is respectively used as the 2 nd dynamic recursive wavelet neural network input and the corresponding input of the RBF neural network classifier, the 2 nd dynamic recursive wavelet neural network output is respectively used as the 3 rd dynamic recursive wavelet neural network input and the corresponding input of the RBF neural network classifier, the 3 rd dynamic recursive wavelet neural network is used as the corresponding input of the RBF neural network classifier, numbers representing different livestock and poultry species are used as the corresponding input of the RBF neural network classifier, and the trapezoidal fuzzy number output by the RBF neural network classifier represents the temperature suitability level.
5. The livestock and poultry house environment temperature detection system based on the cloud platform as claimed in claim 4, wherein: the RBF neural network classifier divides the influence degree of the environment temperature of the livestock and poultry house on the livestock and poultry growth process into 5 suitability grades, the 5 suitability grades are respectively generally suitable, relatively suitable, very suitable, unsuitable and very unsuitable and respectively correspond to 5 different trapezoidal fuzzy numbers, a corresponding relation table of the 5 trapezoidal fuzzy numbers and the 5 suitability grades is established, the similarity between the trapezoidal fuzzy number output by the RBF neural network classifier and the 5 ladder numbers representing the 5 suitability grades is calculated, and the suitability grade corresponding to the trapezoidal fuzzy number with the maximum similarity is determined as the suitability grade of the environment temperature of the livestock and poultry house.
6. The system for detecting the environmental temperature of the livestock and poultry house based on the cloud platform as claimed in claim 1 or 2, wherein: the livestock and poultry house environmental parameter acquisition and control platform comprises detection nodes, control nodes, gateway nodes, a field monitoring end, a cloud platform and a mobile end App of the livestock and poultry house environmental parameters, and the detection nodes, the control nodes and the gateway nodes are communicated by constructing a CAN communication network; the detection node sends the detected environment parameters of the livestock and poultry house to an on-site monitoring end through a communication interface of the gateway node, and the on-site monitoring end manages the sensor data and predicts the temperature; the gateway node realizes bidirectional transmission of the livestock and poultry house environmental parameters between the communication module and the cloud platform and between the cloud platform and the mobile terminal App through the wireless network, and the gateway node realizes bidirectional transmission of the livestock and poultry house environmental parameters between the field monitoring terminal and the field monitoring terminal through the communication interface; the mobile terminal App provides real-time inquiry of the environment data and the historical data of the livestock and poultry house for managers, and the managers can remotely check the current environment parameters of the livestock and poultry house through the mobile terminal APP; the cloud platform is mainly responsible for processing, storing, analyzing and displaying the received environment parameters of the livestock and poultry house.
CN202110041246.3A 2021-01-13 2021-01-13 Livestock and poultry house ambient temperature detection system based on cloud platform Pending CN112906856A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110041246.3A CN112906856A (en) 2021-01-13 2021-01-13 Livestock and poultry house ambient temperature detection system based on cloud platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110041246.3A CN112906856A (en) 2021-01-13 2021-01-13 Livestock and poultry house ambient temperature detection system based on cloud platform

Publications (1)

Publication Number Publication Date
CN112906856A true CN112906856A (en) 2021-06-04

Family

ID=76112708

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110041246.3A Pending CN112906856A (en) 2021-01-13 2021-01-13 Livestock and poultry house ambient temperature detection system based on cloud platform

Country Status (1)

Country Link
CN (1) CN112906856A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115016275A (en) * 2022-06-17 2022-09-06 淮阴工学院 Intelligent feeding and livestock and poultry house big data internet of things system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115016275A (en) * 2022-06-17 2022-09-06 淮阴工学院 Intelligent feeding and livestock and poultry house big data internet of things system
CN115016275B (en) * 2022-06-17 2023-06-06 淮阴工学院 Intelligent feeding and livestock house big data Internet of things system

Similar Documents

Publication Publication Date Title
CN112906735B (en) Domestic fungus environment big data detecting system
CN110647979B (en) Greenhouse environment multi-parameter intelligent monitoring system based on Internet of things
CN110084417B (en) Intelligent strawberry greenhouse environment parameter monitoring system based on GRNN neural network
CN107085732B (en) Cowshed environment ammonia intelligent monitoring system based on wireless sensor network
CN110705757B (en) Multi-point temperature sensor intelligent monitoring system based on field bus network
CN110109193B (en) Intelligent eggplant greenhouse temperature detection device based on DRNN 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
CN115016276B (en) Intelligent water content adjustment and environment parameter Internet of things big data system
CN110119086B (en) Tomato greenhouse environmental parameter intelligent monitoring device based on ANFIS neural network
CN110766132B (en) Orchard yield intelligent prediction system based on Internet of things
CN113031555B (en) Intelligent purification system for harmful gas in environment of livestock and poultry house
CN111476278B (en) Intelligent gas concentration detection system
CN113281465A (en) Livestock and poultry house breeding environment harmful gas detection system
CN113126676A (en) Livestock and poultry house breeding environment parameter intelligent control system
CN112862256A (en) Big data detection system of beasts and birds house environment
CN110083190A (en) A kind of green pepper greenhouse intelligent monitor system based on subtractive clustering classifier
CN110119767A (en) A kind of cucumber green house temperature intelligent detection device based on LVQ neural network
CN116029435B (en) Environmental comfort early warning system is bred to live pig facility
CN112903929A (en) Food quality detection system
CN113065749A (en) Building material's curing room environment intelligent system
CN115128978A (en) Internet of things environment big data detection and intelligent monitoring system
CN114418183B (en) Livestock and poultry health sign big data internet of things detection system
CN110119165B (en) Aquaculture pond dissolved oxygen detection device
CN112911533B (en) Temperature detection system based on remove end App

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