CN109235793A - A kind of intelligent rain shed system and its control method based on deep learning - Google Patents

A kind of intelligent rain shed system and its control method based on deep learning Download PDF

Info

Publication number
CN109235793A
CN109235793A CN201811209786.2A CN201811209786A CN109235793A CN 109235793 A CN109235793 A CN 109235793A CN 201811209786 A CN201811209786 A CN 201811209786A CN 109235793 A CN109235793 A CN 109235793A
Authority
CN
China
Prior art keywords
deep learning
awning
executive device
learning model
control
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201811209786.2A
Other languages
Chinese (zh)
Other versions
CN109235793B (en
Inventor
吴端坡
段文昊
丁颖铖
邢懿鹏
费丹丽
张鹤
许刘蓉
吴端榆
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.)
Hangzhou Dianzi University
Hangzhou Electronic Science and Technology University
Original Assignee
Hangzhou Electronic Science and Technology University
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 Hangzhou Electronic Science and Technology University filed Critical Hangzhou Electronic Science and Technology University
Priority to CN201811209786.2A priority Critical patent/CN109235793B/en
Publication of CN109235793A publication Critical patent/CN109235793A/en
Application granted granted Critical
Publication of CN109235793B publication Critical patent/CN109235793B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • EFIXED CONSTRUCTIONS
    • E04BUILDING
    • E04FFINISHING WORK ON BUILDINGS, e.g. STAIRS, FLOORS
    • E04F10/00Sunshades, e.g. Florentine blinds or jalousies; Outside screens; Awnings or baldachins
    • DTEXTILES; PAPER
    • D06TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
    • D06FLAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
    • D06F57/00Supporting means, other than simple clothes-lines, for linen or garments to be dried or aired 
    • D06F57/08Folding stands
    • D06F57/10Folding stands of the lazy-tongs type
    • DTEXTILES; PAPER
    • D06TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
    • D06FLAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
    • D06F57/00Supporting means, other than simple clothes-lines, for linen or garments to be dried or aired 
    • D06F57/12Supporting means, other than simple clothes-lines, for linen or garments to be dried or aired  specially adapted for attachment to walls, ceilings, stoves, or other structures or objects
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00Programme-control systems
    • G05B19/02Programme-control systems electric
    • G05B19/04Programme control other than numerical control, i.e. in sequence controllers or logic controllers
    • G05B19/042Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00Program-control systems
    • G05B2219/20Pc systems
    • G05B2219/26Pc applications
    • G05B2219/2613Household appliance in general
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02ATECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00Adapting or protecting infrastructure or their operation
    • Y02A30/24Structural elements or technologies for improving thermal insulation
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02BCLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B80/00Architectural or constructional elements improving the thermal performance of buildings

Landscapes

  • Engineering & Computer Science (AREA)
  • Architecture (AREA)
  • Textile Engineering (AREA)
  • Civil Engineering (AREA)
  • Structural Engineering (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The present invention is a kind of intelligent rain shed system based on deep learning, including at least awning executive device, cloud server and mobile terminal, wherein, the awning executive device wirelessly accesses cloud server, for acquiring current environment parameter and being sent to cloud server;Controlling model is arranged in the cloud server, and the Controlling model uses deep learning model, for exporting control instruction according to current environment parameter so that the awning executive device executes corresponding operating;Mobile terminal remote access cloud server is to obtain the current working status of the awning executive device or remotely control the awning executive device.

Description

A kind of intelligent rain shed system and its control method based on deep learning
Technical field
The present invention relates to the communication technology and field of computer technology more particularly to a kind of intelligent rain sheds based on deep learning System and its control method.
Background technique
Currently, indoor clothing too occupied space, and outdoor dry in the air clothing exist because of Changes in weather caused by rainwater drench etc. and to cause The problem of property loss or other negative effects.Such as in some cases, weather is rain or shine indefinite, when sunny weather It gives the clothes an airing, can also encounter the rainy situation of burst, at this time people will occur having little time the case where collecting clothes outgoing.
Traditional intelligent rain shed only obtains environmental parameter by single-sensor and automatically controls to realize, leads to precise control Degree is not high, once encountering the situation of weather complexity, does not just have good practicability.With the rapid hair of internet science and technology Exhibition, technology of Internet of things serve people at more and more aspects, save manpower and material resources for people.The intelligence under Internet of Things framework Awning exactly is used to solve above-mentioned technical problem.Meanwhile intelligent rain shed also can be used as the important composition portion in smart home system Point, it applies in school, private or public place.
Summary of the invention
The purpose of the present invention is to propose to a kind of intelligent rain shed system and its control method based on deep learning, by cloud Controlling model is set on the server of end, so as to identify current weather conditions according to the parameter high accuracy currently acquired, and Automatically select the awning control model of suitable current weather.
In order to solve technical problem of the existing technology, technical scheme is as follows:
A kind of intelligent rain shed system based on deep learning includes at least awning executive device, cloud server and shifting Dynamic terminal, wherein the awning executive device wirelessly accesses cloud server, concurrent for acquiring current environment parameter Give cloud server;Controlling model is arranged in the cloud server, and the Controlling model uses deep learning model, is used for root Control instruction is exported according to current environment parameter so that the awning executive device executes corresponding operating;The mobile terminal remote connects Enter cloud server to obtain the current working status of the awning executive device or remotely control the awning executive device;
The awning executive device further comprises awning main body (1), and telescopic clothes airing frame is arranged in the awning main body (1) (7);Motor (2) in clothes hanger (7) side is set, and the control unit (3) for controlling motor (2);Control unit (3) It further comprise the electric machine controller (4) being connect with motor (2), single-chip microcontroller (5), rainwater inductor (6), WIFI module (8), temperature Humidity sensor (9), light intensity sensor (10) and camera (11);
The deep learning model utilizes the rainwater inductor (6) of system, Temperature Humidity Sensor (9), light intensity sensor (10) it can reflect the parameter of weather conditions to obtain with camera (11) collected information and make sample collection, based on this Training deep learning model parameter;Judged corresponding to information parameter currently entered by trained deep learning model Weather pattern simultaneously exports control instruction with this.
APP program matched with control system, the APP program is arranged in the mobile phone terminal as a preferred technical solution, Instruction comprising control motor positive and inverse shows current awning state (stretch/pack up) and receives and show temperature and humidity and light Strong instruction.
The electric machine controller uses TB6600 electric machine controller as a preferred technical solution,.
The single-chip microcontroller uses STM32 single-chip microcontroller as a preferred technical solution,.
The WIFI module uses ESP8266WIFI module as a preferred technical solution,.
The Temperature Humidity Sensor uses DHT11 Temperature Humidity Sensor as a preferred technical solution,;The light intensity sensing Device uses TSL2561 light intensity sensor.
In order to solve technical problem of the existing technology, the present invention proposes a kind of intelligent rain shed system based on deep learning The control method of system, comprising the following steps:
Step S1: awning executive device obtains current environment parameter and is sent to cloud server;
Step S2: current environment parameter is inputted the Controlling model to set within it and export control by cloud server to be referred to It enables, wherein the Controlling model uses deep learning model;
Step S3: awning executive device receives control instruction and executes corresponding operating;
Wherein, the deep learning model is realized by following steps:
Step S21: training samples information obtains:
It is adopted using the rainwater inductor (6) of system, Temperature Humidity Sensor (9), light intensity sensor (10) and camera (11) The acquisition of information collected can reflect the parameter of weather conditions and make sample collection, and sample size included in sample set is no less than 1000;A large amount of training is carried out to deep learning model using training sample set so as to accurately export the shape of current weather Condition parameter;
Step S22: collected sample training deep learning model is used:
The parameter that all training samples are extracted instructs deep learning model as the input of deep learning model Practice;
Step S23: acquiring environmental parameter in real time, and data are sent to long-range clothes by WIFI network using ICP/IP protocol It is engaged in device;
Step S24: weather corresponding to information parameter currently entered is judged by trained deep learning model Type;
Step S25: according to the weather pattern judged, server sends control instruction to awning by wireless network and executes Device.
It is further comprising the steps of as a preferred technical solution:
Cloud server by the work state information of awning executive device by wireless network be sent to mobile phone terminal or Receive the control command that mobile phone terminal is sent and the working condition that awning executive device is controlled with this.
APP program matched with control system is arranged in mobile phone terminal as a preferred technical solution, which includes It controls the instruction of motor positive and inverse, the current awning state (stretch/pack up) of display and receives and show temperature and humidity and light intensity Instruction.
Deep learning model uses the AlexNet/ of the deep learning model of existing maturation as a preferred technical solution, It is any in ResNet/GoogleNet.
Compared with prior art, the invention has the following beneficial effects:
Since Controlling model is arranged on server beyond the clouds, so as to according to the parameter high accuracy identification currently acquired Current weather conditions, and automatically select the awning control model of suitable current weather;User's drying article is solved perfectly rain or shine Under indefinite weather because of the reason of rainwater caused by property damage the problem of, allow user is away from home all the time all need not be again Because worrying that weather reason damages the property of oneself, while there is the clothes hanger of Telescopic can save the interior space.
Detailed description of the invention
Fig. 1 is that the present invention is based on the structural schematic diagrams of the intelligent rain shed system of deep learning.
Fig. 2 is that the present invention is based on the flow charts of the intelligent rain shed system control method of deep learning.
Fig. 3 is the flow diagram of deep learning model in the present invention.
Fig. 4 is each functional module logic chart of intelligent rain shed system of the present invention.
The structure chart of deep learning network in the present invention of the position Fig. 5.
Following specific implementation will further illustrate the present invention in conjunction with above-mentioned attached drawing.
Specific embodiment:
Referring to Fig. 1 and 4, it is shown a kind of structural schematic diagram of the intelligent rain shed system based on deep learning of the present invention, until It less include awning executive device, cloud server and mobile terminal, wherein the awning executive device wirelessly accesses Cloud server, for acquiring current environment parameter and being sent to cloud server;Controlling model is arranged in the cloud server, The Controlling model uses deep learning model, for exporting control instruction according to current environment parameter so that the awning executes Device executes corresponding operating;The mobile terminal remote accesses cloud server to obtain the current work of the awning executive device Make state or remotely controls the awning executive device;
Further, the awning executive device further comprises awning main body (1), is arranged in the awning main body (1) and stretches Contracting clothes hanger (7);Motor (2) in clothes hanger (7) side is set, and the control unit (3) for controlling motor (2);Control Unit (3) processed further comprises the electric machine controller (4), single-chip microcontroller (5), rainwater inductor (6), WIFI connecting with motor (2) Module (8), Temperature Humidity Sensor (9), light intensity sensor (10) and camera (11);
Wherein, deep learning model utilizes the rainwater inductor (6) of system, Temperature Humidity Sensor (9), light intensity sensor (10) it can reflect the parameter of weather conditions to obtain with camera (11) collected information and make sample collection, based on this Training deep learning model parameter;Judged corresponding to information parameter currently entered by trained deep learning model Weather pattern simultaneously exports control instruction with this.
In a preferred embodiment, according to the present invention to need for weather to be divided into 3 seed types: excellent weather (sunny, Cloudy weather), ugly sky (weather such as light rain), bad weather (weather such as violent storm) further works awning shape State is divided into 3 seed types: can be sufficiently by the state of illumination in order to make to give the clothes an airing under good weather --- and awning is shunk, and dry in the air clothing Frame stretching, extension;For the state that guarantee clothing is not drenched by rainwater under rainy weather --- awning stretching, extension, clothes hanger stretching, extension;In order to The state that clothing is not drenched is further ensured that under the bad weather of strong wind and heavy rain --- awning stretching, extension, clothes hanger are shunk.3 kinds Weather pattern respectively corresponds 3 kinds of different awning system use states: excellent weather --- and awning is shunk, clothes hanger stretching, extension;Yin Heavy weather --- awning stretching, extension, clothes hanger stretching, extension;Bad weather --- awning stretching, extension, clothes hanger are shunk.
Further, APP program matched with control system is arranged in mobile phone terminal, which includes to control motor just Instruction, the current awning state (stretch/pack up) of display and the instruction for receiving and showing temperature and humidity and light intensity of reversion.Meanwhile Cloud server sends mobile phone terminal APP by wireless network for awning work state information and shows.User opens cell phone application, And network is connected, APP will be got information by network and be shown on a user interface, and by clicking APP Shang couple The key of clothes hanger stretch/shrink should be controlled, to control motor positive and inverse, remotely to realize the Telescopic of clothes hanger.
Specifically, user can decide whether telescopic clothes airing frame according to the weather condition shown on APP, user clicks APP The key of upper corresponding control clothes hanger stretch/shrink, corresponding instruction is sent to the WIFI module on single-chip microcontroller by network, then passes through string Mouth is sent to MCU, after MCU is received from clothes hanger stretching, extension/contraction signal that mobile phone terminal transmits, will be transmitted by gpio interface Control command is to electric machine controller, to control motor positive and inverse, motor shaft end controls clothes-horse by the rotation of idler wheel Litter it is elastic, to realize the Telescopic of clothes hanger.
The DHT11 Temperature Humidity Sensor that system uses as a preferred technical solution, acquires ring with dedicated digital module The temperature humidity information in border is simultaneously stored as digital signal, transmits data in single-chip microcontroller and is stored in variable.DHT11 and place Managing device single communication time is 4ms or so, and primary complete data are transmitted as 40bits:8bits humidity integer data+8bits Humidity fraction data+8bits temperature integer data+8bits temperature fraction data+8bits verification and.
The TSL2561 light intensity sensor that system uses is light-digital quantizer, and it is defeated that light intensity is converted into digital signal by it Out, there is direct I2C interface or SMBus interface.Light-dependent current is converted into a number by two integrated analog-digital converters Output, integration type analog-digital converter integrates the electric current for flowing through photodiode, and is converted to digital quantity, in conversion end Transformation result is stored in chip interior channel 0 and the respective register in channel 1 afterwards, then this numeral output is input to processing It is saved in device.
Further, the collected data information of sensor is sent to WIFI module by serial ports by MCU, passes through WIFI mould Block is reported to cloud server.User opens cell phone application, and connects network, and APP will obtain the light of acquisition by server By force, it temperature and humidity information and shows on a user interface.The end APP can obtain local weather forecast information simultaneously from network Real-time display is on interface.On a user interface, it can be observed that real time temperature, humidity, light intensity and current rain shade shape State (unlatching/closing), can also learn local weather forecast information.User can judge to work as the day before yesterday according to gained information data Vaporous condition, to voluntarily judge whether to need to open rain shade or whether need to close rain shade, and by user interface (unlatching/closing) key realize operation, specifically, user can work as mobile phone by pressing the opening by key control rain shade After APP receives the demand of user, this control instruction (open command 1, out code 0) is issued to WIFI by cloud Module, WIFI module are sent to MCU by serial ports, and MCU can control stepper motor according to the instruction issued, stepper motor Signal input port can receive a pulse signal, and (the positive and negative and length of pulse signal is respectively depending on switch operation and touching Press the time), after receiving pulse signal, stepper motor responds this pulse signal, can finally realize that APP is remotely supervised in real time Control weather conditions and the Push And Release for controlling rain shade.
Referring to fig. 2 with 3, it show the control method of the intelligent rain shed the present invention is based on deep learning comprising the steps of:
Step S1: awning executive device obtains current environment parameter and is sent to cloud server;
Step S2: current environment parameter is inputted the Controlling model to set within it and export control by cloud server to be referred to It enables, wherein the Controlling model uses deep learning model;
Step S3: awning executive device receives control instruction and executes corresponding operating;
Wherein, the deep learning model is realized by following steps:
Step S21: training samples information obtains:
It is adopted using the rainwater inductor (6) of system, Temperature Humidity Sensor (9), light intensity sensor (10) and camera (11) The sample that the photo collected obtains weather conditions makes sample collection, and sample size included in sample set is no less than 1000. Deep learning model is largely trained using training sample set, it is ensured that training is accurate, so as to accurately export The condition parameter of current weather.
Specifically, the situation in order to identify current weather from photo, can pass through the thickness of the sky cloud layer from photo It spends and the brightness of whole photo is judged, the method used in the present embodiment are as follows: first use scene classifier from figure to be identified Sky image is detected as in, the sky image of preceding acquisition is handled, and can be the contrast of enhancing image, or can be with It is to be sharpened to image, then extracts the feature by processing image, weather conditions are obtained by algorithm.It is passed in conjunction with temperature and humidity The temperature humidity data of sensor acquisition, the collected light intensity parameter of light intensity sensor make sample.
Step S22: collected sample training deep learning model is used
The parameter that all training samples are extracted is trained deep learning model as the input of deep learning model
Deep learning model includes multiple structure sheafs, is sequentially connected between layers, upper one layer of output will be by as under One layer of input, to constitute a structure end to end, used deep learning model be can choose existing here Mature one kind, such as AlexNet/ResNet/GoogleNet of deep learning model etc..
Deep learning network is divided into: input layer, hidden layer and output layer,
Input layer is the data set that rainwater sensed parameter, temperature and humidity, intensity of illumination and the weather image data of acquisition obtain, Using data set as the input of the deep learning model.
Hidden layer includes convolutional layer, pond layer and full articulamentum.
Use the data of first layer acquisition as the input data of the second layer, to obtain the spy for having more expression ability than input Sign.
After study obtains n-th layer, by the input of n-th layer exported as (n+1)th layer, by constantly training, finally Output can accurately indicate the feature of current weather conditions
Output layer exports the weather recognition result of three types, and every kind of weather pattern corresponds to a kind of awning control action, Training stage, this weather pattern are carried out thinking to mark by user.
Step S23: acquisition rainwater sensed parameter in real time, temperature and humidity parameter, intensity of illumination parameter and weather image data, Data are sent in remote server by WIFI network using ICP/IP protocol.
Step S24: the environmental parameter of server end real-time reception acquisition, by trained deep learning model come to this A little data are identified, obtain corresponding weather pattern.
It is specific: by the rainwater sensed parameter of sample, data of the Temperature and Humidity module, intensity of illumination data and treated weather picture The characteristic parameter extracted is inputted into trained deep learning model, can identify weather corresponding to input parameter Type.
Step S25: according to the weather pattern judged, server sends a control signal to awning system by wireless network System controls it and transforms to corresponding use state, while and sending awning work state information at this time by wireless network It is shown to mobile phone terminal APP.
Specific: deep learning model identifies preset three kinds of weather patterns (excellent weather/ugly sky/severe day Gas) after one, server end will send its corresponding marking signal, and the WIFI mould of SCM system is sent to by wireless network Block, then microprocessor is sent to by serial ports.After system processor termination receives signal, motor control is sent a control signal to Device is realized the positive and negative rotation of the motor of control awning and clothes hanger, is then realized in preset three kinds of awning system operating modes A kind of: excellent weather corresponds to awning contraction state, clothes hanger extended state;Ugly sky corresponds to awning extended state, clothes hanger Extended state;Bad weather corresponds to awning extended state, clothes hanger contraction state.
Specific: by the rainwater sensed parameter of sample, temperature and humidity, weather picture extracts intensity of illumination data with treated Characteristic parameter out is inputted into trained deep learning model, can identify weather pattern corresponding to input parameter, The signature of final output current weather type.
Deep learning model includes multiple structure sheafs, is sequentially connected between layers, upper one layer of output will be by as under One layer of input, to constitute a structure end to end, used deep learning model be can choose existing here Mature one kind, such as AlexNet/ResNet/GoogleNet of deep learning model etc..
The present invention can realize the flexible multistage adjusting of awning by change parameter, herein be only to enumerate a kind of specific practice Situation.Specific changing mode has mature technology, does not repeat herein.
The above description of the embodiment is only used to help understand the method for the present invention and its core ideas.It should be pointed out that pair For those skilled in the art, without departing from the principle of the present invention, the present invention can also be carried out Some improvements and modifications, these improvements and modifications also fall within the scope of protection of the claims of the present invention.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one The widest scope of cause.

Claims (10)

1. a kind of intelligent rain shed system based on deep learning, which is characterized in that include at least awning executive device, cloud service Device and mobile terminal, wherein the awning executive device wirelessly accesses cloud server, for acquiring current environment Parameter is simultaneously sent to cloud server;Controlling model is arranged in the cloud server, and the Controlling model uses deep learning mould Type, for exporting control instruction according to current environment parameter so that the awning executive device executes corresponding operating;The movement Terminal remote accesses cloud server to obtain the current working status of the awning executive device or remotely control the rain Canopy executive device;
The awning executive device further comprises awning main body (1), and telescopic clothes airing frame (7) are arranged in the awning main body (1);If The motor (2) in clothes hanger (7) side is set, and the control unit (3) for controlling motor (2);Control unit (3) is further Including the electric machine controller (4), single-chip microcontroller (5), rainwater inductor (6), WIFI module (8), temperature and humidity biography being connect with motor (2) Sensor (9), light intensity sensor (10) and camera (11);
The deep learning model can reflect the parameters of weather conditions simultaneously using the collected information of awning executive device to obtain Collection is maked sample, trains deep learning model parameter based on this;Judged by trained deep learning model current Weather pattern corresponding to the information parameter of input simultaneously exports control instruction with this.
2. the intelligent rain shed system according to claim 1 based on deep learning, which is characterized in that the mobile phone terminal is set APP program matched with control system is set, which includes the instruction of control motor positive and inverse, the current awning state of display (stretch/pack up) and the instruction for receiving and showing temperature and humidity and light intensity.
3. the intelligent rain shed system according to claim 1 or 2 based on deep learning, which is characterized in that the motor control Device processed uses TB6600 electric machine controller.
4. the intelligent rain shed system according to claim 1 or 2 based on deep learning, which is characterized in that the single-chip microcontroller Using STM32 single-chip microcontroller.
5. the intelligent rain shed system according to claim 1 or 2 based on deep learning, which is characterized in that the WIFI mould Block uses ESP8266WIFI module.
6. the intelligent rain shed system according to claim 1 or 2 based on deep learning, which is characterized in that the temperature and humidity Sensor uses DHT11 Temperature Humidity Sensor;The light intensity sensor uses TSL2561 light intensity sensor.
7. a kind of control method of the intelligent rain shed system based on deep learning, which comprises the following steps:
Step S1: awning executive device obtains current environment parameter and is sent to cloud server;
Step S2: cloud server is by the Controlling model that the input of current environment parameter sets within it and exports control instruction, In, the Controlling model uses deep learning model;
Step S3: awning executive device receives control instruction and executes corresponding operating;
Wherein, the deep learning model is realized by following steps:
Step S21: training samples information obtains:
It is collected using the rainwater inductor (6) of system, Temperature Humidity Sensor (9), light intensity sensor (10) and camera (11) Acquisition of information can reflect the parameter of weather conditions and make sample collection, sample size included in sample set is no less than 1000 Item;A large amount of training is carried out to deep learning model using training sample set to join so as to accurately export the situation of current weather Number;
Step S22: collected sample training deep learning model is used:
The parameter that all training samples are extracted is trained deep learning model as the input of deep learning model;
Step S23: weather pattern corresponding to information parameter currently entered is judged by trained deep learning model;
Step S24: according to the weather pattern judged, server sends control instruction to awning by wireless network and executes dress It sets.
8. the control method of the intelligent rain shed system according to claim 7 based on deep learning, which is characterized in that also wrap Include following steps:
Cloud server sends mobile phone terminal or reception by wireless network for the work state information of awning executive device The control command of mobile phone terminal transmission and the working condition that awning executive device is controlled with this.
9. the control method of the intelligent rain shed system according to claim 8 based on deep learning, which is characterized in that mobile phone APP program matched with control system is arranged in terminal, which includes the instruction of control motor positive and inverse, the current rain of display Canopy state (stretch/pack up) and the instruction for receiving and showing temperature and humidity and light intensity.
10. the control method of the intelligent rain shed system according to claim 7 based on deep learning, which is characterized in that deep It spends any in AlexNet/ResNet/GoogleNet of the learning model using the deep learning model of existing maturation.
CN201811209786.2A 2018-10-17 2018-10-17 Intelligent canopy system based on deep learning and control method thereof Active CN109235793B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811209786.2A CN109235793B (en) 2018-10-17 2018-10-17 Intelligent canopy system based on deep learning and control method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811209786.2A CN109235793B (en) 2018-10-17 2018-10-17 Intelligent canopy system based on deep learning and control method thereof

Publications (2)

Publication Number Publication Date
CN109235793A true CN109235793A (en) 2019-01-18
CN109235793B CN109235793B (en) 2021-03-09

Family

ID=65053806

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811209786.2A Active CN109235793B (en) 2018-10-17 2018-10-17 Intelligent canopy system based on deep learning and control method thereof

Country Status (1)

Country Link
CN (1) CN109235793B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110387722A (en) * 2019-07-01 2019-10-29 珠海格力电器股份有限公司 A kind of method, apparatus and Intellective airer controlling Intellective airer
CN110528233A (en) * 2019-08-12 2019-12-03 珠海格力电器股份有限公司 A kind of method, apparatus that test article is dried and Intellective airer
CN110531673A (en) * 2019-09-09 2019-12-03 广州格绿朗遮阳篷科技有限公司 A kind of environment adjustment method and system for outdoor assembly building
CN110820287A (en) * 2019-11-29 2020-02-21 深圳市欧瑞博科技有限公司 Intelligent clothes hanger system and control method and control equipment thereof
CN111235709A (en) * 2020-03-18 2020-06-05 东华大学 Online detection system for spun yarn evenness of ring spinning based on machine vision
CN111813004A (en) * 2020-07-20 2020-10-23 广州百畅信息科技有限公司 Clothes hanger remote control system dries in air
CN113282014A (en) * 2021-04-16 2021-08-20 广州中大中鸣科技有限公司 Intelligent control method, system and device for garbage station, storage medium and garbage station
CN113463344A (en) * 2021-07-20 2021-10-01 的卢技术有限公司 Outdoor clothes hanger system based on cloud computing weather analysis and control method thereof

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010027846A1 (en) * 2000-01-31 2001-10-11 Osinga Anne J. Awning assembly and control system
WO2006033959A2 (en) * 2004-09-20 2006-03-30 Girard Systems Load detection system for motorized lateral and vertical arm awnings
CN204959405U (en) * 2015-06-03 2016-01-13 林少芬 Intelligence clothes hanger that dries in air based on thing networking
TW201621111A (en) * 2014-12-05 2016-06-16 Univ Chienkuo Technology Intelligent type clothes-airing apparatus
CN105803738A (en) * 2016-05-26 2016-07-27 三峡大学 Intelligent retractable drying rack based on internet of things
CN107169598A (en) * 2017-05-05 2017-09-15 上海斐讯数据通信技术有限公司 A kind of weather prediction method and system based on deep learning
CN107562023A (en) * 2017-08-01 2018-01-09 上海电机学院 Smart home managing and control system based on user behavior custom
CN206920839U (en) * 2017-05-03 2018-01-23 南京交通职业技术学院 Intelligent rain shed and clothes hanger
CN108469764A (en) * 2018-03-24 2018-08-31 佛山市聚成知识产权服务有限公司 A kind of balcony Internet-based keeps off the rain panel control system
CN108534325A (en) * 2017-09-27 2018-09-14 缤果可为(北京)科技有限公司 Indoor and outdoor surroundings parameter monitors regulating device and applies its unmanned convenience store automatically

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010027846A1 (en) * 2000-01-31 2001-10-11 Osinga Anne J. Awning assembly and control system
WO2006033959A2 (en) * 2004-09-20 2006-03-30 Girard Systems Load detection system for motorized lateral and vertical arm awnings
TW201621111A (en) * 2014-12-05 2016-06-16 Univ Chienkuo Technology Intelligent type clothes-airing apparatus
CN204959405U (en) * 2015-06-03 2016-01-13 林少芬 Intelligence clothes hanger that dries in air based on thing networking
CN105803738A (en) * 2016-05-26 2016-07-27 三峡大学 Intelligent retractable drying rack based on internet of things
CN206920839U (en) * 2017-05-03 2018-01-23 南京交通职业技术学院 Intelligent rain shed and clothes hanger
CN107169598A (en) * 2017-05-05 2017-09-15 上海斐讯数据通信技术有限公司 A kind of weather prediction method and system based on deep learning
CN107562023A (en) * 2017-08-01 2018-01-09 上海电机学院 Smart home managing and control system based on user behavior custom
CN108534325A (en) * 2017-09-27 2018-09-14 缤果可为(北京)科技有限公司 Indoor and outdoor surroundings parameter monitors regulating device and applies its unmanned convenience store automatically
CN108469764A (en) * 2018-03-24 2018-08-31 佛山市聚成知识产权服务有限公司 A kind of balcony Internet-based keeps off the rain panel control system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
王伟军: "《大数据分析》", 30 April 2017, 重庆大学出版社 *
王米成著: "《智能家居 重新定义生活》", 30 June 2017, 上海交通大学出版社 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110387722A (en) * 2019-07-01 2019-10-29 珠海格力电器股份有限公司 A kind of method, apparatus and Intellective airer controlling Intellective airer
CN110528233A (en) * 2019-08-12 2019-12-03 珠海格力电器股份有限公司 A kind of method, apparatus that test article is dried and Intellective airer
CN110528233B (en) * 2019-08-12 2020-11-27 珠海格力电器股份有限公司 Method and device for testing drying of articles and intelligent clothes hanger
CN110531673A (en) * 2019-09-09 2019-12-03 广州格绿朗遮阳篷科技有限公司 A kind of environment adjustment method and system for outdoor assembly building
CN110820287A (en) * 2019-11-29 2020-02-21 深圳市欧瑞博科技有限公司 Intelligent clothes hanger system and control method and control equipment thereof
CN111235709A (en) * 2020-03-18 2020-06-05 东华大学 Online detection system for spun yarn evenness of ring spinning based on machine vision
CN111813004A (en) * 2020-07-20 2020-10-23 广州百畅信息科技有限公司 Clothes hanger remote control system dries in air
CN111813004B (en) * 2020-07-20 2021-07-30 广州百畅信息科技有限公司 Clothes hanger remote control system dries in air
CN113282014A (en) * 2021-04-16 2021-08-20 广州中大中鸣科技有限公司 Intelligent control method, system and device for garbage station, storage medium and garbage station
CN113463344A (en) * 2021-07-20 2021-10-01 的卢技术有限公司 Outdoor clothes hanger system based on cloud computing weather analysis and control method thereof

Also Published As

Publication number Publication date
CN109235793B (en) 2021-03-09

Similar Documents

Publication Publication Date Title
CN109235793A (en) A kind of intelligent rain shed system and its control method based on deep learning
CN208128532U (en) A kind of multifunctional plant growth and habitat information monitoring system
CN203220229U (en) Control device and system for intelligent home electric curtain
CN105040377A (en) Intelligent clothes hanger and work method of same
CN205038546U (en) Intelligent greenhouse big -arch shelter remote monitering system of zigbee technique
CN106802585A (en) The intelligent clothes hanger and its method of drying time are estimated based on data of weather forecast
CN108239862A (en) A kind of Intellective airer
CN107942691A (en) A kind of intelligent home control system of the gesture identification with luminance compensation
CN210445075U (en) Agricultural intelligent greenhouse monitoring system based on Internet of things
CN106768067A (en) Plant monitoring system and its application method
CN209128755U (en) A kind of automatic contraction clothes hanger
CN204466002U (en) A kind of SCM Based Intelligent street lamp control system
CN206117702U (en) Intelligence house sunning system
CN208395511U (en) A kind of intelligence based on Internet of Things is dried in the air clothing system
CN203741620U (en) Control device of automatic drying device
CN208235175U (en) A kind of intelligent sound sensing control clothes-horse
CN208722009U (en) A kind of intelligent heating cup temperature control device based on STM32F103 single-chip microcontroller
CN106793281A (en) A kind of campus LED illumination intelligence control system
CN207526019U (en) A kind of Intelligent balcony sunshade rain-proof device
CN211006024U (en) Intelligent airing system based on image or machine vision recognition
CN205474477U (en) Remote intelligent retractable balcony clothes hanger that dries in air based on wiFi
CN107780172A (en) One kind can receive the system and device that hangs out automatically according to weather
CN205862184U (en) A kind of Intelligent window system
CN205359145U (en) Intelligence curtain control system
CN205563257U (en) Thing networking intelligent greenhouse observes and controls system based on labview

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