CN107965828B - The air draught condition control method and smoke exhaust ventilator of smoke exhaust ventilator - Google Patents
The air draught condition control method and smoke exhaust ventilator of smoke exhaust ventilator Download PDFInfo
- Publication number
- CN107965828B CN107965828B CN201711034512.XA CN201711034512A CN107965828B CN 107965828 B CN107965828 B CN 107965828B CN 201711034512 A CN201711034512 A CN 201711034512A CN 107965828 B CN107965828 B CN 107965828B
- Authority
- CN
- China
- Prior art keywords
- mentioned
- exhaust ventilator
- smoke
- oil smoke
- smoke exhaust
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24C—DOMESTIC STOVES OR RANGES ; DETAILS OF DOMESTIC STOVES OR RANGES, OF GENERAL APPLICATION
- F24C15/00—Details
- F24C15/20—Removing cooking fumes
- F24C15/2021—Arrangement or mounting of control or safety systems
Abstract
The invention discloses the air draught condition control methods and smoke exhaust ventilator of a kind of smoke exhaust ventilator.Wherein, this method comprises: the status information for passing through oil smoke produced by acquisition smoke exhaust ventilator；The control instruction of above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information；The air draught state of above-mentioned smoke exhaust ventilator is controlled according to above-mentioned control instruction.The present invention, which solves existing smoke exhaust ventilator, to adjust air draught state according to oil smoke concentration and distribution situation, lead to the technical problem that smoke absorption effect is bad.
Description
Technical field
The present invention relates to field of intelligent control, a kind of air draught condition control method in particular to smoke exhaust ventilator and
Smoke exhaust ventilator.
Background technique
The suction of conventional extraction hood is needed by manually controlling to adjust, for example, being set on smoke exhaust ventilator by clicking
Perhaps rotary switch increases or reduces the suction of smoke exhaust ventilator the key set, and still, only may be used by manually being manually controlled
To control the size of the suction of smoke exhaust ventilator, the oil smoke concentration and oil smoke distribution situation of smoke exhaust ventilator can not be specifically identified, adapt to
Property the problem of adjusting the air draught state of smoke exhaust ventilator, often will appear that suction is insufficient or suction excessive waste of resource.
Also, in many cases user can not the air draught state timely to smoke exhaust ventilator control is adjusted, for example,
When user's discovery needs to adjust the suction of Cooker hood, the oil smoke concentration in room may be exceeded, causes smoke exhaust ventilator
Smoking effect is bad, and then has seriously affected the health and usage experience of user.
Air draught state can not be adjusted according to oil smoke concentration and distribution situation for above-mentioned existing smoke exhaust ventilator, cause to inhale
The ineffective problem of oil smoke, currently no effective solution has been proposed.
Summary of the invention
The embodiment of the invention provides the air draught condition control methods and smoke exhaust ventilator of a kind of smoke exhaust ventilator, at least to solve
Existing smoke exhaust ventilator can not adjust air draught state according to oil smoke concentration and distribution situation, lead to the technology that smoke absorption effect is bad
Problem.
According to an aspect of an embodiment of the present invention, a kind of air draught condition control method of smoke exhaust ventilator is provided, comprising:
Obtain the status information of oil smoke produced by smoke exhaust ventilator；The control instruction of above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information；
The air draught state of above-mentioned smoke exhaust ventilator is controlled according to above-mentioned control instruction.
Further, the status information of oil smoke produced by smoke exhaust ventilator is obtained, comprising: obtain the first image of above-mentioned oil smoke
Information；Above-mentioned first image information is analyzed using the first model, determines the first state in above-mentioned first image information
Information, wherein above-mentioned first model is obtained using multi-group data by machine learning training, every in above-mentioned multi-group data
Group data include: status information corresponding to image information and image information.
Further, before the control instruction that above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information, the above method is also wrapped
It includes: obtaining the first oil smoke concentration for passing through oil smoke concentration detector test；By above-mentioned first concentration and above-mentioned first state information
In the second oil smoke concentration be compared；In above-mentioned first concentration and the difference of above-mentioned second oil smoke concentration less than the first default threshold
When value, triggering determines the control instruction of above-mentioned smoke exhaust ventilator.
Further, before the control instruction that above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information, the above method is also wrapped
It includes: obtaining the second image information of above-mentioned oil smoke, wherein above-mentioned second image information and above-mentioned first image information are from difference
The image information that angle acquires simultaneously；Above-mentioned second image information is analyzed using the first model, determines above-mentioned second figure
As the second status information in information, wherein above-mentioned first model is obtained using multi-group data by machine learning training,
Every group of data in above-mentioned multi-group data include: status information corresponding to image information and image information；According to above-mentioned shape
State information determines the control instruction of above-mentioned smoke exhaust ventilator, comprising: more above-mentioned first state information and above-mentioned second status information,
And when the difference of above-mentioned first state information and above-mentioned second status information is less than the second preset threshold, from above-mentioned first state
A status information is selected in information and above-mentioned second status information；Status information according to selection determines above-mentioned control instruction.
Further, above-mentioned status information includes: the distributed areas of the concentration of above-mentioned oil smoke, above-mentioned oil smoke.
Further, the control instruction of above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information, comprising: determining and above-mentioned shape
Corresponding first instruction of the concentration of above-mentioned oil smoke in state information, wherein carry target air volume value in above-mentioned first instruction；Foundation
Above-mentioned control instruction controls the air draught state of above-mentioned smoke exhaust ventilator, comprising: according to the target air volume value tune in above-mentioned first instruction
The airflow value of whole above-mentioned smoke exhaust ventilator.
Further, above-mentioned target air volume value determines in the following manner: obtaining the concentration of above-mentioned oil smoke；Use third mould
Type analyzes the concentration of above-mentioned oil smoke, determines the corresponding airflow value of the concentration of above-mentioned oil smoke, wherein above-mentioned third model is
It is obtained using multi-group data by machine learning training, every group of data in above-mentioned multi-group data include: the concentration of oil smoke
With airflow value corresponding with the concentration of oil smoke.
Further, the control instruction of above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information, comprising: in above-mentioned smoke pumping
When machine is provided with smoke deflector, the second instruction corresponding with the distributed areas of above-mentioned oil smoke in above-mentioned status information is determined, wherein on
State the target aperture that smoke deflector is carried in the second instruction；The air draught shape of above-mentioned smoke exhaust ventilator is controlled according to above-mentioned control instruction
State, comprising: the aperture of above-mentioned smoke deflector is adjusted according to the target aperture in above-mentioned second instruction.
Further, above-mentioned target aperture determines in the following manner: obtaining the distributed areas of above-mentioned oil smoke；Use the 4th
Model analyzes the distributed areas of above-mentioned oil smoke, determines the corresponding aperture in the distributed areas of above-mentioned oil smoke, wherein above-mentioned
Four models are obtained using multi-group data by machine learning training, and every group of data in above-mentioned multi-group data include: oil
The distributed areas of cigarette and target aperture corresponding with the distributed areas of oil smoke.
According to another aspect of an embodiment of the present invention, a kind of smoke exhaust ventilator is additionally provided, comprising: image collecting device is used
In the image information for obtaining oil smoke produced by smoke exhaust ventilator, and from above-mentioned image information extract oil smoke status information；Processing
Device, for determining the control instruction of above-mentioned smoke exhaust ventilator according to above-mentioned status information；And according in the control of above-mentioned control instruction
State the air draught state of smoke exhaust ventilator.
In embodiments of the present invention, by the way of intelligent control, by the state for obtaining oil smoke produced by smoke exhaust ventilator
Information；The control instruction of above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information；Above-mentioned oil pumping is controlled according to above-mentioned control instruction
The air draught state of smoke machine has reached the purpose that the air draught state of above-mentioned smoke exhaust ventilator is controlled according to oil smoke concentration and distribution situation,
To realize improve kitchen ventilator smoke absorption effect, reduce the technical effect of energy consumption, so solve existing smoke exhaust ventilator without
Method adjusts air draught state according to oil smoke concentration and distribution situation, leads to the technical problem that smoke absorption effect is bad.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is a kind of step flow chart of the air draught condition control method of smoke exhaust ventilator according to an embodiment of the present invention；
Fig. 2 is a kind of step process of the air draught condition control method of optional smoke exhaust ventilator according to an embodiment of the present invention
Figure；
Fig. 3 is a kind of structural schematic diagram of smoke exhaust ventilator according to an embodiment of the present invention；And
Fig. 4 is a kind of structural schematic diagram of the air draught behavior control device of smoke exhaust ventilator according to an embodiment of the present invention.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
Firstly, understand the embodiment of the present invention for convenience, below will to part term involved in the present invention or noun into
Row illustrates:
Pixel: being the minimum unit that can be shown on computer screen, for indicating the unit of image, referring to can be shown
Horizontal and vertical pixel array, the pixel in screen is more, and the resolution ratio of picture is higher, and image is finer and smoother and forces
Very；Pixel: refer to the numerical value of pixel.
Binaryzation: refer to the picture to camera shooting, most of is color image, and color image information contained amount is huge
Greatly, for the content of picture, it can simply be divided into prospect and background, first cromogram is handled, picture is made there was only prospect
Information and background information, can simply define foreground information is black, and background information is white, and here it is binary pictures.
CNN: convolutional neural networks refer to that the operation described to input picture, one group of output describe point of picture material
Class or the probability of classification, i.e., identify the image of input, to export the probability of the object in image；Pass through a series of convolution
Level builds up more abstract concept, including establishes multiple neurons, and establishes corresponding input layer and output layer, thus will
The node of input is constantly associated with by neuron, is obtained optimization object, generally be will include convolutional layer, filter layer, by preceding to biography
Lead, loss function, backward conduction and function are updated as a learning cycle, to each trained picture, program will repeat solid
Fixed number purpose periodic process, to continue to optimize trained learning outcome.
To scheme to search figure: referring to after getting image, be ranked up by deep learning to result, and pass through user record
Triple data (inquiry picture, click picture and do not click on picture) the sequence loss function that carrys out training pattern, to obtain
Ranking results, after image is opened in input one, model can detect main body automatically, and it is related right to be then discharged according to ranking score height
The result of elephant.
Transfer learning: essence is images match, is applied model in every field by transfer learning, specifically data
The vector representation X of picture in library is moved on the image X1 in other field by linear transformation, by quoting random Fourier
Migration transformation is changed into nonlinear function, the image then needed by function.
Naive Bayesian: being to show a picture, can be classified with returning an object value, using picture recognition as a simple state
Degree, to obtain corresponding object.
Dependency grammar: referring to the relationship between building subject term and the word for describing subject term, do not have in dependency grammar phrase this
Level, each node is corresponding with the word in sentence, can directly handle the relationship in sentence between word and word, in order to
Analysis and information extraction.
Decision tree: referring to and classified according to feature, and each node proposes a problem, splits data into two classes, and after
Continuous to put question to, these problems are the learning trainings in existing data, with when putting into new data, according on the tree where data
The problem of, data are divided on corresponding leaf.
Deep learning: being a kind of method based on to data progress representative learning in machine learning, concept is derived from artificial mind
Research through network, motivation are that foundation, simulation human brain carry out the neural network of analytic learning, and the mechanism that it imitates human brain is come
Explain data, such as image, sound and text.By combination low-level feature formed it is more abstract it is high-rise indicate attribute classification or
Feature, to find that the distributed nature of data indicates, the multilayer perceptron containing more hidden layers is exactly a kind of deep learning structure.
KNN algorithm: if the k in feature space most like samples (i.e. closest in feature space) of a sample
In it is most of belong to some classification, then the sample also belongs to this classification.In KNN algorithm, selected neighbours are
Object through correctly classifying.
Embodiment 1
According to embodiments of the present invention, a kind of air draught condition control method embodiment of smoke exhaust ventilator is provided, needs to illustrate
, step shown in the flowchart of the accompanying drawings can hold in a computer system such as a set of computer executable instructions
Row, although also, logical order is shown in flow charts, and it in some cases, can be to be different from sequence herein
Execute shown or described step.
Fig. 1 is according to a kind of step flow chart of the air draught condition control method of smoke exhaust ventilator of the embodiment of the present application, such as
Shown in Fig. 1, this method comprises the following steps:
Step S102 obtains the status information of oil smoke produced by smoke exhaust ventilator；
Step S104 determines the control instruction of above-mentioned smoke exhaust ventilator according to above-mentioned status information；
Step S106 controls the air draught state of above-mentioned smoke exhaust ventilator according to above-mentioned control instruction.
In the embodiment of the present application, by the way of intelligent control, by the state for obtaining oil smoke produced by smoke exhaust ventilator
Information；The control instruction of above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information；Above-mentioned oil pumping is controlled according to above-mentioned control instruction
The air draught state of smoke machine has reached oil smoke concentration and distribution situation according to smoke exhaust ventilator, controls the air draught state of smoke exhaust ventilator
Purpose, thus realize improve kitchen ventilator smoke absorption effect, reduce the technical effect of energy consumption, and then solve existing oil pumping
Smoke machine can not adjust air draught state according to oil smoke concentration and distribution situation, lead to the technical problem that smoke absorption effect is bad.
In an alternative embodiment, above-mentioned status information includes: the distributed area of the concentration of above-mentioned oil smoke, above-mentioned oil smoke
Domain.
As a kind of optional embodiment, above-mentioned steps S102 obtains the status information of oil smoke produced by smoke exhaust ventilator, packet
It includes: obtaining the first image information of above-mentioned oil smoke；Above-mentioned first image information is analyzed using the first model, is determined above-mentioned
First state information in first image information, wherein above-mentioned first model is to pass through machine learning training using multi-group data
It obtains, every group of data in above-mentioned multi-group data include: status information corresponding to image information and image information.
In the embodiment of the present application, one or more can be arranged in the specified region in the room for being provided with above-mentioned smoke exhaust ventilator
A image collecting device, (for example, camera), to acquire the image information of oil smoke, for the setting position of camera in the application
It sets without limitation, for example, can be, but not limited to the stir-fry in kitchen so that above-mentioned smoke exhaust ventilator is arranged in ordinarily resident family as an example
Pot region house at the top of, it is close but not be located at smoke exhaust ventilator suction opening at, a camera is respectively set；But if
Above-mentioned smoke exhaust ventilator setting is then needed in large-scale dining room, hotel, the setting number and deployment range of above-mentioned camera according to possible
The setting of the case where there are oil smoke adaptability.
In one alternate embodiment, image collecting device also can be set on smoke exhaust ventilator, for example, setting is being pumped
At the suction opening of smoke machine, alternatively, the marginal position of smoke exhaust ventilator is arranged in.
Camera by the way that different location is arranged in can acquire the image of the oil smoke of region respectively, in acquisition image
When, it can be every preset time period (for example, every one minute) and shoot an image, then generated according to above-mentioned image analysis
The status information of oil smoke, and determine according to above-mentioned status information the control instruction of above-mentioned smoke exhaust ventilator, and then according to above-mentioned control
Instruction controls the air draught state of above-mentioned smoke exhaust ventilator.
It should be noted that in the application without limitation for the classification of the image of shooting, including but not limited to: artwork master
As (gray level image), color image (RGB image).It, can be according to binary image processing mode analysis chart when analyzing image
Information as in, specifically, can be carried out to the pixel position in pixels multiple in image and history image in analysis
Compare, whether, to determine the pixel having differences, the pixel that difference then will be present distinguishes, obtain depositing in image
In the image information of oil smoke.
Wherein, above-mentioned first image information can refer to the image of the oil smoke taken, and image is sent to database
In.In embodiment provided herein, can by multiple cameras respectively with smoke exhaust ventilator, server and subscriber household
The gateway in (dining room, restaurant, hotel etc.) establishes network connection, and after collecting the image of oil smoke, sends above-mentioned oil
The image of cigarette is into database, to facilitate server to be analyzed and processed the image information of oil smoke.It should be noted that above-mentioned
Gateway can include but is not limited to: wireless network card, bluetooth, Wi-Fi etc..
As an alternative embodiment, the application can be stored in advance one in server or database in advance
Predetermined template image, for example, the image of one oil smoke of shooting needs to illustrate using the image as predetermined template image in advance
It is that the application is not especially limited the predetermined template image prestored, can is but be not limited to any one smoke exhaust ventilator
A (one or multiple) predetermined template image is all prestored, with for being compared with the image information got later, but
Be since multiple smoke exhaust ventilators may be provided in a region, for example, multiple smoke exhaust ventilators are communicated using internet,
And then can cooperate with or division of labor smoke pumping, it therefore, can be there are the numbers of connection relationship with above-mentioned multiple smoke exhaust ventilators
According to prestoring a predetermined template image in library.
After acquiring above-mentioned first image information, the first image information and predetermined template image can be compared
Compared with to analyze difference, foundation difference determines the first state information in above-mentioned first image information.Wherein, pre- solid plate
May include multiple information in image, can include but is not limited to: oil smoke, oil smoke concentration (for example, can be by the face of picture
Color depth is shallowly determined), the letter such as the distributed areas (for example, can be determined by the distribution of the shade of picture) of oil smoke
Breath, multiple information in predetermined template image is analyzed, and predetermined template image and template image information are stored in
It states in the first model, to be analyzed for the image information later to the oil smoke taken.
Wherein, analyze current shooting oil smoke image and predetermined template image difference when, can be by binaryzation at
Reason mode pre-processes image, to extract the place in image there are notable difference.In binary conversion treatment, Ke Yifen
The pixel difference and color difference where each pixel in analysis image, so that it is determined that going out difference existing for whole image.
As an alternative embodiment, above-mentioned database or server can be stored in advance in predetermined template image
Pre-stored multiple characteristic informations, thus the image information and the difference of predetermined template image of the oil smoke acquired in analysis
When, it can determine to have differences place by comparing characteristic information.
Wherein it is possible to multiple characteristic informations of oil smoke are extracted from the image information taken using CNN algorithm,
It when extraction, can will be input in neural network in image, with by establishing corresponding neuron, and according between neuron
Preset function (such as Sigmoid function) determines characteristics of image and image feature maps, thus according to determining Feature Mapping, output
Multiple features of image.In addition, analysis the image difference different time, can use deep learning, establish the first preset model and then
When secondary progress user identity feature and user characteristics extract, it can use to scheme to search to clap in the method for figure search database with current
The similar image of image is taken the photograph, and extracts oil smoke characteristic information in image, further, it is also possible to be extracted using NB Algorithm
Oil smoke characteristic information.
When analyzing the target object in image, it can use deep learning or KNN algorithm, will exist in image information
The image information of same characteristic features filters out, and with the characteristic information being had differences, and then obtains the image information and template of oil smoke
The different information of image.For example, be compared image information with predetermined template image in the image information for taking oil smoke,
If judging there is no target object (oil smoke) in image, can not the air draught state to smoke exhaust ventilator be adjusted, such as
The fruit smoke exhaust ventilator is in the open state, it is also an option that closing the smoke exhaust ventilator；It, can be with if judging there are target object
The control instruction of smoke exhaust ventilator is determined according to the status information of oil smoke, and then controls the air draught state of the smoke exhaust ventilator.
The application analyze oil smoke image when, can be, but not limited to use in a manner of scheming to search figure, by model with work as
Preceding image has the image zooming-out of similar features to come out, and by transfer learning algorithm, determines immediate image.And in oil smoke
The corresponding smoke exhaust ventilator of status information control instruction, and control according to above-mentioned control instruction the air draught shape of above-mentioned smoke exhaust ventilator
When state, the air draught state of the corresponding smoke exhaust ventilator of above-mentioned control instruction can be extracted by KNN algorithm.In above-mentioned air draught state
Air draught air quantity, direction and speed, the aperture of smoke deflector, can be (large-scale, small-sized, indoor according to the type of smoke exhaust ventilator
Type, outdoor version, household, hotel with etc. types) carry out in advance distinguish setting.
When establishing above-mentioned first model, can be believed by the image information and image of the oil smoke shot in historical time section
The corresponding status information of breath, indicates oil smoke image tag.It can be extracted emphatically in the image information of shooting dense comprising oil smoke
The image information of degree and distributed areas, and in the database by corresponding user images label and the storage of oil smoke image, to allow machine
Device learning training, to can be analyzed in image according to the image information of input after the image for taking newest oil smoke
Oil smoke status information, and then determine the control instruction of above-mentioned smoke exhaust ventilator.
It should be noted that the second model, third model and the 4th model that occur in any one following embodiment
Establish mode, and the mode analyzed corresponding data can be, but not limited to the side of above-mentioned first model analysis data
Formula.
Furthermore it is possible to establish each user or smoke exhaust ventilator adjustment ginseng that family (dining room, restaurant, hotel etc.) is correspondingly arranged
Number, and identity matches and deposits in the database, and establishes one by supplemental characteristic and user or family (dining room, restaurant, hotel etc.)
A data model, to extract corresponding smoke pumping after determining user or family (dining room, restaurant, hotel etc.) identity information
Machine adjusting parameter enhances the experience sense of user so as to effectively control the air draught state of smoke exhaust ventilator.
In an alternative embodiment, as shown in Fig. 2, determining the control of above-mentioned smoke exhaust ventilator according to above-mentioned status information
Before instruction, the above method further includes following steps:
Step S202 obtains the first oil smoke concentration for passing through oil smoke concentration detector test；
The second oil smoke concentration in above-mentioned first concentration and above-mentioned first state information is compared by step S204；
Step S206, when above-mentioned first concentration and the difference of above-mentioned second oil smoke concentration are less than the first preset threshold, touching
Hair determines the control instruction of above-mentioned smoke exhaust ventilator.
In order to improve the accuracy for the air draught state for controlling kitchen ventilator, the usage experience of user is improved, according to above-mentioned setting
The mode of one or more cameras obtains the first image information of oil smoke, using the first model to above-mentioned first image information into
Row analysis, determines the first state information in above-mentioned first image information, wherein include at least in above-mentioned first state information:
Second oil smoke concentration.In addition to this, the application can also be by the first oil smoke concentration of oil smoke concentration detector test, and
When one concentration and the difference of above-mentioned second oil smoke concentration are less than the first preset threshold, triggering determines that the control of above-mentioned smoke exhaust ventilator refers to
Order controls the air draught state of smoke extractor.
By identifying the generating region of oil smoke, and according to the oil smoke concentration detected, the control of corresponding smoke exhaust ventilator is determined
System instruction, may be implemented that control targetedly is adjusted to the air draught state of smoke exhaust ventilator, inhale so as to improve kitchen ventilator
Oil smoke effect reduces the consumption of the energy.
In optional embodiment provided herein, the control of above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information
Before instruction, the above method further include:
Obtain the second image information of above-mentioned oil smoke, wherein above-mentioned second image information and above-mentioned first image information are
The image information acquired simultaneously from different perspectives；
Above-mentioned second image information is analyzed using the first model, determines the second shape in above-mentioned second image information
State information, wherein above-mentioned first model is obtained using multi-group data by machine learning training, in above-mentioned multi-group data
Every group of data include: status information corresponding to image information and image information；
It should be noted that above-mentioned second image information can be but be not limited to the acquisition side of above-mentioned first image information
Formula is acquired, and may refer to above-mentioned the first image information of acquisition, and determine the associated description of first state information, herein
It repeats no more.
As a kind of optional embodiment, the control instruction of above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information, comprising:
More above-mentioned first state information and above-mentioned second status information, and in above-mentioned first state information and above-mentioned second status information
Difference less than the second preset threshold when, state letter is selected from above-mentioned first state information and above-mentioned second status information
Breath；Status information according to selection determines above-mentioned control instruction.
In order to improve the accuracy for the air draught state for controlling kitchen ventilator, the usage experience of user is improved, and then can basis
The image information of the oil smoke acquired twice, and the first state information analyzed by corresponding analysis model and
Second status information is compared, and default less than second in the difference of above-mentioned first state information and above-mentioned second status information
When threshold value, a status information is selected, and determine above-mentioned control instruction according to selected status information.
In another optional embodiment, the control instruction of above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information,
Comprise determining that the first instruction corresponding with the concentration of oil smoke above-mentioned in above-mentioned status information, wherein carry in above-mentioned first instruction
There is target air volume value；The air draught state of above-mentioned smoke exhaust ventilator is controlled according to above-mentioned control instruction, comprising: according to above-mentioned first instruction
In target air volume value adjust the airflow value of above-mentioned smoke exhaust ventilator.
Due to including: concentration and the distributed areas of oil smoke of oil smoke in above-mentioned status information, determining above-mentioned state
After information, processing can be distinguished to above-mentioned status information, when above-mentioned status information is the concentration of oil smoke, it is determining with it is upper
Corresponding first instruction of concentration of above-mentioned oil smoke in status information is stated, and according to the target air volume value adjustment in above-mentioned first instruction
The airflow value of above-mentioned smoke exhaust ventilator.
In an alternative embodiment, the airflow value of above-mentioned smoke exhaust ventilator can be not provided with specific gear, Ye Jiwu
Gear is different from existing fixation according to fast gear and slow gear control mode, according to the concentration of oil smoke and distributed areas, no shelves
Position carries out Boiler pressure control, and the effect for more accurately adjusting control may be implemented.
In an alternative embodiment, the airflow value of above-mentioned smoke exhaust ventilator can be with adjustment air quantity in the prior art
The air quantity gear of value matches, and then can be by way of according to above-mentioned first instruction control air quantity gear, can be more quasi-
The air draught state of true adjusting control smoke exhaust ventilator.
Through the foregoing embodiment, can the air draught state targetedly to smoke exhaust ventilator control, Jin Erke is adjusted
To achieve the purpose that control the air draught state of smoke exhaust ventilator according to the oil smoke concentration of smoke exhaust ventilator, to realize improvement kitchen ventilator
Smoke absorption effect reduces the technical effect of energy consumption.
As a kind of optional embodiment, above-mentioned target air volume value determines in the following manner: obtaining the dense of above-mentioned oil smoke
Degree；It is analyzed using concentration of the third model to above-mentioned oil smoke, determines the corresponding airflow value of the concentration of above-mentioned oil smoke, wherein
Above-mentioned third model is obtained using multi-group data by machine learning training, and every group of data in above-mentioned multi-group data are wrapped
It includes: the concentration of oil smoke and airflow value corresponding with the concentration of oil smoke.
Optionally, the concentration of above-mentioned oil smoke can be but be not limited to the mode of above-mentioned the first concentration of acquisition, for example, can lead to
Oil smoke concentration detector test is crossed to obtain.
It should be noted that above-mentioned analyzed using concentration of the third model to above-mentioned oil smoke, so that it is determined that above-mentioned oil
The embodiment of the corresponding airflow value of the concentration of cigarette may refer to the first model of above-mentioned use and carry out to above-mentioned first image information
Analysis, determines the associated description of the first state information in above-mentioned first image information, details are not described herein again.
In an alternative embodiment, the control instruction of above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information, comprising:
When above-mentioned smoke exhaust ventilator is provided with smoke deflector, determine and the distributed areas of above-mentioned oil smoke corresponding second in above-mentioned status information
Instruction, wherein the target aperture of smoke deflector is carried in above-mentioned second instruction；Above-mentioned smoke pumping is controlled according to above-mentioned control instruction
The air draught state of machine, comprising: the aperture of above-mentioned smoke deflector is adjusted according to the target aperture in above-mentioned second instruction.
It, can be with if concentration is compared in oil smoke distributed areas in above-mentioned status information as a kind of optional embodiment
It sets the smoke deflector being arranged in above-mentioned smoke exhaust ventilator to compared with small guide vane, correspondingly, if oil smoke is distributed in above-mentioned status information
Region is more dispersed, then can set biggish aperture for above-mentioned smoke deflector.Specifically, can be according to the distribution of above-mentioned oil smoke
Region carries out adaptability adjusting to the opening size of above-mentioned smoke deflector.
The above embodiments of the present application are led by identifying the generating region of oil smoke, and according to the control of detection oil smoke distributed areas
Aerofoil is flexible to form different suction, can the air draught state targetedly to smoke exhaust ventilator be adjusted control, and then can be with
Achieve the purpose that the air draught state for controlling smoke exhaust ventilator according to the oil smoke concentration of smoke exhaust ventilator, is inhaled to realize and improve kitchen ventilator
Oil smoke effect reduces the technical effect of energy consumption.
In addition, being illustrated below by way of a kind of optional embodiment, above-mentioned target aperture how is determined: obtaining above-mentioned
The distributed areas of oil smoke；The distributed areas of above-mentioned oil smoke are analyzed using the 4th model, determine the distributed area of above-mentioned oil smoke
The corresponding aperture in domain, wherein above-mentioned 4th model is obtained using multi-group data by machine learning training, above-mentioned multiple groups number
Every group of data in include: oil smoke distributed areas and target aperture corresponding with the distributed areas of oil smoke.
Optionally, in the embodiment of the present application, it can be, but not limited to by way of shooting image obtain above-mentioned oil smoke
Distributed areas.
It should be noted that above-mentioned analyze the distributed areas of above-mentioned oil smoke using the 4th model, so that it is determined that on
The embodiment for stating the corresponding aperture in distributed areas of oil smoke may refer to the first model of above-mentioned use and believe above-mentioned first image
Breath is analyzed, and determines the associated description of the first state information in above-mentioned first image information, details are not described herein again.
Embodiment 2
The embodiment of the present application additionally provides a kind of for implementing the oil pumping of the air draught condition control method of above-mentioned smoke exhaust ventilator
Smoke machine, Fig. 3 be according to a kind of structural schematic diagram of smoke exhaust ventilator of the embodiment of the present application, as shown in figure 3, above-mentioned smoke exhaust ventilator,
It include: image collecting device 30 and processor 32, wherein
Image collecting device 30, for obtaining the image information of oil smoke produced by smoke exhaust ventilator, and from above-mentioned image information
The middle status information for extracting oil smoke；Processor 32, for determining the control instruction of above-mentioned smoke exhaust ventilator according to above-mentioned status information；
And the air draught state of above-mentioned smoke exhaust ventilator is controlled according to above-mentioned control instruction.
It, can be with it should be noted that the air draught condition control method of any one smoke exhaust ventilator in above-described embodiment 1
It executes or realizes in the smoke exhaust ventilator provided by the present embodiment.
In addition, still it should be noted that the optional or preferred embodiment of the present embodiment may refer to the phase in embodiment 1
Description is closed, details are not described herein again.
Embodiment 3
According to embodiments of the present invention, it additionally provides a kind of for implementing the air draught condition control method of above-mentioned smoke exhaust ventilator
Device, Fig. 4 are a kind of structural schematic diagram of the air draught behavior control device of smoke exhaust ventilator according to an embodiment of the present invention, such as Fig. 4
It is shown, the air draught behavior control device of above-mentioned smoke exhaust ventilator, comprising: module 40, determining module 42 and control module 44 are obtained,
In,
Module 40 is obtained, for obtaining the status information of oil smoke produced by smoke exhaust ventilator；Determining module 42, for according to
State the control instruction that status information determines above-mentioned smoke exhaust ventilator；Control module 44, it is above-mentioned for being controlled according to above-mentioned control instruction
The air draught state of smoke exhaust ventilator.
Herein it should be noted that above-mentioned acquisition module 40, determining module 42 and control module 44 correspond in embodiment 1
Step S102 to step S106, three modules are identical as example and application scenarios that corresponding step is realized, but are not limited to
1 disclosure of that of above-described embodiment.It should be noted that above-mentioned module may operate in computer as a part of device
In terminal.
It should be noted that the optional or preferred embodiment of the present embodiment may refer to the associated description in embodiment 1,
Details are not described herein again.
The air draught behavior control device of above-mentioned smoke exhaust ventilator can also include processor and memory, above-mentioned acquisition module
40, determining module 42 and control module 44 etc. store in memory as program unit, are stored in by processor execution
Above procedure unit in reservoir realizes corresponding function.
Include kernel in processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can be set one
Or more, the operating parameter of smoke exhaust ventilator is adjusted, by adjusting kernel parameter with the suction of reasonable, accurate adjustment smoke exhaust ventilator
Wind state and air quantity.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, if read-only memory (ROM) or flash memory (flash RAM), memory include that at least one is deposited
Store up chip.
The embodiment of the present application also provides a kind of storage mediums.Optionally, in the present embodiment, above-mentioned storage medium includes
The program of storage, wherein equipment where controlling above-mentioned storage medium in above procedure operation executes any one of the above oil pumping
The air draught condition control method of smoke machine.
Optionally, in the present embodiment, above-mentioned storage medium can be located in computer network in computer terminal group
In any one terminal, or in any one mobile terminal in mobile terminal group.
The embodiment of the present application also provides a kind of processors.Optionally, in the present embodiment, above-mentioned processor is for running
Program, wherein above procedure executes the air draught condition control method of any one of the above smoke exhaust ventilator when running.
The embodiment of the present application provides a kind of equipment, equipment include processor, memory and storage on a memory and can
The program run on a processor, processor perform the steps of the shape of oil smoke produced by obtaining smoke exhaust ventilator when executing program
State information；The control instruction of above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information；Above-mentioned pumping is controlled according to above-mentioned control instruction
The air draught state of kitchen ventilator.
Optionally, when above-mentioned processor executes program, the first image information of above-mentioned oil smoke can also be obtained；Use first
Model analyzes above-mentioned first image information, determines the first state information in above-mentioned first image information, wherein above-mentioned
First model is obtained using multi-group data by machine learning training, and every group of data in above-mentioned multi-group data include:
Status information corresponding to image information and image information.
Optionally, when above-mentioned processor executes program, the first oil by oil smoke concentration detector test can also be obtained
Smoke density；The second oil smoke concentration in above-mentioned first concentration and above-mentioned first state information is compared；It is dense above-mentioned first
When the difference of degree and above-mentioned second oil smoke concentration is less than the first preset threshold, triggering determines the control instruction of above-mentioned smoke exhaust ventilator.
Optionally, when above-mentioned processor executes program, the second image information of above-mentioned oil smoke can also be obtained, wherein on
It states the second image information and above-mentioned first image information is the image information from different perspectives while acquired；Use the first model pair
Above-mentioned second image information is analyzed, and determines the second status information in above-mentioned second image information, wherein above-mentioned first mould
Type is obtained using multi-group data by machine learning training, and every group of data in above-mentioned multi-group data include: image letter
Status information corresponding to breath and image information；The control instruction of above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information, comprising:
More above-mentioned first state information and above-mentioned second status information, and in above-mentioned first state information and above-mentioned second status information
Difference less than the second preset threshold when, state letter is selected from above-mentioned first state information and above-mentioned second status information
Breath；Status information according to selection determines above-mentioned control instruction.
Optionally, when above-mentioned processor executes program, the concentration with oil smoke above-mentioned in above-mentioned status information can also be determined
Corresponding first instruction, wherein carry target air volume value in above-mentioned first instruction；Above-mentioned pumping is controlled according to above-mentioned control instruction
The air draught state of kitchen ventilator, comprising: the airflow value of above-mentioned smoke exhaust ventilator is adjusted according to the target air volume value in above-mentioned first instruction.
Optionally, when above-mentioned processor executes program, the concentration of above-mentioned oil smoke can also be obtained；Using third model to upper
The concentration for stating oil smoke is analyzed, and determines the corresponding airflow value of the concentration of above-mentioned oil smoke, wherein above-mentioned third model is using more
Group data are obtained by the way that machine learning is trained, every group of data in above-mentioned multi-group data include: oil smoke concentration and with oil
The corresponding airflow value of the concentration of cigarette.
Optionally, when above-mentioned processor executes program, can also when above-mentioned smoke exhaust ventilator is provided with smoke deflector, determine with
Corresponding second instruction in the distributed areas of above-mentioned oil smoke in above-mentioned status information, wherein carried in above-mentioned second instruction and lead cigarette
The target aperture of plate；The air draught state of above-mentioned smoke exhaust ventilator is controlled according to above-mentioned control instruction, comprising: according to above-mentioned second instruction
In target aperture adjust the aperture of above-mentioned smoke deflector.
Optionally, when above-mentioned processor executes program, the distributed areas of above-mentioned oil smoke can also be obtained；Use the 4th model
The distributed areas of above-mentioned oil smoke are analyzed, determine the corresponding aperture in the distributed areas of above-mentioned oil smoke, wherein above-mentioned 4th mould
Type is obtained using multi-group data by machine learning training, and every group of data in above-mentioned multi-group data include: oil smoke
Distributed areas and target aperture corresponding with the distributed areas of oil smoke.
Present invention also provides a kind of computer program products, when executing on data processing equipment, are adapted for carrying out just
The program of beginningization there are as below methods step: the status information of oil smoke produced by smoke exhaust ventilator is obtained；It is true according to above-mentioned status information
The control instruction of fixed above-mentioned smoke exhaust ventilator；The air draught state of above-mentioned smoke exhaust ventilator is controlled according to above-mentioned control instruction.
Optionally, when above-mentioned computer program product executes program, the first image information of above-mentioned oil smoke can also be obtained；
Above-mentioned first image information is analyzed using the first model, determines the first state information in above-mentioned first image information,
Wherein, above-mentioned first model is obtained using multi-group data by machine learning training, every group of number in above-mentioned multi-group data
According to including: status information corresponding to image information and image information.
Optionally, it when above-mentioned computer program product executes program, can also obtain through oil smoke concentration detector test
The first oil smoke concentration；The second oil smoke concentration in above-mentioned first concentration and above-mentioned first state information is compared；Upper
When stating the difference of the first concentration and above-mentioned second oil smoke concentration less than the first preset threshold, triggering determines the control of above-mentioned smoke exhaust ventilator
System instruction.
Optionally, when above-mentioned computer program product executes program, the second image information of above-mentioned oil smoke can also be obtained,
Wherein, above-mentioned second image information and above-mentioned first image information are the image information acquired simultaneously from different perspectives；Use
One model analyzes above-mentioned second image information, determines the second status information in above-mentioned second image information, wherein on
It states the first model and is obtained using multi-group data by machine learning training, every group of data in above-mentioned multi-group data are wrapped
It includes: status information corresponding to image information and image information；The control of above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information
Instruction, comprising: more above-mentioned first state information and above-mentioned second status information, and in above-mentioned first state information and above-mentioned the
When the difference of two-state information is less than the second preset threshold, selected from above-mentioned first state information and above-mentioned second status information
One status information；Status information according to selection determines above-mentioned control instruction.
Optionally, it when above-mentioned computer program product executes program, can also determine and oil above-mentioned in above-mentioned status information
Corresponding first instruction of the concentration of cigarette, wherein carry target air volume value in above-mentioned first instruction；According to above-mentioned control instruction control
Make the air draught state of above-mentioned smoke exhaust ventilator, comprising: adjust above-mentioned smoke exhaust ventilator according to the target air volume value in above-mentioned first instruction
Airflow value.
Optionally, when above-mentioned computer program product executes program, the concentration of above-mentioned oil smoke can also be obtained；Use third
Model analyzes the concentration of above-mentioned oil smoke, determines the corresponding airflow value of the concentration of above-mentioned oil smoke, wherein above-mentioned third model
Multi-group data is used to obtain by machine learning training, every group of data in above-mentioned multi-group data include: the dense of oil smoke
Degree and airflow value corresponding with the concentration of oil smoke.
Optionally, when above-mentioned computer program product executes program, above-mentioned smoke exhaust ventilator can also be provided with smoke deflector
When, determine the second instruction corresponding with the distributed areas of above-mentioned oil smoke in above-mentioned status information, wherein take in above-mentioned second instruction
Target aperture with smoke deflector；The air draught state of above-mentioned smoke exhaust ventilator is controlled according to above-mentioned control instruction, comprising: according to above-mentioned
Target aperture in second instruction adjusts the aperture of above-mentioned smoke deflector.
Optionally, when above-mentioned computer program product executes program, the distributed areas of above-mentioned oil smoke can also be obtained；It uses
4th model analyzes the distributed areas of above-mentioned oil smoke, determines the corresponding aperture in the distributed areas of above-mentioned oil smoke, wherein on
It states the 4th model and is obtained using multi-group data by machine learning training, every group of data in above-mentioned multi-group data are wrapped
It includes: the distributed areas of oil smoke and target aperture corresponding with the distributed areas of oil smoke.
Using the embodiment of the present application, a kind of scheme of the air draught state control of smoke exhaust ventilator is provided.It is pumped by obtaining
The status information of oil smoke produced by smoke machine；The control instruction of above-mentioned smoke exhaust ventilator is determined according to above-mentioned status information；According to above-mentioned
Control instruction controls the air draught state of above-mentioned smoke exhaust ventilator, has reached according to oil smoke concentration and distribution situation, controls above-mentioned oil pumping
The purpose of the air draught state of smoke machine reduces the technical effect of energy consumption, and then solve so that realizing improves kitchen ventilator smoke absorption effect
Existing smoke exhaust ventilator of having determined can not adjust air draught state according to oil smoke concentration and distribution situation, cause smoke absorption effect bad
Technical problem.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
In the above embodiment of the invention, it all emphasizes particularly on different fields to the description of each embodiment, does not have in some embodiment
The part of detailed description, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the unit, Ke Yiwei
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module
It connects, can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
On unit.It can some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can for personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes: that USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic or disk etc. be various to can store program code
Medium.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (8)
1. a kind of air draught condition control method of smoke exhaust ventilator characterized by comprising
Obtain the status information of oil smoke produced by smoke exhaust ventilator；
The control instruction of the smoke exhaust ventilator is determined according to the status information；
The air draught state of the smoke exhaust ventilator is controlled according to the control instruction；
Wherein, the status information of oil smoke produced by smoke exhaust ventilator is obtained, comprising: obtain the first image information of the oil smoke；Make
The first image information is analyzed with the first model, determines the first state information in the first image information,
In, first model is obtained using multi-group data by machine learning training, every group of data in the multi-group data
It include: status information corresponding to image information and image information；
Before the control instruction for determining the smoke exhaust ventilator according to the status information, the method also includes: acquisition passes through oil
First oil smoke concentration of smoke density detector test；By the second oil smoke concentration in the first concentration and the first state information into
Row compares；When first concentration and the difference of second oil smoke concentration are less than the first preset threshold, trigger described in determining
The control instruction of smoke exhaust ventilator.
2. the method according to claim 1, wherein
Before the control instruction for determining the smoke exhaust ventilator according to the status information, the method also includes: obtain the oil
Second image information of cigarette, wherein second image information and the first image information are to acquire simultaneously from different perspectives
Image information；Second image information is analyzed using the first model, determines in second image information
Two-state information, wherein first model is obtained using multi-group data by machine learning training, the multi-group data
In every group of data include: status information corresponding to image information and image information；
The control instruction of the smoke exhaust ventilator is determined according to the status information, comprising: the first state information and institute
The second status information is stated, and in the difference of the first state information and second status information less than the second preset threshold
When, a status information is selected from the first state information and second status information；Status information according to selection
Determine the control instruction.
3. the method according to claim 1, wherein the status information includes: the concentration, described of the oil smoke
The distributed areas of oil smoke.
4. according to the method described in claim 3, it is characterized in that,
The control instruction of the smoke exhaust ventilator is determined according to the status information, comprising: described in the determining and status information
Corresponding first instruction of the concentration of oil smoke, wherein carry target air volume value in first instruction；
The air draught state of the smoke exhaust ventilator is controlled according to the control instruction, comprising: according to the target in first instruction
Airflow value adjusts the airflow value of the smoke exhaust ventilator.
5. according to the method described in claim 4, it is characterized in that, the target air volume value determines in the following manner:
Obtain the concentration of the oil smoke；
It is analyzed using concentration of the third model to the oil smoke, determines the corresponding airflow value of the concentration of the oil smoke, wherein
The third model is obtained using multi-group data by machine learning training, and every group of data in the multi-group data are wrapped
It includes: the concentration of oil smoke and airflow value corresponding with the concentration of oil smoke.
6. according to the method described in claim 3, it is characterized in that,
The control instruction of the smoke exhaust ventilator is determined according to the status information, comprising: be provided in the smoke exhaust ventilator and lead cigarette
When plate, the second instruction corresponding with the distributed areas of oil smoke described in the status information is determined, wherein in second instruction
Carry the target aperture of smoke deflector；
The air draught state of the smoke exhaust ventilator is controlled according to the control instruction, comprising: according to the target in second instruction
Aperture adjusts the aperture of the smoke deflector.
7. according to the method described in claim 6, it is characterized in that, the target aperture determines in the following manner:
Obtain the distributed areas of the oil smoke；
The distributed areas of the oil smoke are analyzed using the 4th model, determines that the distributed areas of the oil smoke are corresponding and opens
Degree, wherein the 4th model is obtained using multi-group data by machine learning training, every group in the multi-group data
Data include: oil smoke distributed areas and target aperture corresponding with the distributed areas of oil smoke.
8. a kind of smoke exhaust ventilator characterized by comprising
Image collecting device is extracted for obtaining the image information of oil smoke produced by smoke exhaust ventilator, and from described image information
The status information of oil smoke；
Processor, for determining the control instruction of the smoke exhaust ventilator according to the status information；And refer to according to the control
Enable the air draught state for controlling the smoke exhaust ventilator；
The smoke exhaust ventilator is also used to obtain the first image information of the oil smoke；The first image is believed using the first model
Breath is analyzed, and determines the first state information in the first image information, wherein first model is to use multiple groups number
According to what is obtained by machine learning training, every group of data in the multi-group data include: image information and image information institute
Corresponding status information；Be also used to the processor according to the status information determine the smoke exhaust ventilator control instruction it
Before, obtain the first oil smoke concentration for passing through oil smoke concentration detector test；It will be in the first concentration and the first state information
Second oil smoke concentration is compared；In first concentration and the difference of second oil smoke concentration less than the first preset threshold
When, triggering determines the control instruction of the smoke exhaust ventilator.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711034512.XA CN107965828B (en) | 2017-10-30 | 2017-10-30 | The air draught condition control method and smoke exhaust ventilator of smoke exhaust ventilator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711034512.XA CN107965828B (en) | 2017-10-30 | 2017-10-30 | The air draught condition control method and smoke exhaust ventilator of smoke exhaust ventilator |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107965828A CN107965828A (en) | 2018-04-27 |
| CN107965828B true CN107965828B (en) | 2019-06-14 |
Family
ID=61999873
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711034512.XA Active CN107965828B (en) | 2017-10-30 | 2017-10-30 | The air draught condition control method and smoke exhaust ventilator of smoke exhaust ventilator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107965828B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110658118B (en) * | 2018-06-29 | 2023-05-02 | 九阳股份有限公司 | Cooking smoke detection method and smoke machine |
| CN108954453A (en) * | 2018-09-17 | 2018-12-07 | 广东海信家电有限公司 | A kind of side extraction cooking fume extractor and its control method |
| CN109237582A (en) * | 2018-11-15 | 2019-01-18 | 珠海格力电器股份有限公司 | Range hood control method based on image recognition, control system, range hood |
| CN110220862A (en) * | 2018-11-20 | 2019-09-10 | 华帝股份有限公司 | Infrared array detection device for detecting oil smoke and detection method thereof |
| CN109602264A (en) * | 2019-01-08 | 2019-04-12 | 广东万和热能科技有限公司 | A kind of food identification intelligent cooking control method based on convolutional neural networks |
| CN110094782B (en) * | 2019-05-20 | 2020-09-04 | 珠海格力电器股份有限公司 | Control method of intelligent range hood and intelligent range hood |
| CN113124433A (en) * | 2019-12-31 | 2021-07-16 | 青岛海尔智慧厨房电器有限公司 | Range hood control method and device, range hood and storage medium |
| CN111006261A (en) * | 2019-12-31 | 2020-04-14 | 青岛海尔智慧厨房电器有限公司 | Range hood control method and device, range hood and storage medium |
| CN111780185A (en) * | 2020-07-13 | 2020-10-16 | 合肥瑞纳通软件技术开发有限公司 | Oil smoke control method and system based on target recognition model and computer equipment |
| CN111780186A (en) * | 2020-07-13 | 2020-10-16 | 合肥瑞纳通软件技术开发有限公司 | Range hood with active smoke guide device and control method thereof |
| CN112903550B (en) * | 2021-01-28 | 2022-04-19 | 宁波方太厨具有限公司 | Oil smoke concentration data set generation method, device, system, equipment and medium |
| CN113435758B (en) * | 2021-06-30 | 2024-03-22 | 青岛海尔科技有限公司 | Wind power grade determining method and device, storage medium and electronic device |
| CN115839514B (en) * | 2023-02-24 | 2023-05-23 | 杭州老板电器股份有限公司 | Control method of range hood |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104456675B (en) * | 2014-11-22 | 2017-01-18 | 浙江苏泊尔家电制造有限公司 | Double-air-inlet range hood and control method thereof |
| CN106091063A (en) * | 2016-08-10 | 2016-11-09 | 广东顺德东方麦田工业设计有限公司 | A kind of intelligent fume exhauster and control method thereof |
-
2017
- 2017-10-30 CN CN201711034512.XA patent/CN107965828B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107965828A (en) | 2018-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107965828B (en) | The air draught condition control method and smoke exhaust ventilator of smoke exhaust ventilator | |
| CN108052199A (en) | Control method, device and the smoke exhaust ventilator of smoke exhaust ventilator | |
| CN108088235B (en) | The control method and device of dryer, dryer, memory, processor | |
| CN108234870B (en) | Image processing method, device, terminal and storage medium | |
| CN105844295B (en) | A kind of video smoke sophisticated category method based on color model and motion feature | |
| KR102174595B1 (en) | System and method for identifying faces in unconstrained media | |
| CN104537336B (en) | A kind of face identification method and system for possessing self-learning function | |
| CN108105136A (en) | Control method, device and the fan of fan | |
| CN107239514A (en) | A kind of plants identification method and system based on convolutional neural networks | |
| CN104866868B (en) | Metal coins recognition methods based on deep neural network and device | |
| CN109460708A (en) | A kind of Forest fire image sample generating method based on generation confrontation network | |
| CN107153817A (en) | Pedestrian's weight identification data mask method and device | |
| CN109237582A (en) | Range hood control method based on image recognition, control system, range hood | |
| CN108140032A (en) | Automatic video frequency is summarized | |
| CN107066938A (en) | Video analysis equipment, method and computer program product | |
| CN108717524A (en) | It is a kind of based on double gesture recognition systems and method for taking the photograph mobile phone and artificial intelligence system | |
| KR20160136391A (en) | Information processing apparatus and information processing method | |
| CN109173263A (en) | A kind of image processing method and device | |
| CN109711366A (en) | A kind of recognition methods again of the pedestrian based on group information loss function | |
| JP2008146539A (en) | Face authentication device | |
| CN108229674A (en) | The training method and device of cluster neural network, clustering method and device | |
| CN111597955A (en) | Smart home control method and device based on expression emotion recognition of deep learning | |
| CN108280436A (en) | A kind of action identification method based on the multi-grade remnant network for stacking recursive unit | |
| CN108197635A (en) | Methods of exhibiting and device, the smoke exhaust ventilator of cooking method | |
| CN108052858A (en) | The control method and smoke exhaust ventilator of smoke exhaust ventilator |
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 |