KR102473440B1 - Intergrated sensor module for smart farm and control method thereof - Google Patents

Abstract

Disclosed are an integrated sensor module for a smart farm and a control method thereof, which may improve productivity and affordability. According to one embodiment of the present invention, the integrated sensor module for a smart farm includes: a sensing unit which generates first sensing data by sensing temperature, generates second sensing data by sensing humidity, generates third sensing data by sensing ammonia, and generates fourth sensing data by sensing carbon dioxide; a control unit which generates a first output voltage and a first output current by performing smoothing of the first sensing data, amplifying, and switching, generates a second output voltage and a second output current by performing smoothing of the second sensing data, amplifying, and switching, generates a third output voltage and a third output current by performing smoothing of the third sensing data, amplifying, and switching, and generates a fourth output voltage and a fourth output current by performing smoothing of the fourth sensing data, amplifying, and switching; a voltage output unit which selectively outputs the first to fourth output voltages; and a current output unit which selectively outputs the first to fourth output currents.

Description

Integrated sensor module for smart farm and its control method {INTERGRATED SENSOR MODULE FOR SMART FARM AND CONTROL METHOD THEREOF}

The following embodiments relate to an integrated sensor module for a smart farm in which several sensor modules are implemented as one complex module and a control method thereof.

As a background art related to the embodiments, Korean Patent Publication No. KR 10-2018-0003225 A discloses a smart IT convergence framework system using a Lego type sensor module. Specifically, prior literature sets a prototype of a framework by implementing communication between a server, an Arduino sensor, and a mobile device, so that it can be applied to various contents production in an IoT environment by using a Lego-type sensor module. A smart IT convergence framework system using a sensor module is disclosed.

Through this, there is an effect that the prior literature can be efficiently applied to the production of various contents in the IoT environment.

In addition, Korean Patent Publication No. KR 10-2019-0123915 A discloses a virtual environment control device for integrated and distributed control through virtualization of a plurality of environment control devices (or IoT sensor nodes) and a system for generating the same. Specifically, the prior literature includes a communication control module, a control control module, a sensor control module, and an actuator module, and each of the plurality of environment control devices includes at least one of the communication control module, the control control module, the sensor control module, and the actuator module. Each of the control control module, sensor control module, and actuator module of the virtual environment control device is a control element of each of the communication control module, control control module, sensor control module, and actuator module of the plurality of environment control devices. Discloses a virtual environment control device including at least one of them.

Through this, prior literature can create and use a virtual environment controller according to the purpose of use, so purpose and flexibility can be secured. For example, it is used for overall monitoring for sensor and operating status, error warning, used for detailed control for correcting environmental information or executing operating commands, or used for linkage monitoring of production and sales information.

However, prior literature does not disclose an integrated sensor module for smart farms in which several sensor modules are implemented as one complex module.

Korean Patent Publication No. KR 10-2018-0003225 A Korean Patent Publication No. KR 10-2019-0123915 A

Embodiments are intended to provide an integrated sensor module for smart farms in which several sensor modules are implemented as one complex module.

The integrated sensor module for smart farms according to an embodiment of the present invention generates first sensing data by sensing temperature, generates second sensing data by sensing humidity, generates third sensing data by sensing ammonia, a sensing unit configured to sense carbon dioxide and generate fourth sensing data; Generating a first output voltage and a first output current by performing smoothing, amplification, and switching of the first sensed data, and performing smoothing, amplification, and switching of the second sensed data to generate a second output voltage and a second output current. Generating a third output voltage and a third output current by performing smoothing, amplification, and switching of the third sensing data, and performing smoothing, amplification, and switching of the fourth sensing data to generate a fourth output voltage and a control unit generating a fourth output current; a voltage output unit selectively outputting the first to fourth output voltages; and a current output unit selectively outputting the first to fourth output currents.

In the control method of the integrated sensor module for smart farm according to an embodiment of the present invention, when the first temperature corresponding to the first sensing data is less than or equal to the first threshold value, the first difference between the first threshold value and the first temperature calculating the gap temperature; controlling a set temperature of a heating device in a space in which the integrated sensor module is installed to increase by the first gap temperature; calculating a second gap temperature that is a difference between the first temperature and the second threshold when the first temperature is greater than or equal to a second threshold; controlling the set temperature of the heating device to decrease by the second gap temperature; calculating a first gap humidity that is a difference between the third threshold and the first humidity when the first humidity corresponding to the second sensing data is equal to or less than a third threshold; controlling a set humidity of a humidifier in a space where the integrated sensor module is installed to increase by the first gap humidity; calculating a second gap humidity that is a difference between the first humidity and the fourth threshold when the first humidity is greater than or equal to a fourth threshold; and controlling the set temperature of the humidifier to decrease by the second gap humidity.

As an embodiment, receiving spatial information of a space in which the integrated sensor module is installed; calculating a volume of a space in which the integrated sensor module is installed from the space information; calculating a concentration per unit volume of first ammonia corresponding to the calculated volume and the third sensing data; forming a first control signal for controlling a ventilator in a space in which the integrated sensor module is installed to operate when the calculated concentration per unit volume is equal to or greater than a fifth threshold value; forming a second control signal for controlling doors and windows of a space in which the integrated sensor module is installed to be opened when the concentration per unit volume is equal to or greater than a sixth threshold value higher than the fifth threshold value; and forming a third control signal for operating an alarm device in a space where the integrated sensor module is installed and transmitting an access prohibition announcement when the concentration per unit volume is equal to or greater than a seventh threshold value higher than the sixth threshold value. may further include.

As an embodiment, receiving spatial information of a space in which the integrated sensor module is installed; calculating a volume of a space in which the integrated sensor module is installed from the space information; calculating a concentration per first unit volume of the first carbon dioxide corresponding to the calculated volume and fourth sensing data at a first time point; Calculating a concentration per second unit volume of a second carbon dioxide corresponding to fourth sensing data at a second time point after a preset time has elapsed from the first time point; calculating a concentration change rate of carbon dioxide using the first and second concentrations per unit volume; calculating a first difference between the eighth threshold and the concentration change rate when the concentration change rate is equal to or less than an eighth threshold value; calculating a first ratio of the first difference value to the eighth threshold value; increasing the illuminance of a lighting device in a space where the integrated sensor module is installed by the first ratio according to the first ratio; calculating a second difference between the concentration change rate and the eighth threshold value when the concentration change rate is greater than or equal to the eighth threshold value; calculating a second ratio of the second difference value to the eighth threshold value; and reducing the illuminance of the lighting device by the second ratio according to the second ratio.

As one embodiment, when it is detected through the first image that there are weeds in the space in which the integrated sensor module is installed, obtaining a second image including the cutter and the weeds; detecting the cutter in the second image; setting a first length by estimating a short axis length of the cutter detected in the second image; detecting the weeds in the second image; setting a second length by estimating the length of the weeds detected in the second image; Checking a third length that is the actual length of the cutter; and estimating a fourth length, which is an actual length of the weeds, using the first length, the second length, and the third length.

An apparatus according to an embodiment may be combined with hardware and controlled by a computer program stored in a medium to execute any one of the methods described above.

Embodiments can contribute to improving productivity and economic feasibility by providing an integrated sensor module applicable in various environments by changing the use environment through sensor selection according to the purpose of use and applying only necessary types of sensors.

1 is a diagram for explaining an integrated sensor module for a smart farm according to an embodiment of the present invention.
2 is a diagram for explaining learning of a neural network according to an embodiment of the present invention.
3 is a diagram for explaining a control unit according to an embodiment of the present invention.
4 is a configuration diagram of an integrated sensor module for smart farms according to an embodiment of the present invention.
5 is a flowchart of an integrated sensor module control method for smart farms according to an embodiment of the present invention.
6 is an exemplary view of the configuration of a device according to an embodiment of the present invention.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes can be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents or substitutes to the embodiments are included within the scope of rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only, and may be modified and implemented in various forms. Therefore, the embodiments are not limited to the specific disclosed form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Although terms such as first or second may be used to describe various components, such terms should only be construed for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

It should be understood that when an element is referred to as being “connected” to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle.

Terms used in the examples are used only for descriptive purposes and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

In addition, in the description with reference to the accompanying drawings, the same reference numerals are given to the same components regardless of reference numerals, and overlapping descriptions thereof will be omitted. In describing the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description will be omitted.

The embodiments may be implemented in various types of products such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent vehicles, kiosks, and wearable devices.

1 is a diagram for explaining an integrated sensing environment for a smart farm according to an embodiment of the present invention.

As shown in FIG. 1, the integrated sensing environment 100 for smart farm includes a sensing unit 110, a control unit 120, a voltage output unit 130, a current output unit 140, a heating device 151, and a humidifier. device 152, ventilation device 153, door/window 154, alarm device 155, speaker 156, recording device 157, cutter 158, lighting device 159, and system bus 160 ) may be included. According to one embodiment, the sensing unit 110, the control unit 120, the voltage output unit 130 and the current output unit 140 may constitute an integrated sensor module for smart farms. For example, a heating device 151, a humidifier 152, a ventilation device 153, a door/window 154, an alarm device 155, a speaker 156, a photographing device 157, a cutter 158 And the lighting device 159 may be communicatively connected through the system bus 160 .

The sensing unit 110 detects the temperature of the space where the integrated sensor module for smart farm is installed to generate first sensing data, detects humidity to generate second sensing data, and detects ammonia to generate third sensing data. And, by detecting carbon dioxide, fourth sensing data may be generated.

The controller 120 generates a first output voltage and a first output current by performing smoothing, amplification, and switching of the first sensed data, and performs smoothing, amplification, and switching of the second sensed data to obtain a second output voltage and A second output current may be generated. In addition, the controller 120 generates a third output voltage and a third output current by performing smoothing, amplification, and switching of the third sensed data, and performs smoothing, amplification, and switching of the fourth sensed data to generate a fourth output voltage. A voltage and a fourth output current may be generated.

When the first temperature corresponding to the first sensing data is equal to or less than the first threshold value, the controller 120 may calculate a first gap temperature that is a difference between the first threshold value and the first temperature. According to an embodiment, the controller 120 may calculate the first gap temperature using Equation 1 below.

[Equation 1]

First gap temperature = first threshold value - first temperature

The control unit 120 may control the set temperature of the heating device 151 of the space where the integrated sensor module for smart farm is installed to be increased by the first gap temperature.

The controller 120 may calculate a second gap temperature that is a difference between the first temperature and the second threshold when the first temperature is greater than or equal to the second threshold. According to an embodiment, the controller 120 may calculate the second gap temperature using Equation 2 below.

[Equation 2]

Second gap temperature = first temperature - second threshold

The controller 120 may control the set temperature of the heating device 151 to decrease by the second gap temperature.

The controller 120 may calculate a first gap humidity that is a difference between the third threshold value and the first humidity when the first humidity corresponding to the second sensing data is equal to or less than the third threshold value. According to an embodiment, the controller 120 may calculate the first gap humidity using Equation 3 below.

[Equation 3]

First gap humidity = third threshold value - first humidity

The controller 120 may control the set humidity of the humidifier 152 in the space where the integrated sensor module for smart farm is installed to increase by the first gap humidity.

The control unit 120 calculates a second gap humidity that is a difference between the first humidity and the fourth threshold value when the first humidity is equal to or greater than the fourth threshold value, and controls the set temperature of the humidifier to decrease by the second gap humidity can do. According to an embodiment, the controller 120 may calculate the second gap humidity using Equation 4 below.

[Equation 4]

Second gap humidity = first humidity - fourth threshold

The control unit 120 may receive spatial information of a space in which the integrated sensor module for smart farm is installed, and calculate the volume of the space in which the integrated sensor module for smart farm is installed from the spatial information. According to one embodiment, the control unit 120 may receive spatial information of a space in which an integrated sensor module for smart farm is installed from an external server through a network.

The control unit 120 calculates the concentration per unit volume of the first ammonia corresponding to the calculated volume and the third sensing data, and if the calculated concentration per unit volume is equal to or greater than the fifth threshold value, ventilation of the space where the integrated sensor module for smart farm is installed is installed. A first control signal for controlling the device 153 to operate may be formed. According to one embodiment, the ventilation device 153 may operate by receiving a first control signal through the system bus 160 .

The control unit 120 forms a second control signal for controlling the opening of the door and window 154 of the space where the integrated sensor module for smart farm is installed when the concentration per unit volume is greater than the sixth threshold value higher than the fifth threshold value. can According to an embodiment, the door and window 154 may operate by receiving a second control signal through the system bus 160 .

The controller 120 activates the alarm device 155 in the space where the integrated sensor module for smart farm is installed when the concentration per unit volume is higher than the seventh threshold value higher than the sixth threshold value and broadcasts an access prohibition announcement through the speaker 156. A third control signal for controlling to be transmitted may be formed.

The control unit 120 may receive spatial information of a space in which the integrated sensor module for smart farm is installed, and calculate the volume of the space in which the integrated sensor module for smart farm is installed from the spatial information.

The controller 120 may calculate the concentration per first unit volume of the first carbon dioxide corresponding to the calculated volume and the fourth sensing data at the first time point.

The controller 120 controls the second unit volume of the second carbon dioxide corresponding to the fourth sensing data at the second time point after a preset time (eg, 10 minutes, 30 minutes, 1 hour, etc.) has elapsed from the first time point. concentration can be calculated.

The controller 120 may calculate the concentration change rate of carbon dioxide using the first and second concentrations per unit volume. According to an embodiment, the control unit 120 may calculate the concentration change rate of carbon dioxide using Equation 5 below.

[Equation 5]

The controller 120 may calculate a first difference between the eighth threshold and the concentration change rate when the concentration change rate is equal to or less than the eighth threshold value, and calculate a first ratio of the first difference value to the eighth threshold value. can According to an embodiment, the controller 120 may calculate the first difference value using Equation 6 below, and calculate the first ratio using Equation 7 below.

[Equation 6]

1st difference value = 8th threshold value - rate of concentration change

[Equation 7]

The control unit 120 may increase the illuminance of the lighting device 159 in the space where the integrated sensor module for smart farm is installed according to the first ratio by the first ratio. Due to this, it is possible to reduce the amount of carbon dioxide by increasing the amount of photosynthesis in the space where the integrated sensor module for smart farm is installed.

The controller 120 may calculate a second difference between the concentration change rate and the eighth threshold value when the concentration change rate is equal to or greater than the eighth threshold value, and calculate a second ratio of the second difference value to the eighth threshold value. can According to an embodiment, the controller 120 may calculate the second difference value using Equation 8 below, and calculate the second ratio using Equation 9 below.

[Equation 8]

Second difference = rate of concentration change - 8th threshold

[Equation 9]

The controller 120 may decrease the illuminance of the lighting device 159 by a second ratio according to the second ratio. Because of this, if the amount of carbon dioxide in the space where the integrated sensor module for smart farm is installed is below the threshold value, the amount of photosynthesis can be reduced to adjust the amount of carbon dioxide.

The control unit 120 may acquire a first image from image information photographed inside when the inside of the space in which the integrated sensor module for smart farm is installed is being photographed through the photographing device 157 . At this time, the control unit 120 may acquire image information generated by shooting the inside of the space where the integrated sensor module for smart farm is installed in real time, and obtain an image at a specific point in time as the first image.

The control unit 120 may detect whether there are weeds in the space where the integrated sensor module for smart farm is installed through the first image. When it is confirmed through the first image that weeds are not detected inside the space where the integrated sensor module for smart farm is installed, the controller 120 acquires the first image again from the image information taken inside the space where the integrated sensor module for smart farm is installed. can do. At this time, the control unit 120 may acquire the first image again when it is confirmed that the photographing device 157 has moved by a certain distance or more while being drawn into the space where the integrated sensor module for smart farm is installed.

The controller 120 may obtain a second image captured by the cutter 158 and the weeds when it is confirmed through the first image that weeds are detected in the space where the integrated sensor module for smart farm is installed. At this time, the control unit 120 acquires image information generated by shooting the inside of the space where the integrated sensor module for smart farm is installed in real time, and when it is confirmed that the cutter 158 is attached to the weeds, the cutter 158 An image of a moment when the weed attaches to the weed may be obtained as a second image.

The controller 120 may estimate the short axis length of the cutter 158 detected in the second image and set the first length to the estimated short axis length. In this case, the controller 120 may derive an elliptic equation from the detected cutter 158 and generate a minor axis length of the detected cutter 158 based on the derived elliptic equation.

The controller 120 may detect weeds in the second image. At this time, the controller 120 may detect a box corresponding to the weed based on deep learning.

The controller 120 may estimate the length of the weeds detected in the second image and set the estimated length of the weeds as the second length. At this time, the controller 120 may check the lengths of the long axis and the diagonal line of the box corresponding to the weeds, and set the second length as an average value of the long axis and the diagonal line of the box.

The controller 120 may check the third length, which is the actual length of the cutter 158. In this case, the control unit 120 may inquire information stored in the database and check the third length, which is the actual length of the cutter 158 provided in the photographing device 157 .

The controller 120 may estimate the fourth length, which is the actual length of the weeds, using the first length, the second length, and the third length.

Specifically, the controller 120 determines the fourth length through a process of calculating a first ratio, which is the ratio of the first length to the third length, and calculating a fourth length by applying the second length to the first ratio. can be estimated

For example, when the first length is 10 cm, the second length is 20 cm, and the third length is 15 cm, the controller 120 may calculate the first ratio as 1.5 using the first length and the third length. And, by applying the second length to the first ratio, the fourth length can be calculated as 30 cm.

The control unit 120, when it is detected that there are weeds in the space where the integrated sensor module for smart farm is installed through the first image formed using the photographing device 157, obtains a second image captured including cutters and weeds, , Detects the cutter in the second image, estimates the short axis length of the cutter detected in the second image, sets the first length, detects weeds in the second image, and detects weeds in the second image. Estimating the length of the weeds, setting the second length, confirming the third length, which is the actual length of the cutter, and using the first length, the second length, and the third length, to determine the fourth length, which is the actual length of the weeds. can be estimated

The controller 120 may recognize the presence of weeds from image information photographed through the photographing device 157 .

The control unit 120 may obtain an image captured at a first point in time as a first image when the interior of the space in which the integrated sensor module for smart farm is installed is being photographed through the photographing device 157 . Here, the first viewpoint may be set differently according to embodiments.

The controller 120 may generate a first input signal by encoding the first image. Specifically, the controller 120 may generate a first input signal by encoding pixels of the first image into color information. Color information may include RGB color information, brightness information, and chroma information, but is not limited thereto. The controller 120 may convert the color information into numerical values, and encode the first image in the form of a data sheet including the values.

The controller 120 may input the first input signal to the artificial neural network trained in advance within the controller 120 .

The controller 120 may obtain a first output signal from the artificial neural network based on a result of the input of the artificial neural network.

The controller 120 may detect whether there are weeds in the first image based on the first output signal, and when it is detected that there are weeds in the first image, the weeds may be detected as applause.

The controller 120 may analyze the box detected in the first image and check the long axis length and the diagonal length of the box, respectively.

The controller 120 may calculate a second average value, which is an average value of long axis lengths and diagonal lengths of boxes detected in the first image.

The controller 120 may check whether the second average value is greater than the reference value. Here, the reference value may be set differently according to embodiments.

If the controller 120 determines that the second average value is smaller than the reference value, the controller 120 may determine that no weeds are detected in the first image. Thereafter, the controller 120 may change the first viewpoint and acquire an image captured at the changed first viewpoint as the first image again.

If the controller 120 determines that the second average value is greater than the reference value, the controller 120 may determine that weeds are detected in the first image. Thereafter, while displaying the first image, the operation of the output device may be controlled so that the box detected in the first image is highlighted. In this case, a box detected in the first image may be highlighted in a bright color.

The manager using the photographing device 157 can confirm that there are weeds in the space where the integrated sensor module for smart farm is installed through the first image taken at the first point in time, and to remove the identified weeds, the cutter 158 can be moved to attach to weeds. When it is confirmed that the cutter 158 is attached to the weed at the second viewpoint, the controller 120 may acquire an image captured at the second viewpoint as the second image.

The voltage output unit 130 may selectively output the first to fourth output voltages generated by the control unit 120 .

The current output unit 140 may selectively output the first to fourth output currents generated by the control unit 120 .

The heating device 151 is a device capable of adjusting the temperature of the space in which the integrated sensor module for smart farm is installed, and raises the set temperature by the first gap temperature under the control of the control unit 120 or raises the set temperature by the second gap temperature can be lowered

The humidifying device 152 is a device capable of adjusting the humidity of the space where the integrated sensor module for smart farm is installed, and raises the set humidity by the first gap humidity under the control of the control unit 120 or increases the set humidity by the second gap humidity can be lowered

The ventilation device 153 is a device for ventilating a space in which an integrated sensor module for smart farm is installed, and may operate when a first control signal is received under the control of the control unit 120.

Doors and windows 154 may be installed in a space where an integrated sensor module for smart farms is installed and opened when a second control signal is received under the control of the control unit 120.

The alarm device 155 may be installed in the space where the integrated sensor module for smart farm is installed and operate when receiving a third control signal under the control of the control unit 120.

The speaker 156 is installed in the space where the integrated sensor module for smart farm is installed and can operate when receiving a third control signal under the control of the control unit 120.

The photographing device 157 is installed in the space where the integrated sensor module for smart farm is installed and can generate a first image and a second image of the space where the integrated sensor module for smart farm is installed under the control of the control unit 120 . According to one embodiment, the first image includes an image of weeds in the space where the integrated sensor module for smart farm is installed, and the second image may include the image of the cutter 158 and weeds in the space where the integrated sensor module for smart farm is installed. .

The cutter 158 is installed in the space where the integrated sensor module for smart farm is installed and can be used for weed removal.

The lighting device 159 may be installed in a space where the integrated sensor module for smart farm is installed and increase or decrease the illuminance by a first ratio or a second ratio under the control of the control unit 120 .

In the present invention, artificial intelligence (AI) means a technology that imitates human learning ability, reasoning ability, perception ability, etc., and implements it with a computer, and concepts such as machine learning and symbolic logic can include Machine learning (ML) is an algorithm technology that classifies or learns the characteristics of input data by itself. Artificial intelligence technology is a machine learning algorithm that analyzes input data, learns the result of the analysis, and can make judgments or predictions based on the result of the learning. In addition, technologies that mimic the functions of the human brain, such as recognition and judgment, using machine learning algorithms, can also be understood as artificial intelligence. For example, technical fields such as linguistic understanding, visual understanding, inference/prediction, knowledge expression, and motion control may be included.

Machine learning may refer to processing that trains a neural network model using experience of processing data. Through machine learning, computer software could mean improving its own data processing capabilities. A neural network model is constructed by modeling a correlation between data, and the correlation may be expressed by a plurality of parameters. The neural network model derives a correlation between data by extracting and analyzing features from given data, and optimizing the parameters of the neural network model by repeating this process can be referred to as machine learning. For example, a neural network model may learn a mapping (correlation) between an input and an output with respect to data given as an input/output pair. Alternatively, even when only input data is given, the neural network model may learn the relationship by deriving a regularity between given data.

An artificial intelligence learning model or a neural network model may be designed to implement a human brain structure on a computer, and may include a plurality of network nodes having weights while simulating neurons of a human neural network. A plurality of network nodes may have a connection relationship between them by simulating synaptic activities of neurons that transmit and receive signals through synapses. In the artificial intelligence learning model, a plurality of network nodes can send and receive data according to a convolutional connection relationship while being located in layers of different depths. The artificial intelligence learning model may be, for example, an artificial neural network model, a convolutional neural network model (CNN), and the like. As an embodiment, the artificial intelligence learning model may be machine-learned according to methods such as supervised learning, unsupervised learning, and reinforcement learning. Machine learning algorithms for performing machine learning include Decision Tree, Bayesian Network, Support Vector Machine, Artificial Neural Network, Ada-boost , Perceptron, Genetic Programming, Clustering, etc. may be used.

Of these, CNNs are a type of multilayer perceptrons designed to use minimal preprocessing. A CNN consists of one or several convolution layers and general artificial neural network layers on top, and additionally utilizes weights and pooling layers. Thanks to this structure, CNN can fully utilize the input data with a two-dimensional structure. Compared to other deep learning structures, CNN shows good performance in both video and audio fields. CNNs can also be trained via standard back-propagation. CNNs are easier to train than other feedforward artificial neural network techniques and have the advantage of using fewer parameters.

Convolutional networks are neural networks that contain sets of nodes with bound parameters. The increasing size of available training data and the availability of computational power, combined with algorithmic advances such as piecewise linear unit and dropout training, have greatly improved many computer vision tasks. With huge data sets, such as those available for many tasks today, overfitting is not critical, and increasing the size of the network improves test accuracy. Optimal use of computing resources becomes a limiting factor. To this end, a distributed, scalable implementation of deep neural networks can be used.

In the present invention, through the development of an IoT (Internet of Things)-based integrated sensor module model for a low-end smart farm, it can contribute to improving the productivity of facility farms and increasing the income of facility farms. If the use environment is changed through sensor selection and firmware updater according to the purpose of use and the firmware is updated by applying only the necessary sensors, it can be applied in various environments (eg, facility house, cold storage, barn, insect breeding, etc.). .

In the present invention, a plurality of sensor modules are configured as one complex module, so that a farmhouse that requires a total of 4 types of sensors is equipped with all 4 types of sensors. We plan to develop an integrated sensor module for smart farms by improving the design process and signal processing circuit manufacturing process so that

Recently, at a time when the installation and utilization of smart farms are rapidly increasing, it is possible to supply at low cost through localization of integrated sensor modules for smart farms.

According to the results of a survey conducted on farms, obstacles to the introduction of the current smart farm include burden of facility cost (24%), lack of follow-up management by the installer (19%), frequent breakdowns (16%), and lack of management technology (15%). etc., and it is judged that it is urgent to research and develop integrated sensor technology for environmental control along with the development of various single sensors (temperature, humidity, carbon dioxide, nitrogen, etc.) for smart farm environment control.

The integrated sensor module for smart farms of the present invention can be designed to integrally manufacture a plurality of sensor modules and have a simple detachable structure. According to one embodiment, it is developed in a connector type, and the external appearance is the same by waterproof treatment, but only the necessary sensors inside can be developed in a detachable structure.

2 is a diagram for explaining learning of a neural network according to an embodiment of the present invention.

As shown in FIG. 2 , the learning device may train the neural network 124 to extract weed images or cutter 158 images included in the images. According to one embodiment, the learning device may be a separate subject different from the control unit 120, but is not limited thereto.

The neural network 124 includes an input layer 122 into which training samples are input and an output layer 126 which outputs training outputs, and may be learned based on differences between the training outputs and labels. Here, labels may be defined based on image information corresponding to an object. The neural network 124 is connected to a group of a plurality of nodes, and is defined by weights between connected nodes and an activation function that activates the nodes.

The learning device may train the neural network 124 using a gradient descent (GD) technique or a stochastic gradient descent (SGD) technique. The learning device may use a loss function designed by outputs and labels of the neural network.

The learning device may calculate a training error using a predefined loss function. The loss function may be predefined with labels, outputs and parameters as input variables, where the parameters may be set by weights in the neural network 124. For example, the loss function may be designed in a mean square error (MSE) form, an entropy form, and the like, and various techniques or methods may be employed in an embodiment in which the loss function is designed.

The learning device may find weights affecting the training error using a backpropagation technique. Here, weights are relationships between nodes in neural network 124 . The learning device may use the SGD technique using labels and outputs to optimize the weights found through the backpropagation technique. For example, the learning device may update weights of a loss function defined based on labels, outputs, and weights using the SGD technique.

According to an embodiment, the learning device may obtain training images and extract training objects from the training images. The learning device may obtain pre-labeled information (first labels) for each of the training objects, and may obtain first labels that are image information corresponding to the training objects.

According to an embodiment, the learning device may generate training feature vectors based on size features, length features, and color features of training objects. Various methods may be employed to extract features.

According to an embodiment, the learning device may obtain training outputs by applying the training feature vectors to the neural network 124 . The learning device may train an image extraction algorithm of the neural network 124 based on the training outputs and the first labels. The learning device may train the image extraction algorithm of the neural network 124 by calculating training errors corresponding to the training outputs and optimizing a connection relationship between nodes in the neural network 124 to minimize the training errors. The server 120 may extract weed images or cutter images from the images using the neural network 124 that has been trained.

3 is a diagram for explaining a control unit according to an embodiment of the present invention.

As shown in FIG. 3 , the controller 120 may include one or more processors 121 , one or more memories 123 , and/or a transceiver 125 . As an example, at least one of these components of the controller 120 may be omitted or another component may be added to the controller 120 . Additionally or alternatively, some of the components may be integrated and implemented, or implemented as a singular or plural entity. At least some of the components inside and outside the controller 120 are connected to each other through a bus, general purpose input/output (GPIO), serial peripheral interface (SPI), or mobile industry processor interface (MIPI). Data and/or signals can be sent and received.

One or more processors 121 may control at least one component of the control unit 120 connected to the processor 121 by driving software (eg, instructions, programs, etc.). In addition, the processor 121 may perform operations such as various calculations, processing, data generation, and processing related to the present invention. Also, the processor 121 may retrieve data from one or more memories 123 or store data in one or more memories 123 .

As described above, the one or more processors 121 may receive the first to fourth sensing data from the sensing unit 110 through the transceiver 125 in real time or non-real time in the form of digital packets.

The one or more processors 121 may receive first sensed data from the sensing unit 110 and perform smoothing, amplification, and switching of the first sensed data to generate a first output voltage and a first output current.

The one or more processors 121 may receive second sensed data from the sensing unit 110 and generate a second output voltage and a second output current by performing smoothing, amplification, and switching of the second sensed data.

The one or more processors 121 may receive third sensed data from the sensing unit 110 and generate a third output voltage and a third output current by performing smoothing, amplification, and switching of the third sensed data.

The one or more processors 121 may receive fourth sensed data from the sensing unit 110 and generate a fourth output voltage and a fourth output current by performing smoothing, amplification, and switching of the fourth sensed data.

One or more processors 121 may transmit the generated first to fourth output voltages to the voltage output unit 130 through the transceiver 123 .

One or more processors 121 may transmit the generated first to fourth output currents to the current output unit 130 through the transceiver 123 .

One or more memories 123 may store various data. Data stored in the memory 123 is data obtained, processed, or used by at least one component of the controller 120, and may include software (eg, commands, programs, etc.). Memory 123 may include volatile and/or non-volatile memory. In the present invention, a command or program is software stored in the memory 123, and is an operating system for controlling the resources of the server 120, an application, and/or an application that provides various functions so that the application can utilize the resources of the server 120. It may include middleware provided to .

One or more memories 123 may store the above-described first to fourth sensing data, first to fourth output voltages, first to fourth output currents, and the like. In addition, the one or more memories 123 may store instructions that cause the one or more processors 121 to perform calculations when executed by the one or more processors 121 .

As an embodiment, the controller 120 may further include a transceiver 125 . The transceiver 125 may perform wireless or wired communication between the sensing unit 110, the control unit 120, the voltage output unit 130, the current output unit 140, and/or other devices. For example, the transceiver 125 may include enhanced mobile broadband (eMBB), ultra reliable low-latency communications (URLC), massive machine type communications (MMTC), long-term evolution (LTE), LTE Advance (LTE-A), UMTS (Universal Mobile Telecommunications System), GSM (Global System for Mobile communications), CDMA (code division multiple access), WCDMA (wideband CDMA), WiBro (Wireless Broadband), WiFi (wireless fidelity), Bluetooth (Bluetooth), NFC ( Wireless communication may be performed according to a method such as near field communication (GPS), global positioning system (GPS), or global navigation satellite system (GNSS). For example, the transceiver 125 may perform wired communication according to a method such as universal serial bus (USB), high definition multimedia interface (HDMI), recommended standard 232 (RS-232), or plain old telephone service (POTS). have.

As an example, one or more processors 121 may obtain information from the sensing unit 110 , the voltage output unit 130 , and the current output unit 140 by controlling the transceiver 125 . Information obtained from the sensing unit 110 , the voltage output unit 130 , and the current output unit 140 may be stored in one or more memories 123 .

As an embodiment, the controller 120 may be various types of devices. For example, the controller 120 may be a portable communication device, a computer device, or a device according to a combination of one or more of the foregoing devices. The controller 120 of the present invention is not limited to the above devices.

Various embodiments of the controller 120 according to the present invention may be combined with each other. Each embodiment may be combined according to the number of cases, and the embodiment of the control unit 120 made in combination also belongs to the scope of the present invention. In addition, internal/external components of the control unit 120 according to the present invention described above may be added, changed, replaced, or deleted according to embodiments. Also, the aforementioned internal/external components of the control unit 120 may be implemented as hardware components.

4 is a configuration diagram of an integrated sensor module for smart farms according to an embodiment of the present invention.

As shown in Figure 4, the integrated sensor module for smart farm may include a sensing unit and a control unit 110, a voltage output unit 130 and a current output unit 140.

According to one embodiment, in order to reduce cost, the sensing unit and the control unit 110 may use a 32-bit MCU (Micro Controller Unit), and the voltage output unit 130 and the current output unit 140 may use an 8-bit MCU.

Data may be shared between the sensing unit and the controller 110, the voltage output unit 130, and the current output unit 140 using a universal asynchronous receiver/transmitter (UART) communication method. According to one embodiment, the voltage output unit 130 may output a voltage in the range of 0 to 10V, and the current output unit 140 may output a current in the range of 4mA to 20mA.

Since the biggest problem with the voltage input to the sensor is the ripple voltage, a Low Drop Out (LDO) regulator with less ripple can be applied.

According to one embodiment, the integrated sensor module for smart farm may separate the sensor part and the output part, and separate the power line and the signal line. Parts can be placed according to the flow of analog signals, noise-generating lines can be separated by GND, and the distance between parts can be minimized.

5 is a flowchart of an integrated sensor module control method for smart farms according to an embodiment of the present invention.

Although process steps, method steps, algorithms, etc. are described in a sequential order in the flowchart of FIG. 5, such processes, methods and algorithms may be configured to operate in any suitable order. In other words, the steps of the processes, methods and algorithms described in the various embodiments of the invention need not be performed in the order described herein. Also, although some steps are described as being performed asynchronously, in other embodiments some of these steps may be performed concurrently. Further, illustration of a process by depiction in the drawings does not mean that the illustrated process is exclusive of other changes and modifications thereto, and that any of the illustrated process or steps thereof may be one of various embodiments of the present invention. It is not meant to be essential to one or more, and it does not imply that the illustrated process is preferred.

As shown in FIG. 5 , in step S510, a first gap temperature is calculated. For example, referring to FIGS. 1 to 4 , the control unit 120 determines the first temperature corresponding to the first sensing data generated by the sensing unit 110 when the first temperature is less than or equal to the first threshold value and the first temperature value. A first gap temperature that is a difference of 1 temperature may be calculated.

In step (S520), the set temperature of the heating device is raised. For example, referring to Figures 1 to 4, the controller 120, the set temperature of the heating device 151 of the space in which the integrated sensor module for smart farm is installed to increase by the first gap temperature calculated in step S510 You can control it.

In step S530, a second gap temperature is calculated. For example, referring to FIGS. 1 to 4 , the controller 120 may calculate a second gap temperature that is a difference between the first temperature and the second threshold when the first temperature is greater than or equal to the second threshold.

In step (S540), the set temperature of the heating device is lowered. For example, referring to FIGS. 1 to 4, the control unit 120 lowers the set temperature of the heating device 151 of the space where the integrated sensor module for smart farm is installed by the second gap temperature calculated in step S530 You can control it.

In step S550, a first gap humidity is calculated. For example, referring to FIGS. 1 to 4 , the controller 120 determines the third threshold value and the third threshold value when the first humidity corresponding to the second sensing data generated by the sensing unit 110 is equal to or less than the third threshold value. A first gap humidity that is a difference of 1 humidity may be calculated.

In step S560, the set humidity of the humidifying device is increased. For example, referring to FIGS. 1 to 4, the control unit 120 increases the set humidity of the humidifying device 152 in the space where the integrated sensor module for smart farm is installed by the first gap humidity calculated in step S550 You can control it.

In step S570, a second gap humidity is calculated. For example, referring to FIGS. 1 to 4 , the controller 120 may calculate a second gap humidity that is a difference between the first humidity and the fourth threshold when the first humidity is equal to or greater than the fourth threshold.

In step S580, the set humidity of the humidifying device is lowered. For example, referring to FIGS. 1 to 4, the control unit 120 lowers the set humidity of the humidifying device 152 in the space where the integrated sensor module for smart farm is installed by the second gap humidity calculated in step S570 You can control it.

6 is an exemplary view of the configuration of a device according to an embodiment of the present invention.

Device 401 according to an embodiment includes a processor 402 and a memory 403 . The device 401 according to an embodiment may be the above-described server or terminal. The processor may include at least one device described above with reference to FIGS. 1 to 4 or may perform at least one method described above with reference to FIGS. 1 to 4 . The memory 403 may store information related to the above method or store a program in which the above method is implemented. Memory 403 may be volatile memory or non-volatile memory.

The processor 402 may execute a program and control the device 401 . Codes of programs executed by the processor 402 may be stored in the memory 403 . The device 401 may be connected to an external device (eg, a personal computer or network) through an input/output device (not shown) and exchange data.

The embodiments described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. The device can be commanded. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

delete

Claims (3)

a sensing unit configured to sense temperature to generate first sensing data, detect humidity to generate second sensing data, detect ammonia to generate third sensing data, and detect carbon dioxide to generate fourth sensing data;
Generating a first output voltage and a first output current by performing smoothing, amplification, and switching of the first sensed data, and performing smoothing, amplification, and switching of the second sensed data to generate a second output voltage and a second output current. Generating a third output voltage and a third output current by performing smoothing, amplification, and switching of the third sensing data, and performing smoothing, amplification, and switching of the fourth sensing data to generate a fourth output voltage and a control unit generating a fourth output current;
a voltage output unit selectively outputting the first to fourth output voltages; and
A current output unit configured to selectively output the first to fourth output currents,
The control unit,
Receives spatial information of the space where the integrated sensor module for smart farm is installed, calculates the volume of the space where the integrated sensor module for smart farm is installed from the spatial information, and corresponds to the calculated volume and the fourth sensing data at the first point in time Calculate a concentration per unit volume of the first carbon dioxide, calculate a concentration per second unit volume of the second carbon dioxide corresponding to the fourth sensing data at a second time point that has elapsed a predetermined time from the first time point, A concentration change rate of carbon dioxide is calculated using the first and second concentrations per unit volume, and a first difference between the eighth threshold value and the concentration change rate is calculated when the concentration change rate is equal to or less than an eighth threshold value; A first ratio of the first difference value to the eighth threshold is calculated, and the illumination intensity of the lighting device in the space where the integrated sensor module for smart farm is installed is increased by the first ratio according to the first ratio, and the concentration When the rate of change is greater than or equal to the eighth threshold, calculating a second difference between the rate of change in concentration and the eighth threshold, and calculating a second ratio of the second difference to the eighth threshold, Decreasing the illuminance of the lighting device by the second ratio according to the second ratio,
Integrated sensor module for smart farm. As a control method of the integrated sensor module for smart farm according to claim 1,
calculating a first gap temperature that is a difference between the first temperature and the first temperature when the first temperature corresponding to the first sensing data is equal to or less than a first threshold;
Controlling a set temperature of a heating device in a space where the smart farm integrated sensor module is installed to increase by the first gap temperature;
calculating a second gap temperature that is a difference between the first temperature and the second threshold when the first temperature is greater than or equal to a second threshold;
controlling the set temperature of the heating device to decrease by the second gap temperature;
calculating a first gap humidity that is a difference between the third threshold and the first humidity when the first humidity corresponding to the second sensing data is equal to or less than a third threshold;
Controlling a set humidity of a humidifier in a space where the integrated sensor module for the smart farm is installed to increase by the first gap humidity;
calculating a second gap humidity that is a difference between the first humidity and the fourth threshold when the first humidity is greater than or equal to a fourth threshold; and
Controlling the set temperature of the humidifier to decrease by the second gap humidity
containing
Control method of integrated sensor module for smart farm. According to claim 2,
Receiving spatial information of a space in which the integrated sensor module for the smart farm is installed;
Calculating the volume of the space in which the integrated sensor module for the smart farm is installed from the space information;
calculating a concentration per unit volume of first ammonia corresponding to the calculated volume and the third sensing data;
Forming a first control signal for controlling the ventilator of the space in which the integrated sensor module for the smart farm is installed to operate when the calculated concentration per unit volume is greater than or equal to a fifth threshold value;
Forming a second control signal for controlling to open the door and window of the space where the integrated sensor module for smart farm is installed when the concentration per unit volume is equal to or greater than a sixth threshold value higher than the fifth threshold value; and
When the concentration per unit volume is greater than the seventh threshold value higher than the sixth threshold value, a third control signal is formed to control the alarm device of the space where the integrated sensor module for smart farm is installed and to transmit an access prohibition announcement step
Including more,
Control method of integrated sensor module for smart farm.

Images