Greenhouse Smart Farm Sensor Anomaly Detection and Response System and Method

Abstract

This invention provides a greenhouse smart farm sensor anomaly detection and response system and method. [Solution] The smart farm management method according to the present invention includes the steps of: the management device acquiring environmental data collected by the main sensor; the management device analyzing the environmental data to determine whether or not there is an abnormality in the main sensor; and the management device activating redundant backup sensors for the main sensor.

Description

Technical Field

[0001] The present invention relates to smart farm technology.

Background Art

[0002] In recent years, with the development of technology, the field of smart farm technology, in which information and communication technologies such as big data, IoT, and AI are applied to agriculture, has been steadily growing. Smart farms are leading agricultural innovations, such as controlling greenhouse environments with sensors, monitoring growth environments, and improving resource use efficiency with energy management systems. Research on smart farm technology has been continuously progressing. Especially recently, by combining with artificial intelligence, smart farms are developing in the direction of reducing human labor, such as decision-making support systems, automatic environment control, and detection of pests and diseases.

[0003] However, in order to further develop and stably develop smart farms combined with artificial intelligence, a large amount of data is required. Currently, in fact, there is a lack of data related to agriculture in South Korea, which may become a problem in the development of smart farm technology.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In greenhouse environments, malfunctions in sensors monitoring growing conditions can prevent timely detection of environmental changes, potentially negatively impacting crops. This can reduce crop productivity and quality. In particular, malfunctions in key environmental sensors such as those for temperature, humidity, and lighting within the greenhouse can lead to malfunctions in interconnected environmental management systems, resulting in greater damage. Furthermore, as more data is needed for the further development of AI-based smart agriculture, data loss due to sensor malfunctions can also be a problem.

[0006] This invention discloses a method for detecting sensor abnormalities at an appropriate time and responding to them promptly.

[0007] The present invention is not limited to the problems described above. Other technical problems not mentioned should be clearly understood by those with ordinary skill in the art to which the present invention pertains from the content described later. [Means for solving the problem]

[0008] In one embodiment of the present invention, a smart farm management method includes the steps of: a management device acquiring environmental data collected by a main sensor; the management device analyzing the environmental data to determine whether or not there is an abnormality in the main sensor; and the management device activating redundant backup sensors for the main sensor.

[0009] In one embodiment, the management device may include a computing device and a storage device that includes commands to cause the management device to perform an action when executed by the computing device. The action may include the management device acquiring environmental data collected by the main sensor, the management device analyzing the environmental data to determine whether or not there is an abnormality in the main sensor, and the management device activating a redundant backup sensor for the main sensor.

[0010] In one embodiment, the smart farm system may include a main sensor, a backup sensor, and a management device. [Effects of the Invention]

[0011] According to the present invention, smart farms can be managed efficiently. The collected data can be used to detect sensor abnormalities in real time using a deep learning-based algorithm. Furthermore, according to the present invention, by installing backup sensors in the smart farm's internal sensors, data loss can be prevented, and damage to farmers that may occur in the event of a sensor malfunction can be minimized. [Brief explanation of the drawing]

[0012] [Figure 1] This figure shows one embodiment in which a management device (100) controls an environmental management device based on environmental data acquired from a main sensor. [Figure 2] This figure shows one embodiment in which a control device activates a backup sensor when a malfunction occurs in the main sensor. [Figure 3] This figure shows one embodiment in which a control device analyzes the environmental impact on crops due to a malfunction in the main sensor. [Figure 4] This figure shows one embodiment of the control device. [Modes for carrying out the invention]

[0013] The present invention is subject to various modifications and can have many different embodiments. Specific embodiments of the present invention may be described in the specification and drawings. However, these are merely illustrative and not intended to limit the present invention to any particular embodiment. Therefore, all modifications, equivalents, or substitutes that fall within the spirit and technical scope of the present invention should be understood as being included within the scope of the present invention.

[0014] In the terms used below, singular expressions should be understood to include plural expressions unless the context clearly indicates otherwise, and terms such as “includes” should be understood to mean that the described features, quantities, stages, actions, components, parts, or combinations thereof exist, without prejudice to the possibility of the existence or addition of one or more other features, quantities, stages, actions, components, parts, or combinations thereof.

[0015] Before providing a detailed explanation of the drawings, it is important to clarify that the classification of components in this specification is merely based on the primary function that each component performs. That is, two or more components described later may be combined into a single component, or a single component may be divided into two or more components based on more subdivided functions. Furthermore, each component described later may additionally perform some or all of the functions performed by other components, in addition to the primary function that it itself performs, and some of the primary functions that each component performs may be exclusively performed by other components.

[0016] Furthermore, when performing a method or operation, each step constituting the method may be performed in a different order than specified, unless the context clearly indicates a specific order. That is, each step may be performed in the same order as specified, substantially simultaneously, or in the reverse order.

[0017] Figure 1 shows one embodiment in which the management device 100 controls the environmental management device based on environmental data acquired from the main sensor.

[0018] The management device 100 can be embodied in a variety of physical forms. For example, the management device 100 can take the form of a PC, a notebook computer, a smart device, a server, or a dedicated data processing chipset.

[0019] The control device 100 can acquire the environmental data collected by the main sensor.

[0020] The main sensor is a sensor installed in the smart farm.

[0021] The main sensor is a sensor that collects environmental data within the smart farm. The main sensor is a sensor that collects environmental data within the smart farm during normal times.

[0022] The main sensor can include various sensors. As an example, the main sensor can include a temperature sensor, a humidity sensor, a soil moisture sensor, an illuminance sensor, an oxygen sensor, a carbon dioxide sensor, a wind speed sensor, a wind direction sensor, etc. As another example, the main sensor can include data such as a voltage sensor and a current sensor.

[0023] The main sensor can transmit the environmental data collected via wired communication to the management device. The main sensor can transmit the environmental data collected via wireless communication to the management device. As an example, the main sensor can transmit the environmental data collected via a wireless communication module such as Wi-Fi to the management device.

[0024] The management device can control the environmental management device based on the environmental data.

[0025] The environmental management device is a device installed in the smart farm.

[0026] The environmental management device is a device that controls the crop cultivation environment of the smart farm. The environmental management device can include an air conditioner, a chiller, a heater, a humidifier, a dehumidifier, a water supply device, a lighting device, an oxygen supply device, a carbon dioxide supply device, an air purifier, a ventilation fan, a power supply, a power generator, etc.

[0027] The environmental control device manages the environment of the smart farm to ensure that the crops grown there are cultivated under optimal conditions. The environmental control device can be controlled based on environmental data. For example, if a crop that thrives at 25°C is being cultivated in the smart farm, the environmental control device can adjust the temperature so that the internal environment of the smart farm remains at 25°C.

[0028] Figure 2 shows an example of how the control device activates a backup sensor when a malfunction occurs in the main sensor.

[0029] The control device can acquire environmental data collected by the main sensor.

[0030] The control device can analyze environmental data to determine whether or not there is a malfunction in the main sensor.

[0031] Determining whether or not there is an abnormality may include using an analytical model to analyze environmental data and determine whether or not there is an abnormality in the main sensor. Examples of when an abnormality occurs in the main sensor include the presence of impurities, the main sensor being oriented incorrectly, the main sensor being subjected to physical impact, or the main sensor not receiving power properly.

[0032] The analysis model is designed to detect sensor anomalies and predict signs of those anomalies. It takes environmental data as input and outputs information regarding the presence or absence of anomalies in the main sensor.

[0033] An analytical model is a machine learning (ML) based model. An analytical model can be a model trained on training data. An analytical model can be a model trained to perform a specific task based on training data.

[0034] The analytical model may be of various types. For example, machine learning models may include decision trees, RF (random forest), KNN (K-nearest neighbor), Naive Bayes, SVM (support vector machine), ANN (artificial neural network), etc.

[0035] The aforementioned ANN may be a DNN (Deep Neural Network), which may include CNNs (Convolutional Neural Networks), RNNs (Recurrent Neural Networks), RBMs (Restricted Boltzmann Machines), DBNs (Deep Belief Networks), GANs (Generative Adversarial Networks), and RLs (Relational Networks).

[0036] The analytical model may be a model that processes time series data. The analytical model may also be an LSTM (Long Short-Term Memory) based model. An LSTM-based model is a model that processes time series data.

[0037] The analysis model analyzes whether or not there is an abnormality in the main sensor based on past environmental data. The analysis model analyzes whether or not there is an abnormality in the main sensor based on environmental data corresponding to a predetermined past period. The analysis model predicts future environmental data based on environmental data corresponding to a predetermined past period, and analyzes whether or not there is an abnormality in the main sensor by comparing and analyzing the predicted results with the measured environmental data.

[0038] If the main sensor is detected to be malfunctioning, the management device can activate a redundant backup sensor to replace the main sensor.

[0039] A backup sensor is a sensor provided in case the main sensor malfunctions. It is a backup sensor designed to activate when the main sensor fails. The backup sensor plays a role in ensuring the continuous collection of environmental data in a smart farm, acting as a substitute for the main sensor.

[0040] The backup sensor may be of the same type as the main sensor. For example, if the main sensor is a temperature sensor, the backup sensor will also be a temperature sensor.

[0041] Spare sensors may be stored in a spare sensor storage box. The spare sensor storage box may be a storage box surrounding the spare sensors. The spare sensor storage box may also be a sealed case for the spare sensors. For example, the spare sensor storage box may be a storage box made of a durable material such as acrylic.

[0042] A spare sensor storage box can serve to protect spare sensors. It can protect spare sensors from external physical shocks or changes in the external environment, or from the causes of malfunctions in the main sensor.

[0043] The backup sensor may not function under normal circumstances. The backup sensor may not function while the main sensor is operating.

[0044] The control device can activate the backup sensors and simultaneously open the backup sensor storage box. For example, the control device can open the backup sensor storage box by adjusting a door attached to one side of the box. By storing the physical sensors and backup sensors separately in this way, even if a malfunction occurs in the physical sensors, continuous environmental data measurement can be performed by activating the backup sensors.

[0045] If the main sensor detects an abnormality, the control device can control the environmental control device based on the environmental data measured by the backup sensor.

[0046] Figure 3 shows one embodiment in which a control device analyzes the environmental impact on crops due to a malfunction in the main sensor.

[0047] The control device can acquire environmental data measured by the main sensor, environmental data measured by the backup sensor, and operational data of the environmental control device.

[0048] The control device can compare and analyze environmental data measured by the main sensor, environmental data measured by the backup sensor, and operational data from the environmental control device.

[0049] The control device can analyze the impact on crops by controlling the environmental control device based on environmental data measured from the main sensor with abnormalities, based on the results of comparative analysis.

[0050] The time at which the control device determines that there is a malfunction in the main sensor may not precisely coincide with the time the malfunction occurred. In this case, the control device may operate based on the environmental data collected by the malfunctioning main sensor during the time before the backup sensor is activated. Controlling the environmental control device based on such incorrect environmental data could have a significant impact on the crops grown inside the smart farm.

[0051] For example, let's assume that the analysis model determines whether or not a malfunction has occurred in the main sensor based on environmental data from 10 hours prior to a predetermined standard. Let's also assume that the crops grown in the smart farm must be grown at 25°C. Furthermore, let's assume that due to a malfunction in the main sensor, the actual temperature in the smart farm is incorrectly measured as 30°C, even though it is 25°C. In addition, if a malfunction occurs in the main sensor, the control device cannot immediately determine that the main sensor is malfunctioning. This is because the analysis model determines whether or not there is a malfunction in the sensor based on environmental data from 10 hours prior to a predetermined time standard, so it cannot determine the malfunction of the main sensor immediately after it occurs. However, as time passes, the probability of the control device determining that a malfunction has occurred in the main sensor increases. This is because the analysis model is continuously inputting environmental data measured by the malfunctioning main sensor. Thus, between the time the malfunction occurs in the main sensor and the time the control device detects the malfunction and activates the backup sensor, the control device begins to control the environmental control device based on the environmental data of the malfunctioning main sensor. In other words, if the main sensor incorrectly measures the smart farm's temperature as 30°C when it is actually 25°C, the control device can control the air conditioner, which is one of the environmental control devices, to lower the smart farm's temperature. In this case, crops that should be grown at 25°C may be affected. When such a situation occurs, the smart farm manager must understand the impact of the main sensor malfunction on the crops. Therefore, the control device can analyze the impact of the main sensor malfunction on the crops based on the data measured by the main sensor, the data measured by the backup sensor, and environmental data, and output this analysis to the user. If necessary, the control device can also utilize an artificial neural network-based model.

[0052] The management system can also inform users of appropriate actions based on the impact on crops.

[0053] For example, the control device can inform the user of what chemicals are currently needed for the crop. Alternatively, the control device can inform the user of who the expert is who can solve the above problem.

[0054] Figure 4 shows one embodiment of the control device 100.

[0055] The management device 100 may include at least one input device 110, a storage device 120, an arithmetic unit 130, an output device 140, an interface device 150, and a communication device 160.

[0056] The input device 110 can input data, information, or models necessary to perform the smart farm management method described above. The input device 110 can input environmental data and operational data. The input device 110 can input analytical models. The input device 110 can input training data necessary to train the analytical models. The input device 110 may also include a device for inputting certain commands or data (such as a keyboard, mouse and touchscreen, joystick, trackball, or touchpad). The input device 110 may also include a configuration in which data is input via a separate storage device (such as a USB drive, CD drive, or hard disk). The input device 110 may also input data via a separate measuring device (such as a sensor, microphone, camera, or scanner) or a separate database. Data may be input to the input device 110 via wired or wireless connection through the communication device 160. Control signals for controlling the management device 100 may be input to the input device 110.

[0057] The storage device 120 can store data, information, or models necessary for executing the smart farm management method described above. The storage device 120 can store environmental data and operational data. The storage device 120 can store analytical models. The storage device 120 can store training data necessary for training analytical models. The storage device 120 may also be a device for storing certain data, information, or models. The storage device 120 can store data, information, and models input via the input device 110. The storage device 120 can store instruction words that cause the arithmetic unit 130 to execute the operations necessary for the smart farm management method. The storage device 120 can store information generated during the calculation process of the arithmetic unit 130. In other words, the storage device 120 can include memory. For example, the storage device can include an HDD (Hard Disk Drive), SSD (Solid State Drive), ROM, RAM, and CD-ROM magnetic tape or floppy disk.

[0058] The computing device 130 can perform the calculations necessary to execute the smart farm management method described above. The computing device 130 can perform the calculations necessary for the management device to acquire environmental data collected by the main sensor. The computing device 130 can perform the calculations necessary for the management device to analyze the environmental data and determine whether or not there is an abnormality in the main sensor. The computing device 130 can perform the calculations necessary for the management device to activate redundant backup sensors for the main sensor. The computing device 130 is a device such as a processor, application processor (AP), or chip with a program embedded in it that processes data and performs certain calculations. For example, the computing device 130 may include a CPU (Central Processing Unit), a graphics processing unit (GPU), or a neural processing unit (NPU). The computing device 130 can generate control signals to control the management device 100. The computing device 130 can generate control signals to control the input device 110, storage device 120, output device 140, interface device 150, and communication device 160 included in the management device 100.

[0059] The output device 140 may be a device that outputs certain data, information, and models. The output device 140 may be a device that outputs certain data, information, and models outside of the management device 100. The output device 140 can also output interfaces necessary for the data processing process, input data, analysis results, etc. The output device 140 may also include a device that outputs data etc. by tactile, visual, auditory, gustatory, and olfactory methods. The output device 140 can be embodied in a variety of physical forms, such as a display, speaker, vibration motor, or document output device. The output device 140 can output data, information, or models stored in the storage device 120. The output device 140 can output data, information, and models generated during the calculation process of the arithmetic unit 130. The output device 140 can output the results calculated by the arithmetic unit 130.

[0060] The interface device 150 is a device that receives certain commands and data from an external source. The interface device 150 can receive control signals for controlling the management device 100. The interface device 150 can output the results analyzed by the management device 100. The interface device 150 can receive information necessary to execute the smart farm management method described above from a physically connected input device or external storage device.

[0061] The communication device 160 can receive information necessary to perform the smart farm management method described above. The communication device 160 can receive models necessary to perform the smart farm management method described above. The communication device 160 can send and receive environmental data and operational data. The communication device 160 can send and receive analysis models. The communication device 160 can receive control signals necessary to control the management device 100. The communication device 160 can transmit the results analyzed by the management device 100. The communication device 160 can be configured to send and receive certain data, information, and models via a wired or wireless network. The communication device 160 can perform network communication such as Wi-Fi (Wireless Fidelity), Wi-Fi Direct, Bluetooth, UWB (Ultra-Wide Band), or NFC (Near Field Communication), USB (Universal Serial Bus), or HDMI (High Definition Multimedia Interface), or LAN (Local Area Network).

[0062] The smart farm management methods described above can be implemented as programs (or applications) that include algorithms executable by a computer.

[0063] The program may be provided stored on a temporary or non-transitory computer-readable medium.

[0064] The aforementioned temporary computer-readable storage medium refers to various types of RAM, including static RAM (SRAM), dynamic RAM (DRAM), SDRAM (Synchronous DRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synclink DRAM (SLDRAM), and direct Rambus RAM (DRRAM).

[0065] The aforementioned non-temporary computer-readable storage medium refers to a storage medium that stores data semi-permanently and is readable by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, the various applications or programs mentioned above may be provided stored on non-temporary computer-readable storage media such as CDs, DVDs, hard disks, Blu-ray discs, USB memory sticks, memory cards, ROMs (read-only memory), PROMs (programmable read-only memory), EPROMs (Erasable PROMs, EPROMs), or EEPROMs (Electrically EPROMs), or flash memory.

[0066] Furthermore, the embodiments and accompanying drawings of the present invention only clearly illustrate a part of the technical concept of the present invention described above, and it is obvious that all modifications and specific embodiments that can be easily inferred by a person skilled in the art within the scope of the technical concept contained in the aforementioned specification and drawings fall within the scope of the rights of the aforementioned technology.

Claims

1. The management device acquires environmental data collected by the main sensor, The management device performs the steps of analyzing the environmental data to determine whether or not there is an abnormality in the main sensor, A smart farm management method comprising the step of the management device activating redundant backup sensors for the main sensor.

2. The smart farm management method according to claim 1, further comprising the step of the management device controlling an environmental management device based on environmental data collected by the main sensor.

3. Detecting an abnormality in the main sensor includes analyzing environmental data using an analysis model to detect the abnormality in the main sensor. The smart farm management method according to claim 1, wherein the analysis model includes a machine learning (ML) based model.

4. The smart farm management method according to claim 3, wherein the analysis model predicts future environmental data based on relevant environmental data from a predetermined past period, and compares and analyzes the predicted results with the environmental data collected by the acquired main sensor to determine whether or not there is an abnormality in the main sensor.

5. The aforementioned spare sensor is stored in a spare sensor storage box that is physically separated from the main sensor. The smart farm management method according to claim 1, wherein activating the spare sensor includes opening one side of the spare sensor that stores the spare sensor.

6. The management device includes the step of acquiring environmental data measured by the auxiliary sensor, The smart farm management method according to claim 1, further comprising the step of the management device controlling an environmental management device based on environmental data measured by the auxiliary sensor.

7. The management device acquires environmental data measured by the auxiliary sensor and operational data of the environmental management device. The management device performs the steps of comparing and analyzing the environmental data measured by the main sensor, the environmental data measured by the backup sensor, and the operating data of the environmental management device. The smart farm management method according to claim 1, further comprising the step of analyzing the impact on crops by controlling the environmental management device based on environmental data measured from the abnormal main sensor, based on the results of the comparison and analysis.

8. The smart farm management method according to claim 7, further comprising the step of the management device informing the user of countermeasures based on the impact on the crop.

9. Includes a computing device and a storage device containing instruction words that cause a management device to perform an operation when the computing device is running, The aforementioned operation is, The aforementioned management device performs the operation of acquiring environmental data collected by the main sensor, The management device performs the operation of analyzing the environmental data to determine whether or not there is an abnormality in the main sensor, The management device includes the operation of activating redundant backup sensors for the main sensor.

10. The management device according to claim 9, further comprising the step of controlling an environmental management device based on environmental data collected by the main sensor.

11. Detecting an abnormality in the main sensor includes analyzing environmental data using an analysis model to detect the abnormality in the main sensor. The management device according to claim 9, wherein the analysis model includes a machine learning (ML) based model.

12. The management device according to claim 11, wherein the analysis model predicts future environmental data based on relevant environmental data from a predetermined past period, and compares and analyzes the predicted results with the environmental data collected by the acquired main sensor to determine whether or not there is an abnormality in the main sensor.

13. The aforementioned spare sensor is stored in a spare sensor storage box that is physically separated from the main sensor. The control device according to claim 9, wherein activating the spare sensor includes opening one side of the spare sensor that stores the spare sensor.

14. The management device includes the step of acquiring environmental data measured by the auxiliary sensor, The management device according to claim 9, further comprising the step of controlling an environmental management device based on environmental data measured by the auxiliary sensor.

15. The management device acquires environmental data measured by the auxiliary sensor and operational data of the environmental management device. The management device performs the steps of comparing and analyzing the environmental data measured by the main sensor, the environmental data measured by the backup sensor, and the operating data of the environmental management device. The management device according to claim 9, further comprising the step of analyzing the impact on crops by controlling the environmental management device based on environmental data measured from the abnormal main sensor, based on the results of the comparison and analysis.

16. The management device according to claim 15, further comprising the step of informing the user of countermeasures based on the impact on the crop.

17. A smart farm system including a main sensor, a backup sensor, and a management device, The aforementioned main sensor collects environmental data from the smart farm. The management device acquires the environmental data collected by the main sensor, The management device analyzes the environmental data to determine whether or not there is an abnormality in the main sensor. The management device transmits a signal to the main sensor to activate the redundant backup sensor, The aforementioned auxiliary sensor collects environmental data of the smart farm in accordance with the operating signal. Smart farm system.

Images