KR102602273B1 - System and method for recognizing dynamic anomalies of multiple livestock equipment in a smart farm system - Google Patents

Abstract

The present invention relates to a dynamic abnormal situation recognition system for multiple livestock housing equipment in a smart farm system.
The present invention collects status data including environmental information of the livestock house and driving information of the driving equipment and provides it to the central server, and when receiving list information about the prediction model for determining abnormal situations of the driving equipment from the central server, a prediction model is created. A smart environment provision system that selects a prediction model that matches the state data collected from the list and delivers it to the central server; and receiving state data collected by the smart environment provision system, accumulating and storing the received state data, generating a prediction model based on the state data provided through each smart environment provision system, and storing the generated prediction models. It is stored and managed in the list pool, the list of stored prediction models is provided to the smart environment provision system, and when information about the target prediction model is received from the smart environment provision system, the abnormal situation of the driving equipment is determined using the corresponding prediction model. and a central server that provides the results to the corresponding smart environment provision system.

Description

System and method for recognizing dynamic anomalies of multiple livestock equipment in a smart farm system}

The present invention relates to a system for recognizing dynamic abnormal situations of multiple livestock housing equipment in a smart farm system. More specifically, the present invention relates to a dynamic abnormal situation recognition system for multiple livestock equipment in a smart farm system to determine whether the automation equipment required for building a smart farm system is broken. It's about cognitive systems.

Recently, the size of livestock farms has increased significantly compared to the past, and as a result, interest in automated livestock farming smart environment provision systems is increasing.

This smart environment provision system increases the productivity of livestock by maintaining an environment suitable for livestock growth conditions within the livestock barn.

Here, maintaining an appropriate environment is possible by building and controlling many equipment inside and outside the livestock house, that is, control equipment such as temperature, humidity, CO2, ammonia sensors, exhaust fans, flow fans, cooling pads, radiators, etc.

However, the sensors and control devices of the smart environment provision system have a high risk of failure due to poor environments such as closed livestock spaces and lack of stable power supply, but there is a problem in that it is difficult to easily determine this.

In general, the operation of such control equipment is mainly carried out through the initial installation and setup of livestock farms, and subsequent monitoring of the control equipment is insufficient or, even if monitored, due to the absence of systematic management and analysis of collected data, the installed equipment is not accurate and prompt. Error judgment, that is, detection of abnormal states and malfunctions such as sensor status and errors, and controller status and errors, is not easy.

As a result, a suitable environment is not maintained, which greatly affects the productivity of livestock.

Moreover, there are various types of livestock barns in Korea, and each livestock barn is equipped with a variety of equipment.

A method is required to quickly detect abnormal situations by using these diverse and numerous pieces of equipment simultaneously and adaptively to the environment of each livestock farm.

The present invention is intended to solve the conventional problems, by simultaneously constructing an analysis model for multiple livestock equipment abnormal situations through information collected from multiple equipment (environmental sensors and driving equipment) installed in the livestock barn, and dynamically applying it to the livestock barn. The purpose is to provide a dynamic abnormal situation recognition system for multiple livestock farming equipment in a smart farm system that quickly detects equipment malfunctions adaptively to each livestock farm.

The object of the present invention is not limited to the object mentioned above, and other objects not mentioned will be clearly understood by those skilled in the art from the description below.

In a smart farm system according to an embodiment of the present invention to achieve the above object, the dynamic abnormal situation recognition system of multiple livestock barn equipment collects status data including environmental information of the livestock barn and driving information of the driving equipment and provides it to the central server. And, upon receiving list information about prediction models for determining abnormal situations of driving equipment from the central server, a smart environment is provided that selects a prediction model that matches the collected state data from the prediction model list and transmits it to the central server. system; And receiving state data collected by the smart environment providing system, accumulating and storing the received state data, generating a prediction model based on the state data provided through each smart environment providing system, and generating the generated prediction models. It is stored and managed in a storage list pool, the list of prediction models being stored is provided to the smart environment provision system, and when information on the prediction model to be predicted is received from the smart environment provision system, the prediction model is used to detect abnormalities in the driving equipment. It includes a central server that judges the situation and provides the results to the corresponding smart environment provision system.

The smart environment provision system includes a plurality of sensors that collect status data including environmental sensing information such as temperature, humidity, CO2, and ammonia information; Driving equipment that drives to form the environment of the livestock house and provides status data containing the driving information; and a local server that stores state data provided from the sensors and driving equipment in the dataset database and provides the state data stored in the dataset database to the central server.

Additionally, the local server includes a data collection unit that collects state data and stores the collected state data in a database; a data pre-processing unit that pre-processes the collected state data and stores the pre-processed state data in a purification database; a data provider providing refined state data stored in the refined database to the central server; A prediction model selection unit that receives a list of learned prediction models from the central server, selects a prediction model from the list of prediction models provided based on the collected state data, and provides selected prediction model information to the central server. ; and a malfunction detection unit that detects a malfunction of the compared driving equipment according to a result of comparing state data through a prediction model selected by the central server.

The local server dynamically receives a prediction model list from the central server, and the prediction model list preferably includes state data variable information of the driving equipment and sensors applied to the prediction model.

In the local server, a prediction model of driving devices can be identified by a variable (instance), which is an entity for recognition of each device.

Meanwhile, the central server includes a data collection unit that collects status data of sensors and driving equipment for each livestock house from a smart environment provision system for each livestock house; a prediction model generator that generates a prediction model for detecting abnormal situations using the collected state data; and a model list providing unit that dynamically distributes the generated prediction model to the smart environment provision system of the livestock farm of the corresponding farm.

The central server stores the generated learning model and manages it by storing it in a learning model pool.

The central server executes a prediction model based on state data corresponding to the identified variables and determines abnormal situations of each equipment through the prediction result value.

And in a smart farm system according to an embodiment of the present invention, the method of recognizing dynamic abnormal situations of multiple livestock barn equipment collects status data including environmental information of the livestock barn and driving information of the driving equipment by a smart environment provision system and collects status data including driving information of the driving equipment to a central server. Steps provided to; receiving, by the central server, state data collected by the smart environment providing system and accumulating and storing the received state data; Creating a prediction model based on state data provided through each smart environment provision system by the central server, and storing and managing the generated prediction models in a storage list pool; providing, by the central server, a list of stored prediction models to the smart environment providing system; When the smart environment provision system receives list information about prediction models for determining abnormal situations of driving equipment from the central server, it selects a prediction model that matches the collected status data from the prediction model list and sends it to the central server. delivering; And when information on the prediction target prediction model is received from the smart environment provision system by the central server, determining an abnormal situation of the driving equipment using the corresponding prediction model and providing the results to the corresponding smart environment provision system. Includes.

The step of collecting and providing state data to the central server by the smart environment providing system includes collecting state data including environmental sensing information such as temperature, humidity, CO2, and ammonia information; Driving to create an environment in a livestock farm and providing state data including driving information; Storing state data provided from the sensors and the driving equipment in a dataset database; It includes storing status data provided from the sensors and driving equipment in the dataset database, and providing the status data stored in the dataset database to the central server.

In the step of selecting a prediction model that matches the collected state data and transmitting it to the central server, the prediction model list from the central server includes variable information to be applied to each prediction model, and is collected by the smart environment providing system. You can select the prediction model you want to apply by comparing the status information with the variables of the prediction model.

In addition, the step of providing state data stored in the dataset database to the central server by the smart environment providing system preprocesses the collected state data and stores the preprocessed state data in the purification database.

The step of accumulating and storing the received state data by the central server includes collecting state data of sensors and driving equipment for each livestock house from a smart environment provision system for each livestock house; generating a prediction model to detect an abnormal situation using the collected state data; and storing the generated model in a pool and dynamically distributing the list of prediction models stored in the pool to the smart environment providing system.

The central server stores and manages the generated prediction model in a learning model pool.

When state information is received from the smart environment providing system, the central server determines whether a prediction model stored in the learning model pool exists using the state information as a variable, and if so, learns it through the received state information.

When the prediction model stored in the learning model pool is learned by the central server, the list of prediction models stored in the learning model pool is dynamically provided to each smart environment providing system.

According to one embodiment of the present invention, from equipment information collection to abnormal situation recognition, no matter what equipment in the livestock environment is given, information related to the livestock equipment, learning, and model extraction, whenever a learning prediction model is created or updated. It has the effect of providing prediction and result information by dynamically distributing the model.

Figure 1 is a functional block diagram for explaining a dynamic abnormal situation recognition system for multiple livestock housing equipment in a smart farm system according to the present invention.
Figure 2 is a conceptual diagram of a dynamic abnormal situation recognition system for multiple livestock housing equipment in a smart farm system according to the present invention.
Figure 3 is a functional block diagram for explaining the smart environment provision system for livestock farms in Figure 1.
Figure 4 is a functional block diagram for explaining the detailed configuration of the local server of Figure 3
Figure 5 is a functional block diagram for explaining the detailed configuration of the central server of Figure 1.
Figure 6 is a signal flow diagram illustrating a method for recognizing dynamic abnormal situations of multiple livestock housing equipment in a smart farm system according to an embodiment of the present invention.
Figure 7 is a mechanism procedure diagram for explaining a method of recognizing dynamic abnormal situations of multiple livestock housing equipment in a smart farm system according to an embodiment of the present invention.
Figure 8 is a flowchart illustrating detailed steps of a method for providing a smart environment according to an embodiment of the present invention.
Figure 9 is a reference diagram for explaining detailed blocks and message flow diagrams in a method for providing a smart environment according to an embodiment of the present invention.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and will be implemented in various different forms. The present embodiments only serve to ensure that the disclosure of the present invention is complete and that common knowledge in the technical field to which the present invention pertains is not limited. It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims. Meanwhile, the terms used in this specification are for describing embodiments and are not intended to limit the present invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” means that a referenced element, step, operation and/or element precludes the presence of one or more other elements, steps, operations and/or elements. or does not rule out addition.

Figure 1 is a functional block diagram for explaining a dynamic abnormal situation recognition system of multiple livestock housing equipment in a smart farm system according to the present invention, and Figure 2 is a functional block diagram of a dynamic abnormal situation recognition system of multiple livestock equipment in a smart farm system according to the present invention. It is a concept diagram.

As shown in Figures 1 and 2, the dynamic abnormal situation recognition system of multiple livestock barn equipment in a smart farm system according to an embodiment of the present invention includes a plurality of smart environment provision systems 100 and a central server 200. do.

The smart environment provision system 100 collects status data including environmental information of the livestock farm and operation information of the driving equipment and provides it to the central server 200.

And the smart environment providing system 100 receives list information about prediction models for determining abnormal situations of driving equipment from the central server 200, and selects a prediction model matching the collected state data from the prediction model list. Select and deliver to the central server 200.

The central server 200 receives state data collected by the smart environment provision system 100, accumulates and stores the received state data, and makes predictions based on the state data provided through each smart environment provision system 100. Create a model.

The central server 200 stores and manages the generated prediction models in a storage list pool and provides the stored prediction model list to the smart environment providing system 100.

In addition, when information about the prediction model to be predicted is received from the smart environment provision system 100, the central server 200 determines an abnormal situation of the driving equipment using the corresponding prediction model and sends the result to the smart environment provision system 100. ) is provided.

Therefore, according to an embodiment of the present invention, there is an advantage of increasing the productivity of various types of livestock farms with various types of equipment in livestock farms by quickly and adaptively processing the determination of abnormal situations in the driving equipment for each livestock barn. there is.

Figure 3 is a functional block diagram for explaining the smart environment provision system for livestock farms in Figure 1.

As shown in FIG. 3, the smart environment providing system 100 according to an embodiment of the present invention includes a plurality of sensors 110, a plurality of driving equipment 120, a dataset database 130, and a local server 140. ) includes.

The sensor 110 may be implemented in various ways, such as temperature, humidity, CO2, and ammonia sensors, and collects state data including environmental sensing information, which is sensing information collected from each sensor 110.

The driving equipment 120 is equipment for forming the environment of the livestock house and may be equipment such as an exhaust fan, flow fan, cooling pad, or radiator, but is not limited thereto. This driving equipment 120 drives to create the environment of the livestock house and provides state data containing the driving information.

The dataset database 130 stores state data provided from the sensors 110 and the driving equipment 120.

The local server 140 stores state data provided from the sensors 110 and the driving equipment 120 in the dataset database 130, and sends the state data stored in the dataset database 130 to the central server 200. provided to. At this time, when storing state data in the dataset database 130, the local server 140 may perform preprocessing to standardize the data.

Then, the local server 140 applies the collected state data to a prediction model dynamically provided by the central server 200 to detect whether the driving equipment 120 and the sensors 110 are operating abnormally.

Hereinafter, the detailed configuration of the local server 140 according to an embodiment of the present invention will be described with reference to FIG. 4.

FIG. 4 is a functional block diagram for explaining the detailed configuration of the local server of FIG. 3.

As shown in FIG. 4, the local server 140 includes a data collection unit 141, a data preprocessing unit 142, a data providing unit 143, a prediction model selection unit 144, and a malfunction detection unit 145. do.

The data collection unit 141 collects state data from the sensor 110 and the driving equipment 120. Status data collected in this way can be stored and managed in an arbitrary database in the form of LOW data.

The data preprocessing unit 120 preprocesses the collected state data and stores the preprocessed state data in the dataset database 130.

The data provider 143 provides the preprocessed state data stored in the datanet database 130 to the central server 200.

The prediction model selection unit 144 receives a list of learned prediction models from the central server 200, selects a prediction model from the list of prediction models provided based on the collected state data, and provides the selected prediction model information. Provided to the central server 200.

The malfunction detection unit 145 detects a malfunction of the compared driving equipment 120 according to the result of comparing state data through the prediction model selected by the central server 200.

That is, in one embodiment of the present invention, the local server 140 selects the prediction model to be applied from the prediction model list provided by the central server 200, and the central server 200 selects the prediction model selected in the local server 140. A malfunction is detected using and the result is delivered to the local server 140.

In the following, the detailed configuration of the central server 200 according to an embodiment of the present invention will be described with reference to FIG. 5.

FIG. 5 is a functional block diagram for explaining the detailed configuration of the central server of FIG. 1.

As shown in FIG. 5, the central server 200 includes a data collection unit 210, a prediction model creation unit 220, a learning model storage unit 230, a model list providing unit 240, and an abnormality determination unit. Includes (250).

The data collection unit 210 collects status data of the sensor 110 and the driving equipment 120 for each livestock barn from the smart environment provision system 100 of each livestock barn.

The prediction model generator 220 uses the collected state data to create a prediction model for detecting abnormal situations.

The learning model storage unit 230 stores and manages the generated learning model. The learning model storage unit 230 stores information about a learned prediction model and a list of prediction models being managed. Here, it is desirable that the prediction model list includes prediction model information and individual variables (state data) applied to the prediction model.

The model list providing unit 240 dynamically distributes the list of stored prediction models to the corresponding smart environment providing system 100.

When the prediction model selected from the smart environment provision system 100 is provided, the abnormality determination unit determines whether the driving equipment is abnormal using the selected prediction model and provides the result to the smart environment provision system 100.

In this way, the central server 200 can identify the prediction models of the driving equipment 120 by variables (instances), which are entities for recognition of each equipment, through each prediction model.

According to one embodiment of the present invention, the local server 140 of the livestock farm stores a model list of each equipment as an analysis client (308), and the prediction model selected by the local server 140 is stored in the central server 200. Collect equipment information by performing prediction (309) using data input from the current data client, determining the correlation between actual and predicted values (312), and determining whether there is equipment malfunction (310) according to the results. From recognition of abnormal situations, to collection and learning of information related to the livestock equipment and model extraction, no matter what equipment in the livestock environment is given, whenever the learning model is updated, the model can be dynamically distributed to provide prediction and result information. It works.

Figure 6 is a signal flow diagram for explaining a method for recognizing dynamic abnormal situations of multiple livestock housing equipment in a smart farm system according to an embodiment of the present invention, and Figure 7 is a signal flow diagram for multiple livestock housing equipment in a smart farm system according to an embodiment of the present invention. This is a mechanism procedure diagram to explain the dynamic abnormal situation recognition method.

Hereinafter, a method for recognizing dynamic abnormal situations of multiple livestock housing equipment in a smart farm system according to an embodiment of the present invention will be described with reference to FIG. 6.

First, status data including environmental information of the livestock house and driving information of the driving equipment 120 are collected by the smart environment providing system 100 and provided to the central server 200 (S100).

Next, the central server 200 receives the state data collected by each smart environment providing system 100 and accumulates and stores the received state data (S200). The central server 200 may continuously learn and update the prediction model created using state data collected from each smart environment providing system 100. Thereafter, the central server 200 creates a prediction model based on the state data provided through each smart environment providing system 100, and manages the generated prediction models by storing them in a storage list pool (S300). Additionally, even when the prediction model is updated, a prediction model list including the corresponding prediction model can be dynamically provided to the smart environment providing system 100.

Next, the central server 200 provides the list of stored prediction models to the smart environment providing system 100 (S400).

Thereafter, when list information about prediction models is received from the central server 200 by the smart environment providing system 100, a prediction model matching the collected state data is selected from the prediction model list and the central server 200 ) is transmitted to (S500). That is, it is desirable for the prediction model of the driving equipment 120 to be identified by a variable (instance), which is an entity included in the state information collected by the smart environment providing system 100.

Subsequently, when information on the prediction model to be predicted is received from the smart environment providing system 100 by the central server 200, the abnormal situation of the driving equipment 120 is determined using the corresponding prediction model, and the result is determined. is provided to the corresponding smart environment provision system 100 (S600).

FIG. 8 is a flowchart for explaining detailed steps in a method for providing a smart environment according to an embodiment of the present invention, and FIG. 9 is a detailed block and message flow chart for explaining detailed steps in a method for providing a smart environment according to an embodiment of the present invention. This is a reference diagram.

Hereinafter, the detailed steps of collecting state data performed by the smart environment providing system 100 of the present invention and providing it to the central server 200 (S100) will be described with reference to FIGS. 8 and 9. .

Status data including environmental sensing information such as temperature, humidity, CO2, and ammonia information is collected (S110).

Then, it is driven to create the environment of the livestock house, and state data containing the driving information is provided (S120).

Next, state data provided from the sensors 110 and the driving equipment 120 are stored in the dataset database 130 (S130). Additionally, the collected state data may be preprocessed and stored.

Afterwards, the state data stored in the dataset database 130 is provided to the central server 200 (S140).

Meanwhile, in one embodiment of the present invention, the smart environment providing system 100 and the central server 200 may be configured to include a communication module, memory, and processor, respectively.

The communication module transmits and receives data within the smart environment provision system 100, which includes the sensor 110, driving equipment 120, database 130, and local server 140, and data with the central server 200.

Such communication modules may include both wired communication modules and wireless communication modules. The wired communication module may be implemented as a power line communication device, a telephone line communication device, home cable (MoCA), Ethernet, IEEE1294, integrated wired home network, and RS-485 driving equipment 120. Additionally, the wireless communication module can be implemented with WLAN (wireless LAN), Bluetooth, HDR WPAN, UWB, ZigBee, Impulse Radio, 60GHz WPAN, Binary-CDMA, wireless USB technology, and wireless HDMI technology.

The memory of the smart environment providing system 100 stores a program that collects and transmits state data and a program that selects and provides a prediction model based on the state data from a prediction model list, and the processor executes the program stored in the memory.

And in the memory of the central server 200, a program for storing and managing the state data provided by each smart environment providing system 100, a program for generating a prediction model through the state data, and storing the generated prediction models in the pool. A program for determining whether there is an abnormality in the driving equipment using the management program and the prediction model selected by the smart environment providing system 100 and providing the results to the smart environment providing system 100 is stored, and the processor Runs the program stored in memory.

At this time, memory is a general term for non-volatile storage devices and volatile storage devices that continue to retain stored information even when power is not supplied.

For example, memory can be found in compact flash (CF) cards, secure digital (SD) cards, memory sticks, solid-state drives (SSD), and micro SD cards. It may include magnetic computer storage devices such as NAND flash memory and hard disk drives (HDD), and optical disc drives such as CD-ROM and DVD-ROM.

For reference, components according to embodiments of the present invention may be implemented in the form of software or hardware such as FPGA (Field Programmable Gate Array) or ASIC (Application Specific Integrated Circuit), and may perform certain roles.

However, 'components' are not limited to software or hardware, and each component may be configured to reside on an addressable storage medium or may be configured to run on one or more processors.

Thus, as an example, a component may include components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, and sub-processes. Includes routines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables.

Components and the functionality provided within them may be combined into a smaller number of components or further separated into additional components.

At this time, it will be understood that each block of the processing flow diagram diagrams and combinations of the flow diagram diagrams can be performed by computer program instructions. These computer program instructions can be mounted on a processor of a general-purpose computer, special-purpose computer, or other programmable data processing equipment, so that the instructions performed through the processor of the computer or other programmable data processing equipment are described in the flow chart block(s). It creates the means to perform functions. These computer program instructions may be stored in a computer-readable memory or may be stored in a computer-readable memory that can be directed to a computer or other programmable data processing equipment to implement a function in a particular manner. The instructions stored in memory may also produce manufactured items containing instruction means to perform the functions described in the flow diagram block(s). Computer program instructions can also be mounted on a computer or other programmable data processing equipment, so that a series of operational steps are performed on the computer or other programmable data processing equipment to create a process that is executed by the computer, thereby generating a process that is executed by the computer or other programmable data processing equipment. Instructions that perform processing equipment may also provide steps for executing the functions described in the flow diagram block(s).

Additionally, each block may represent a module, segment, or portion of code that includes one or more executable instructions for executing specified logical function(s). Additionally, it should be noted that in some alternative execution examples it is possible for the functions mentioned in the blocks to occur out of order. For example, it is possible for two blocks shown in succession to be performed substantially at the same time, or it is possible for the blocks to be performed in reverse order depending on the corresponding function.

At this time, the term '~unit' used in this embodiment refers to software or hardware components such as FPGA or ASIC, and the '~unit' performs certain roles. However, '~part' is not limited to software or hardware. The '~ part' may be configured to reside in an addressable storage medium and may be configured to reproduce on one or more processors. Therefore, as an example, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. Additionally, components and 'parts' may be implemented to regenerate one or more CPUs within a device or a secure multimedia card.

Above, the configuration of the present invention has been described in detail with reference to the accompanying drawings, but this is merely an example, and those skilled in the art will be able to make various modifications and changes within the scope of the technical idea of the present invention. Of course this is possible. Therefore, the scope of protection of the present invention should not be limited to the above-described embodiments, but should be determined by the description of the claims below.

Claims (16)

Status data including environmental information of the livestock shed and operation information of the driving equipment is collected and provided to the central server, and when list information about prediction models for determining abnormal situations of the driving equipment is received from the central server, the prediction model list is selected. A smart environment providing system that selects a prediction model matching the collected state data and delivers it to the central server; and
State data collected by the smart environment provision system is received, the received state data is accumulated and stored in an internal database, a prediction model is generated based on the state data provided through each smart environment provision system, and the generated prediction is made. Models are stored and managed in a storage list pool, a list of stored prediction models is provided to the smart environment provision system, and when information on the prediction model to be predicted is received from the smart environment provision system, the corresponding prediction model is used to drive equipment. It includes a central server that determines abnormal situations and provides the results to the corresponding smart environment provision system,
The local server is
Dynamically receive a prediction model list from the central server,
In the prediction model list,
State data variable information of the driving equipment and sensors applied to the prediction model is included,
It further includes a prediction model selection unit that receives a list of prediction models from the central server, selects a prediction model from the list of prediction models provided based on the collected state data, and provides selected prediction model information to the central server. doing
A dynamic abnormal situation recognition system for multi-housing equipment in a smart farm system.
In paragraph 1
The smart environment provision system is,
A plurality of sensors that collect status data including environmental sensing information including at least one of temperature, humidity, CO2, and ammonia information;
Driving equipment that drives to form the environment of the livestock house and provides status data containing the driving information; and
Dynamic abnormal situations of multiple livestock housing equipment in a smart farm system including a local server that stores status data provided from the sensors and driving equipment in a dataset database and provides the status data stored in the dataset database to the central server. cognitive system.
delete According to clause 2,
The local server is,
a data collection unit that collects state data and stores the collected state data in a database;
a data pre-processing unit that pre-processes the collected state data and stores the pre-processed state data in a purification database;
a data provider providing refined state data stored in the refined database to the central server; and
A dynamic abnormal situation recognition system for multiple livestock housing equipment in a smart farm system including a malfunction detection unit that detects malfunction of the compared driving equipment according to the result of comparing status data through the prediction model selected by the central server.
In paragraph 1
The local server is,
A dynamic abnormal situation recognition system for multiple livestock housing equipment in a smart farm system in which the prediction model of the driving equipment is identified by variables (instances), which are entities for recognition of each equipment.
According to clause 1,
The central server is,
A data collection unit that collects status data of sensors and driving equipment for each livestock barn from the smart environment provision system for each livestock barn;
a prediction model generator that generates a prediction model for detecting abnormal situations using the collected state data; and
A dynamic abnormal situation recognition system for multiple livestock farming equipment in a smart farm system, including a model list provision unit that dynamically distributes the generated prediction model to the smart environment provision system of the livestock farm of the corresponding farm.
According to clause 6,
The central server is,
A dynamic abnormal situation recognition system for multi-housing equipment in a smart farm system that stores the generated learning model and manages it by storing it in a learning model pool.
According to clause 7,
The central server is,
In a smart farm system, the prediction model corresponding to the learning model pool is executed based on the status data received from the smart environment providing system and the selected prediction model, and the abnormal situation of each equipment is determined through the prediction result value. Dynamic abnormal situation recognition system for multi-housing equipment.
Collecting status data including environmental information of a livestock farm and driving information of driving equipment by a smart environment providing system and providing the information to a central server;
receiving, by the central server, state data collected by the smart environment providing system and accumulating and storing the received state data;
Creating a prediction model based on state data provided through each smart environment provision system by the central server, and storing and managing the generated prediction models in a storage list pool;
providing, by the central server, a list of stored prediction models to the smart environment providing system;
When the smart environment provision system receives list information about prediction models for determining abnormal situations of driving equipment from the central server, it selects a prediction model that matches the collected status data from the prediction model list and sends it to the central server. delivering; and
When information on a prediction model to be predicted is received from the smart environment provision system by the central server, determining an abnormal situation of the driving equipment using the prediction model and providing the results to the smart environment provision system However,
The step of selecting a prediction model that matches the collected state data and transmitting it to the central server,
The prediction model list from the central server includes variable information matching the state data to be applied to each prediction model,
A method of recognizing dynamic abnormal situations of multiple livestock housing equipment in a smart farm system in which the status information collected by the smart environment provision system is compared with the variables of the prediction model and a prediction model to be applied is selected.
In clause 9
The step of collecting status data and providing it to the central server by the smart environment providing system is,
Collecting state data including one or more environmental sensing information of temperature, humidity, CO2, and ammonia information;
Driving to create an environment in a livestock farm and providing state data including driving information;
Storing state data provided from sensors and the driving equipment in a dataset database;
Dynamic abnormal situations of multiple livestock housing equipment in a smart farm system comprising the steps of storing status data provided from the sensors and driving equipment in the dataset database and providing the status data stored in the dataset database to the central server. Cognitive method.
delete According to clause 10,
The step of providing state data stored in the dataset database to the central server by the smart environment provision system,
A method for recognizing dynamic abnormal situations of multiple livestock farming equipment in a smart farm system, which includes pre-processing the collected state data and storing the pre-processed state data in a purified database.
According to clause 9,
The step of accumulating and storing the received state data by the central server,
Collecting status data of sensors and driving equipment for each livestock barn from a smart environment provision system for each livestock barn;
generating a prediction model to detect an abnormal situation using the collected state data; and
A method for recognizing dynamic abnormal situations of multiple livestock farming equipment in a smart farm system, comprising the steps of storing the generated model in a pool and dynamically distributing the list of prediction models stored in the pool to a smart environment provision system.
According to clause 13,
A method for recognizing dynamic abnormal situations of multiple livestock housing equipment in a smart farm system, wherein the generated prediction model is stored and managed in a learning model pool by the central server.
According to clause 14,
When state information is received from the smart environment providing system, the central server determines whether a prediction model stored in the learning model pool exists using the state information as a variable, and if so, learns through the received state information. A method for recognizing dynamic abnormal situations in multi-housing equipment in a farm system.
According to clause 15,
When the prediction model stored in the learning model pool is learned by the central server, dynamically providing a list of prediction models stored in the learning model pool to each smart environment provision system. How to recognize abnormal situations.