Industrial IoT monitoring system including complex sensor, field RTU terminal, and central control server

Abstract

The present invention relates to an industrial IoT monitoring system including a complex sensor, a field RTU terminal, and a central control server, the system including: a plurality of complex sensors installed in a plurality of areas of an industrial site, respectively, to generate state information sensed in the corresponding area and determination information obtained by determining whether an accident has occurred in the corresponding area on the basis of the state information and transmit the state information and the determination information to a field RTU terminal; a field RTU terminal for verifying whether an accident has occurred in the corresponding area on the basis of the state information and the determination information received from the complex sensor, and transmitting the state information and the determination information received from the complex sensor to a central control server when it is determined that the accident has occurred; and a central control server for controlling a monitoring system on the basis of the state information and the determination information of the corresponding complex sensor received from the field RTU terminal, wherein the complex sensor includes a deep learning-based accident occurrence determination model for determining whether an accident has occurred in an area in which the complex sensor is installed on the basis of the state information sensed by the complex sensor itself, whereby an accident in an area of an industrial site is detected by the plurality of complex sensors installed at regular intervals in areas, respectively, the areas dividing the industrial site, whether an accident has occurred is verified by the field RTU terminal, the location and type of the accident are identified, and training data for accident detection is generated to train the complex sensor.

Description

Industrial IoT surveillance system including complex sensors, field RTU terminals, and central control servers.

[0001] The present invention relates to an industrial IoT surveillance system including a composite sensor, a field RTU terminal, and a central control server, and comprises: a plurality of composite sensors installed in each of a plurality of zones of an industrial site, generating status information sensed in the zone and judgment information for determining whether an accident has occurred in the zone based on the status information, and transmitting the status information and judgment information to a field RTU terminal; a field RTU terminal verifying whether an accident has occurred in the zone based on the status information and judgment information received from the composite sensor, and transmitting the status information and judgment information received from the composite sensor to a central control server when it is determined that an accident has occurred; And a central control server that controls the surveillance system based on status information and judgment information for the composite sensor received from the field RTU terminal; wherein the composite sensor includes a deep learning-based accident occurrence judgment model that judges whether an accident has occurred in the area where the composite sensor is installed based on the status information sensed by itself, thereby detecting an accident in an area of ​​the industrial site by a plurality of composite sensors installed at regular intervals for each area that divides the industrial site, verifying whether an accident has occurred, identifying the location and type of the accident by the field RTU terminal, and generating learning data for accident detection to train the composite sensor. The present invention relates to an industrial IoT surveillance system including a composite sensor, a field RTU terminal, and a central control server.

[0002]

[0003] The proliferation of the Industrial Internet of Things (IIoT) is driving a growing demand for standards-based communication, data, and service distribution / management. Technologies are being developed to remotely detect industrial accidents or control devices installed at industrial sites, without requiring managers to physically visit the site. RTU terminals, installed at industrial sites such as factories, communicate with a management server operated by the manager according to a preset program, transmitting status information sensed at the site to the management server or, through device control signals received from the management server, enabling managers to control and manage devices without having to physically visit the site.

[0004] Meanwhile, accidents that can occur in industrial settings take a variety of forms, including water leaks, fires, and electric shocks. To detect and prevent accidents in advance, various types of sensors are being installed in industrial settings. Furthermore, to minimize damage from accidents in industrial settings, more accurate assessment of whether an accident has occurred is necessary, and if so, where and what type of accident occurred. However, as mentioned above, the wide variety of accidents that can occur in industrial settings presents challenges in making these assessments.

[0005] Therefore, in order to solve the above problems, there is an emerging need to develop a technology that can go beyond simply determining whether an accident occurred in an industrial site based on various sensing values ​​such as temperature and humidity by applying deep learning-based technology, and determine where the accident occurred and what type of accident occurred in the event of an accident.

[0006]

[0007] The present invention relates to an industrial IoT surveillance system including a composite sensor, a field RTU terminal, and a central control server, and comprises: a plurality of composite sensors installed in each of a plurality of zones of an industrial site, generating status information sensed in the zone and judgment information for determining whether an accident has occurred in the zone based on the status information, and transmitting the status information and judgment information to a field RTU terminal; a field RTU terminal verifying whether an accident has occurred in the zone based on the status information and judgment information received from the composite sensor, and transmitting the status information and judgment information received from the composite sensor to a central control server when it is determined that an accident has occurred; And a central control server that controls the surveillance system based on status information and judgment information for the composite sensor received from the field RTU terminal; wherein the composite sensor includes a deep learning-based accident occurrence judgment model that judges whether an accident has occurred in the area where the composite sensor is installed based on the status information sensed by itself, thereby detecting an accident in an area of ​​the industrial site by a plurality of composite sensors installed at regular intervals for each area that divides the industrial site, verifying whether an accident has occurred, identifying the location and type of the accident by the field RTU terminal, and generating learning data for accident detection to train the composite sensor, the purpose of the present invention is to provide an industrial IoT surveillance system including a composite sensor, a field RTU terminal, and a central control server.

[0008]

[0009] In order to solve the above problem, in one embodiment of the present invention, an industrial IoT surveillance system including a composite sensor, a field RTU terminal, and a central control server, the surveillance system comprising: a plurality of composite sensors installed in each of a plurality of zones of an industrial site, generating status information sensed in the zone and judgment information for determining whether an accident has occurred in the zone based on the status information, and transmitting the status information and the judgment information to a field RTU terminal; a field RTU terminal verifying whether an accident has occurred in the zone based on the status information and judgment information received from the composite sensor, and transmitting the status information and the judgment information received from the composite sensor to the central control server when it is determined that an accident has occurred; And a central control server that performs control of the surveillance system based on status information and judgment information for the composite sensor received from the field RTU terminal; wherein the composite sensor includes a deep learning-based accident occurrence judgment model that judges whether an accident has occurred in an area where the composite sensor is installed based on the status information sensed by the composite sensor itself, and the central control server generates learning data for training the accident occurrence judgment model based on status information when an accident is determined to have occurred, and commands the composite sensor to train the accident occurrence judgment model with the learning data, thereby providing an industrial IoT surveillance system.

[0010] In one embodiment of the present invention, by means of the composite sensor, at least one of temperature, humidity, hazardous gas, and operation of industrial equipment in the area is sensed to generate status information, and by inputting the status information into the accident occurrence judgment model, judgment information on whether an accident has occurred, including at least one of fire, equipment failure, accident, theft, and damage in the area, can be generated.

[0011] In one embodiment of the present invention, an accident detection step is performed in which, based on status information about the zone, judgment information about the zone is generated by the composite sensor and transmitted to the field RTU terminal; and, based on status information received from the composite sensor that determined, by the field RTU terminal, that an accident has occurred based on the judgment information and from one or more other composite sensors located within a preset distance of the composite sensor that transmitted the judgment information, an accident information derivation step is performed in which, based on status information received from the composite sensor that transmitted the judgment information and from another composite sensor that transmitted the judgment information, whether an accident has occurred in the zone is verified and the location and type of the accident are identified; an accident information transmission step in which location information and status information about the zone in which the accident occurred are transmitted to a central control server; And a sensor learning request step of labeling information related to the composite sensor determining whether an accident has occurred among the status information determined to have occurred, thereby generating learning data, and retransmitting the data to one or more composite sensors; and a sensor learning step of learning a deep learning-based accident occurrence judgment model that detects whether an accident has occurred based on the learning data by the composite sensor; can be performed.

[0012] In one embodiment of the present invention, the accident information derivation step may include an accident verification step of verifying whether an accident has occurred based on status information received from a composite sensor that has identified an accident and one or more composite sensors positioned within a preset distance from the composite sensor that has identified the accident; an accident location identification step of identifying a location where an accident has occurred by comparing and verifying status information received from a composite sensor that has identified an accident and one or more composite sensors positioned within a preset distance from the composite sensor that has identified the accident; and an accident type identification step of identifying a type of accident by comparing and verifying status information received from a composite sensor that has identified an accident and one or more composite sensors positioned within a preset distance from the composite sensor that has identified the accident.

[0013] In one embodiment of the present invention, the accident location identification step can identify the location of the accident by proportionally comparing the size of status information received from the composite sensor that identified the accident and one or more composite sensors located within a preset distance of the composite sensor that identified the accident to the location information of the composite sensor.

[0014] In order to solve the above-described problem, in one embodiment of the present invention, there is provided an industrial IoT monitoring method performed by an industrial IoT monitoring system including a composite sensor, a field RTU terminal, and a central control server, wherein the monitoring system comprises: a plurality of composite sensors installed in each of a plurality of zones of an industrial site, generating status information sensed in the zone and judgment information for determining whether an accident has occurred in the zone based on the status information, and transmitting the status information and the judgment information to a field RTU terminal; a field RTU terminal verifying whether an accident has occurred in the zone based on the status information and the judgment information received from the composite sensor, and transmitting the status information and the judgment information received from the composite sensor to a central control server when it is determined that an accident has occurred; And a central control server that performs control of a surveillance system based on status information and judgment information for the composite sensor received from the field RTU terminal; wherein the composite sensor includes a deep learning-based accident occurrence judgment model that judges whether an accident has occurred in an area where the composite sensor is installed based on the status information sensed by the composite sensor itself, and the central control server generates learning data for training the accident occurrence judgment model based on status information when an accident is determined to have occurred, and commands the composite sensor to train the accident occurrence judgment model with the learning data, and the industrial IoT surveillance method includes an accident detection step of generating judgment information for the area based on status information for the area by the composite sensor and transmitting the information to the field RTU terminal; An accident information derivation step in which, based on the status information received from the composite sensor that transmitted the judgment information and the composite sensor that transmitted the judgment information, determines that an accident has occurred based on the judgment information by the above-mentioned field RTU terminal, and identifies the location and type of accident and verifies whether an accident has occurred in the relevant area;An industrial IoT monitoring method is provided, comprising: an accident information transmission step for transmitting location information and status information about an area where an accident occurred to a central control server by the on-site RTU terminal; a sensor learning request step for labeling, by the on-site RTU terminal, information related to determining whether an accident has occurred among status information determined to have occurred by the on-site RTU terminal, thereby generating learning data, and retransmitting the data to one or more complex sensors; and a sensor learning step for learning, by the complex sensor, a deep learning-based accident occurrence judgment model for detecting whether an accident has occurred based on the learning data.

[0015]

[0016] According to one embodiment of the present invention, a composite sensor installed in multiple areas of an industrial site is a composite sensor including at least one of a temperature sensor, an acoustic sensor, a humidity sensor, and a hazardous gas sensor, and can measure multiple factors for determining whether an accident has occurred, the location of the accident, the type of accident, etc. at the industrial site.

[0017] According to one embodiment of the present invention, a field RTU terminal can receive status information from one or more composite sensors located at a short distance from an accident occurrence location, verify whether an accident has occurred, and derive accident information including the accident location and accident type.

[0018] According to one embodiment of the present invention, a field RTU terminal can improve the accuracy of accident detection and accident information by deriving accident information by considering multiple factors related to the accident.

[0019] According to one embodiment of the present invention, the field RTU terminal is located physically close to the composite sensor, so that data transmission and reception with the composite sensor is easy, and by transmitting accident information derived from multiple composite sensors to the central control server, network load can be reduced.

[0020] According to one embodiment of the present invention, a composite sensor can improve the accuracy of accident detection by including a deep learning-based accident occurrence judgment model for accident detection and learning learning data for accident detection received from a field RTU terminal.

[0021]

[0022] Figure 1 schematically illustrates the components and operation sequence of an accident system according to one embodiment of the present invention.

[0023] FIG. 2 illustrates a method for identifying an accident based on first sensing information received from a composite sensor according to one embodiment of the present invention and verifying an accident at an industrial site in a first accident verification step.

[0024] FIG. 3 illustrates a method for identifying an accident based on second sensing information received from a composite sensor according to one embodiment of the present invention and verifying an accident at an industrial site in a second accident verification step.

[0025] Figure 4 illustrates a step of identifying an accident location in an accident location identification step according to one embodiment of the present invention.

[0026] Figure 5 schematically illustrates the internal configuration of a computing device according to one embodiment of the present invention.

[0027]

[0028] Hereinafter, various embodiments and / or aspects are now disclosed with reference to the drawings. In the following description, for purposes of explanation, numerous specific details are set forth to provide a thorough understanding of one or more aspects. However, it will be apparent to one skilled in the art that such aspects may be practiced without these specific details. The following description and the attached drawings detail specific exemplary aspects of one or more aspects. However, these aspects are exemplary, and it is to be understood that any of the various methods within the principles of the various aspects may be utilized, and the description is intended to encompass all such aspects and their equivalents.

[0029]

[0030] Additionally, various aspects and features will be presented by systems that may include a number of devices, components, and / or modules. It is also to be understood and appreciated that various systems may include additional devices, components, and / or modules, and / or may not include all of the devices, components, and modules discussed in connection with the drawings.

[0031] The terms "embodiment," "example," "aspect," and "example" used herein may not be construed as implying that any aspect or design described is better or advantageous than other aspects or designs. The terms "part," "component," "module," "system," and "interface" used below generally refer to computer-related entities, and may refer to, for example, hardware, a combination of hardware and software, or software.

[0032] Additionally, it should be understood that the terms "comprises" and / or "comprising" imply the presence of the features and / or components, but do not preclude the presence or addition of one or more other features, components and / or groups thereof.

[0033] Additionally, terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but the components are not limited by these terms. These terms are used solely to distinguish one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component. The term and / or includes a combination of a plurality of related described items or any of a plurality of related described items.

[0034] Additionally, in the embodiments of the present invention, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by those of ordinary skill in the art to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in the embodiments of the present invention.

[0035]

[0036] Figure 1 schematically illustrates the components and operation sequence of an accident system according to one embodiment of the present invention.

[0037]

[0038] As illustrated in FIG. 1, an industrial IoT surveillance system including a composite sensor (1), a field RTU terminal (2), and a central control server (3) is provided, wherein the surveillance system comprises: a plurality of composite sensors (1) installed in each of a plurality of zones of an industrial site, generating status information sensed in the zone and judgment information for determining whether an accident has occurred in the zone based on the status information, and transmitting the status information and judgment information to a field RTU terminal (2); a field RTU terminal (2) verifying whether an accident has occurred in the zone based on the status information and judgment information received from the composite sensor (1), and transmitting the status information and judgment information received from the composite sensor (1) to a central control server (3) when it is determined that an accident has occurred; And a central control server (3) that performs control of the surveillance system based on status information and judgment information for the composite sensor (1) received from the field RTU terminal (2); wherein the composite sensor (1) includes a deep learning-based accident occurrence judgment model that judges whether an accident has occurred in an area where the composite sensor (1) is installed based on the status information sensed by the composite sensor (1), and the central control server (3) can generate learning data for learning the accident occurrence judgment model based on status information when an accident is judged to have occurred, and command the composite sensor (1) to learn the accident occurrence judgment model with the learning data.

[0039] In addition, by means of the above-mentioned complex sensor (1), at least one of temperature, humidity, hazardous gas, and operation of industrial equipment in the area is sensed to generate status information, and by inputting the status information into the above-mentioned accident occurrence judgment model, judgment information on whether an accident has occurred, including at least one of fire, equipment failure, accident, theft, and damage in the area, can be generated.

[0040]

[0041] Below, the components of the thinking system of the present invention are described.

[0042]

[0043] The composite sensor (1) is a sensor that detects the presence of an accident at an industrial site and generates status information. The composite sensor may further include multiple sensors, such as a temperature sensor, a humidity sensor, and a hazardous gas sensor, for determining the presence of an accident at an industrial site. In addition, the composite sensor (1) can early identify the presence of an accident at an industrial site and transmit the status information to the field RTU terminal (2).

[0044] Specifically, the composite sensor (1) is a composite sensor (1) capable of measuring multiple factors including temperature, pressure, acceleration, and vibration, and can improve the accident detection success rate by considering multiple factors when deriving accident information.

[0045]

[0046] The accident detection step, which can be performed with a relatively simple calculation process with the above structure, is performed by a composite sensor (1), and the accident information derivation step, which requires a complex calculation process, specifically the step of double-verifying whether an accident has occurred and identifying the location and type of accident, can be performed by a field RTU terminal (2).

[0047]

[0048] In addition, the composite sensor (1) can improve the accuracy of accident detection by further including a deep learning-based accident occurrence judgment model for accident detection and performing machine learning on data regarding accident detection. Specifically, the composite sensor (1) receives training data generated by labeling status information judged as an accident from the field RTU terminal (2) and trains a deep learning-based accident occurrence judgment model that detects the presence or absence of an accident, thereby improving the success rate of accident detection.

[0049]

[0050] The field RTU terminal (2) is a component that derives accident information based on status information received from a composite sensor (1), and can perform an accident verification step of verifying whether an accident has occurred based on status information received from the composite sensor (1) that identified the accident and one or more composite sensors (1) that are positioned within a preset distance from the composite sensor (1) that identified the accident, an accident location identification step of identifying the location of the accident by comparing and verifying status information received from the composite sensor (1) that identified the accident and one or more composite sensors (1) that are positioned within a preset distance from the composite sensor (1) that identified the accident, and an accident type identification step of identifying the type of accident by comparing and verifying status information received from the composite sensor (1) that identified the accident and one or more composite sensors (1) that are positioned within a preset distance from the composite sensor (1) that identified the accident.

[0051]

[0052] Specifically, the field RTU terminal (2) can double-verify whether an accident has occurred based on the status information received from the composite sensor (1) that identified the accident, and can identify the location of the accident and the type of the accident by receiving status information from the composite sensor (1) located within a preset distance from the composite sensor (1) that identified the accident. Preferably, the field RTU terminal (2) can receive status information from one or more composite sensors (1) located within a preset distance from the composite sensor (1) that transmitted the accident occurrence information, or can receive status information from a preset number of composite sensors (1) located within a short distance from the composite sensor (1) that transmitted the accident occurrence information.

[0053] With the above structure, the field RTU terminal (2) can derive accident information by linking multiple composite sensors (1) located within a certain range from the location of the accident, and can identify the location of the accident and the type of accident that cannot be derived from status information by a single composite sensor (1).

[0054]

[0055] In addition, the field RTU terminal (2) can generate learning data by labeling information related to determining whether an accident has occurred among the status information determined to be an accident. Specifically, the learning data is information necessary for the composite sensor (1) to identify an accident. By having the composite sensor (1) learn the learning data when an accident occurs, the accident detection success rate of the composite sensor (1) can be improved.

[0056] Meanwhile, the field RTU terminal (2) is physically located in close proximity to the composite sensor (1), so that data transmission and reception with the composite sensor (1) is easy, and accident information can be derived and transmitted to the central control server (3). Specifically, the field RTU terminal (2) can reduce network costs and transmission delays due to data transmission and reception by transmitting accident information that is the result of compiling status information generated by multiple composite sensors (1) to the central control server (3).

[0057]

[0058] As a result, the field RTU terminal (2) can perform an accident information derivation step that is difficult for the composite sensor (1) to perform due to the complex calculation process required based on the status information received from multiple composite sensors (1), and can transmit the accident information to the central control server (3) so that the manager can take appropriate measures in response to an accident at the industrial site. In addition, by generating learning data for training the composite sensor (1) and training the composite sensor (1), the accident detection success rate of the composite sensor (1) can be improved.

[0059]

[0060] The central control server (3) is a component that comprehensively controls the accident system, and the manager can check the presence or absence of an accident and status information at the industrial site through the central control server (3). Specifically, the central control server (3) can receive accident information from the field RTU terminal (2), and the accident information is information derived by collecting only information about the accident from multiple status information generated by multiple composite sensors (1), and the manager can selectively obtain only information about the area of ​​the work site where the accident occurred.

[0061] Preferably, the central control server (3) receives accident information from the field RTU terminal (2), and the manager can check whether an accident has occurred at the industrial site, the type of accident, and the location of the accident, and take appropriate measures accordingly.

[0062] In addition, the central control server (3) can control the operation of the complex sensor (1) and the field RTU terminal (2), which are components of the accident system.

[0063]

[0064] Below, the operation steps of the thinking system of the present invention will be described.

[0065]

[0066] As illustrated in Fig. 1, the composite sensor (1) can continuously generate status information and perform an accident detection step to detect whether an accident has occurred in an industrial setting. Specifically, the composite sensor (1) includes at least one of a temperature sensor, a hazardous gas sensor, a vibration sensor, and a pressure sensor, and can identify whether an accident has occurred based on first sensing information and second sensing information received from the sensors.

[0067] For example, if the first sensing information is a sensing value for temperature and the second sensing information is a sensing value for oxygen, the composite sensor (1) can determine that an accident has occurred at an industrial site if the first sensing information exceeds the first threshold or the second sensing information is below the second threshold.

[0068] Additionally, the status information derived from the composite sensor (1) can be transmitted to the field RTU terminal (2).

[0069]

[0070] The on-site RTU terminal (2) can perform a step of receiving status information from another composite sensor (1) located within a preset distance from the composite sensor (1) that transmitted the accident occurrence information. Specifically, the other composite sensor (1) that transmits the status information in the step is a composite sensor (1) located within a preset distance from the composite sensor (1) that transmitted the accident occurrence information. As a result, the on-site RTU terminal (2) can receive status information from the composite sensor (1) closest to the location of the accident occurrence and another composite sensor (1) located within a short distance from the composite sensor (1) closest to the location of the accident occurrence, and can verify whether an accident has occurred based on a plurality of pieces of status information and identify the location and type of the accident.

[0071]

[0072] Next, the field RTU terminal (2) can perform an accident verification step of double-verifying whether an accident has occurred based on status information received from the composite sensor (1) that transmitted the accident occurrence information and another composite sensor (1) located in close proximity to the composite sensor (1).

[0073] Specifically, the accident verification step is a step included in the accident information derivation step performed by the field RTU terminal (2), and is a step for verifying whether an accident occurred at an industrial site based on the first sensing information and the second sensing information received from the composite sensor (1) that transmitted the accident occurrence information and another composite sensor (1) located in close proximity to the composite sensor (1).

[0074]

[0075] The on-site RTU terminal (2) can perform an accident location identification step for identifying the location of the accident by comparing and verifying status information received from the composite sensor (1) that transmitted the accident occurrence information and another composite sensor (1) located in close proximity to the composite sensor (1), and an accident type identification step for identifying the type of accident. Specifically, the accident location identification step and the accident type identification step are steps included in the accident information derivation step performed by the on-site RTU terminal (2), and are steps for identifying the location and type of the accident based on status information received from the composite sensor (1) that transmitted the accident occurrence information and another composite sensor (1) located in close proximity to the composite sensor (1).

[0076]

[0077] The accident type identification step performed following the accident location identification step is a step of identifying the type of accident based on status information received from the composite sensor (1) that transmitted the accident occurrence information and another composite sensor (1) located in close proximity to the composite sensor (1). The field RTU terminal (2) can identify the type of accident based on various factors sensed at the industrial site.

[0078]

[0079] As a result, the on-site RTU terminal (2) can perform calculations on multiple factors to derive accident types that cannot be identified by a single composite sensor (1) or a single factor. Furthermore, by learning multiple factors as data when an accident occurs, the accuracy of the accident type identification step can be improved.

[0080]

[0081] Next, the field RTU terminal (2) can perform an accident information transmission step of transmitting location information and status information about the area of ​​the industrial site where the accident occurred to the central control server (3). Specifically, the accident information transmission step is a step of transmitting accident information including location information, type of accident, and status information about the work site where the accident occurred derived by the field RTU terminal (2) to the central control server (3). This can have the effect of reducing human waste and network load by selectively receiving only accident information when an accident occurs, breaking away from the conventional method in which a manager had to receive data from all complex sensors (1) to detect an accident in an area of ​​the industrial site.

[0082]

[0083] Next, the field RTU terminal (2) performs a sensor learning request step of labeling information related to the composite sensor (1) determining whether or not an accident has occurred among the status information determined to be an accident to generate learning data and retransmit the data to one or more composite sensors (1), and the composite sensor (1) can perform a sensor learning step of learning a deep learning-based accident occurrence judgment model that receives the learning data and detects whether or not an accident has occurred.

[0084] Specifically, the complex sensor (1) includes a deep learning-based accident occurrence judgment model capable of learning learning data on multiple accident factors, and by learning the learning data, the accuracy of the accident detection stage can be improved. Preferably, the learning data may include data on accident sounds that are easy to learn as intelligent information, such as second sensing information, first sensing information, or simple repeated sounds when an accident occurs.

[0085]

[0086] As a result, the composite sensor (1) can generate status information by sensing multiple factors and verify whether an accident has occurred, and the field RTU terminal (2) can verify whether an accident has occurred at the relevant industrial site based on the status information received from the multiple composite sensors (1) and derive accident information including detailed information about the accident. In addition, the composite sensor (1) can improve the accuracy of the accident detection stage by learning learning data about the accident.

[0087]

[0088] Figure 2 illustrates a method for identifying an accident based on first sensing information received from a composite sensor (1) according to one embodiment of the present invention and verifying the accident at an industrial site in a first accident verification step. For example, the first sensing information may be temperature sensing information.

[0089] In addition, an accident detection step is performed by the composite sensor (1) to generate judgment information for the area based on status information for the area and transmit it to the field RTU terminal (2); an accident information derivation step is performed by the field RTU terminal (2) to determine that an accident has occurred based on the judgment information and to verify whether an accident has occurred in the area based on status information received from the composite sensor (1) that transmitted the judgment information and one or more other composite sensors (1) located within a preset distance of the composite sensor (1) that transmitted the judgment information; an accident information transmission step to transmit location information and status information for the area where the accident has occurred to the central control server (3); And a sensor learning request step of labeling information related to the determination of whether an accident has occurred by the composite sensor (1) among the status information determined to have occurred, thereby generating learning data, and retransmitting the data to one or more composite sensors (1); and a sensor learning step of learning a deep learning-based accident occurrence judgment model that detects whether an accident has occurred based on the learning data by the composite sensor (1); can be performed.

[0090] In addition, the accident information derivation step may include an accident verification step for verifying whether an accident has occurred based on status information received from a composite sensor (1) that has identified an accident and one or more composite sensors (1) that are positioned within a preset distance from the composite sensor (1) that has identified the accident; an accident location identification step for identifying a location where an accident has occurred by comparing and verifying status information received from a composite sensor (1) that has identified an accident and one or more composite sensors (1) that are positioned within a preset distance from the composite sensor (1) that has identified the accident; and an accident type identification step for identifying a type of accident by comparing and verifying status information received from a composite sensor (1) that has identified an accident and one or more composite sensors (1) that are positioned within a preset distance from the composite sensor (1) that has identified the accident.

[0091] In addition, the accident location identification step can identify the location of the accident by proportionally comparing the size of the status information received from the complex sensor (1) that identified the accident and one or more complex sensors (1) located within a preset distance of the complex sensor (1) that identified the accident to the location information of the complex sensor (1).

[0092]

[0093] The composite sensor (1) can detect an accident at a work site and transmit accident occurrence information and status information. Specifically, the first sensing information (80 in this example) detected by the composite sensor (1) #2 of FIG. 2 exceeds the first threshold (70 in this example), and the composite sensor (1) #2 can transmit the status information to the field RTU terminal (2). Subsequently, the field RTU terminal (2) can request transmission of status information to the composite sensors (1) (composite sensors (1) #1 and #3) located within a preset distance of the composite sensor (1) (composite sensor (1) #2) that transmitted the accident occurrence information, and can receive the corresponding information.

[0094] The on-site RTU terminal (2) can perform a first accident verification step of verifying whether the first sensing information received from the composite sensor (1) (composite sensor (1) #2) that transmitted the accident occurrence information and the composite sensors (1) (composite sensors (1) #1 and #3) located within a preset distance of the composite sensor (1) (composite sensor (1) #2) exceeds the first threshold.

[0095]

[0096] As illustrated in Fig. 2, the first sensing information (80 in this example) transmitted by the composite sensor (1) #2 exceeds the first threshold (70 in Fig. 3), and the field RTU terminal (2) can identify that an accident has occurred. For example, in this case, the accident may be a fire.

[0097]

[0098] Figure 3 illustrates a method for identifying an accident based on second sensing information received from a composite sensor (1) according to one embodiment of the present invention and verifying the accident at an industrial site in a second accident verification step. For example, the second sensing information may be a sensing value for oxygen.

[0099]

[0100] As illustrated in FIG. 3, the composite sensor (1) can detect an accident at a work site and transmit accident occurrence information and status information. Specifically, the second sensing information (60 in this example) detected by the composite sensor (1) #3 of FIG. 3 is less than the second threshold (70 in this example), and the composite sensor (1) #3 can transmit the status information to the field RTU terminal (2). Subsequently, the field RTU terminal (2) can request transmission of status information to the composite sensors (1) (#1 and #2) located within a preset distance of the composite sensor (1) (composite sensor (1) #3) that transmitted the accident occurrence information, and can receive the corresponding information. The on-site RTU terminal (2) can perform a second accident verification step of verifying whether the second sensing information received from the composite sensor (1) (composite sensor (1) #3) that transmitted the accident occurrence information and the composite sensor (1) (composite sensor (1) #1 and #3) located within a preset distance of the composite sensor (1) (composite sensor (1) #3) is less than the second threshold.

[0101] As shown in Fig. 3, the second sensing information transmitted by the composite sensor (1) #3 is less than the second threshold, and the field RTU terminal (2) can identify that an accident has occurred at the work site.

[0102]

[0103] As a result, the accident detection system of the present invention can double-check whether an accident has occurred at a work site based on the first and second sensing information, thereby preventing the possibility of misjudgment that may occur in identifying the presence of an accident. In addition, as described above, the factor by which the accident detection system of the present invention detects an accident at a work site may be one of multiple factors that can be measured by a composite sensor (1), such as temperature, hazardous gas concentration, oxygen, and humidity.

[0104]

[0105] Figure 4 illustrates a step of identifying an accident location in an accident location identification step according to one embodiment of the present invention.

[0106]

[0107] The on-site RTU terminal (2), which has completed verification of the accident in the above-mentioned accident verification step, can then perform an accident location identification step to specify the accident location. Specifically, the database of the on-site RTU terminal (2) stores distance information between composite sensors (1), and the location of the accident occurrence point can be identified based on status information received from multiple composite sensors (1) and distance information between composite sensors (1).

[0108]

[0109] As illustrated in Fig. 4, when an accident occurs, the field RTU terminal (2) can receive status information including first sensing information and second sensing information from a plurality of composite sensors (1). Specifically, the status information can be received from one or more composite sensors (1) located within a preset distance of the composite sensor (1) #3 whose first sensing information exceeds the first threshold or the composite sensor (1) #4 whose second sensing information is less than the second threshold.

[0110] As a result, the field RTU terminal (2) can identify the location of the accident based on the status information received from the composite sensors (1) (composite sensors (1) #1, #2, #3 and #4) located within a preset distance from the location of the accident. Specifically, the graph at the bottom of Fig. 4 illustrates the second sensing information received by the field RTU terminal (2) from each composite sensor (1). The second sensing information of the composite sensors (1) #1, #2 and #3 located throughout the location of the accident is the point before the accident occurred, and therefore transmits the second sensing information for the normal state.

[0111] On the other hand, the second sensing information of the composite sensor (1) #4 is located at a point after the point where the accident occurred, so the second sensing information has decreased below the second threshold. Consequently, the field RTU terminal (2) can identify that the accident occurred in the section between the composite sensor (1) #3, where the second sensing information maintains a normal state, and the composite sensor (1) #4, where the second sensing information has decreased below the second threshold.

[0112]

[0113] Next, the graph in the middle of FIG. 4 illustrates the first sensing information received by the field RTU terminal (2) from each composite sensor (1). The first sensing information of the composite sensor (1) #3, which is located at the closest distance from the location of the accident, has the highest value exceeding the first threshold, and then the size of the first sensing information decreases as the distance from the location of the accident increases.

[0114]

[0115] The on-site RTU terminal (2) can identify the accident location based on the size of the first sensing information and the location information of each composite sensor (1). Specifically, the location information of each composite sensor (1), i.e., the distance between each composite sensor (1), is pre-stored in the database of the on-site RTU terminal (2), and the location of the accident can be specified by proportionally measuring the distance and the size of the first sensing information.

[0116]

[0117] For example, in the drawing of FIG. 4, the composite sensor (1) #3 is the composite sensor (1) that transmits the first sensing information having the largest value among the plurality of composite sensors (1), and the composite sensor (1) #4 is the composite sensor (1) that transmits the first sensing information having the next highest value, so that the field RTU terminal (2) can identify that an accident occurred in the section between the composite sensor (1) #3 and the composite sensor (1) #4. In addition, as described above, the distance between the composite sensor (1) #3 and the composite sensor (1) #4 is pre-stored in the database of the field RTU terminal (2), so that the location of the accident can be specified in proportion to the size of the first sensing information of the composite sensor (1) #3 and the composite sensor (1) #4 and the distance between the composite sensor (1) #3 and the composite sensor (1) #4.

[0118] As a result, the accident system of the present invention can derive an accident occurrence section based on second sensing information received from a plurality of composite sensors (1) and specify an accident occurrence location based on first sensing information.

[0119]

[0120] As a result, the composite sensor (1) can identify whether an accident has occurred at a work site based on various factors that can be sensed, such as temperature, humidity, and concentration of hazardous gases. Specifically, the accident detection step performed by the composite sensor (1) can be performed with a relatively simple calculation process, and thus can be performed independently by the composite sensor (1) installed at the work site.

[0121] Preferably, the composite sensor (1) can further include a deep learning-based accident occurrence judgment model that detects whether an accident has occurred, thereby improving the accuracy of the accident detection stage.

[0122]

[0123] Meanwhile, the on-site RTU terminal (2) can receive status information from the composite sensor (1), verify whether an accident has occurred, and perform an accident information derivation step that identifies the location and type of the accident. Specifically, the accident information derivation step is a step that is performed by considering a relatively large number of factors in preparation for the accident detection step, and can identify the location and type of the accident, which are difficult to derive with a single composite sensor (1), through the on-site RTU terminal (2).

[0124]

[0125] In addition, the central control server (3) can generate learning data based on the status information when an accident is finally determined to have occurred, and transmit the generated learning data to each of the multiple composite sensors (1).

[0126] The complex sensor (1) can improve the accuracy of accident judgment by performing learning with the corresponding learning data.

[0127]

[0128] Figure 5 schematically illustrates the internal configuration of a computing device according to one embodiment of the present invention.

[0129]

[0130] The composite sensor (1), field RTU terminal (2), and central control server (3) illustrated in the above-described FIG. 1 may include components of the computing device (11000) illustrated in the above-described FIG. 12.

[0131] As illustrated in FIG. 5, the computing device (11000) may include at least one processor (11100), memory (11200), peripheral interface (11300), input / output subsystem (I / O subsystem) (11400), power circuit (11500), and communication circuit (11600). At this time, the computing device (11000) may correspond to the composite sensor (1), field RTU terminal (2), and central control server (3) illustrated in FIG. 1.

[0132] The memory (11200) may include, for example, high-speed random access memory, a magnetic disk, SRAM, DRAM, ROM, flash memory, or non-volatile memory. The memory (11200) may include software modules, instruction sets, or other various data required for the operation of the computing device (11000).

[0133] At this time, access to the memory (11200) from other components such as the processor (11100) or peripheral interface (11300) may be controlled by the processor (11100).

[0134] The peripheral interface (11300) may couple input and / or output peripherals of the computing device (11000) to the processor (11100) and memory (11200). The processor (11100) may execute software modules or instruction sets stored in the memory (11200) to perform various functions for the computing device (11000) and process data.

[0135] The input / output subsystem can couple various input / output peripherals to the peripheral interface (11300). For example, the input / output subsystem can include a controller for coupling peripherals such as a monitor, a keyboard, a mouse, a printer, or, as needed, a touchscreen or sensor to the peripheral interface (11300). In another aspect, the input / output peripherals can be coupled to the peripheral interface (11300) without going through the input / output subsystem.

[0136] The power circuit (11500) may supply power to all or part of the components of the terminal. For example, the power circuit (11500) may include a power management system, one or more power sources such as a battery or alternating current (AC), a charging system, a power failure detection circuit, a power converter or inverter, a power status indicator, or any other components for power generation, management, and distribution.

[0137] The communication circuit (11600) may enable communication with another computing device using at least one external port.

[0138] Alternatively, as described above, the communication circuit (11600) may enable communication with other computing devices by transmitting and receiving RF signals, also known as electromagnetic signals, including RF circuits, as needed.

[0139] This embodiment of FIG. 5 is only an example of a computing device (11000), and the computing device (11000) may have some components illustrated in FIG. 5 omitted, may further include additional components not illustrated in FIG. 5, or may have a configuration or arrangement that combines two or more components. For example, a computing device for a communication terminal in a mobile environment may further include a touch screen or a sensor, in addition to the components illustrated in FIG. 5, and may include a circuit for RF communication of various communication methods (WiFi, 3G, LTE, Bluetooth, NFC, Zigbee, etc.) in the communication circuit (11600). Components that can be included in the computing device (11000) may be implemented as hardware including one or more signal processing or application-specific integrated circuits, software, or a combination of both hardware and software.

[0140] Methods according to embodiments of the present invention may be implemented in the form of program instructions that can be executed through various computing devices and recorded on a computer-readable medium. In particular, the program according to the present embodiment may be configured as a PC-based program or an application exclusively for mobile terminals. An application to which the present invention is applied may be installed on a computing device (11000) through a file provided by a file distribution system. For example, the file distribution system may include a file transmission unit (not shown) that transmits the file at the request of the computing device (11000).

[0141]

[0142] The devices described above may be implemented as hardware components, software components, and / or a combination of hardware components and software components. For example, the devices and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. Furthermore, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is sometimes described as being used alone; however, one of ordinary skill in the art will recognize that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing unit may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

[0143] Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing device to perform a desired operation or may, independently or collectively, command the processing device. The software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave, for interpretation by the processing device or for providing instructions or data to the processing device. The software may also be distributed across network-connected computing devices and stored or executed in a distributed manner. The software and data may be stored on one or more computer-readable recording media.

[0144] The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the medium may be those specially designed and configured for the embodiment or may be those known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of the program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiment, and vice versa.

[0145]

[0146] Although the embodiments have been described with limited examples and drawings, those skilled in the art will appreciate that various modifications and variations can be made based on the above teachings. For example, appropriate results can be achieved even if the described techniques are performed in a different order than described, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents. Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the claims described below.

Claims

1. An industrial IoT monitoring system including a complex sensor, a field RTU terminal, and a central control server. The above surveillance system, A plurality of composite sensors installed in each of multiple zones of an industrial site, generating status information sensed in the zone and judgment information determining whether an accident has occurred in the zone based on the status information, and transmitting the status information and judgment information to a field RTU terminal; A field RTU terminal that verifies whether an accident has occurred in the relevant area based on the status information and judgment information received from the above-mentioned complex sensor, and transmits the status information and judgment information received from the complex sensor to the central control server if an accident is determined to have occurred; and A central control server that performs control of the surveillance system based on status information and judgment information for the corresponding complex sensor received from the above-mentioned field RTU terminal; The above complex sensor includes a deep learning-based accident occurrence judgment model that determines whether an accident has occurred in the area where the complex sensor is installed based on the status information sensed by the complex sensor itself. An industrial IoT surveillance system in which the central control server generates learning data for training the accident occurrence judgment model based on status information when an accident is determined to have occurred, and commands the complex sensor to train the accident occurrence judgment model with the learning data.

2. In claim 1, By the above composite sensor, An industrial IoT surveillance system that senses at least one of temperature, humidity, hazardous gas, and operation of industrial equipment in the above-mentioned area to generate status information, inputs the status information into the above-mentioned accident occurrence judgment model, and generates judgment information on whether an accident has occurred, including at least one of fire, equipment failure, accident, theft, and damage in the area.

3. In claim 1, By the above composite sensor, Based on the status information for the above zone, an accident detection step is performed to generate judgment information for the zone and transmit it to the field RTU terminal; By the above field RTU terminal, An accident information derivation step for verifying whether an accident has occurred in the relevant area and identifying the location and type of the accident based on status information received from a composite sensor that transmitted the judgment information and one or more other composite sensors located within a preset distance of the composite sensor that transmitted the judgment information, upon determining that an accident has occurred based on the judgment information; An accident information transmission step that transmits location information and status information about the area where the accident occurred to the central control server; and A sensor learning request step is performed to generate learning data by labeling information related to the composite sensor determining whether an accident has occurred among the status information determined to have occurred, and retransmitting the data to one or more composite sensors; By the above composite sensor, An industrial IoT surveillance system that performs a sensor learning step for learning a deep learning-based accident occurrence judgment model that detects an accident based on the above learning data.

4. In claim 3, The above accident information derivation step is, An accident verification step for verifying whether an accident has occurred based on status information received from a composite sensor that has identified an accident and one or more composite sensors placed within a preset distance of the composite sensor that has identified the accident; An accident location identification step for identifying the location of an accident by comparing and verifying status information received from a composite sensor that has identified an accident and one or more composite sensors placed within a preset distance of the composite sensor that has identified the accident; An industrial IoT surveillance system, comprising: an accident type identification step for identifying the type of accident by comparing and verifying status information received from a composite sensor that has identified an accident and one or more composite sensors placed within a preset distance of the composite sensor that has identified the accident.

5. In claim 3, The above accident location identification step is: An industrial IoT surveillance system that identifies the location of an accident by proportionally measuring the size of status information received from a composite sensor that identified the accident and one or more composite sensors located within a preset distance of the composite sensor that identified the accident and the location information of the composite sensor.

6. An industrial IoT monitoring method performed by an industrial IoT monitoring system including a complex sensor, a field RTU terminal, and a central control server, The above surveillance system, A plurality of composite sensors installed in each of multiple zones of an industrial site, generating status information sensed in the zone and judgment information determining whether an accident has occurred in the zone based on the status information, and transmitting the status information and judgment information to a field RTU terminal; A field RTU terminal that verifies whether an accident has occurred in the relevant area based on the status information and judgment information received from the above-mentioned complex sensor, and transmits the status information and judgment information received from the complex sensor to the central control server if an accident is determined to have occurred; and A central control server that performs control of the surveillance system based on status information and judgment information for the corresponding complex sensor received from the above-mentioned field RTU terminal; The above complex sensor includes a deep learning-based accident occurrence judgment model that determines whether an accident has occurred in the area where the complex sensor is installed based on the status information sensed by the complex sensor itself. The central control server generates learning data for training the accident occurrence judgment model based on the status information when an accident is determined to have occurred, and commands the complex sensor to train the accident occurrence judgment model with the learning data. The above industrial IoT monitoring method is, An accident detection step of generating judgment information for the zone based on status information for the zone by the above complex sensor and transmitting the information to the field RTU terminal; An accident information derivation step in which, based on the status information received from the composite sensor that transmitted the judgment information and the composite sensor that transmitted the judgment information, determines that an accident has occurred based on the judgment information by the above-mentioned field RTU terminal, and identifies the location and type of accident and verifies whether an accident has occurred in the relevant area; An accident information transmission step for transmitting location information and status information about the area where an accident occurred to a central control server through the above-mentioned field RTU terminal; A sensor learning request step for generating learning data by labeling information related to the composite sensor determining whether an accident has occurred among the status information determined to have occurred by the above-mentioned field RTU terminal, and retransmitting the data to one or more composite sensors; and An industrial IoT monitoring method, comprising a sensor learning step of learning a deep learning-based accident occurrence judgment model that detects whether an accident has occurred based on the learning data using the above complex sensor.

Images