KR20220122922A - Data Logger System based on Artificial Intelligence - Google Patents

Abstract

The present invention relates to an AI-based data logger system, which provides a data analysis solution, comprising: a control panel for controlling an operating part; an AI processing unit for collectively collecting heterogeneous field data; and a management information processing device for differently controlling an adjustment operation of the operating part.

Description

AI-based data logger system {Data Logger System based on Artificial Intelligence}

The content disclosed in this specification relates to a data logger system, and more specifically, transmits on-site monitoring data monitored by an on-site control panel equipped with an external sensor to a server, stores and processes it based on this, and stores and processes the data required by each control panel again. It is about the technology to receive and use.

Unless otherwise indicated herein, the material described in this section is not prior art to the claims of this application, and inclusion in this section is not an admission that it is prior art.

In general, a field measurement system consists of an on-site control panel and a central management information processing device located at a remote location. send to the device.

In addition, the central management information processing device manages the on-site situation based on these transmitted monitoring data, and based on these, various devices connected to the on-site control panel can be operated remotely.

For example, the existing system makes the field control unit PLC (Programmable Logic Control) and RTU (Remote Terminal Unit). So, when the PLC collects the status information of the monitoring target from the measuring device, it transmits the status information to the management information processing device through the RTU, receives control according to the current status, and operates the load equipment such as motors and valves appropriately. . Therefore, the monitoring target is operated in the state desired by the administrator.

On the other hand, among the conventional field measurement systems, the field control panel simply transmits or receives input/output information without the function of a data logger. Uneasy. In addition, there is a problem that it cannot be checked because there is no backup function for these data even after a power outage or abnormal condition of the communication line is terminated.

That is, if such a system shows a failure in PLC, RTU, or communication line, it must be quickly controlled in a different way, but this is not easy. In addition, if a separate emergency system is installed at this time, various difficulties may follow in operation, installation, and maintenance.

(Patent Document 0001) KR10-2108932 B1

(Patent Document 0002) KR10-2019-0046244 A

(Patent Document 0003) KR10-2229387 B1

For reference, the technology of Patent Document 1 makes it easy to set up and collect the detection value of the sensor by connecting the sensor required for facility measurement, even if the type or number of sensors to be installed is different depending on the classification, type, shape, or scale of the facility. let it do

In addition, Patent Document 2 can be installed and used for multiple types of infrastructure using different types of sensors for remote monitoring, and selectively connected to heterogeneous IOT networks.

In addition, Patent Document 3 discloses a technique for measuring data from a remote location using a modem data logger.

In the disclosed contents, first, a separate AI processing unit is provided to add an AI-based data logger function in addition to the existing input/output information. and to provide an AI-based data logger system with the function of restoring it to the computer of the central server.

Also, in this case, the AI processing unit detects and responds to process abnormalities in advance through real-time monitoring in a way that connects various data gathering and communication in general factories or HACCP factories, etc., and supports alarm alerts through data analysis. We provide data analysis solutions.

In addition to this, the AI processing unit implements device hardware based on SBC (Single Board Computing) architecture and provides services for data collection/processing/transmission from various general-purpose facilities, and various functions that can collect data from manufacturing facilities and devices (sensors) Provide I/F.

AI-based data logger system according to the embodiment,

First, in the AI processing unit, that is, the AI-based intelligent data collection and analysis device provides a communication protocol (Unified Gateway) with PLC or SCADA/HMI process monitoring control system and heterogeneous utility linkage system to receive data from field equipment. In addition, in this case, a reliable protocol supporting various devices and data transmission methods is supported.

For example, it provides various data interfaces such as various sensors, devices, IO boards, and PLCs, compared to managing one data item or sensing method in general.

In particular, it is an AI-based intelligent data collection and analysis device that connects with on-site sensors and devices, serves as a communication gateway, provides data analysis, management, and monitoring alarms, and in addition, provides an optimized data collection analysis control system. characterized in that

According to the embodiments, a separate AI processing unit is provided to add an AI-based data logger function in addition to the existing input/output information. We provide an AI-based data logger system with a function to check and restore it to the computer of the central control unit.

In addition, this AI processing unit, that is, AI-based intelligent data collection and analysis equipment collects and processes signals acquired from various sensors of data collection and processing devices, and provides data processing processing and analysis to enable analysis and diagnosis.

In addition, this data collection and analysis device solves the inconvenient point of use because measurement is complicated and there are many connected devices. Therefore, it provides a signal collection device serving as a comprehensive protocol gateway that can collect and analyze various signals such as temperature/pressure/noise/vibration by connecting it to a portable PC or laptop computer.

1 to 3 are diagrams for conceptually explaining an AI-based data logger system according to an embodiment;
4 is a view showing the overall AI-based data logger system according to an embodiment;
5 is a block diagram showing the configuration of an AI-based data logger system according to an embodiment;
6 is a flowchart sequentially illustrating the operation of an AI-based data logger system according to an embodiment;
7 is a view showing an HMI monitoring screen in a factory applied to an AI-based data logger system according to an embodiment;

1 to 3 are diagrams schematically illustrating an AI-based data logger system according to an embodiment.

1 to 3 , in the data logger system of one embodiment, a separate AI processing unit is provided to add an AI-based data logger function in addition to the existing input/output information as shown in FIG. 1 . In addition, in the case of a power outage or communication interruption of the central server, it has a function of checking the data at the time of the problem by the AI processing unit and restoring it to the computer of the central server.

In addition, in this case, we provide a data analysis solution that detects and responds to process abnormalities in advance through real-time monitoring in a way that connects various data gathering and communication in general factories or HACCP factories, and supports alarm alerts through data analysis. do.

In other words, it provides a remote monitoring support hub role by collecting various data from a general factory or HACCP site and comprehensively collecting and analyzing various heterogeneous protocols with a data collection analyzer.

In addition, SBC (Single Board Computing) architecture-based device hardware implementation and support services for data collection/processing/transmission from various general-purpose facilities are provided, and various I/ to provide F.

Specifically, for this purpose, the data logger system includes an AI processing unit, that is, an AI-based data collection and analysis device, as shown in FIG. 2 .

That is, these devices perform the role of a heterogeneous data protocol gateway, perform data control according to the field situation, and are predefined in connection with the data collection and analysis controller in the protocol platform and application that controls the data of the data collection system when it is transmitted.

In addition, this device provides a field data collection device, and this collection device provides an OPC-UA information collection device interface capable of detecting various sensors and collecting device research and field data optimized for various factories. In addition, it also provides a user interface and HMI that is convenient for the user to handle the sensor information collected in this way.

On the other hand, in this case, such a data logger system separately provides a configuration related to gathering and connection with respect to heterogeneous field data, so that heterogeneous field data can be smoothly collected and analyzed.

For example, it communicates by wire or wireless depending on the factory environment and situation, and a mix of wired and wireless is applied. Specifically, the sensor monitors ambient conditions such as temperature and humidity, and converts the data values to digital to transmit the controller speed and On, Off control commands for controlling the temperature and organic concentration inside the factory to the moving part.

Accordingly, in the AI-based data logger system of an embodiment through this, a separate AI processing unit is provided so that an AI-based data logger function can be added in addition to the existing input/output information. And, in addition to this, even in the case of a power outage or communication interruption of the central control unit, the AI-based data logger system having the function of checking the data at the problem point later by the AI processing unit and restoring it to the computer of the central control unit is provided.

In addition, this data logger system collects and processes signals acquired from various sensors of data collection and processing devices, and provides data processing processing and analysis to enable analysis and diagnosis.

In addition, this data collection and analysis device solves the inconvenient point of use because measurement is complicated and there are many connected devices. Therefore, it provides a signal collection device serving as a comprehensive protocol gateway that can collect and analyze various signals such as temperature/pressure/noise/vibration by connecting it to a portable PC or laptop computer.

4 is a view showing the overall AI-based data logger system according to an embodiment.

As shown in FIG. 4, the AI-based data logger system according to an embodiment is largely configured to include an on-site control panel and AI processing unit respectively installed for a number of different factory facilities and situations, and a central management information processing unit located at a remote location. becomes (see a).

In addition, such a system may further include a troubleshooting information processing device (not shown), etc. that connects to the management information processing device and provides services such as troubleshooting.

The control panel is connected to various external sensors for monitoring the field situation, and the data monitored by the external sensors is transmitted to the AI processing unit using the Internet network. Of course, the control panel may receive driving signals for various devices from the management information processing device and control various devices connected thereto based on the received driving signals.

The AI processing unit collects various data transmitted from a remote field control panel, and the collected data is classified and processed by a deep learning module equipped with a neural network, and configured to provide various statistical data and an alarm for efficient data management becomes (see b). In addition, the AI processing unit may be configured to store various transmitted data in the form of a database, and to provide various statistical data and graph data in response to a user's request through an Internet connection. In addition, the self-diagnosis function of the system is provided to prevent an accident in advance by providing the occurrence of abnormal situations to pre-registered users through various routes (eg, text message transmission, etc.). In this way, the AI processing unit functions as a kind of data logger. This AI processing unit can be more useful when managing multiple business sites. When multiple business sites are managed by the AI processing unit, duplicate investment due to the construction of an independent system can be prevented, and efficient management with a minimum number of personnel is possible. That is, several to tens of on-site control units are provided, and these tens of on-site control units transmit data to the AI-based processing unit so that data management of the field control unit can be centrally performed.

The management information processing device may connect to the AI processing unit using the Internet network, receive various data stored in the AI processing unit, and output it, and in some cases, download and store various data. Accordingly, even when a situation such as a power outage or communication abnormality occurs in the management information processing device, after the abnormal situation ends, data for the corresponding period can be downloaded and restored. Accordingly, in the AI-based data logger system according to an embodiment of the present disclosure, a separate AI processing unit is provided to add an AI-based data logger function in addition to the existing input/output information, and in case of a power outage or communication interruption of the central control unit In the future, an AI-based data logger system with the function of checking the data at the time of the problem by the AI processing unit and restoring it to the computer of the central control unit will be provided.

Meanwhile, another AI-based data logger system according to the present disclosure may be applied as follows.

It can be applied to the development of smart products optimized for the smart factories of small businesses. Specifically, the interface with the sensor family, such as power sensors, heat sensors, coefficient sensors, scanners, temperature sensors, and vibration sensors, which are mostly required in small smart factories. can be applied to development.

In addition, it is applicable to companies participating in data collection during the business period to present a representative application model, and it can be applied to technology development of products that contribute to the spread of smart factories of small companies by effectively collecting data of various small factories in the future.

In addition, it can be applied to the development of on-site data collection devices for smart failures, and specifically, it can be optimally applied to small smart factories by exploring, developing, and verifying various sensors. can

In addition, serial communication data collection function and user interface program development (a variety of communication standards exist, RS232 is the most common, but only maintains a transmission distance of up to 50 feet, RS485 is superior to RS232 and supports a transmission distance of up to 5,000 feet) It can be applied, and it can also be applied to the GUI that can be selected by industry and use, the development of smart data collection devices and smart sensors to spread the smart factories of small businesses, and the development of user interface programs for system operation.

5 is a block diagram illustrating the configuration of an AI processing unit applied to an AI-based data logger system according to an embodiment.

As shown in FIG. 5 , the AI processing unit according to an exemplary embodiment mainly includes a key signal input unit, an I/F unit, a signal processing unit, a main processing unit, a database, and a display unit.

The key signal input unit receives various types of administrator setting information used to service the data logger function according to a user's key operation according to an embodiment.

The I/F unit collectively collects various data for each factory facility and situation from a remote site control panel, and transmits the data logger information accordingly to a registration management information processing device at a remote site.

The signal processing unit includes a power supply such as AC and ICP for compatibility with various sensors, a low pass filter for preventing aliasing, and an amplifying device for amplifying an input signal. In addition, the signal processing unit further includes a data acquisition device combining an A/D, a D/A converter, and a DSP.

The main processing unit controls each unit, and collects heterogeneous field data from the field control panel and transmits it to the registration management information processing device. In addition, the main processing unit provides a data logger function by classifying and processing these heterogeneous field data according to different factory facilities and situations. In addition, the main processing unit provides optimal field analysis information for each data according to an embodiment, provides a monitoring function for repetitive and standardized errors and automatic control thereof, and provides a method for pattern analysis and aggregate analysis monitoring do. And, it also improves pre-occurring data errors and provides monitoring and control and fault prevention alarms. In addition, in this case, the main processing unit detects and responds to process anomalies in advance through real-time monitoring in a manner that connects various data gathering and communication in a general factory or HACCP factory, etc. according to an embodiment, and supports alarm alerts through data analysis We provide data analysis solutions that enable In other words, it provides a remote monitoring support hub role by collecting various data from a general factory or HACCP site and comprehensively collecting and analyzing various heterogeneous protocols with a data collection analyzer.

The database stores various registration information (eg, device and status, user information, etc.) and data used to service the data logger function according to an embodiment.

The display unit displays various UIs used to service the data logger function. In this case, the display unit provides a GUI for monitoring and managing the sensor node and gateway network status. Also, in this case, the GUI function is implemented in three parts. First, the Connect function is configured with basic Ethernet by setting the GUI and gateway connection information, and the Sensor Data function implements the periodic upload display of the sensed value transmitted from the sensor module. . Also, as for the connection data acquisition function (system), a universal serial bus (USB) provides a PC to a printer, a monitor, and a peripheral device such as a modem and a DAQ.

6 is a flowchart sequentially illustrating an operation of an AI-based data logger system according to an embodiment.

As shown in FIG. 6 , in the AI-based data logger system according to an embodiment, first, the control panel is installed in each field for a number of different factory facilities and situations, and an external sensor for monitoring each state and a movable part for adjusting the control panel Connected. Therefore, according to this, the field data is sensed using the external sensor to monitor the current field situation and to be adjusted by the movable unit.

Then, the AI processing unit collects the heterogeneous field data monitored by such a control panel (S601) and transmits and relays it to the registration management information processing device (S602), and classifies and processes these heterogeneous field data according to different factory facilities and situations. The data logger function is serviced (S605).

Therefore, the management information processing device uses these heterogeneous field data received by the AI processing unit to determine whether an abnormality has occurred for each factory facility and situation, and controls the operation of the movable part through the corresponding control panel depending on whether the abnormality occurs. to be controlled (S603-S604).

In this state, the data logger system performs the following operations in the AI processing unit.

a) First, when servicing the data logger function, by gathering heterogeneous field data in a communication format corresponding to each control panel device type (including PLC, DCS, OPC, DBMS, and devices) according to different factory facilities and situations, process the signal.

b) Next, the heterogeneous field data is compared with a set reference alarm value (S606), and as a result of the comparison, if the heterogeneous field data belongs to the reference alarm value, it is determined as normal. And, on the other hand, when the heterogeneous field data is out of the reference alarm value, it is determined as abnormal and the data is analyzed.

In addition, the information on the data analysis is transmitted differently for each interface format (including XML, file, and DB access) corresponding to different registered upper systems.

When it is determined as above, the control information of the movable unit is provided to the corresponding control panel in a different communication format for each type of control panel device according to the current abnormal state (S607).

c) In addition, when the heterogeneous field data is collected, the pre-alarm modeling value corresponding to the current heterogeneous field data is extracted according to the following pre-failure processing format and compared with the set pre-alarm value.

As a result of the comparison, if the pre-alarm modeling value corresponding to the current heterogeneous field data belongs to the pre-alarm value, it does not notify, but when the pre-alarm modeling value corresponding to the current heterogeneous field data deviates from the pre-alarm value, it notifies and pre-failures do

Also, in this case, the pre-failure processing format is as follows.

a) First, by classifying and learning heterogeneous field data by a number of different control panel device types and monitoring service types, a format for modeling a standardized and repetitive pre-alarm value is defined.

b) In addition, data sets for heterogeneous field data for a number of different control panel device types and monitoring service types are extracted according to different places and time zones.

c) And, attribute the data set by reflecting different usage places and time zones that provide services, and types of surrounding conditions.

d) Next, the attributes of heterogeneous field data to the control panel device type and monitoring service type are determined using the attribute information.

e) Then, normalize the decision information.

f) So, by using the determination information, each pre-alarm value is preset by modeling the pre-alarm value according to the heterogeneous field data by control panel device type and monitoring service type, and also independent (pre-alarm modeling value) and dependent ( Heterogeneous field data) variables are set.

g) Then, learning and training data is configured with the setting information.

h) So, through this, a pre-failure handling format is configured by the generated information.

Accordingly, in one embodiment, a separate AI processing unit is provided so that an AI-based data logger function can be added in addition to the existing input/output information. And, in addition to this, even in the case of a power outage or communication interruption of the central control unit, the AI-based data logger system having a function to check the data at the problem point later by the AI processing unit and restore it to the computer of the central control unit is provided.

In addition, this data logger system collects and processes the signals acquired from various sensors of the data collection and processing device in the AI processing unit, and analyzes. Provides data processing and analysis to enable diagnosis.

In addition, this data collection and analysis device solves the inconvenient point of use because measurement is complicated and there are many connected devices. Therefore, it provides a signal collection device serving as a comprehensive protocol gateway that can collect and analyze various signals such as temperature/pressure/noise/vibration by connecting it to a portable PC or laptop computer.

As described above, in one embodiment, a separate AI processing unit is provided to add an AI-based data logger function in addition to the existing input/output information. In addition, even in the case of a power outage or communication interruption of the central control unit, it has a function to check the data at the problem point later by the AI processing unit and to restore it to the computer of the central control unit.

Also, in this case, the AI processing unit detects and responds to process abnormalities in advance through real-time monitoring in a way that connects various data gathering and communication in general factories or HACCP factories. In addition, it provides a data analysis solution that can support alarm alerts through data analysis.

In other words, it provides a remote monitoring support hub role by collecting various data from a general factory or HACCP site and comprehensively collecting and analyzing various heterogeneous protocols with a data collection analyzer.

In addition, the AI processing unit implements device hardware based on SBC (Single Board Computing) architecture and provides services for data collection/processing/transmission from various general-purpose facilities, and various Provide I/F.

Accordingly, in one embodiment, a separate AI processing unit is provided so that an AI-based data logger function can be added in addition to the existing input/output information. And, in addition to this, even in the case of a power outage or communication interruption of the central control unit, the AI-based data logger system having a function to check the data at the problem point later by the AI processing unit and restore it to the computer of the central control unit is provided.

In addition, this data logger system collects and processes signals acquired from various sensors of data collection and processing devices in the AI processing unit, and provides data processing processing and analysis to enable analysis and diagnosis.

In addition, this data collection and analysis device solves the inconvenient point of use because measurement is complicated and there are many connected devices. Therefore, it provides a signal collection device serving as a comprehensive protocol gateway that can collect and analyze various signals such as temperature/pressure/noise/vibration by connecting it to a portable PC or laptop computer.

On the other hand, this data logger system provides a slightly better service by matching and maintaining the database from the configuration below, and also securing a connection with the manager mobile terminal, that is, the manager device, when servicing this data logger function. do.

To this end, first, the AI processing unit performs the following operations to match and maintain the database.

a) That is, in the case of servicing the data logger function, first, a table storing device registration information/data is equally provided between the registration control panel, the registration management information processing device, or the registration manager mobile terminal, and matching the table Register the relationship in advance.

b) Then, when the information in the table is changed in the control panel, the management information processing device, or the manager mobile terminal, the corresponding information is synchronized in the table of the AI processing unit according to the matching relationship to match the database with each other.

c) So, in the case of synchronizing the tables of the AI processing unit through this, the database is matched by diversifying the information for each data type for a number of different control panel device types and monitoring service types.

Next, the AI processing unit also performs the following operations to secure a connection with the manager device.

a) First, when communicating with the manager device, that is, the manager mobile terminal, it is first checked whether the registered local network is connected, and as a result of the check, when the local network is connected, setting corresponding to different manager locations Connect as an administrator public account.

b) As a result of the check, if the local communication network is not connected, it is checked whether the registered wireless communication network is connected secondarily, and if the wireless communication network is connected as a result of the check, an individual IP address is connected.

c) As a result of the check, if the wireless communication network is not connected, the connection is made with the terminal identification number of the registered mobile communication network, so that the connection with the manager mobile terminal is secured.

In this case, the AI processing unit also connects with a normal manager from the configuration below, and thus provides a slightly better connection security.

a) That is, for this, an IP table in which an administrator public account of the local communication network and individual IP addresses of the wireless communication network are registered is configured in advance.

b) Next, when information is provided to the manager mobile terminal, a next hop switch IP address is extracted from the response result by sending a hello message of the corresponding communication network.

c) So, the same switch IP address as the next hop switch IP address is checked in the switch neighbor connection relationship list.

d) As a result of the check, if there is a switch IP address identical to the IP address of the next hop switch, it is checked whether the corresponding administrator public account or individual IP address is also in the IP table, so that access by an unauthorized person is checked.

e) So, as a result of the check, if the corresponding administrator public account or individual IP address is also present in the IP table, the JOIN/PRUNE message is transmitted, so that it is connected to the corresponding communication network.

On the other hand, when such a system is monitored in this way, it learns various devices and sensor information from the following configuration according to the surrounding conditions to enable smooth monitoring.

In other words, on the one hand, this system creates a monitoring format in consideration of the on-site situation such as the surrounding state, and provides related monitoring and control information from it according to the on-site situation. provides

In this case, such a learning model attributes data related to various places, time zones, and surrounding conditions, so that the processing rate is further increased.

a) First, the learning model for monitoring each control panel device and sensor provides control information, that is, when a prior alarm value is recommended, various control panel devices and status information for each installation location, temperature, and humidity are displayed at different times, Define a learning model by classifying by place, etc.

b) Next, a basic dataset for a number of different state information is extracted.

c) Then, attribute these datasets to reflect a number of different installation locations, time of day, temperature, humidity, etc.

d) So, the attribute of the state information is determined for each of a number of different learning models based on the attribute result.

e) Then, normalize the determined result.

f) And, based on these normalized results, state information is set for each of a number of different learning models. Therefore, a plurality of different state information is set as independent (recommended information) and dependent (state information) variables for generating recommended information for each on-site situation such as surrounding state.

g) Next, the set result is generated as learning and training data.

h) So, this creates a format for monitoring from these results.

Therefore, in the case of monitoring as described above, such a system provides recommended information, ie, control information, in real time in such a pre-registered format, thereby further enhancing related services.

Additionally, a little bit more about how to create these formats.

First, this format creates a format for a number of different devices. Therefore, a model may be newly created for each device maker in various fields, or a model may be created in several bundles by setting standards. This allows us to determine the appropriate method according to the characteristics of the data.

Next, in the case where a large number of data is not collected due to an error in the device, etc. in the data collected in real time, or when an unusually large number of reservations occur, the corresponding data file is removed.

In addition, if some data is not collected due to data interruption, the corresponding data is removed.

Next, we determine valid attributes for different formats, generate normal values, and then determine independent and dependent variables.

Then, in order to generate a format, training and training data are generated from the entire data. In general, 70% of the entire dataset is used as training data, and 30% is used as training data to test the model after model creation.

Next, create a format. At this stage, you decide which format to use. For example, it refers to a configuration in which the necessary layers are configured based on deep learning and the input and output layers are configured to set the maximum number of outputs. Then, the generated model is evaluated, and if the model is satisfied with the error rate, the model is simulated with new data. If the model update is not required, the format is saved and used.

7 is a view showing an HMI monitoring screen in a factory applied to an AI-based data logger system according to an embodiment.

As shown in FIG. 7 , HMI monitoring according to an embodiment accurately and real-time collects factory site data without omission, is applied to various industries and industries to provide field-verified information, and also provides information on site information events. Provides synchronization (see a).

In addition, this HMI monitoring performs a comprehensive interface for various heterogeneous signals, monitoring aggregation and management, and provides an HMI linkage interface of batch and immediate production facility status data. In addition, it provides immediate alert data for key alarm alert issues (see b).

100: (site) control panel
200: AI processing unit
300: management information processing device

Claims (4)

It is installed on the site for each of a number of different factory facilities and situations, and is connected to an external sensor to monitor each state and a movable part to control, and to detect the on-site data using the external sensor to monitor the current on-site situation and to the movable part. control panel to regulate;
an AI processing unit that collectively collects heterogeneous field data monitored by the control panel, transmits and relays it to a registration management information processing device, categorizes and processes the heterogeneous field data according to different factory facilities and situations, and serves a data logger function; and
a management information processing device for determining whether an abnormality has occurred for each factory facility and situation by using the heterogeneous field data transmitted by the AI processing unit, and differently controlling the control operation of the movable unit through a corresponding control panel according to the occurrence of an abnormality; contains and.

The AI processing unit,
a) When servicing the data logger function, by gathering heterogeneous field data in a communication format corresponding to each control panel device type (including PLC, DCS, OPC, DBMS, and devices) according to different factory facilities and situations, processing heterogeneous signals,
b) The heterogeneous field data is compared with a set reference alarm value, and as a result of the comparison, if the heterogeneous field data belongs to the reference alarm value, it is determined as normal, and when the heterogeneous field data is out of the reference alarm value, it is determined as abnormal. to analyze the data,
In addition, the information on the data analysis is transmitted differently for each interface format (including XML, file, and DB access) corresponding to different registered upper systems,
When it is determined that the above is abnormal, the control information of the movable part is provided to the corresponding control panel in a communication format for each control panel device type differently depending on the current abnormal state,
c) When the heterogeneous field data is collected, the pre-alarm modeling value corresponding to the current heterogeneous field data is extracted according to the following pre-failure processing format and compared with the set pre-alarm value,
As a result of the comparison, if the pre-alarm modeling value corresponding to the current heterogeneous field data belongs to the pre-alarm value, it does not notify, but when the pre-alarm modeling value corresponding to the current heterogeneous field data deviates from the pre-alarm value, it notifies and pre-failures do,
And also, the pre-failure processing format is,
a) First, by classifying and learning heterogeneous field data by a number of different control panel device types and monitoring service types, defining a format for modeling standardized and repetitive pre-alarm values;
b) In addition, data sets for heterogeneous field data for a number of different control panel device types and monitoring service types are respectively extracted according to different places and time zones;
c) attribute the data set by reflecting different usage places and time zones that provide services, and types of surrounding conditions,
d) determining the properties of heterogeneous field data to the control panel device type and the monitoring service type using the attributable information;
e) normalizes said decision information;
f) Using the above-mentioned determination information, each pre-alarm value is preset by modeling the pre-alarm value according to the heterogeneous field data by control panel device type and monitoring service type, and also independent (pre-alarm modeling value) and dependent (heterogeneous site) data) set the variable,
g) by configuring the learning and training data with the setting information,
h) configuring a pre-failure handling format according to the generated information; AI-based data logger system characterized by. The method according to claim 1,
The AI processing unit
a) When servicing the data logger function, a table storing device registration information/data is equally provided between the registration control panel, the registration management information processing device, or the registration manager mobile terminal, and the matching relationship for the table is set in advance. register settings,
b) when the information in the table is changed in the control panel, the management information processing device, or the manager mobile terminal, the corresponding information is synchronized in the table of the AI processing unit according to the matching relationship to match the database with each other;
c) matching the database by diversifying information for each data type of a plurality of different control panel device types and monitoring service types when synchronizing the tables of the AI processing unit; AI-based data logger system characterized by. 3. The method according to claim 2,
The AI processing unit
a) When communicating with the manager mobile terminal, first check whether the registered local network is connected, and if the local network is connected as a result of the check, connect as a setting manager public account corresponding to different manager locations, ,
b) As a result of the above check, if the local communication network is not connected, it is checked whether the registered wireless communication network is connected secondarily, and if the wireless communication network is connected as a result of the check, an individual IP address is connected,
c) as a result of the check, if the wireless communication network is not connected, the connection is made to the terminal identification number of the registered mobile communication network, so as to secure a connection with the manager mobile terminal; AI-based data logger system characterized by. 4. The method of claim 3,
The AI processing unit
a) preconfiguring an IP table in which an administrator public account of the local communication network and individual IP addresses of the wireless communication network are registered;
b) When information is provided to the manager mobile terminal, a next hop switch IP address is extracted from the response result by sending a hello message of the corresponding communication network;
c) check the switch IP address identical to the next hop switch IP address in the switch neighbor connection relationship list;
d) As a result of the check, if there is a switch IP address that is the same as the next hop switch IP address, it is checked whether the corresponding administrator public account or individual IP address is also in the IP table, so that unauthorized access is checked;
e) As a result of the check, if the corresponding administrator public account or individual IP address is also in the IP table, a JOIN/PRUNE message is sent, so connecting to the corresponding communication network; AI-based data logger system characterized by.

Images