KR102488984B1 - Real-time failure detection method and system for satellite ground station based on artificial intelligence - Google Patents

Abstract

The present invention relates to a real-time failure detection method and system for a satellite ground station based on artificial intelligence. The method according to the present invention comprises the steps of: checking whether an error log also occurs in a backup software process for a software process when a predetermined error log occurs in the software process constituting a ground station system; checking whether an error log also occurs in an input system for inputting the input data to the software process and the backup software process when the error log also occurs in the backup software process; checking whether an error log also occurs in a backup system of the input system when the error log also occurs in the input system; checking whether an error log also occurs in a previous input system located in front of the input system and the backup system when an error log occurs in the backup system; and detecting the main cause of failure based on the error logs of the software process, backup software process, input system, backup system, and previous input system. Accordingly, more accurate operation becomes possible.

Description

Real-time failure detection method and system for satellite ground station based on artificial intelligence}

The present invention relates to an AI-based satellite ground station real-time failure detection method and system.

The satellite ground station continuously monitors the operational status of satellites in outer space on the ground, creates commands necessary for mission execution, uploads them to the satellite, and receives and processes data observed by various sensors mounted on the satellite. . To perform these duties, it consists of various equipment and SW such as transmission/reception equipment, transmission/reception monitoring and control SW, control SW, image processing SW, various computer equipment, connection system with external organizations, and network equipment, and operating personnel to control and monitor them. they are needed

However, as the number of operating satellites increases, the types and number of terrestrial systems also increase, but it is not easy to increase the number of operating personnel in proportion thereto. This is because it is not easy to secure operational manpower with excellent technology maturity as well as operational budget issues. In order to solve these problems, the concept of automatic operation of ground systems in various ways (eg, script-based) has been considered, and the system has been improved to automatically produce and display various results with minimal operator intervention.

With the introduction of the concept of automatic operation, it is possible to operate the satellite with a small number of operating personnel compared to when the operator intervened individually, but the automatic operation concept of the existing ground system reveals its limitations when a failure phenomenon occurs other than the normal operating situation. .

Because it is realistically difficult for an operator to sit in front of all monitors and keep an eye on a lot of information, failure detection may be delayed. , In the case of a satellite image processing system composed of multiple sets of backup structures or sequentially processed, the main cause of failure by determining the situation in flashing lights and alarm sounds occurring simultaneously in several systems in an instant and many error logs ( Root Cause) is not easy to find in a short time. In addition, it is necessary to check the possibility of failure due to external environments such as RF interference signals, climate change such as rainfall, and space environment such as solar wind, not the ground system.

Therefore, delays in identifying and responding to failures are inevitable, and in particular, when an operator with sufficient knowledge about the system is not present or the operator only knows about a part of the system, it takes time to identify the cause, which inevitably leads to smooth operation of the satellite as a whole. In addition, if multiple satellites are operated, the ripple effect will inevitably increase.

Therefore, the technical problem to be solved by the present invention is to provide an AI-based satellite ground station real-time failure detection method and system.

In order to solve the above technical problem, the artificial intelligence-based satellite ground station real-time failure detection method according to an embodiment of the present invention, when a predetermined error log occurs in a software process constituting a ground station system, backup software for the software process Checking whether an error log has occurred in the process, if an error log has also occurred in the backup software process, checking whether an error log has occurred in the software process and an input system for inputting input data to the backup software process, If an error log has occurred in the system, checking whether an error log has also occurred in the backup system of the input system. If an error log has also occurred in the backup system, the input system and the previous input system located in front of the backup system Checking whether an error log has occurred, and detecting a main cause of failure based on the error logs of the software process, the backup software process, the input system, the backup system, and the previous input system.

If an error log does not occur in the backup software process, the software process is detected as a main cause of failure, and if an error log does not occur in the backup system, the input system is detected as a main cause of failure, and the backup software process is detected as a main cause of failure. If a failure occurs in both the process and the backup system, and an error log is also generated in the previous input system, the previous input system can be detected as the main cause of the failure.

If the previous input system in which the error log is generated is a satellite, it may be determined whether the satellite is the main cause of the failure by referring to the satellite telemetry monitoring result.

If it is confirmed that the satellite is not the main cause of failure, it may be determined whether the main cause of failure is due to the operating environment of the ground station system by referring to a result of monitoring the operating environment of the ground station system.

The error log of the software process, the backup software process, the input system, the backup system, and the previous input system, the satellite telemetry monitoring result, and the operating environment monitoring result of the ground station system are converted to a pre-learned artificial intelligence model. You can output the error handling procedure by inputting it.

According to the present invention, there is an advantage in that it is possible to quickly identify the cause of failure and respond to it even in a situation where there is no manpower with high technological maturity. In addition, artificial intelligence performs constant monitoring on behalf of the operator with setting information for input and output data based on the operation schedule, so that the cause of failure can be identified in real time after a failure occurs, and the operational impact of changes in the external environment can be quickly analyzed, enabling more accurate operation. There is an advantage to canceling.

1 is a block diagram of an AI-based satellite ground station real-time failure detection system according to an embodiment of the present invention.
2 is an operation flowchart of an AI-based satellite ground station real-time failure detection system according to an embodiment of the present invention.
3 is a diagram for explaining a method for determining a main cause of failure based on a failure error log according to an embodiment of the present invention.

Then, with reference to the accompanying drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily practice the present invention.

1 is a block diagram of an AI-based satellite ground station real-time failure detection system according to an embodiment of the present invention.

Referring to FIG. 1 , the AI-based satellite ground station real-time failure detection system 100 according to the present invention may include a mission operation monitoring unit 110, an operating environment monitoring unit 120, and an integrated operation unit 130.

The mission operation monitoring unit 110 may collect error logs related to components of the satellite ground station system, software processes, and input systems, and may detect a main cause of failure based on the collected error logs.

Specifically, the mission operation monitoring unit 110 may include a ground station system software monitoring module 111 , a ground station system hardware monitoring module 113 , and a satellite mission monitoring module 115 .

Ground station system software monitoring is performed for satellite control, image pre-processing, and other software that needs to be monitored installed in the ground system. The ground station system software monitoring module 111 may collect error log messages generated by ground station system software processes. The error log message contains critical information among log messages, such as when input data to be entered within a specified time is not delivered, when output is not generated or only part of it is generated, software malfunction, and violation of major requirements such as timeliness requirement. It is a log message with a log message, and the collected error logs can be set based on the log ID.

Ground station system hardware monitoring refers to monitoring of computer equipment installed with satellite control, image pre-processing, and other software. The ground station system hardware monitoring module 113 monitors the normal operation of each computer equipment and network traffic based on model/version information constituting the ground station system computer equipment, equipment connection information, and network configuration information.

The ground station system hardware monitoring module 113 may be mounted on the ground computer equipment or may be implemented to monitor warning lights, screens, etc. related to the operation of the ground computer equipment based on images. For example, the ground station system hardware monitoring module 113 monitors whether or not a color change of a status indicator light on ground computer equipment or a graph change on the monitor screen of the ground station system hardware monitoring module 113 can be generated, and an error log can be generated. . To this end, the ground station system hardware monitoring module 113 may use an artificial intelligence model learned to determine whether or not there is an error according to the state of the ground computer equipment. For reference, disk damage, which frequently occurs among computer equipment, can be recognized by whether or not the color of the alarm lamp of the equipment has changed. In addition, the ground station system hardware monitoring module 113 monitors and records the CPU, RAM, and disk capacities of the computing equipment in which the ground system software processes are running, and displays them on the main screen to inform the operator of the stable operation of the equipment in case of a high risk level. The environment can also make it possible.

The satellite mission monitoring module 115 monitors the state of the satellite and checks whether or not the payload has been photographed according to the photographing schedule, and may monitor related telemetry transmitted from the satellite for this purpose.

The satellite mission monitoring module 115 may perform satellite telemetry monitoring and provide the monitoring result to the integrated operation unit 130 .

The operating environment monitoring unit 120 may monitor the operating environment of the mission operation monitoring unit 110 and detect whether a failure occurs in the operating environment. Since the causes of failures occurring during operation of the mission operation monitoring unit 110 may come from internal/external environments other than satellites or terrestrial systems, monitoring of the operating environment is also required to accurately detect failures.

The operating environment monitoring unit 120 may monitor the operating environment of the ground station system and provide the monitoring result to the integrated operating unit 130 .

The operating environment monitoring unit 120 may include an RF environment monitoring module 121 , a meteorological climate monitoring module 123 , and a constant temperature/humidity monitoring module 125 .

The RF environment monitoring module 121 may monitor the spectrum monitor screen for the operating frequency band of the mission operation monitoring unit 110 instead of the operator. As described above, the RF environment monitoring module 121 may recognize and monitor the spectrum monitor screen based on vision, or may be installed in RF environment monitoring equipment.

If an external RF interference signal is generated in the vicinity of a ground station and affects transmission/reception equipment, a failure in which an image is lost may occur even if the satellite properly captures and transmits an image signal as commanded. Therefore, when an RF interference signal occurs, the graph of the spectrum monitor is significantly different from the learning data in the normal operating environment, and immediately upon detection, the operator can display the RF interference signal generation, generation time, and confirmation method on the screen. For this purpose, the RF environment monitoring module 121 can learn the graph data of the spectrum monitor and implement it as an artificial intelligence model trained to output RF interference signal generation, generation time, confirmation method, and the like.

The meteorological climate monitoring module 123 may collect and process meteorological information such as rainfall/humidity/atmospheric pressure/wind speed observed by automatic meteorological measurement equipment installed near the antenna building on the ground. In addition, the weather climate monitoring module 123 is provided by the National Weather Service Center or an overseas space weather agency (US National Oceanic and Atmospheric Administration Space Weather Prediction Center, etc.) because satellites operating in geostationary orbit can be affected by solar wind in outer space. Depending on forecast and special information, it is also possible to determine the presence or absence of solar wind, observation grade, solar wind speed, and solar wind magnetic fields that affect satellite operation by time period. The meteorological climate monitoring module 123 may also be implemented through an artificial intelligence model to predict the possibility of failure based on past learning data even when forecast information is given in advance or collected in real time.

The constant temperature and humidity monitoring module 125 can control and monitor the temperature/humidity of the ground station's internal operating environment, such as an equipment room and a control room, and can be implemented using a thermo-hygrostat device and IoT equipment.

The ground station system software monitoring module 111, the ground station system hardware monitoring module 113, the satellite mission monitoring module 115, the RF environment monitoring module 121, the weather climate monitoring module 123, and the constant temperature and humidity monitoring module 125 are Each operates independently, and when a failure of the monitoring target is detected, related information can be delivered to a higher level.

The mission operation monitoring unit 110 collects error logs for each component monitored by the ground station system software monitoring module 111, the ground station system hardware monitoring module 113, and the satellite mission monitoring module 115. , the main cause of failure can be detected through the following procedure.

Hereinafter, a procedure for detecting a main cause of failure in the ground station system software monitoring module 111 will be described.

2 is an operation flowchart of an AI-based satellite ground station real-time failure detection system according to an embodiment of the present invention.

Referring to FIG. 2, first, when an error log occurs in the software process (S205), the ground station system software monitoring module 111 checks whether a major error log, that is, a predetermined error log, has occurred based on the log ID of the corresponding error log. Do (S210). All error logs can be used for failure detection, but in order to analyze the causes of major failures and reduce processing time, ground stations can pre-determine and extract logs corresponding to major errors with high impact among multiple error logs through machine learning. A system software monitoring module 111 may be implemented.

If the error log generated in the software process is not the main error log (S210-N), the ground station system software monitoring module 111 may determine that it is a simple error and display and record related information on the screen (S215).

Meanwhile, if the corresponding error log is the main error log (S210-Y), the ground station system software monitoring module 111 checks whether the same error log has occurred in the backup software process for the software process in which the corresponding error log occurred (S220).

3 is a diagram for explaining a failure determination method based on a failure error log according to an embodiment of the present invention.

As illustrated in FIG. 3 (a), for example, when the error log does not occur in the backup software process (SWP 2) of the software process (SWP 1) in which the error log occurred (S220-N), the software process (SWP It is possible to analyze the cause of the main failure with the single failure of 1) (S225).

Meanwhile, as illustrated in FIG. 3(b), when an error occurs in the backup software process (SWP 2) of the software process (SWP 1) in which the error log occurred (S220-Y), the software process (SWP 1) and the backup software process The cause may be an error that occurred in the input system (A) that inputs common input data to (SWP 2) or an error that occurred in the previous input system located at the front of the input system (A).

It is checked whether an error log has occurred in the input system (A) and its backup system (B) (S230), and if an error log has occurred only in the input system (A) (S230-N), the input system (A) is the main cause of failure. It is possible to detect and complete the main failure cause analysis (S290).

On the other hand, if an error log occurs in both the input system (A) and its backup system (B) (S230-Y), the error log is located in the previous input system located in front of the input system (A) and the backup system (B). It can be confirmed whether or not it has occurred (S240). Step S240 may be repeated until the previous input system, which is estimated to have a failure, is checked while repeatedly checking the previous input system located in the previous stage of the input system in which the error log has occurred.

If the previous input system of the frontmost stage, which is estimated to have a failure in step S240, is a satellite (S250-Y), the integrated operation unit 130 may check whether or not a satellite failure has occurred by referring to the satellite telemetry monitoring result. (S260).

When the occurrence of failure in the satellite is confirmed (S260-Y), the integrated operation unit 130 can detect the satellite as the main cause of failure and complete the analysis of the main cause of failure (S290).

On the other hand, if the satellite does not have a failure (S260-N), the integrated operation unit 130 may check whether the main cause of the failure is due to the operating environment of the ground station system by referring to the operating environment monitoring result of the ground station system (S270).

When it is confirmed that an abnormality has occurred in the operating environment of the ground station system (S270-Y), the integrated operation unit 130 can detect the operating environment of the ground station system as a main cause of failure and complete analysis of the main cause of failure (S290).

On the other hand, if an error does not occur in the operating environment of the ground station system (S270-N), the integrated operation unit 130 may output and record the unresolved main failure cause analysis on the screen (S280).

In the method described above, the integrated operation unit 130 checks the cause of the main failure, and monitors the software process, the backup software process, the input system, the error log of the backup system and the previous input system, the satellite telemetry monitoring result, and the operating environment of the ground station system. The result can be input into a pre-learned artificial intelligence model to output an error handling procedure.

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

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

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

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

Claims (10)

In the artificial intelligence-based satellite ground station real-time failure detection method,
When a predetermined error log occurs in a software process constituting the ground station system, confirming whether an error log also occurs in a backup software process for the software process;
If an error log is also generated in the backup software process, confirming whether an error log is generated in the software process and an input system for inputting input data to the backup software process;
If an error log is generated in the input system, checking whether an error log is also generated in the backup system of the input system;
If an error log has also occurred in the backup system, confirming whether an error log has also occurred in the input system and the previous input system located in front of the backup system; and
Detecting a main cause of failure based on error logs of the software process, the backup software process, the input system, the backup system, and the previous input system.
How to include.
In claim 1,
If an error log does not occur in the backup software process, the software process is detected as the main cause of failure,
If an error log does not occur in the backup system, the input system is detected as the main cause of failure,
If a failure occurs in both the backup software process and the backup system, and an error log is also generated in the previous input system, detecting the previous input system as a main cause of failure.
In paragraph 2,
If the previous input system in which the error log is generated is a satellite, a method of confirming whether the satellite is the main cause of failure by referring to a satellite telemetry monitoring result.
In paragraph 3,
If it is confirmed that the satellite is not the main cause of failure, the method of determining whether the main cause of failure is due to the operating environment of the ground station system by referring to a result of monitoring the operating environment of the ground station system.
In paragraph 4,
The error log of the software process, the backup software process, the input system, the backup system, and the previous input system, the satellite telemetry monitoring result, and the operating environment monitoring result of the ground station system are converted to a pre-learned artificial intelligence model. An artificial intelligence-based real-time failure detection method that outputs failure handling procedures by inputting data.
In the artificial intelligence-based satellite ground station real-time failure detection system,
When a predetermined error log occurs in a software process constituting the ground station system, it is checked whether an error log also occurs in a backup software process for the software process, and if an error log occurs in the backup software process, the software process and the backup software process also generate an error log. It is checked whether an error log has occurred in the input system that inputs input data to the software process, and if an error log has occurred in the input system, it is checked whether an error log has also occurred in the backup system of the input system, and an error log is also generated in the backup system. If an error log has occurred, it is checked whether an error log has also occurred in the previous input system located in front of the input system and the backup system, and the software process, the backup software process, the input system, the backup system, and the previous input system. Mission operation monitoring unit that detects the main cause of failure based on the error log
A system that includes.
In paragraph 6,
The mission operation monitoring unit,
If an error log does not occur in the backup software process, the software process is detected as a main cause of failure, and if an error log does not occur in the backup system, the input system is detected as a main cause of failure, and the backup software process is detected as a main cause of failure. If a failure occurs in both the process and the backup system, and an error log also occurs in the previous input system, the system detects the previous input system as the main cause of the failure.
In paragraph 7,
If the previous input system in which the error log is generated is a satellite, the system further includes an integrated management unit that checks whether the satellite is a main cause of failure by referring to satellite telemetry monitoring results.
In paragraph 8,
The integrated operation department,
If it is confirmed that the satellite is not the main cause of failure, the system for confirming whether the main cause of failure is due to the operating environment of the ground station system by referring to the operating environment monitoring result of the ground station system.
In paragraph 9,
The integrated operation department,
The error log of the software process, the backup software process, the input system, the backup system, and the previous input system, the satellite telemetry monitoring result, and the operating environment monitoring result of the ground station system are converted to a pre-learned artificial intelligence model. An artificial intelligence-based real-time failure detection system that outputs failure handling procedures by inputting data.

Images