JP-7857143-B2 - Wireless communication system, wireless communication method, and control station

JP7857143B2JP 7857143 B2JP7857143 B2JP 7857143B2JP-7857143-B2

Inventors

玉木諭
石井裕丈
石本英史
桐村亮好
江口裕介

Assignees

日立建機株式会社

Dates

Publication Date: 20260512
Application Date: 20220407

Claims (9)

A wireless communication system in a control system including a control station and a plurality of mobile vehicles connected to the control station via wireless communication, The aforementioned multiple mobile vehicles or fixed radio stations connected to the aforementioned multiple mobile vehicles by radio communication periodically measure location information and radio communication quality information indicating the quality of the radio communication, and report the measurement results to the control station. The control station defines the driving trajectories of the multiple mobile vehicles and the area including said driving trajectories based on the location information reported by the multiple mobile vehicles, divides the area into multiple sub-areas, selects a first time range from the measurement results reported by the multiple mobile vehicles as the learning target, groups the measurement results belonging to the first time range based on the location information to correspond to the multiple sub-areas, and learns the distribution of the wireless communication quality information for each of the grouped sub-areas. From the measurement results reported by the multiple mobile vehicles, a second time range, separate from the first time range, is selected as the target of detection processing, and measurement results belonging to the second time range are acquired. Using the learned distribution of wireless communication quality information for each subdivided area, the proportion of outliers in the measurement results belonging to the second time range for each subdivided area is derived. The control station has an anomaly detection device that detects the occurrence of anomalies in each of the plurality of subdivided areas in the second time range based on the ratio of the presence of the outliers. The anomaly detection device is a wireless communication system having a display unit that displays the area, each of the plurality of subdivision areas, and the travel trajectory of the moving vehicle, and highlights the subdivision area among the plurality of subdivision areas in which an anomaly has occurred in wireless communication.
A wireless communication system according to claim 1, wherein the control station determines that an abnormality has occurred in the wireless communication system when there is a small divided area where the ratio of outliers is equal to or greater than a threshold.
A wireless communication system according to claim 1, A wireless communication system further comprising: a device that, when the proportion of outliers in each of the aforementioned subdivision areas is greater than or equal to a threshold, classifies the subdivision area as an outlier subdivision area; when the proportion of outliers is less than the threshold, classifies the subdivision area as a normal range; uses the data obtained from this classification as training data to perform a learning process for a binary classifier; and when the position of the moving vehicle is classified using the binary classifier, determines an anomaly detection for the moving vehicle if the position of the moving vehicle is included in the outlier subdivision area.
A wireless communication method between a control station and a plurality of mobile vehicles connected to the control station via wireless communication, The plurality of mobile vehicles or the fixed radio station connected to the plurality of mobile vehicles by wireless communication periodically measure location information and wireless communication quality information indicating the quality of the wireless communication, and report the measurement results to the control station. Based on the location information reported from the plurality of mobile vehicles, the driving trajectories of the plurality of mobile vehicles and the area including said driving trajectories are defined, and the area is divided into a plurality of subdivision areas, and from the measurement results reported from the plurality of mobile vehicles, a first time range is selected as the learning target, and the measurement results belonging to the first time range are grouped according to the plurality of subdivision areas based on the location information, and the distribution of the wireless communication quality information is learned for each of the grouped subdivision areas. From the measurement results reported by the multiple mobile vehicles, a second time range, separate from the first time range, is selected as the target of detection processing, and measurement results belonging to the second time range are acquired. Using the learned distribution of wireless communication quality information for each subdivided area, the proportion of outliers in the measurement results belonging to the second time range for each subdivided area is derived. Based on the ratio of outliers, the occurrence of anomalies in wireless communication in each of the plurality of subdivided areas within the second time range is detected. A wireless communication method characterized by displaying the area, each of the plurality of subdivision areas, and the travel trajectory of the moving vehicle, and highlighting the subdivision area among the plurality of subdivision areas in which an abnormality has occurred in wireless communication.
A wireless communication method according to claim 4, wherein an abnormality in the wireless communication is determined when there is a small divided area where the ratio of outliers is equal to or greater than a threshold.
A wireless communication method according to claim 4, A wireless communication method comprising: classifying a subdivision area as an outlier subdivision area if the proportion of outliers in each subdivision area is equal to or greater than a threshold; classifying a subdivision area as a normal range if the proportion of outliers is less than the threshold; using the data obtained from this classification as training data to perform a binary classifier training process; and determining an anomaly detection for the moving vehicle when the position of the moving vehicle is classified using the binary classifier and the position of the moving vehicle is included in the outlier subdivision area.
A control station that is connected to multiple mobile vehicles via wireless communication and constitutes a control system, The control station is equipped with an anomaly detection device for detecting anomalies in the wireless communication, The aforementioned abnormality detection device is, From the aforementioned multiple mobile vehicles, the measurement results of location information and wireless communication quality information indicating the quality of the wireless communication are received periodically. Based on the location information reported from the plurality of mobile vehicles, the driving trajectories of the plurality of mobile vehicles and the area including said driving trajectories are defined, and the area is divided into a plurality of subdivision areas, and from the measurement results reported from the plurality of mobile vehicles, a first time range is selected as the learning target, and the measurement results belonging to the first time range are grouped according to the plurality of subdivision areas based on the location information, and the distribution of the wireless communication quality information is learned for each of the grouped subdivision areas. From the measurement results reported by the multiple mobile vehicles, a second time range, separate from the first time range, is selected as the target of detection processing, and measurement results belonging to the second time range are acquired. Using the learned distribution of wireless communication quality information for each subdivided area, the proportion of outliers in the measurement results belonging to the second time range for each subdivided area is derived. The anomaly detection device detects the occurrence of anomalies in each of the plurality of subdivided areas in the second time range based on the ratio of the presence of the outliers, The anomaly detection device has a display unit that displays the area, each of the plurality of subdivision areas, and the travel trajectory of the moving vehicle, and also highlights the subdivision area among the plurality of subdivision areas in which an anomaly has occurred in wireless communication. Control station.
A control station according to claim 7, wherein the anomaly detection device determines that an anomaly has occurred in the wireless communication system when there is a small divided area where the ratio of outliers is equal to or greater than a threshold.
A control station according to claim 7, The anomaly detection device classifies each of the subdivision areas as an outlier subdivision area if the proportion of outliers in each subdivision area is greater than or equal to a threshold, and classifies each subdivision area as a normal range if the proportion of outliers is less than the threshold. The control station uses this data as training data to perform a binary classifier learning process, and when classifying the position of the moving vehicle using the binary classifier, determines that an anomaly has been detected for the moving vehicle if the position of the moving vehicle is included in the outlier subdivision area.

Description

This invention relates to a wireless communication system, a wireless communication method, and a control station constituting said wireless communication system, used for controlling mobile objects. In recent years, wireless communication has been used in a variety of environments for a variety of purposes. One form of wireless communication use is in control systems where a central control station collects information from multiple mobile objects, such as vehicles, and controls the movement of each of these objects. In air traffic control systems, if radio communication with a vehicle under the control of the central control station is interrupted, not only will the central control station be unable to adequately control that vehicle, but it will also be unable to obtain the necessary information from that vehicle to perform control. Furthermore, a communication interruption in one vehicle can affect the control of other vehicles. Therefore, when applying radio communication to air traffic control systems, it is extremely important to prevent communication interruptions and ensure the reliability of the radio communication. On the other hand, the propagation of radio waves used in wireless communication is greatly affected by structures and other objects in the propagation area. Furthermore, movement or deformation of these structures can cause fluctuations in radio wave propagation and, consequently, the quality of wireless communication, leading to communication interruptions. The occurrence and frequency of communication interruptions vary depending on the location and fluctuate over time. Therefore, to ensure the reliability of wireless communication, technologies have been proposed that measure communication quality during communication and take action based on the measurement results. For example, Patent Document 1 discloses a wireless communication technology for autonomous dump trucks in mines that ensures the reliability of wireless communication and allows the dump truck to operate autonomously even in mines with poor radio wave conditions. This is achieved by setting a permitted driving section when the communication quality meets a predetermined standard. In other words, the technology disclosed in Patent Document 1 determines the connection status based on the communication quality measured by the autonomous dump truck in the mine, and allows driving in a predetermined permitted driving section when the communication quality meets a predetermined standard, thereby enabling the dump truck to operate autonomously smoothly. However, the technology disclosed in Patent Document 1 detects fluctuations in radio wave propagation due to movement or deformation of structures, as well as fluctuations in wireless communication quality due to equipment malfunctions, retrospectively. Therefore, there is a problem in that, depending on the cause of the communication quality fluctuation, the target control may not be able to be executed. Japanese Patent Publication No. 2015-210595 This is a schematic diagram of the wireless communication system configuration according to an embodiment of the present invention.This is a schematic diagram of the abnormality detection unit according to an embodiment of the present invention.This is a schematic diagram of the hardware configuration of the anomaly detection unit according to an embodiment of the present invention.This is an example of an information structure held in the radio station information holding unit of an embodiment of the present invention.This is an example of an information structure held in the radio station information holding unit of an embodiment of the present invention.This is an example of an information structure held in the radio station information holding unit of an embodiment of the present invention.This is an example of an information structure held in the radio station information holding unit of an embodiment of the present invention.This is an example of an information structure held in the radio station information holding unit of an embodiment of the present invention.This is an example of the processing flow for the learning process in an embodiment of the present invention.This is an example of an information structure representing the typical wireless communication quality of an embodiment of the present invention.This is an example of an information structure representing the typical wireless communication quality of an embodiment of the present invention.This is an example of an information structure representing the typical wireless communication quality of an embodiment of the present invention.This is an example of the positional range of an embodiment of the present invention.This is an example of the processing flow for outlier learning according to an embodiment of the present invention.This is the process execution flow of the abnormality detection unit 131 by scheduled operation according to an embodiment of the presen