Wireless communication system, wireless communication method, and control station
By regularly measuring and learning communication quality information in wireless communication systems and identifying outliers in abnormal detection, the problem of inability to deal with communication quality changes in the prior art is solved, and the reliability of wireless communication in mobile control is improved and Reliability of control.
Patent Information
- Application Number
- CN202380030474.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-04-07
- Filing Date
- 2023-04-05
- Publication Date
- 2024-11-12
AI Technical Summary
The existing wireless communication system cannot detect and respond to changes in communication quality before the communication quality does not meet the specified quality, resulting in the inability to achieve control targets and affect the trust of mobile body control.
By setting a control station in the wireless communication system, the location information and communication quality information are measured regularly by mobile vehicles and fixed wireless base stations, and the measurement results are reported to the control station. Based on this information, the distance in abnormal detection is identified and judged. Group value, realize abnormal detection and analysis.
A wireless communication system is provided that can detect and respond to changes before the communication quality does not meet the specified quality, which improves the reliability of wireless communication in mobile control and ensures the stability of communication quality and the reliability of control.
Smart Images

Figure CN118947161A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a wireless communication system used for mobile object control, a wireless communication method, and a control station constituting the wireless communication system. Background Art
[0002] In recent years, wireless communication has been used for various purposes in various environments. As one form of using wireless communication, there is a control system that collects information from a plurality of moving objects such as vehicles at a central control station and controls the movement of each moving object.
[0003] If the wireless communication of a vehicle under control from the central control station is disconnected, the control system cannot fully control the vehicle from the central control station, and the central control station cannot obtain the information required for control from the vehicle. On this basis, the disconnection of communication in one vehicle will also affect the control of other vehicles. Therefore, when applying wireless communication to a control system, etc., it is extremely important to ensure the reliability of wireless communication without communication disconnection.
[0004] On the other hand, the transmission of radio waves used for wireless communication is greatly affected by structures in the transmission area. In addition, the movement and deformation of structures can also affect the transmission of radio waves, which can cause changes in the quality of wireless communication and communication interruption. The presence and frequency of communication interruption vary depending on the location and also change with time. Therefore, in order to ensure the reliability of wireless communication, a technology has been proposed to measure the communication quality during communication and take measures based on the measurement results.
[0005] For example, Patent Document 1 discloses a wireless communication technology that sets a driving permission interval for an autonomously driven dump truck in a mine when the communication quality satisfies a prescribed quality, thereby ensuring the reliability of wireless communication and enabling the dump truck to drive smoothly and autonomously even in a mine with poor radio wave conditions. That is, in the technology disclosed in Patent Document 1, the connection status is determined based on the communication quality measured in the autonomously driven dump truck in the mine, and when the communication quality satisfies the prescribed quality, driving in a prescribed driving permission interval is permitted, thereby enabling the dump truck to drive smoothly and autonomously.
[0006] However, the technology disclosed in Patent Document 1 is to detect changes in radio wave transmission caused by the movement and deformation of structures, etc., and to detect changes in the quality of wireless communication caused by abnormalities in equipment, etc., and there is a possibility that the target control cannot be executed due to the cause of the change in communication quality.
[0007] Prior art literature
[0008] Patent Literature
[0009] Patent Document 1: Japanese Patent Application Publication No. 2015-210595 Summary of the invention
[0010] The present invention aims to solve the above-mentioned problems and to provide a highly reliable wireless communication system, a wireless communication method, and a control station constituting the wireless communication system that can detect changes in communication quality before the communication quality fails to satisfy a specified quality.
[0011] The wireless communication system of the present invention is 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, wherein the plurality of mobile vehicles or a fixed wireless base station connected to the plurality of mobile vehicles via wireless communication periodically measures position information and wireless communication quality information indicating the quality of the wireless communication, and reports the measurement results to the control station. The control station aggregates the measurement results belonging to a first time range from the measurement results reported by the plurality of mobile vehicles based on the position information, and learns the distribution of the wireless communication quality information for each of the aggregated position ranges. Furthermore, the control station obtains the measurement results belonging to a second time range different from the first time range from the measurement results reported by the plurality of mobile vehicles, and uses the distribution of the wireless communication quality information for each of the position ranges that has been learned to derive the proportion of outliers in the measurement results belonging to the second time range. The system has an abnormality detection device that determines abnormality detection based on the proportion of outliers.
[0012] Effects of the Invention
[0013] According to the present invention, it is possible to provide a wireless communication system having high reliability for wireless communication for mobile object control, a wireless communication method, and a control station constituting the wireless communication system. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] Figure 1 It is a schematic diagram of the configuration of a wireless communication system according to an embodiment of the present invention.
[0015] Figure 2 It is a schematic diagram of an abnormality detection device according to an embodiment of the present invention.
[0016] Figure 3 It is a schematic diagram of the hardware configuration of the abnormality detection device according to the embodiment of the present invention.
[0017] Figure 4A This is an example of the information structure held in the wireless base station information holding unit according to the embodiment of the present invention.
[0018] Figure 4BThis is an example of the information structure held in the wireless base station information holding unit according to the embodiment of the present invention.
[0019] Figure 4C This is an example of the information structure held in the wireless base station information holding unit according to the embodiment of the present invention.
[0020] Figure 4D This is an example of the information structure held in the wireless base station information holding unit according to the embodiment of the present invention.
[0021] Figure 4E This is an example of the information structure held in the wireless base station information holding unit according to the embodiment of the present invention.
[0022] Figure 5 This is an example of the flow of the learning process in the embodiment of the present invention.
[0023] Fig. 6A This is an example of the information structure representing the wireless communication quality according to the embodiment of the present invention.
[0024] Figure 6B This is an example of the information structure representing the wireless communication quality according to the embodiment of the present invention.
[0025] Figure 6C This is an example of the information structure representing the wireless communication quality according to the embodiment of the present invention.
[0026] Figure 7 This is an example of the position range of an embodiment of the present invention.
[0027] Figure 8 This is an example of a process flow of the outlier learning process according to the embodiment of the present invention.
[0028] Fig.9A This is a flow of processing execution based on timer driving of the abnormality detection device 131 according to the embodiment of the present invention.
[0029] Fig. 9B This is a flow of processing execution based on timer driving of the abnormality detection device 131 according to the embodiment of the present invention.
[0030] Fig.10 This is a flow of processing execution by the abnormality detection device 131 according to the embodiment of the present invention based on request drive.
[0031] Fig.11 This is an example of analysis processing performed according to the abnormality factor analysis processing of the embodiment of the present invention.
[0032] Fig.12This is a process flow of another example of the analysis process performed by the abnormality cause analysis process according to the embodiment of the present invention.
[0033] Fig.13 This is one of the explanatory diagrams of another example of the analysis process performed by the abnormality cause analysis process according to the embodiment of the present invention.
[0034] Fig.14 This is one of the explanatory diagrams of another example of the analysis process performed by the abnormality cause analysis process according to the embodiment of the present invention.
[0035] Fig.15 This is another example of the analysis process performed by the abnormality factor analysis process according to the embodiment of the present invention. DETAILED DESCRIPTION
[0036] In the following, embodiments of the present invention are described using the drawings. In the following embodiments, a plurality of components are sometimes listed with specific numbers, but the number of components may be different from the examples unless otherwise specified.
[0037] In addition, although the following embodiments sometimes describe processing in a specific order, the order of processing can be changed or processed in parallel, except for the case where there is a dependency on the order such as using the result of a certain processing in other processing. Even when the processing of a later step uses the result of the processing of the previous step, the respective processing can be executed asynchronously, and the latest processing execution result of the previous step at the time of the processing execution of the later step is used in the processing of the later step.
[0038] Figure 1 1 is a schematic diagram of a wireless communication system according to an embodiment of the present invention. The wireless communication system according to this embodiment includes a mobile vehicle 100 , a fixed wireless base station 110 , a fixed network 120 , a control station 130 , and a mobile network 140 .
[0039] The mobile vehicle 100 includes a mobile wireless base station 101 (101-a, 101-b) and a position sensor 102. In addition, the control station 130 includes an abnormality detection device 131. The abnormality detection device 131 can include a display (display unit 131D) that displays the abnormality detection result. The mobile wireless base station 101 and the fixed wireless base station 110 are connected by wireless communication via the mobile network 140, and the fixed wireless base station 110 and the control station 130 are connected by wired communication or wireless communication via the fixed network 120. In addition, Figure 1 Although three fixed wireless base stations 110 ( 110 -A, 110 -B, 110 -C) and two mobile vehicles 100 are shown in the figure, the number is of course not limited to this.
[0040] One or both of the mobile wireless base station 101 and the fixed wireless base station 110 measure the wireless communication quality of the mobile network 140, and periodically notify the abnormality detection device 131 in the control station 130 of the wireless communication quality information as the measurement result through one or both of the fixed network 120 and the mobile network 140. The wireless communication quality information is information related to the quality of wireless communication between the mobile wireless base station 101 and the fixed wireless base station 110, and includes, as an example, received power, SNR (Signal-to-noise Ratio), and information on the time when the wireless communication quality is measured. In addition, the wireless communication quality information obtained by the mobile wireless base station 101 may include the ID of the mobile wireless base station 101 that performs the measurement.
[0041] In addition, hereinafter, when necessary to distinguish, the wireless communication quality, received power, and SNR measured by the fixed wireless base station 110 are referred to as "uplink wireless communication quality", "uplink received power", and "uplink SNR", respectively. In addition, the wireless communication quality, received power, and SNR measured by the mobile wireless base station 101 are referred to as "downlink wireless communication quality", "downlink received power", and "downlink SNR", respectively.
[0042] The fixed wireless base station 110 measures the quality of wireless communication between itself and each of the mobile wireless base stations 101 of the communication object, that is, the wireless communication quality. The wireless communication quality information is not limited to specific information, but includes, for example, the ID of the mobile wireless base station 101 of the communication object. The wireless communication quality information may also include the position information of the mobile vehicle 100 measured by the position sensor 102, such as GNSS (Global Navigation Satellite System).
[0043] The mobile wireless base station 101 or the fixed wireless base station 110 adds time information to the measured position information and notifies the abnormality detection device 131 in the control station 130 via the mobile network 140 and / or the fixed network 120. The abnormality detection device 131 performs abnormality detection processing of the wireless communication system based on the notified wireless communication quality information and position information.
[0044] In addition, although the position information of the mobile vehicle 100 is measured using the position sensor 102 in the above example, it is also possible to replace or add to it, for example, use the arrival time difference of radio waves and the arrival direction of radio waves to measure on the side of the fixed wireless base station 110, and based on this, measure the positions of the mobile wireless base station 101 and the mobile vehicle 100. In this case, the time information is added to the position information measured by the fixed wireless base station 110, and the added information is notified to the abnormality detection device 131 in the control station 130 through the fixed network 120.
[0045] Reference Figure 2 , the structure of the abnormality detection device 131 is described in more detail. The abnormality detection device 131 includes, as an example, an information interface processing unit 201, a learning processing unit 202, an outlier detection processing unit 203, an abnormality factor analysis processing unit 204, and a detection result interface processing unit 205. In addition, the abnormality detection device 131 includes a wireless base station information storage unit 211, a learning result storage unit 212, a detection result storage unit 213, and an analysis result storage unit 214 as a storage unit for storing information.
[0046] Figure 3 1 is a schematic diagram of a hardware configuration for realizing the abnormality detection device 131. The abnormality detection device 131 of this embodiment includes, as a hardware configuration, a CPU / DSP 301, a storage unit 302, a logic circuit 303, a LAN I / F 304, and a bus 305 connecting these components.
[0047] Various calculations, judgments, and input / output in the information interface processing unit 201, the learning processing unit 202, the outlier detection processing unit 203, the abnormality factor analysis processing unit 204, and the detection result interface processing unit 205 are performed, for example, according to a computer program stored in the storage unit 302, using resource files of the CPU / DSP 301, the storage unit 302, and the logic circuit 303. In addition, it is preferred that each process in the abnormality detection device 131 operates independently, or operates independently as a flow or thread that is different for some processes.
[0048] The wireless base station information storage unit 211, the learning result storage unit 212, the detection result storage unit 213, and the analysis result storage unit 214 store their respective information in the storage unit 302. The storage unit 302 may include, for example, a volatile memory such as a RAM (Random Access Memory), a non-volatile memory such as an SSD (Solid State Drive), a magnetic storage device such as an HDD (Hard Disk Drive), and the like.
[0049] The information interface processing unit 201 and the detection result interface processing unit 205, which are the interface processing units of the abnormality detection device 131, exchange information with the outside of the abnormality detection device 131 via the LAN I / F 304. The information interface processing unit 201 receives the position information of the mobile vehicle 100 obtained by the measurement in the position sensor 102 through the fixed network 120, and the wireless communication quality information of the mobile network 140 obtained by the measurement in one or both of the mobile wireless base station 101 and the fixed wireless base station 110. In addition, when the wireless communication quality information does not include the time information, the information interface processing unit 201 adds the time information to the received information and stores the data in the wireless base station information storage unit 211.
[0050] The wireless base station information storage unit 211 associates and stores the wireless communication quality information with the location information based on the time information. Here, for example, when the acquisition frequency of the location information is lower than the acquisition frequency of the wireless communication quality information, the interpolated location information can be associated with the wireless communication quality information.
[0051] Figure 4A to Figure 4E An example of the data structure of the information stored in the wireless base station information storage unit 211 is shown. Figure 4A to Figure 4E In the example, the case where the values of two indicators of reception power and SNR are used as the wireless communication quality is given, but other reception quality indicators may also be used.
[0052] Figure 4A This is an example of the data structure of information in the case where, in the mobile network 140, a wireless communication method such as SFN (Single Frequency Network) is adopted in which signals of the same frequency channel that do not need to be distinguished on the mobile wireless base station 101 side are transmitted from a plurality of different fixed wireless base stations 110, and the mobile wireless base station 101 measures the wireless communication quality. In this case, Figure 4A As shown, in the wireless base station information storage unit, a combination of time, position coordinates, wireless mobile base station ID, downlink received power, and downlink SNR is recorded using time and wireless mobile base station ID as keys.
[0053] Figure 4B This is an example of a case where a wireless communication method such as wireless LAN (Local Area Network) and cellular communication is adopted in the mobile network 140, in which signals of different channels that need to be distinguished on the mobile wireless base station 101 side are transmitted from a plurality of different fixed wireless base stations 110, and the mobile wireless base station 101 side measures the wireless communication quality. In this case, Figure 4BAs shown in FIG. 1 , the wireless base station information storage unit 211 records the time, position coordinates, wireless mobile base station ID, and the combination of downlink received power and downlink SNR of each fixed wireless base station 110 ((A) to (C)) using the time and wireless mobile base station ID as key values. In addition, in the mobile wireless base station 101, when it is impossible to receive a signal from a specific fixed wireless base station 110, the wireless communication quality related to the fixed wireless base station 110 is handled as a defect value.
[0054] Figure 4C This is an example of a case where the wireless communication quality is measured by the fixed wireless base station 110. Figure 4C As shown, the wireless base station information storage unit 211 records the time, position coordinates, wireless mobile base station ID, and the combination of uplink received power and uplink SNR of each fixed wireless base station 110 measured, using the time and wireless mobile base station ID as key values. In addition, in a case where reception of a signal from the mobile wireless base station 101 is impossible in a specific fixed wireless base station 110, the wireless communication quality related to the fixed wireless base station 110 is handled as a defect value.
[0055] Figure 4D This is an example of the data structure of information in the case where, in the mobile network 140, a wireless communication method such as SFN (Single Frequency Network) is adopted in which signals of the same frequency channel are transmitted from a plurality of different fixed wireless base stations 110 without being distinguished on the mobile wireless base station 101 side, and the mobile wireless base station 101 and the fixed wireless base station 110 both measure the wireless communication quality. In this case, Figure 4D As shown, in the wireless base station information storage unit 211, the time, position coordinates, wireless mobile base station ID, downlink received power, downlink SNR, uplink received power of each fixed wireless base station 110, and uplink SNR are recorded with the time and wireless mobile base station ID as key values. Figure 4C The same situation.
[0056] Figure 4E This is an example of the data structure of information in the case where, in the mobile network 140, a wireless communication method is adopted in which signals of different channels that need to be distinguished on the mobile wireless base station 101 side are transmitted from a plurality of different fixed wireless base stations 110, such as wireless LAN (Local Area Network) and cellular communication, and the mobile wireless base station 101 and the fixed wireless base station 110 both measure the wireless communication quality. In this case, Figure 4EAs shown in FIG. 1 , in the wireless base station information holding unit 211, the time, position coordinates, wireless mobile base station ID, and the combination of downlink reception power and downlink SNR of each fixed wireless base station 110, and uplink reception power and uplink SNR of each fixed wireless base station 110 are recorded with the time and wireless mobile base station ID as key values. In addition, the processing of the missing value when the signal reception is impossible is the same as Figure 4B as well as Figure 4C The same situation.
[0057] The learning processing unit 202 retrieves information held in the wireless base station information holding unit 211 in each fixed time range and fixed position range, learns the distribution representing the respective wireless communication qualities, and holds the learned results in the learning result holding unit 212 .
[0058] Reference Figure 5 The flowchart of FIG. 5 illustrates an example of the flow of the learning process of the learning processing unit 202 in this embodiment. The learning processing unit 202 first sets the time range to be the learning object in step S510. Here, the time range of the learning object refers to, for example, a range of 24 hours on a specific day.
[0059] Then, in steps S511 to S517, loop processing (aggregation) is performed for each position range. In step S512, data that matches the time range set in step S510 and the position range of this loop processing is extracted from the wireless base station information holding unit 211. In the subsequent step S513, the amount of the extracted data is confirmed. If the amount of data is less than the specified value, for example, less than 100 points (no), the loop processing corresponding to the position range being processed is terminated and returned to step S511, and processing is performed for the next position range. If the amount of data is greater than the specified value, the process proceeds to step S514.
[0060] Then, in step S514, a representative wireless communication quality value is generated. Here, if there are multiple downlink wireless communication quality values for a single key value consisting of time and wireless mobile base station ID, Figure 4B and 4E In such a case, the value representing the wireless communication quality means that a value of the downlink wireless communication quality is selected. In addition, if there are multiple uplink wireless communication quality values for a single key value consisting of time and wireless mobile base station ID, Figure 4C , Figure 4D , Figure 4E In that case, it means that one uplink wireless communication quality value is selected. As a selection method representing the wireless communication quality, for example, a wireless communication quality value, a received power, and an SNR that are not defective values and have the largest value among a plurality of wireless communication qualities can be selected.
[0061] The wireless communication quality information stored in the wireless base station information storage unit 211 is: Figure 4A or Figure 4B In the case of the form, such as Fig. 6A As shown in FIG. 1 , the array consisting of two elements, the downlink representative received power and the downlink representative SNR, becomes the representative wireless communication quality value. In addition, the wireless communication quality information stored in the wireless base station information storage unit 211 is Figure 4C In the case of the form, such as Figure 6B As shown in FIG. 1 , the array consisting of two elements, the uplink representative received power and the uplink representative SNR, becomes the representative wireless communication quality value. The wireless communication quality information stored in the wireless base station information storage unit 211 is: Figure 4D or Figure 4E In the case of the form, such as Figure 6C As shown, the array consisting of four elements of downlink representative received power, downlink representative SNR, uplink representative received power, and uplink representative SNR becomes the representative wireless communication quality value.
[0062] In the subsequent step S515, the characteristics of the distribution representing the wireless communication quality value are learned. As a distribution learning method, for example, the following method can be adopted: assuming a Gaussian distribution with the same number of dimensions as the number of elements representing the wireless communication quality value, the mean value and standard deviation of each dimension of the Gaussian distribution are calculated so that, for example, 95% of the object data is within 3σ. As another distribution learning method, for example, a method of constructing a One Class SVM classifier in such a way that 95% of the data is within the normal value range can be adopted.
[0063] Then, in step S516, the learning result is stored as a classifier in the learning result storage unit 212. The above processing is repeated, and if there is still a position range that has not been processed in step S517, the process returns to step S511, and if the processing for all position ranges is completed, the learning step S202 is terminated.
[0064] Figure 7 is an example of a position range in this embodiment. In this embodiment, the entire site range 710 is defined so as to include the driving track 700 of the mobile vehicle 100, and the entire site range 710 is divided into a plurality of small divided sites 720, for example, at equal intervals. The small divided sites 720 are set as processing units for the learning process in the learning processing unit 202.
[0065] The outlier detection processing unit 203 extracts the wireless communication quality information and location information maintained in the wireless base station information maintaining unit 211 within each fixed time range and fixed location range, and uses the classifier maintained in the learning result maintaining unit 212 to classify the extracted information, and maintains the classification results in the detection result maintaining unit 213.
[0066] Reference Figure 8 , which illustrates an example of the process flow of the outlier detection processing unit 203 in the present embodiment. The outlier detection processing unit 203 first sets the time range set as the object of the outlier detection processing and the time range of the classifier used for the outlier detection processing in step S810. Here, the time range set as the object of the outlier detection processing refers to, for example, a specific time range (for example, one hour) on a specific day. In addition, the time range of the classifier used for the outlier detection processing refers to, for example, the time range of the previous day of the time range set as the object of the outlier detection processing (for example, the twenty-four hours of the previous day).
[0067] Then, the loop process is performed for each position range from step S811 to step S818 . In step S812 , the classifier of the target position range and the classifier time used for the outlier detection process is extracted from the learning result storage unit 212 .
[0068] In the subsequent step S813, it is confirmed whether the classifier is extracted (whether it exists). In step S812, if the matching classifier does not exist in the learning result storage unit 212, the extraction fails (no), and the loop processing for the position range in the process is terminated, and the process returns to step S811 to perform processing on the next position range. If the classifier is extracted, the process transfers to step S814.
[0069] In step S814, information is extracted from the wireless base station information storage unit 211, which information matches the time range set as the object of the outlier detection process in step S810 and the position range of this loop processing. In step S815, the data volume of the extracted information is confirmed. If the data volume is less than the specified value, for example, less than 50 points, the loop processing corresponding to the position range in the process is terminated and returned to step S811, and the processing is performed for the next position range. If the data volume is more than the specified value, the process moves to step S816.
[0070] In step S816, the data extracted in step S814 are classified using the classifier extracted in step S812. In subsequent step S817, the classification result and statistical information are recorded in the detection result storage unit 213. The classification result and statistical information include the following as an example.
[0071] ·The number of data to be classified
[0072] The number of data in the normal value range of the classification results
[0073] The number of outliers in the classification results
[0074] Average wireless communication quality value of all data
[0075] Average wireless communication quality value of data within the normal value range
[0076] · Average wireless communication quality value of data that is an outlier
[0077] Repeat the above steps. If there is a position range in which the above steps are not performed in step S818, return to step S811 and repeat the same process. On the other hand, if the process for all position ranges is completed, the outlier detection process is completed. The abnormality cause analysis processing unit 204 analyzes the abnormality when an abnormality occurs in wireless communication based on the information stored in the detection result storage unit 213, and records the result in the analysis result storage unit 214.
[0078] The detection result interface processing unit 205 outputs the analysis result recorded in the analysis result storage unit 214 to, for example, an external terminal for monitoring, via the fixed network 120. Furthermore, the detection result interface processing unit 205 outputs the analysis result recorded in the analysis result storage unit 214 to, for example, an external terminal for monitoring, via the fixed network 120, for example, based on an analysis request instruction requested from the external terminal for monitoring via the fixed network 120, and after performing various processes in the learning processing unit 202, the outlier detection processing unit 203, and the abnormality factor analysis processing unit 204 as needed.
[0079] Reference Fig.9A , Fig. 9B The flowchart of FIG. 1 illustrates the sequence of the processing based on the timing drive of the abnormality detection device 131. As the processing of the timing drive, for example, Fig.9A As in step S910, once a day, the processing is started according to the timing of maintaining the wireless communication quality of the previous day in the wireless base station information maintaining unit 211. In step S911, the learning object time range is set to the time of the previous day and the processing of the learning processing unit 202 is started, and the result is recorded in the learning result maintaining unit 212.
[0080] As a timing driven process, in addition, it is possible to Fig. 9BAs in step S920, once an hour, the processing is started according to the timing of maintaining one hour of wireless communication quality information in the wireless base station information maintaining unit 211. And, in step S921, using the learning result of the previous day produced in step S911, and taking the wireless communication quality information of the immediately previous hour as the classification object, the outlier detection processing unit 203 performs outlier detection processing, and records the result in the detection result maintaining unit 213. Then, in step S922, the abnormality factor analysis processing unit 204 performs factor analysis processing, and records the result in the analysis result maintaining unit 214. And, in step S923, the analysis result is output to the outside through the detection result interface processing unit 205.
[0081] Reference Fig.10 The flowchart of FIG. 1 illustrates the sequence of detection processing of the abnormality detection device 131 when there is an analysis request (request drive). For example, when the detection result interface processing unit 205 receives the analysis request instruction, Fig.10 The processing starts.
[0082] If you start according to the analysis requirements Fig.10 If the analysis result corresponding to the analysis request instruction is present in the analysis result storage unit 214, first, in step S1010, it is confirmed whether the analysis result corresponding to the analysis request instruction exists. If the analysis result exists, the process proceeds to step S1016, and if not, the process proceeds to step S1011.
[0083] In step S1011, it is confirmed whether the detection result corresponding to the analysis request instruction exists in the detection result storage unit 213. If the detection result exists, the process proceeds to step S1015, and if not, the process proceeds to step S1012. In step S1012, it is confirmed whether the learning result corresponding to the analysis request instruction exists in the learning result storage unit 212. If the learning result exists, the process proceeds to step S1014, and if not, the process proceeds to step S1013.
[0084] In step S1013, the learning processing unit 202 performs the learning processing within the time range of the learning object corresponding to the analysis requirement instruction received by the detection result interface processing unit 205 and records the result in the learning result storage unit 212. In step S1014, the outlier detection processing unit 203 performs the outlier detection processing within the time range of the classifier and the classification object corresponding to the analysis requirement instruction received by the detection result interface processing unit 205, and records the result in the detection result storage unit 213. In the subsequent step S1015, the abnormal cause analysis processing unit 204 performs the abnormal cause analysis processing corresponding to the analysis requirement instruction received by the detection result interface processing unit 205, and records the result in the analysis result storage unit 214. In step S1016, based on the information recorded in the analysis result storage unit 214, the analysis result corresponding to the analysis requirement instruction received by the detection result interface processing unit 205 is output to the outside.
[0085] Reference Fig.11 , an example of analysis processing in the abnormality cause analysis processing unit 204 is described. Fig.11 In the analysis processing of the example, the driving trajectory 700 of the mobile vehicle 100 and the overall range 710 of the site are displayed on the display 131D of the abnormality detection device 131, and the learning object time range of the classifier used in the classification processing and the object time range of the data that becomes the classification object are displayed as time range information 730.
[0086] In addition, for each position range, the outlier ratio obtained by dividing the number of data that are outliers in the classification result in the outlier detection processing unit 203 by the total number of data is calculated, and the position range where the outlier ratio is greater than a threshold value (for example, 0.5) is highlighted, for example, as shown by reference numeral 740. The area of reference numeral 740 is recognized as a site where an abnormality has occurred. In addition, when the number of sites where an abnormality has occurred is greater than a certain level, it can be recognized that an abnormality has occurred in the entire wireless communication system.
[0087] Reference Fig.12 The flowchart of FIG. 1 illustrates an example of another process of the analysis process performed by the abnormality factor analysis processing unit 204. Fig.12 In the analysis process, first, in step S1210, the learning time range of the classifier and the time range of the wireless communication quality information to be classified are set. Then, in step S1211, the statistical value corresponding to the time range set in step S1210 is read from the detection result storage unit 213.
[0088] In the subsequent step S1212, Fig.11Similarly, the analysis process in step S1213 calculates the existence ratio of outliers for each position range, for example, classifies the position range with an existence ratio of outliers greater than 0.5 as an outlier position range, and classifies the position range with an existence ratio of outliers less than 0.5 as a normal position range. Fig.13 As an example, the distances to all fixed wireless base stations (ground wireless base stations) 110 are calculated. Here, the position information of the ground wireless base stations 110 used for calculation may be position information measured using GNSS or the like, or may be a value stored in advance as a constant.
[0089] Then, in step S1214, the classification results of the normal position range and the outlier position range based on the existence ratio of the outliers obtained in step S1212 are used as the teacher data, and the distance from each ground wireless base station is used as a parameter to perform the binary classifier learning process. And, using the learned binary classifier, as shown in FIG. Fig.14 For example, the entire site range 710 is classified into a normal position range and an outlier position range by a binary classifier. The binary classifier used here may be a simple classifier such as a decision tree or a classifier such as Adaboost based on a combination of decision trees.
[0090] Then, in step S1215, the installation position of each ground wireless base station 110 is classified as being in the outlier position range or the normal position range. As a result, when the ground wireless base station 110 is classified as being in the outlier position range, it can be recognized that some kind of communication failure (communication disconnection, etc.) has occurred in the ground wireless base station.
[0091] In the subsequent step S1216, the importance of the feature quantity during binary classifier learning is evaluated. For the ground wireless base station 110 classified as being in the normal position range in step S1215, the importance is regarded as 0. For the ground wireless base station 110 classified as being in the outlier position range in step S1215, it can be recognized that the higher the importance of the feature quantity, the higher the possibility of an abnormality occurring.
[0092] Fig.15 This is another example of the analysis process performed by the abnormality factor analysis processing unit 204. The horizontal axis of the graph represents the change in time (time), and the vertical axis represents the change in time (time) per hour. Fig.12 By confirming the temporal variation of the value of the feature quantity importance, it is possible to estimate the time range in which the abnormality occurred for each terrestrial wireless base station 110.
[0093] In addition, the present invention is not limited to the above-mentioned embodiments, and includes various modified examples and equivalent structures within the gist of the attached technical solutions. For example, the above-mentioned embodiments are described in detail in order to easily understand the present invention, but the present invention is not limited to having all the structures described. In addition, a part of the structure of a certain embodiment can be replaced with the structure of other embodiments. In addition, the structure of other embodiments can be added to the structure of a certain embodiment. In addition, other structures can be added, deleted, or replaced for a part of the structure of each embodiment.
[0094] In addition, some or all of these can be implemented by hardware such as integrated circuits. In addition, the above-mentioned various structures, functions, processing units, processing methods, etc. can also be implemented by software by interpreting and executing computer programs that implement various functions through a processor. In addition, when there are multiple functions with the same structure, the hardware or software that implements each function can be installed independently, or a single installed hardware or software can be used multiple times in time to perform multiple processes. In addition, even if it is a single function in structure, multiple hardware or software with the same function can be used for distributed processing.
[0095] Information such as programs, tables, and files that realize various functions can be stored in storage devices such as memories, hard disks, and SSDs (Solid State Drives), or recording media such as IC cards, SD cards, and DVDs.
[0096] In addition, the control lines and information lines show the parts that are considered necessary for the description, and do not show all the control lines and information lines required for implementation. In fact, it can be considered that almost all components are connected to each other.
[0097] Description of Reference Numerals
[0098] 100…mobile vehicle, 101…mobile wireless base station, 102…position sensor, 110…fixed wireless base station, 120…fixed network, 130…control station, 131…abnormality detection device, 140…mobile network, 201…information interface processing unit, 202…learning processing unit, 203…outlier detection processing unit, 204…abnormality factor analysis processing unit, 205…detection result interface processing unit, 211…wireless base station information holding unit, 212…learning result holding unit, 213…detection result holding unit, 214…analysis result holding unit, 301…CPU / DSP, 302…storage unit (memory), 303…logic circuit, 304…LANI / F, 305…bus.
Claims
1. A wireless communication system, comprising a control station and a plurality of mobile vehicles connected to the control station via wireless communication, characterized in that: The plurality of mobile vehicles or the fixed wireless base station connected to the plurality of mobile vehicles through wireless communication periodically measures position information and wireless communication quality information indicating the quality of the wireless communication, and reports the measurement result to the control station, The control station aggregates the measurement results belonging to the first time range from among the measurement results reported by the plurality of the mobile vehicles based on the location information, and learns the distribution of the wireless communication quality information for each aggregated location range. Furthermore, the control station obtains measurement results belonging to a second time range different from the first time range from among the measurement results reported by the plurality of the mobile vehicles, and uses the distribution of the wireless communication quality information of each of the position ranges that has been learned to derive the existence ratio of outliers in the measurement results belonging to the second time range, And the wireless communication system has an abnormality detection device that determines abnormality detection based on the existence ratio of the outliers.
2. The 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 position range in which the existence ratio of the outliers is equal to or greater than a threshold value.
3. The wireless communication system according to claim 1, wherein: A display unit is provided for displaying a display corresponding to the existence ratio of the outliers in each of the position ranges.
4. The wireless communication system according to claim 1, wherein: There is also an anomaly detection device, which uses the following data as teacher data to perform learning processing of a binary classifier, wherein the data classifies the position range as an outlier position range when the existence ratio of the outliers in each position range is above a threshold value, and classifies the position range as a normal range when the existence ratio of the outliers is less than the threshold value. When the anomaly detection device uses the binary classifier to classify the position of the moving vehicle, if the position of the moving vehicle is included in the outlier position range, the anomaly detection device determines an abnormality detection for the moving vehicle.
5. A wireless communication method, a wireless communication method between a control station and a plurality of mobile vehicles connected to the control station via wireless communication, characterized in that: The plurality of mobile vehicles or the fixed wireless base station connected to the plurality of mobile vehicles through wireless communication periodically measures position information and wireless communication quality information indicating the quality of the wireless communication, and reports the measurement result to the control station, aggregating the measurement results belonging to the first time range from among the measurement results reported from the plurality of the moving vehicles based on the position information, and learning the distribution of the wireless communication quality information for each of the aggregated positions; obtaining measurement results belonging to a second time range different from the first time range from among the measurement results reported by the plurality of the mobile vehicles, and deriving the existence ratio of outliers in the measurement results belonging to the second time range using the distribution of the wireless communication quality information for each position range after the learning, When the existence ratio of the outliers is equal to or greater than a threshold value, abnormality detection is determined in the position range.
6. The wireless communication method according to claim 5, wherein: If there is a position range in which the outlier existence ratio is equal to or greater than a threshold value, it is determined that an abnormality has occurred in the wireless communication.
7. The wireless communication method according to claim 5, wherein: A display is performed according to the existence ratio of the outliers in each of the position ranges.
8. The wireless communication method according to claim 5, wherein: The following data is used as teacher data to perform learning processing of a binary classifier, and the data classifies the position range as an outlier position range when the existence ratio of the outliers in each position range is above a threshold value, and classifies the position range as a normal range when the existence ratio of the outliers is less than the threshold value. When the wireless communication method uses the binary classifier to classify the position of the moving vehicle, when the position of the moving vehicle is included in the outlier position range, it is determined that an abnormality is detected for the moving vehicle.
9. A control station connected to a plurality of mobile vehicles via wireless communication to form a control system, wherein the control station is characterized in that: The control station has an abnormality detection device for detecting abnormality in the wireless communication. The abnormality detection device is configured as follows: periodically receiving position information and measurement results of wireless communication quality information indicating the quality of the wireless communication from a plurality of the mobile vehicles, aggregating the measurement results belonging to the first time range from among the measurement results reported from the plurality of the moving vehicles based on the position information, and learning the distribution of the wireless communication quality information for each of the aggregated positions; obtaining measurement results belonging to a second time range different from the first time range from among the measurement results reported by the plurality of the mobile vehicles, and deriving the existence ratio of outliers in the measurement results belonging to the second time range using the distribution of the wireless communication quality information for each position range after the learning, When the existence ratio of the outliers is equal to or greater than a threshold value, abnormality detection is determined in the position range.
10. The control station according to claim 9, characterized in that The abnormality detection device determines that an abnormality has occurred in the wireless communication system when a position range exists in which the existence ratio of the outliers is equal to or greater than a threshold value.
11. The control station according to claim 9, characterized in that A display is performed according to the existence ratio of the outliers in each of the position ranges.
12. The control station according to claim 9, characterized in that The anomaly detection device uses the following data as teacher data to perform learning processing of the binary classifier. The data classifies the position range as an outlier position range when the existence ratio of the outliers in each position range is above a threshold value, and classifies the position range as a normal range when the existence ratio of the outliers is less than the threshold value. When the anomaly detection device uses the binary classifier to classify the position of the moving vehicle, it determines the abnormality detection of the moving vehicle when the position of the moving vehicle is included in the outlier position range.
