A base station fault detection method, device, equipment and storage medium

Abstract

The present application discloses a base station fault detection method, device, equipment and storage medium. The base station fault detection method includes: obtaining the observation data of the target base station in the target time period, the integrity data of the target satellite system observed by the target base station, and the ionospheric activity levels respectively observed by multiple satellites in the target satellite system; determining the abnormal moments in the target time period based on the observation data of the target base station, the integrity data of the target satellite system, and the multiple ionospheric activity levels; inputting the abnormal parameters corresponding to the abnormal moments into a preset fault detection model to obtain the target fault root cause of the target base station; the preset fault detection model is trained based on historical abnormal parameters and the fault root causes corresponding to the historical abnormal parameters. By using the base station fault detection method provided by the present application, the fault detection efficiency of the base station can be effectively improved, and the labor cost can also be reduced.

Description

Technical Field

[0001] This application relates to the field of satellite navigation technology, and in particular, to a method, device, equipment, and storage medium for detecting base station faults. Background Art

[0002] Satellite navigation, as a technology that uses navigation satellites to perform navigation and positioning for ground, ocean, air, and space users, has been increasingly widely used in work and life.

[0003] As an important device in satellite navigation technology, once a base station fails, it may affect the satellite navigation result, thereby affecting the quality of satellite navigation services and user experience. Therefore, it is necessary to detect base station faults. At present, technicians usually manually detect the root cause of base station faults to maintain the base station according to the root cause of the faults. In this way, the efficiency of base station fault detection is relatively low. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide a method, device, equipment, and storage medium for detecting base station faults, which can solve the technical problem that manual detection of the root cause of base station faults in the prior art leads to low efficiency of base station fault detection.

[0005] The technical solution of this application is as follows:

[0006] In a first aspect, a method for detecting base station faults is provided, including:

[0007] Obtain the observation data of the target base station during the target time period, the integrity data of the target satellite system observed by the target base station, and the ionospheric activity levels observed by multiple satellites in the target satellite system;

[0008] Based on the observation data of the target base station, the integrity data of the target satellite system, and multiple ionospheric activity levels, determine the abnormal moments during the target time period;

[0009] Input the abnormal parameters corresponding to the abnormal moments into a preset fault detection model to obtain the target root cause of the target base station's faults; the preset fault detection model is trained based on historical abnormal parameters and the fault root causes corresponding to the historical abnormal parameters.

[0010] In some embodiments, based on the observation data of the target base station, the integrity data of the target satellite system, and multiple ionospheric activity levels, determining the abnormal moments during the target time period includes:

[0011] Perform data preprocessing on the observation data of the target base station, the integrity data of the target satellite system, and multiple ionospheric activity levels to obtain time series data of the satellite system at different frequencies;

[0012] Based on time series data, determine the abnormal moments within the target time period.

[0013] In some embodiments, determining the abnormal moments within the target time period based on time series data includes:

[0014] Detect the missing moments in the time series of the time series data, and determine the missing moments as missing abnormal moments;

[0015] Calculate the satellite search rate of the target satellite system at multiple moments within the target time period based on the time series data, and determine the moments corresponding to the target search rates less than the preset search rate threshold as search rate abnormal moments;

[0016] Calculate the pseudorange availability rate of the target satellite system at each frequency point at multiple moments within the target time period based on the time series data, and determine the moments corresponding to the target pseudorange availability rates less than the preset availability rate threshold as pseudorange abnormal moments;

[0017] Determine the carrier-to-noise ratio fluctuations of the target satellite system at each frequency point at multiple moments within the target time period based on the time series data, and determine the moments corresponding to the target carrier-to-noise ratio fluctuations greater than the preset fluctuation threshold as carrier-to-noise ratio abnormal moments;

[0018] Obtain the respective observation data of multiple satellites of the target satellite system by adjacent base stations of the target base station within the target time period, and calculate the ionospheric activity levels observed by the multiple satellites of the target satellite system at different moments based on the observation data of the target base station within the target time period and the observation data of the adjacent base stations;

[0019] When the number of target ionospheric activity levels greater than the preset activity threshold at the same moment is greater than the preset number and the satellites corresponding to the multiple target ionospheric activity levels are aggregated and distributed, determine the moments corresponding to the target ionospheric activity levels as ionospheric abnormal moments.

[0020] In some embodiments, before inputting the abnormal parameters corresponding to the abnormal moments into a preset fault detection model to obtain the target fault root cause of the target base station, it further includes:

[0021] Perform missing value processing on the missing abnormal moments to obtain the missing values corresponding to each missing abnormal moment;

[0022] Extract the abnormal parameters corresponding to each abnormal moment, and the abnormal parameters include one or more of the missing values, target search rates, target pseudorange availability rates, target carrier-to-noise ratio fluctuations, and target ionospheric activity levels.

[0023] In some embodiments, the observed data of the target base station includes the number of satellites in the target satellite system observed by the target base station, the frequency points of multiple satellites in the target satellite system, the carrier-to-noise ratio and pseudorange of each satellite at each frequency point; the integrity data includes the theoretical number of satellites in the satellite system.

[0024] Calculating the satellite search rate of the target satellite system at multiple moments within the target time period based on the time series data, including:

[0025] Calculating the satellite search rate of the target satellite system based on the theoretical number of satellites and the number of satellites in the target satellite system observed by the target base station.

[0026] Calculating the pseudorange availability rate of the target satellite system at each frequency point at multiple moments within the target time period based on the time series data, including:

[0027] Determining the number of available pseudoranges in the pseudoranges of each satellite at each frequency point.

[0028] Calculating the pseudorange availability rate of the target satellite system at each frequency point based on the number of available pseudoranges and the number of satellites in the target satellite system observed by the target base station.

[0029] Determining the carrier-to-noise ratio fluctuation of the target satellite system at each frequency point at multiple moments within the target time period based on the time series data, including:

[0030] Taking the first-order difference of the carrier-to-noise ratio of the target satellite system at each frequency point to obtain the carrier-to-noise ratio fluctuation of the target satellite system at each frequency point.

[0031] In some embodiments, inputting the abnormal parameters corresponding to the abnormal moments into a preset fault detection model to obtain the target fault root cause of the target base station, including:

[0032] Inputting the abnormal parameters corresponding to the abnormal moments into a preset fault detection model to obtain the occurrence probabilities of multiple preset fault root causes at each abnormal moment.

[0033] Determining the target fault root cause of the target base station based on the occurrence probabilities of multiple preset fault root causes at each abnormal moment.

[0034] In some embodiments, determining the target fault root cause of the target base station based on the occurrence probabilities of multiple preset fault root causes at each abnormal moment, including:

[0035] Calculating the target occurrence probabilities of multiple preset fault root causes at each in the target time period according to the occurrence probabilities of multiple preset fault root causes at each abnormal moment.

[0036] Determining the preset fault root cause corresponding to the maximum value of the target occurrence probability as the target fault root cause of the target base station.

[0037] In some embodiments, the preset fault detection model is a four-layer fully connected neural network.

[0038] In a second aspect, a base station fault detection device is provided, including:

[0039] A data acquisition module, configured to acquire the observation data of the target base station during the target time period, the integrity data of the target satellite system observed by the target base station, and the ionospheric activity levels respectively observed by multiple satellites in the target satellite system;

[0040] A determination module, configured to determine the abnormal moments during the target time period based on the observation data of the target base station, the integrity data of the target satellite system, and the multiple ionospheric activity levels;

[0041] A fault detection module, configured to input the abnormal parameters corresponding to the abnormal moments into the preset fault detection model to obtain the target fault root cause of the target base station; the preset fault detection model is trained based on historical abnormal parameters and the fault root causes corresponding to the historical abnormal parameters.

[0042] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of the base station fault detection method described in the first aspect are implemented.

[0043] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the base station fault detection method described in the first aspect are implemented.

[0044] The technical solution provided by the embodiment of the present application at least brings the following beneficial effects:

[0045] The base station fault detection method provided by the embodiment of the present application obtains the observation data of the target base station during the target time period, the integrity data of the target satellite system observed by the target base station, and the ionospheric activity levels respectively observed by multiple satellites in the target satellite system, and determines the abnormal moments during the target time period based on the observation data of the target base station, the integrity data of the target satellite system, and the multiple ionospheric activity levels; then inputs the abnormal parameters corresponding to the abnormal moments into the preset fault detection model to obtain the target fault root cause of the target base station; wherein, the preset fault detection model is trained based on historical abnormal parameters and the fault root causes corresponding to the historical abnormal parameters. In this way, the preset fault detection model can be used to automatically detect the fault root cause of the base station based on the observation data of the target base station, the integrity data of the target satellite system, and the multiple ionospheric activity levels. Compared with the manual detection of the fault root cause of the base station in the prior art, it can not only effectively improve the fault detection efficiency of the base station, but also reduce the labor cost.

[0046] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and do not limit this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application, and do not constitute an improper limitation of this application.

[0048] Figure 1 is a schematic flowchart of a base station fault detection method provided by an embodiment of this application;

[0049] Figure 2 is a schematic structural diagram of a base station fault detection device provided by an embodiment of this application;

[0050] Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] In order to enable those of ordinary skill in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only intended to explain this application, rather than to limit this application. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is only intended to provide a better understanding of this application by showing examples of this application.

[0052] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned accompanying drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. On the contrary, they are merely examples consistent with some aspects of this application as detailed in the appended claims.

[0053] Based on the background technology, it can be seen that in the prior art, technicians manually detect the root cause of base station faults, which will result in low efficiency of base station fault detection.

[0054] Specifically, technicians who detect the root cause of base station failures need to have a high level of navigation knowledge and Internet Technology (IT) skills. Moreover, when technicians conduct manual inspections, they need to quickly screen various possible root causes of base station failures manually to determine the actual root cause of the base station failure. This undoubtedly depends on the professional level of the technicians, usually taking up a lot of time and energy of the technicians, resulting in low efficiency of base station failure detection and increasing labor costs.

[0055] Based on the above findings, embodiments of the present application provide a base station failure detection method, device, equipment, and storage medium. By obtaining the observation data of the target base station during the target period, the integrity data of the target satellite system observed by the target base station, and the ionospheric activity levels observed by multiple satellites in the target satellite system, the abnormal moments during the target period are determined based on the observation data of the target base station, the integrity data of the target satellite system, and the multiple ionospheric activity levels. Then, the abnormal parameters corresponding to the abnormal moments are input into a preset failure detection model to obtain the target root cause of the target base station failure. Among them, the preset failure detection model is trained based on historical abnormal parameters and the root causes of failures corresponding to the historical abnormal parameters. In this way, the preset failure detection model can be used to automatically detect the root cause of base station failures based on the observation data of the target base station, the integrity data of the target satellite system, and the multiple ionospheric activity levels. Compared with the prior art of manually detecting the root cause of base station failures, it can not only effectively improve the efficiency of base station failure detection but also reduce labor costs.

[0056] The following will describe in detail the base station failure detection method, device, equipment, and storage medium provided by the embodiments of the present application with reference to the accompanying drawings.

[0057] Figure 1 The flowchart of a base station failure detection method provided by an embodiment of the present application is shown. This method can be applied to a server or a server cluster, such as Figure 1 shown, and the method includes:

[0058] S110, obtain the observation data of the target base station during the target period, the integrity data of the target satellite system observed by the target base station, and the ionospheric activity levels observed by multiple satellites in the target satellite system.

[0059] Among them, the target base station can be any base station for which failure detection is performed.

[0060] The target period can be a historical period whose time interval from the detection moment is a preset duration. For example, if the detection moment is 10:00 and the preset duration is 5 minutes, then the target period is 09:55 - 10:00.

[0061] The target satellite system can be the satellite system observed by the target base station. The target satellite system can be one or more, and each satellite system can include one or more satellites.

[0062] When performing fault detection on the target base station, it is necessary to first prepare data, that is, obtain the data required for fault analysis. Specifically, the observation data of the target base station can be obtained. The observation data can include the number of observed satellites of the target base station, as well as the elevation angle, frequency point, carrier-to-noise ratio, pseudorange, carrier wave, Doppler, etc. of each observed satellite. Obtain the integrity data of the target satellite system observed by the target base station, such as the pseudorange integrity, carrier integrity, ionospheric activity, etc. of the target satellite system. Among them, integrity can be the ability of the system to give an alarm in a timely manner when a problem occurs in the satellite system. And obtain the ionospheric activity observed by each of the multiple satellites in the target satellite system. Among them, the ionospheric activity can be obtained through an ionospheric monitoring model. The method of obtaining the ionospheric activity through the ionospheric monitoring model is the same as the prior art and will not be elaborated here.

[0063] It can be understood that the base station fault detection method can be executed after receiving an analysis instruction input by the user, or can be automatically executed after detecting a base station fault.

[0064] S120, determine the abnormal moments within the target time period based on the observation data of the target base station, the integrity data of the target satellite system, and the multiple ionospheric activities.

[0065] After the data is prepared, abnormal moment detection can be performed. That is, after obtaining the observation data of the target base station within the target time period, the integrity data of the target satellite system observed by the target base station, and the ionospheric activities observed by each of the multiple satellites in the target satellite system, the abnormal moments within the target time period can be determined according to the aforementioned observation data of the target base station, the integrity data of the target satellite system, and the multiple ionospheric activities. For example, it can be the moment of time missing within the target time period, the moment with a poor satellite search rate, the moment with a low pseudorange availability rate, the moment with a high carrier-to-noise ratio fluctuation, the moment with a high ionospheric activity, etc.

[0066] S130, input the abnormal parameters corresponding to the abnormal moments into a preset fault detection model to obtain the target fault root cause of the target base station.

[0067] Among them, the preset fault detection model can be trained based on historical abnormal parameters and the fault root causes corresponding to the historical abnormal parameters.

[0068] The preset fault detection model can be a four-layer fully connected neural network, which can output the probability of the preset fault root cause that may occur at each abnormal moment based on the corresponding abnormal parameters at each abnormal moment. From the perspective of information processing, a neural network can be understood as an abstraction of the human brain neuron network. It is an operation model, usually composed of a large number of interconnected nodes. Each node represents a specific output function, called an activation function; the connection between each two nodes represents a weighted value for the signal passing through this connection, called a weight. The output of the network varies depending on the connection method, weight value, and activation function of the network. A neural network itself is usually an approximation of a certain function in nature and is also an expression of a logical strategy. In this way, by using a neural network, the relationship between the data of the base station in each dimension and the fault root cause can be analyzed, and the fault root cause can be located through observation data, integrity data, ionospheric activity, etc. That is, by fusing the detection model of the artificial neural network with the data analysis results, the target fault root cause of the target base station can be determined, which can save labor costs and improve the operation and maintenance efficiency.

[0069] After anomaly detection, the preset fault detection model can be used for fault location. That is, after determining the abnormal moments within the target time period, the data corresponding to the abnormal moments can be obtained, that is, the corresponding abnormal parameters at the abnormal moments, such as parameters such as the satellite search rate, pseudorange availability, carrier-to-noise ratio fluctuation, and ionospheric activity corresponding to the abnormal moments. It can be understood that when there are multiple abnormal moments, the abnormal parameters are the corresponding abnormal parameters for each abnormal moment. Then, the abnormal parameters corresponding to the abnormal moments can be input into the preset fault detection model, and the preset fault detection model can analyze and process the abnormal parameters corresponding to the abnormal moments according to the trained logic to obtain the fault root cause of the target base station, that is, the target fault root cause.

[0070] The base station fault detection method provided by the embodiments of this application determines the abnormal moments within the target time period by obtaining the observation data of the target base station within the target time period, the integrity data of the target satellite system observed by the target base station, and the ionospheric activity observed by each of multiple satellites in the target satellite system, based on the observation data of the target base station, the integrity data of the target satellite system, and multiple ionospheric activities; then input the corresponding abnormal parameters of the abnormal moments into the preset fault detection model to obtain the target fault root cause of the target base station; where the preset fault detection model is trained based on historical abnormal parameters and the fault root causes corresponding to the historical abnormal parameters. In this way, the preset fault detection model can be used to automatically detect the fault root cause of the base station based on the observation data of the target base station, the integrity data of the target satellite system, and multiple ionospheric activities. Compared with the prior art of manually detecting the fault root cause of the base station, it can not only effectively improve the fault detection efficiency of the base station, but also reduce labor costs.

[0071] In some embodiments, abnormal moments within a target period can be determined based on the time-sequenced data. Correspondingly, the specific implementation manner of the above step S120 can be as follows:

[0072] Perform data preprocessing on the observation data of the target base station, the integrity data of the target satellite system, and the activities of multiple ionospheres to obtain time series data of the satellite system at different frequencies.

[0073] Based on the time series data, determine the abnormal moments within the target period.

[0074] When determining the abnormal moments within the target period based on the observation data of the target base station, the integrity data of the target satellite system, and the activities of multiple ionospheres, data preprocessing can be first performed on the observation data of the target base station, the integrity data of the target satellite system, and the activities of multiple ionospheres. For example, data fusion and time sequencing processing can be performed on the observation data of the target base station, the integrity data of the target satellite system, and the activities of multiple ionospheres, and different types of data are integrated according to the satellite system and frequency to obtain time series data of the satellite system at different frequencies.

[0075] It can be understood that when there are multiple target satellite systems observed by the target base station, the result of data preprocessing is the time series data of each satellite system at different frequencies. Then, based on the time series data of the satellite system at different frequencies, the abnormal moments within the target period are determined.

[0076] In this way, since the preprocessed time series data is time-sequenced and is the time-sequenced data of different satellite systems at different frequencies, the time series data is more convenient for determining the abnormal moments within the target period, thereby improving the efficiency and accuracy of determining the abnormal moments and further improving the efficiency and accuracy of base station fault detection.

[0077] In some embodiments, the abnormal moments can include time missing moments, moments with poor satellite search rate, moments with low pseudorange availability rate, moments with high carrier-to-noise ratio fluctuation, and moments with high ionosphere activity within the target period. Correspondingly, the specific implementation manner of the above determining the abnormal moments within the target period based on the time series data can be as follows:

[0078] Detect the missing moments in the time series of the time series data and determine the missing moments as missing abnormal moments;

[0079] Calculate the satellite search rate of the target satellite system at multiple moments within the target period based on the time series data, and determine the moment corresponding to the target search rate less than the preset satellite search rate threshold as the satellite search rate abnormal moment;

[0080] Calculate the pseudorange availability rate of the target satellite system at each frequency point at multiple moments within the target time period based on time series data, and determine the moments corresponding to the target pseudorange availability rate that is less than the preset availability rate threshold as pseudorange anomaly moments;

[0081] Determine the carrier-to-noise ratio fluctuation of the target satellite system at each frequency point at multiple moments within the target time period based on time series data, and determine the moments corresponding to the target carrier-to-noise ratio fluctuation that is greater than the preset fluctuation threshold as carrier-to-noise ratio anomaly moments;

[0082] Obtain the observation data of each of multiple satellites of the target satellite system by adjacent base stations of the target base station within the target time period, and calculate the ionospheric activity levels observed by each of the multiple satellites of the target satellite system at different moments based on the observation data of the target base station and the observation data of the adjacent base stations within the target time period;

[0083] When the number of target ionospheric activity levels greater than the preset activity threshold at the same moment is greater than the preset number and the satellites corresponding to the multiple target ionospheric activity levels are aggregated and distributed, determine the moments corresponding to the target ionospheric activity levels as ionospheric anomaly moments.

[0084] When determining the anomaly moments within the target time period based on time series data, it is possible to detect whether there are missing time series in the time series data. If there are missing time series, the missing moments of the time series may be the moments when faults occur, and the missing moments are marked as anomaly moments. It is also possible to calculate the satellite search rates of the target satellite system at multiple moments within the target time period based on time series data, and obtain the satellite search rates of each target satellite system at each moment within the target time period. After calculating the satellite search rates of the target satellite system at each moment within the target time period, the satellite search rates at each moment can be compared with the preset satellite search rate threshold to determine the target satellite search rate that is less than the preset satellite search rate threshold (such as 0.5). The moments corresponding to the target satellite search rate can be considered as the moments when faults may occur, and the moments corresponding to the target satellite search rate are determined as anomaly moments, that is, satellite search rate anomaly moments.

[0085] It is also possible to calculate the pseudorange availability of the target satellite system at each frequency point at multiple moments within the target time period based on time series data, so as to obtain the pseudorange availability of each target satellite system at each frequency point and at each moment within the target time period. Then, compare the pseudorange availability at each frequency point and moment with a preset availability threshold, and determine the target pseudorange availability that is less than the preset availability threshold (such as 0.5). The moment corresponding to the target pseudorange availability can be considered as the moment when a failure may occur, and the moment corresponding to the target pseudorange availability is determined as an abnormal moment, that is, a pseudorange abnormal moment. While determining the missing abnormal moment, the satellite search rate abnormal moment, and the pseudorange abnormal moment, it is also possible to calculate the carrier-to-noise ratio fluctuation of the target satellite system at each frequency point at multiple moments within the target time period based on time series data, so as to obtain the carrier-to-noise ratio fluctuation of each target satellite system at each frequency point and at each moment within the target time period. Then, perform k-means clustering on the carrier-to-noise ratio fluctuation (k-means clustering algorithm, KMeans clustering) to obtain the moment with a large carrier-to-noise ratio fluctuation (such as the moment corresponding to the carrier-to-noise ratio fluctuation with the largest distance from the clustering center), and determine this moment as the carrier-to-noise ratio abnormal moment.

[0086] Moreover, it is also possible to obtain the respective observation data of multiple satellites of the above-mentioned target satellite system by one or more adjacent base stations of the target base station within the target time period, and then calculate the ionospheric activity levels observed by the multiple satellites of the target satellite system at different moments based on the observation data of the target base station within the target time period and the observation data of the aforementioned adjacent base stations within the target time period. Then, it is possible to check whether there is a target ionospheric activity level greater than the preset activity threshold in the ionospheric activity levels corresponding to each moment. For the moment with a target ionospheric activity level greater than the preset activity threshold, determine the number of target ionospheric activity levels corresponding to each moment with a target ionospheric activity level. Compare the number of target ionospheric activity levels corresponding to each moment with a target ionospheric activity level with the preset activity threshold, determine the moment when the number of target ionospheric activity levels is greater than the preset activity threshold, and then judge whether the satellites corresponding to each target ionospheric activity level at this moment are clustered, such as whether they are concentrated in one area. In the case where the satellites corresponding to each target ionospheric activity level at this moment are clustered, it can be considered that this moment may be the moment when a failure occurs, and this moment is determined as the ionospheric abnormal moment.

[0087] It can be understood that the abnormal moments can include one or more of the above-mentioned time missing moment, satellite search rate abnormal moment, pseudorange abnormal moment, carrier-to-noise ratio abnormal moment, and ionospheric abnormal moment.

[0088] In this way, various moments in different situations, such as moments with time gaps, moments with poor satellite search rates, moments with low pseudorange availability rates, moments with high carrier-to-noise ratio fluctuations, and moments with high ionospheric activities, within the target time period are determined as abnormal moments, which can provide a more accurate and comprehensive data basis for obtaining abnormal data, thereby further improving the accuracy of fault detection results.

[0089] In some embodiments, the abnormal parameter corresponding to the missing abnormal moment may be a missing value. Correspondingly, before the above step S130, the following steps may also be executed:

[0090] Perform missing value processing on the missing abnormal moments to obtain the missing value corresponding to each missing abnormal moment;

[0091] Extract the abnormal parameter corresponding to each abnormal moment.

[0092] Among them, the abnormal parameter may include one or more of a missing value, a target satellite search rate, a target pseudorange availability rate, a target carrier-to-noise ratio fluctuation, and a target ionospheric activity.

[0093] Since there are usually no corresponding observation data, integrity data, and ionospheric data for the missing abnormal moments, before inputting the abnormal parameter into the preset detection model, missing value processing may also be performed on the missing abnormal moments, such as normalizing them to the range of 0 to 1. Then, obtain the abnormal parameter corresponding to each abnormal moment, which may include one or more of a missing value, a target satellite search rate, a target pseudorange availability rate, a target carrier-to-noise ratio fluctuation, and a target ionospheric activity.

[0094] It can be understood that if the missing abnormal moment does not overlap with other abnormal moments, the abnormal parameter corresponding to the missing abnormal moment may only include the missing value. On the contrary, if the missing abnormal moment overlaps with other abnormal moments, the abnormal parameter corresponding to the missing abnormal moment may be one or more of a missing value, a target satellite search rate, a target pseudorange availability rate, a target carrier-to-noise ratio fluctuation, and a target ionospheric activity.

[0095] In some embodiments, the above observation data of the target base station may include the number of satellites in the target satellite system observed by the target base station, the frequencies of multiple satellites in the target satellite system, the carrier-to-noise ratio and pseudorange of each satellite at each frequency; the integrity data may include the theoretical number of satellites in the satellite system;

[0096] Correspondingly, at this time, the specific implementation manner of calculating the satellite search rate of the target satellite system at multiple moments within the target time period based on the time series data may be as follows:

[0097] Calculate the satellite search rate of the target satellite system based on the theoretical number of satellites and the number of satellites in the target satellite system observed by the target base station.

[0098] As an example, the number of satellites in the target satellite system observed by the target base station can be obtained from the observation data of the target base station, and the integrity data can include the theoretical number of satellites in the satellite system. Then, based on the number of satellites in the target satellite system observed by the target base station and the integrity data including the theoretical number of satellites in the satellite system, the satellite search rate of the target satellite system can be calculated. For the satellite search rate at a certain moment, its calculation formula can be as shown in formula (1).

[0099] Satellite search rate = Number of observed satellites / Theoretical number of satellites (1)

[0100] Among them, the number of observed satellites can be obtained from the observation data of the target base station; the theoretical number of satellites can be obtained from the integrity data of the target satellite system, and the theoretical number of satellites can be the total number of satellites in all satellite systems that the target base station theoretically observes.

[0101] The specific implementation method for calculating the pseudorange availability rate of the target satellite system at each frequency point at multiple moments within the target time period based on the time series data can be as follows:

[0102] Determine the number of available pseudoranges in the pseudoranges of each satellite at each frequency point;

[0103] Based on the number of available pseudoranges and the number of satellites in the target satellite system observed by the target base station, calculate the pseudorange availability rate of the target satellite system at each frequency point.

[0104] As an example, when calculating the pseudorange availability rate of the target satellite system at each frequency point, the number of available pseudoranges in the pseudoranges of each satellite at each frequency point can be determined, that is, the total number of available pseudoranges in all the pseudoranges of each satellite in the target satellite system at each of its frequency points. Then, based on the number of available pseudoranges and the number of satellites in the target satellite system observed by the target base station, calculate the pseudorange availability rate of the target satellite system at each frequency point. For the pseudorange availability rate at a certain moment and a certain frequency point, its calculation formula can be as shown in formula (2).

[0105] Pseudorange availability rate = Number of available pseudoranges / Number of observed satellites (2)

[0106] Among them, the number of observed satellites can be obtained from the observation data of the target base station; the number of available pseudoranges can be the number of available pseudoranges in all the pseudoranges of the satellites observed by the target base station. The available pseudoranges can be the pseudoranges that meet the preset conditions, such as the number of pseudoranges within a preset range among all the pseudoranges of the satellites observed by the target base station. The preset range can be set according to the actual situation.

[0107] The specific implementation method for determining the carrier-to-noise ratio fluctuation of the target satellite system at each frequency point at multiple moments within the target time period based on the time series data can be as follows:

[0108] Perform a first-order difference on the carrier-to-noise ratio of the target satellite system at each frequency point to obtain the carrier-to-noise ratio fluctuation of the target satellite system at each frequency point.

[0109] As an example, when determining the carrier-to-noise ratio fluctuations of the target satellite system at each frequency point at multiple moments within the target time period, a first-order difference can be performed on the carrier-to-noise ratio data of the target satellite system at each frequency point to obtain the carrier-to-noise ratio fluctuations of the target satellite system at each frequency point. Specifically, when calculating the carrier-to-noise ratio fluctuation at a certain moment and a certain frequency point, the carrier-to-noise ratio sequence can be obtained from the observation data of the target base station, and a first-order difference is performed on the carrier-to-noise ratio sequence to obtain the carrier-to-noise ratio fluctuation of the target satellite system at that moment and that frequency point.

[0110] In some embodiments, the target fault root cause can be determined based on the occurrence probabilities of multiple preset fault root causes at each abnormal moment. Correspondingly, the specific implementation manner of the above step S130 can be as follows:

[0111] Input the abnormal parameters corresponding to the abnormal moment into the preset fault detection model to obtain the occurrence probabilities of each of the multiple preset fault root causes at each abnormal moment;

[0112] Based on the occurrence probabilities of each of the multiple preset fault root causes at each abnormal moment, determine the target fault root cause of the target base station.

[0113] Among them, the preset fault root cause can be a pre-set possible fault cause.

[0114] After inputting the abnormal parameters corresponding to the abnormal moment into the preset fault detection model, the preset fault detection model can analyze and process the abnormal parameters corresponding to each abnormal moment according to the pre-trained logic to obtain the occurrence probabilities of each of one or several preset fault root causes that may occur at each abnormal moment. Then, the occurrence probabilities of each of the multiple preset fault root causes at the above-mentioned each abnormal moment can be processed to determine the target fault root cause of the target base station.

[0115] In this way, by comprehensively considering the occurrence probabilities of the preset fault root causes corresponding to each abnormal moment to determine the target fault root cause of the target base station, the accuracy of the target fault root cause can be improved.

[0116] In some embodiments, the specific implementation manner of determining the target fault root cause of the target base station based on the occurrence probabilities of each of the multiple preset fault root causes at each abnormal moment can be as follows:

[0117] According to the occurrence probabilities of each of the multiple preset fault root causes at each abnormal moment, calculate the target occurrence probabilities of each of the multiple preset fault root causes during the target time period;

[0118] Determine the target fault root cause of the target base station as the preset fault root cause corresponding to the maximum value of the target occurrence probability.

[0119] When determining the target fault root cause of the target base station based on the occurrence probabilities of multiple preset fault root causes at each abnormal moment, the target occurrence probability of each preset fault root cause within the target time period can be calculated according to the occurrence probability corresponding to each preset fault root cause at each abnormal moment. Then, determine the maximum value among the target occurrence probabilities, and determine the preset fault root cause corresponding to the maximum value of the target occurrence probability as the target fault root cause of the target base station. For example, the occurrence probabilities corresponding to each preset fault root cause at each abnormal moment can be weighted (such as summation) to obtain the total occurrence probability of each preset fault root cause corresponding to each abnormal moment. Then, the preset fault root cause corresponding to the maximum value of the total occurrence probability can be determined as the target fault root cause of the target base station.

[0120] In this way, determining the preset fault root cause with the highest occurrence probability as the target fault root cause of the target base station can make the determined target fault root cause more in line with the actual situation, thereby further improving the accuracy of the target fault root cause.

[0121] Based on the same inventive concept, an embodiment of the present application also provides a base station fault detection device.

[0122] Figure 2 Figure 1 shows a base station fault detection device provided by an embodiment of the present application, as Figure 2 shown, the base station fault detection device 200 may include:

[0123] A data acquisition module 210, which can be used to acquire the observation data of the target base station within the target time period, the integrity data of the target satellite system observed by the target base station, and the ionospheric activity levels observed by multiple satellites in the target satellite system;

[0124] A determination module 220, which can be used to determine the abnormal moments within the target time period based on the observation data of the target base station, the integrity data of the target satellite system, and multiple ionospheric activity levels;

[0125] A fault detection module 230, which can be used to input the abnormal parameters corresponding to the abnormal moments into a preset fault detection model to obtain the target fault root cause of the target base station; the preset fault detection model is trained based on historical abnormal parameters and the fault root causes corresponding to the historical abnormal parameters.

[0126] In some embodiments, the determination module 220 may include:

[0127] A preprocessing unit, which can be used to perform data preprocessing on the observation data of the target base station, the integrity data of the target satellite system, and the activities of multiple ionospheres, so as to obtain time series data of the satellite system at different frequencies;

[0128] A first determination unit, which can be used to determine abnormal moments within the target time period based on the time series data.

[0129] In some embodiments, the determination unit may include:

[0130] A detection subunit, which can be used to detect missing moments in the time series of the time series data and determine the missing moments as missing abnormal moments;

[0131] A first determination subunit, which can be used to calculate the satellite search rate of the target satellite system at multiple moments within the target time period based on the time series data, and determine the moment corresponding to the target satellite search rate less than the preset satellite search rate threshold as the satellite search rate abnormal moment;

[0132] A second determination subunit, which can be used to calculate the pseudorange availability rate of the target satellite system at each frequency at multiple moments within the target time period based on the time series data, and determine the moment corresponding to the target pseudorange availability rate less than the preset availability rate threshold as the pseudorange abnormal moment;

[0133] A third determination subunit, which can be used to determine the carrier-to-noise ratio fluctuation of the target satellite system at each frequency at multiple moments within the target time period based on the time series data, and determine the moment corresponding to the target carrier-to-noise ratio fluctuation greater than the preset fluctuation threshold as the carrier-to-noise ratio abnormal moment;

[0134] A first calculation subunit, which can be used to obtain the observation data of multiple satellites of the target satellite system by adjacent base stations of the target base station within the target time period, and calculate the ionospheric activity observed by each of the multiple satellites of the target satellite system at different moments based on the observation data of the target base station within the target time period and the observation data of the adjacent base stations;

[0135] A fourth determination subunit, which can be used to determine the moment corresponding to the target ionospheric activity as the ionospheric abnormal moment when the number of target ionospheric activities greater than the preset activity threshold at the same moment is greater than the preset number and the satellites corresponding to the multiple target ionospheric activities are aggregated and distributed.

[0136] In some embodiments, the base station fault detection device 200 may further include:

[0137] A processing module, which can be used to process missing values for the missing abnormal moments to obtain the missing values corresponding to each of the missing abnormal moments;

[0138] An extraction module, which can be used to extract abnormal parameters corresponding to each abnormal moment, where the abnormal parameters include one or more of the missing value, the target satellite acquisition rate, the target pseudorange availability rate, the target carrier-to-noise ratio fluctuation, and the target ionospheric activity.

[0139] In some embodiments, the observation data of the target base station may include the number of satellites in the target satellite system observed by the target base station, the frequency points of multiple satellites in the target satellite system, the carrier-to-noise ratio and pseudorange of each satellite at each frequency point; the integrity data may include the theoretical number of satellites in the satellite system;

[0140] The first determination subunit may include:

[0141] A first calculation component, which can be used to calculate the satellite acquisition rate of the target satellite system based on the theoretical number of satellites and the number of satellites in the target satellite system observed by the target base station;

[0142] The second determination subunit may include:

[0143] A determination component, which can be used to determine the number of available pseudoranges in the pseudoranges of each satellite at each frequency point;

[0144] A second calculation component, which can be used to calculate the pseudorange availability rate of the target satellite system at each frequency point based on the number of available pseudoranges and the number of satellites in the target satellite system observed by the target base station;

[0145] The third determination subunit may include:

[0146] A difference component, which can be used to perform a first-order difference on the carrier-to-noise ratio of the target satellite system at each frequency point to obtain the carrier-to-noise ratio fluctuation of the target satellite system at each frequency point.

[0147] In some embodiments, the fault detection module 230 may include:

[0148] An input unit, which can be used to input the abnormal parameters corresponding to the abnormal moment into a preset fault detection model to obtain the occurrence probabilities of multiple preset fault root causes at each abnormal moment;

[0149] A second determination unit, which can be used to determine the target fault root cause of the target base station based on the occurrence probabilities of multiple preset fault root causes at each abnormal moment.

[0150] In some embodiments, the second determination unit may include:

[0151] A second calculation subunit, which can be used to calculate the target occurrence probabilities of the multiple preset fault root causes in the target time period according to the occurrence probabilities of the multiple preset fault root causes at each abnormal moment.

[0152] A fifth determination subunit, which can be used to determine the preset fault root cause corresponding to the maximum value of the target occurrence probability as the target fault root cause of the target base station.

[0153] In some embodiments, the preset fault detection model can be a four-layer fully connected neural network.

[0154] The base station fault detection device provided by the embodiments of the present application can be used to execute the base station fault detection methods provided by the above method embodiments. The implementation principles and technical effects are similar. For the sake of brevity, they will not be elaborated here.

[0155] Based on the same inventive concept, the embodiments of the present application also provide an electronic device.

[0156] Figure 3 It is a schematic structural diagram of an electronic device provided by the embodiments of the present application. As Figure 3 shown, the electronic device may include a processor 301 and a memory 302 storing computer programs or instructions.

[0157] Specifically, the above-mentioned processor 301 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0158] The memory 302 may include a mass storage for data or instructions. By way of example and not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In a suitable case, the memory 502 may include a removable or non-removable (or fixed) medium. In a suitable case, the memory 502 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, the memory 302 is a non-volatile solid-state memory. In a particular embodiment, the memory 302 includes a read-only memory (ROM). In a suitable case, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0159] The processor 301 reads and executes the computer program instructions stored in the memory 302 to implement any one of the base station fault detection methods in the above embodiments.

[0160] In one example, the electronic device may further include a communication interface 303 and a bus 310. Among them, as Figure 3 shown, the processor 301, the memory 302, and the communication interface 303 are connected through the bus 310 and complete communication with each other.

[0161] The communication interface 303 is mainly used to implement communication between the various modules, devices, units, and / or devices in the embodiments of the present invention.

[0162] The bus 310 includes hardware, software, or both, and couples the components of the electronic device to each other. By way of example and not limitation, the bus may include an accelerated graphics port (AGP) or other graphics bus, an enhanced industry standard architecture (EISA) bus, a front-side bus (FSB), a hyperTransport (HT) interconnect, an industry standard architecture (ISA) bus, an InfiniBand interconnect, a low pin count (LPC) bus, a memory bus, a microchannel architecture (MCA) bus, a peripheral component interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a serial advanced technology attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable buses, or a combination of two or more of these. In a suitable case, the bus 310 may include one or more buses. Although the embodiments of the present invention describe and illustrate specific buses, the present invention contemplates any suitable bus or interconnect.

[0163] The electronic device can execute the base station fault detection method in the embodiments of the present invention, so as to implement Figures 1 to 2 the base station fault detection method and device described.

[0164] In addition, in combination with the base station fault detection method in the above embodiments, the embodiments of the present invention can provide a readable storage medium to implement. Program instructions are stored on the readable storage medium; when the program instructions are executed by a processor, any one of the base station fault detection methods in the above embodiments is implemented.

[0165] It should be clear that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, the detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present invention.

[0166] The functional blocks shown in the above structural block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, and so on. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted via a data signal carried in a carrier wave on a transmission medium or a communication link. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical discs, hard disks, fiber optic media, radio frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, and so on.

[0167] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, or different from the order in the embodiments, or several steps can be executed simultaneously.

[0168] As described above, this is only the specific implementation manner of the present invention. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A base station fault detection method, characterized in that, Including: Obtaining the observation data of the target base station during the target time period, the integrity data of the target satellite system observed by the target base station, and the ionospheric activity levels respectively observed by multiple satellites in the target satellite system. The observation data includes at least one of the elevation angle, frequency point, pseudorange, carrier wave, or Doppler of each satellite observed by the target base station; Determining the abnormal moments during the target time period based on the observation data of the target base station, the integrity data of the target satellite system, and multiple ionospheric activity levels; Inputting the abnormal parameters corresponding to the abnormal moments into a preset fault detection model to obtain the target fault root cause of the target base station; The preset fault detection model is trained based on historical abnormal parameters and the fault root causes corresponding to the historical abnormal parameters. The abnormal parameters include multiple of missing values, target satellite acquisition rate, target pseudorange availability rate, target carrier-to-noise ratio fluctuation, and target ionospheric activity level.

2. The method according to claim 1, characterized in that, The determining the abnormal moments during the target time period based on the observation data of the target base station, the integrity data of the target satellite system, and multiple ionospheric activity levels includes: Performing data preprocessing on the observation data of the target base station, the integrity data of the target satellite system, and the multiple ionospheric activity levels to obtain the time series data of the satellite system at different frequency points; Determining the abnormal moments during the target time period based on the time series data.

3. The method according to claim 2, wherein The determining the abnormal moments during the target time period based on the time series data includes: Detecting the missing moments in the time series of the time series data and determining the missing moments as missing abnormal moments; Calculating the satellite acquisition rate of the target satellite system at multiple moments during the target time period based on the time series data, and determining the moments corresponding to the target satellite acquisition rate less than the preset satellite acquisition rate threshold as satellite acquisition rate abnormal moments; Calculating the pseudorange availability rate of the target satellite system at each frequency point at multiple moments during the target time period based on the time series data, and determining the moments corresponding to the target pseudorange availability rate less than the preset availability rate threshold as pseudorange abnormal moments; Determining the carrier-to-noise ratio fluctuation of the target satellite system at each frequency point at multiple moments during the target time period based on the time series data, and determining the moments corresponding to the target carrier-to-noise ratio fluctuation greater than the preset fluctuation threshold as carrier-to-noise ratio abnormal moments; Obtaining the observation data of each of the multiple satellites in the target satellite system by adjacent base stations of the target base station during the target time period, and calculating the ionospheric activity levels respectively observed by the multiple satellites in the target satellite system at different moments based on the observation data of the target base station during the target time period and the observation data of the adjacent base stations; When the number of target ionospheric activity levels greater than the preset activity threshold at the same moment is greater than the preset number and the satellites corresponding to the multiple target ionospheric activity levels are clustered and distributed, determining the moments corresponding to the target ionospheric activity levels as ionospheric abnormal moments.

4. The method according to claim 3, characterized in that, Before inputting the abnormal parameter corresponding to the abnormal moment into a preset fault detection model to obtain the target fault root cause of the target base station, the following steps are further included: Perform missing value processing on the missing abnormal moments to obtain the missing values corresponding to each of the missing abnormal moments; Extract the abnormal parameters corresponding to each abnormal moment, where the abnormal parameters include one or more of the missing value, the target satellite acquisition rate, the target pseudorange availability rate, the target carrier-to-noise ratio fluctuation, and the target ionospheric activity.

5. The method according to claim 3, characterized in that, The observation data of the target base station includes the number of satellites in the target satellite system observed by the target base station, the frequencies of multiple satellites in the target satellite system, the carrier-to-noise ratio and pseudorange of each satellite at each frequency; the integrity data includes the theoretical number of satellites in the satellite system. The calculation of the satellite acquisition rate of the target satellite system at multiple moments within the target time period based on the time series data includes: Calculating the satellite acquisition rate of the target satellite system based on the theoretical number of satellites and the number of satellites in the target satellite system observed by the target base station; The calculation of the pseudorange availability rate of the target satellite system at each frequency at multiple moments within the target time period based on the time series data includes: Determining the number of available pseudoranges in the pseudoranges of each satellite at each frequency; Calculating the pseudorange availability rate of the target satellite system at each frequency based on the number of available pseudoranges and the number of satellites in the target satellite system observed by the target base station; The determination of the carrier-to-noise ratio fluctuation of the target satellite system at each frequency at multiple moments within the target time period based on the time series data includes: Performing a first-order difference on the carrier-to-noise ratio of the target satellite system at each frequency to obtain the carrier-to-noise ratio fluctuation of the target satellite system at each frequency.

6. The method according to claim 4, wherein Inputting the abnormal parameter corresponding to the abnormal moment into a preset fault detection model to obtain the target fault root cause of the target base station includes: Inputting the abnormal parameter corresponding to the abnormal moment into a preset fault detection model to obtain the occurrence probabilities of multiple preset fault root causes at each abnormal moment; Based on the occurrence probabilities of multiple preset fault root causes at each abnormal moment, determining the target fault root cause of the target base station.

7. The method according to claim 6, wherein Based on the occurrence probabilities of multiple preset fault root causes at each abnormal moment, determining the target fault root cause of the target base station includes: Calculating the target occurrence probabilities of the multiple preset fault root causes in the target time period according to the occurrence probabilities of the multiple preset fault root causes at each abnormal moment; Determining the preset fault root cause corresponding to the maximum value of the target occurrence probability as the target fault root cause of the target base station.

8. The method according to any one of claims 1-7, characterized in that, The preset fault detection model is a four-layer fully connected neural network.

9. A base station fault detection device, characterized in that, Including: A data acquisition module, configured to acquire the observation data of a target base station during a target time period, the integrity data of a target satellite system observed by the target base station, and the ionospheric activity levels respectively observed by multiple satellites in the target satellite system, where the observation data includes at least one of the elevation angle, frequency point, pseudorange, carrier wave, or Doppler of each satellite observed by the target base station; A determination module, configured to determine an abnormal moment during the target time period based on the observation data of the target base station, the integrity data of the target satellite system, and multiple ionospheric activity levels; A fault detection module, configured to input the abnormal parameters corresponding to the abnormal moment into a preset fault detection model to obtain the root cause of the target fault of the target base station; The preset fault detection model is trained based on historical abnormal parameters and the root causes of faults corresponding to the historical abnormal parameters, and the abnormal parameters include multiple of missing values, target satellite acquisition rate, target pseudorange availability rate, target carrier-to-noise ratio fluctuation, and target ionospheric activity level.

10. An electronic device, characterized in that, It includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor, and when the program or instruction is executed by the processor, the steps of the base station fault detection method according to any one of claims 1-8 are implemented.

11. A readable storage medium, characterized in that, A program or instruction is stored on the readable storage medium, and when the program or instruction is executed by the processor, the steps of the base station fault detection method according to any one of claims 1-8 are implemented.

Images