Automatic fault prediction method and system for operation and maintenance of base station

Abstract

The invention discloses an automatic fault prediction method and system for operation and maintenance of a base station, and relates to the technical field of operation and maintenance of the base station, and the method comprises the steps: collecting a plurality of signal features at a plurality of monitoring positions of a communication base station, carrying out the change analysis of the signal features of a base station antenna, and obtaining a plurality of signal change parameters; performing base station antenna offset analysis according to the plurality of signal change parameters to obtain a plurality of antenna offset parameters, and performing offset credibility analysis to obtain a plurality of offset credibility; acquiring environment parameters in an environment where the communication base station is located, and performing base station antenna influence offset analysis in combination with the plurality of antenna offset parameters to obtain a plurality of antenna influence offset parameters; and according to the plurality of offset credibility and in combination with the plurality of antenna influence offset parameters, calculating to obtain an antenna fault scale, and taking the antenna fault scale as a base station operation and maintenance fault prediction result. According to the invention, the technical problem of poor fault prediction accuracy in operation and maintenance of the base station in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of base station operation and maintenance, and in particular to an automatic fault prediction method and system for base station operation and maintenance. Background Art

[0002] In wireless communication networks, communication base stations serve as core infrastructure, and the stable operation of their antennas is crucial to ensuring network coverage quality and user experience. Current base station operation and maintenance fault monitoring technologies primarily rely on threshold alarm mechanisms for key base station performance indicators, such as signal strength. However, these methods have significant limitations and are passive responses after the fact. Alarms are typically triggered only after performance has severely degraded or a fault has actually occurred, resulting in a lack of timeliness and prone to misjudgments due to local data anomalies or noise. Existing methods face bottlenecks in the timeliness, accuracy, and robustness of base station fault prediction, making it difficult to meet the urgent needs of modern networks for high reliability and proactive operation and maintenance. Summary of the Invention

[0003] The present application provides a method and system for automatic fault prediction for base station operation and maintenance, which is used to solve the technical problems of poor accuracy and timeliness of fault prediction in base station operation and maintenance in the prior art.

[0004] In view of the above problems, the present application provides a method and system for automatic fault prediction for base station operation and maintenance.

[0005] In a first aspect, the present application provides a method for automatic fault prediction for base station operation and maintenance, the method comprising: At multiple monitoring locations of a communication base station, multiple signal characteristics are collected, and the signal characteristic change analysis of the base station antenna is performed to obtain multiple signal change parameters; Performing base station antenna offset analysis based on multiple signal change parameters to obtain multiple antenna offset parameters, performing offset credibility analysis to obtain multiple offset credibility; Acquire environmental parameters in the environment where the communication base station is located, and perform base station antenna impact offset analysis in combination with multiple antenna offset parameters to obtain multiple antenna impact offset parameters; Based on multiple offset credibility and multiple antenna-affecting offset parameters, the antenna fault scale is calculated and used as the base station operation and maintenance fault prediction result.

[0006] Optionally, multiple signal characteristics are collected at multiple monitoring locations of the communication base station, and a signal characteristic change analysis of the base station antenna is performed to obtain multiple signal change parameters, including: collecting a plurality of signal characteristics at a plurality of monitoring locations of a communication base station, wherein the signal characteristics include signal quality; Acquiring a plurality of standard signal characteristics at a plurality of monitoring locations; The change amplitudes of the plurality of signal features and the plurality of standard signal features are calculated respectively to obtain a plurality of signal change parameters.

[0007] Optionally, performing base station antenna offset analysis based on multiple signal change parameters to obtain multiple antenna offset parameters, performing offset credibility analysis to obtain multiple offset credibility, including: Inputting each signal variation parameter into an antenna offset analyzer, and outputting a plurality of antenna offset parameters, wherein each antenna offset parameter includes an offset direction and an offset scale; Calculating the similarity between each antenna offset parameter and the mean of the plurality of antenna offset parameters to obtain a plurality of first offset credibility; Acquire multiple monitoring distances between multiple monitoring positions and a base station antenna, and calculate multiple second offset credibility levels, wherein the magnitude of the monitoring distance is negatively correlated with the magnitude of the second offset credibility level; A plurality of offset confidence levels are calculated based on the plurality of first offset confidence levels and the plurality of second offset confidence levels.

[0008] Optionally, the step of obtaining the antenna offset analyzer includes: Based on the offset operation and maintenance data of the base station antenna over a historical period, multiple sample signal change parameter sets are collected from multiple monitoring locations. The antenna offset parameters of the base station antenna under different signal change parameters are also collected, and multiple sample antenna offset parameter sets are obtained by annotation. Based on machine learning, multiple antenna offset analysis paths with the same architecture are constructed; Multiple antenna offset analysis paths are supervised and trained using multiple sample signal change parameter sets and multiple sample antenna offset parameter sets respectively. After convergence, they are integrated to obtain an antenna offset analyzer.

[0009] Optionally, obtaining environmental parameters in an environment where the communication base station is located, and performing base station antenna impact offset analysis in combination with multiple antenna offset parameters to obtain multiple antenna impact offset parameters includes: Acquiring environmental parameters within an environment where the communication base station is located, wherein the environmental parameters include meteorological parameters; The environmental parameters are respectively combined with each antenna offset parameter and input into the antenna impact offset analyzer, and a plurality of antenna impact offset parameters are obtained as output.

[0010] Optionally, the steps of constructing the antenna impact offset analyzer include: Based on the base station antenna operation and maintenance data in the historical period, a sample antenna offset parameter set, a sample environment parameter set, and antenna impact offset parameters under the influence of different sample antenna offset parameters and sample environment parameters are collected to obtain a sample antenna impact offset parameter set; Build a machine learning-based antenna impact offset analyzer; The antenna impact offset analyzer is supervised and trained using the sample antenna offset parameter set, the sample environment parameter set, and the sample antenna impact offset parameter set, and is constructed after convergence.

[0011] Optionally, based on multiple offset credibility levels and multiple antenna-affecting offset parameters, an antenna fault scale is calculated and obtained as a base station operation and maintenance fault prediction result, including: Calculating the magnitudes by which the impact offset parameters of multiple antennas exceed the fault offset parameters respectively, and obtaining the fault scales of multiple monitoring antennas; Weights are assigned according to multiple offset credibility scores, and multiple monitoring antenna fault scales are weighted and calculated to obtain the antenna fault scale as the base station operation and maintenance fault prediction result.

[0012] In a second aspect, the present application provides an automatic fault prediction system for base station operation and maintenance, comprising: A signal feature analysis module is used to collect multiple signal features at multiple monitoring locations of a communication base station, analyze changes in the signal features of the base station antenna, and obtain multiple signal change parameters; A credibility analysis module is used to perform base station antenna offset analysis based on multiple signal change parameters to obtain multiple antenna offset parameters, perform offset credibility analysis, and obtain multiple offset credibility; An impact offset analysis module is used to obtain environmental parameters in the environment where the communication base station is located, and perform base station antenna impact offset analysis in combination with multiple antenna offset parameters to obtain multiple antenna impact offset parameters; The fault prediction module is used to calculate the antenna fault scale based on multiple offset credibility and multiple antenna impact offset parameters as the base station operation and maintenance fault prediction result.

[0013] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application proposes an automatic fault prediction method and system for base station operation and maintenance. By collecting signal characteristics at multiple monitoring locations and analyzing their changing parameters, and dynamically calculating antenna fault scales based on environmental factors and offset credibility, this method significantly improves the accuracy and reliability of early predictions of potential base station antenna offset faults. Compared to traditional methods, the technical solution provided by this application breaks through the limitations of passive threshold alarms, enabling multi-dimensional collaborative analysis and quantitative evaluation of fault causes. It can also stably output high-reliability fault warning information even in complex and changing actual deployment environments, ultimately achieving the technical effect of accurately predicting base station antenna offset faults and guiding timely operation and maintenance in the presence of environmental interference. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 A flowchart of an automatic fault prediction method for base station operation and maintenance provided in an embodiment of the present application.

[0016] Figure 2 A schematic diagram of the structure of an automatic fault prediction system for base station operation and maintenance provided in an embodiment of the present application.

[0017] In the accompanying drawings, the components represented by the reference numerals are described as follows: Signal feature analysis module 100 , credibility analysis module 200 , impact offset analysis module 300 , fault prediction module 400 . DETAILED DESCRIPTION

[0018] The present application provides a method and system for automatic fault prediction for base station operation and maintenance, aiming to solve the technical problems of poor accuracy and timeliness of fault prediction in base station operation and maintenance in the prior art.

[0019] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0020] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0021] Example 1, as Figure 1 As shown, the present application provides a method for automatic fault prediction for base station operation and maintenance, wherein the method includes: S10: Collect multiple signal characteristics at multiple monitoring locations of the communication base station, perform signal characteristic change analysis on the base station antenna, and obtain multiple signal change parameters.

[0022] In traditional base station operations and maintenance, antenna status monitoring typically relies on collecting signal features from a single or limited location, resulting in insufficient coverage and sensitivity for signal change analysis. This limited signal feature information makes it difficult to fully capture signal changes caused by physical antenna deviation, especially when detecting early, subtle signs of deviation.

[0023] Step S10 in the method provided in the embodiment of the present application includes: collecting a plurality of signal characteristics at a plurality of monitoring locations of a communication base station, wherein the signal characteristics include signal quality; Acquiring a plurality of standard signal characteristics at a plurality of monitoring locations; The change amplitudes of the plurality of signal features and the plurality of standard signal features are calculated respectively to obtain a plurality of signal change parameters.

[0024] In an embodiment of the present application, a general spectrum analyzer is used to collect and obtain multiple signal characteristics at multiple locations of a communication base station, such as 2 meters away from the center of the base station due east and 2 meters away from the center of the base station due west. The signal characteristics include signal quality. The signal quality is a parameter reflecting the signal strength and is characterized by the received signal strength in dBm.

[0025] Multiple standard signal characteristics at multiple monitoring locations are obtained. The standard signal characteristics refer to the signal strength that the monitoring location should have according to the designed theoretical value under standard working conditions. They can be extracted from the production design data of the communication base station to obtain multiple standard signal characteristics at multiple monitoring locations.

[0026] The magnitude of changes in the plurality of signal features and the plurality of standard signal features are calculated to obtain a plurality of signal change parameters, where the signal change parameter = |signal feature - standard signal feature|.

[0027] By simultaneously collecting signal features at multiple monitoring locations and calculating their variation from standard features, the spatial coverage and sensitivity of signal change analysis are significantly improved. Multi-location data collection captures regional signal anomaly patterns caused by antenna offsets. A dynamic comparison mechanism based on standard features converts raw signals into quantifiable signal variation parameters, eliminating inaccuracies caused by baseline differences and providing highly consistent input data for subsequent analysis.

[0028] S20: Performing base station antenna offset analysis based on multiple signal change parameters to obtain multiple antenna offset parameters, performing offset credibility analysis to obtain multiple offset credibility.

[0029] Existing technologies do not take into account the reliability differences of data at different monitoring locations. For example, the signal reliability at locations farther away from the base station antenna is poor, resulting in inaccurate offset analysis results.

[0030] Step S20 in the method provided in the embodiment of the present application includes: Inputting each signal variation parameter into an antenna offset analyzer, and outputting a plurality of antenna offset parameters, wherein each antenna offset parameter includes an offset direction and an offset scale; The step of obtaining the antenna offset analyzer includes: Based on the offset operation and maintenance data of the base station antenna over a historical period, multiple sample signal change parameter sets are collected from multiple monitoring locations. The antenna offset parameters of the base station antenna under different signal change parameters are also collected, and multiple sample antenna offset parameter sets are obtained by annotation. Based on machine learning, multiple antenna offset analysis paths with the same architecture are constructed; Multiple antenna offset analysis paths are supervised and trained using multiple sample signal change parameter sets and multiple sample antenna offset parameter sets, and integrated after convergence to obtain an antenna offset analyzer. Calculating the similarity between each antenna offset parameter and the mean of the plurality of antenna offset parameters to obtain a plurality of first offset credibility; Acquire multiple monitoring distances between multiple monitoring positions and a base station antenna, and calculate multiple second offset credibility levels, wherein the magnitude of the monitoring distance is negatively correlated with the magnitude of the second offset credibility level; A plurality of offset confidence levels are calculated based on the plurality of first offset confidence levels and the plurality of second offset confidence levels.

[0031] In an embodiment of the present application, multiple sample signal change parameter sets are collected from multiple monitoring locations based on historical offset operation and maintenance data of the base station antenna. Preferably, the historical event can be set to the past 180 days. Multiple signal change parameters are collected from multiple monitoring locations within the past 180 days. The signal change parameters for each monitoring location are integrated into a set to obtain multiple sample signal change parameter sets. Antenna offset parameters of the base station antenna are also collected under different signal change parameters. During operation, the base station antenna may experience slight offsets, resulting in signal variations. The base station antenna azimuth offset is used to characterize the base station antenna offset parameter, where each antenna offset parameter includes an offset direction and an offset scale. For example, due east is designated as 0 degrees, and the clockwise offset angle is the offset direction, measured in degrees. The offset scale is represented by the straight-line distance between the offset and un-offset antenna end positions, measured in centimeters. The antenna offset parameters are annotated and integrated with the signal change parameter and the monitoring location. The antenna offset parameters for each monitoring location are integrated into a set to obtain multiple sample antenna offset parameter sets.

[0032] Based on machine learning, we constructed multiple antenna offset analysis paths with the same architecture. Specifically, we constructed a three-layer structure: an input layer to receive sample signal variation parameters, a hidden layer with 32 nodes activated by the ReLU function, and an output layer that outputs the analyzed antenna offset paths.

[0033] Multiple antenna offset analysis paths are supervised and trained using multiple sets of sample signal variation parameters and multiple sets of sample antenna offset parameters until convergence. For example, if the accuracy of the output antenna offset parameters exceeds 90% for the input signal variation parameters, the antenna offset analysis path training is complete. Multiple trained antenna offset paths are integrated to obtain the antenna offset analyzer.

[0034] Each signal variation parameter is input into an antenna offset analyzer, and multiple antenna offset parameters are output, wherein each antenna offset parameter includes an offset direction and an offset scale.

[0035] Calculate the similarity between each antenna offset parameter and the mean of multiple antenna offset parameters to obtain multiple first offset confidence levels. The first offset confidence level is the mean of the offset direction similarity and the offset scale similarity. Offset direction confidence level = 1 - |antenna offset direction - antenna offset direction mean| ÷ [(antenna offset direction + antenna offset direction mean) ÷ 2], offset scale confidence level = 1 - |antenna offset scale - antenna offset scale mean| ÷ [(antenna offset scale + antenna offset scale mean) ÷ 2]. The first offset confidence level = (antenna offset direction confidence level + offset scale confidence level) ÷ 2. For example, if the antenna offset direction is 3 degrees, the mean offset direction is 5 degrees, the antenna offset scale is 30 cm, and the mean offset scale is 40 cm, then the offset direction reliability = 1-|3-5|÷[(3+5)÷2] = 0.5, the offset scale reliability = 1-|30-40|÷[(30+40)÷2] = 0.71, and the first offset reliability = (0.5+0.71)÷2 = 0.605. The more similar the offset direction and scale, the closer the offset pattern, and the greater the reliability.

[0036] Multiple monitoring distances between multiple monitoring locations and the base station antenna are obtained, and multiple second offset confidence levels are calculated. The monitoring distances are negatively correlated with the second offset confidence levels. For example, based on the map location, multiple straight-line distances between the base station antenna and the multiple monitoring locations are obtained as the monitoring distances, in meters. The second offset confidence level is calculated as 1 - (monitoring distance - minimum monitoring distance) / (maximum monitoring distance - minimum monitoring distance). For example, if the monitoring distance is 50 meters, the maximum monitoring distance is 100 meters, and the minimum monitoring distance is 1 meter, then the second offset confidence level is calculated as 1 - (50 - 1) / (100 - 1) = 0.5. The farther the monitoring location, the more possible influencing factors there are, the greater the signal interference, and the lower the confidence level.

[0037] Multiple offset reliabilities are calculated based on the multiple first offset reliabilities and the multiple second offset reliabilities. Offset reliability = (first offset reliability + second offset reliability) ÷ 2. For example, if the first offset reliability is 0.605 and the second offset reliability is 0.5, then the offset reliability = (0.605 + 0.5) ÷ 2 = 0.552.

[0038] The offset credibility analysis mechanism, after generating antenna offset parameters, simultaneously calculates their similarity to the overall offset mean. This mechanism, combined with the negative impact of monitoring distance on data reliability, dynamically generates a multi-dimensional offset credibility index. This mechanism effectively quantifies the credibility of data at different locations, significantly suppresses the interference of local anomalies on overall offset judgment, and improves the noise resistance and reliability of offset analysis results.

[0039] S30: Acquire environmental parameters in the environment where the communication base station is located, and perform base station antenna impact offset analysis in combination with multiple antenna offset parameters to obtain multiple antenna impact offset parameters.

[0040] Traditional fault prediction methods often treat environmental parameters and antenna offset data in isolation, failing to consider the impact of external dynamic disturbances such as weather changes. Environmental factors are treated as independent threshold alarm items or are simply filtered out, resulting in distorted fault predictions.

[0041] Step S30 in the method provided in the embodiment of the present application includes: Acquiring environmental parameters within an environment where the communication base station is located, wherein the environmental parameters include meteorological parameters; The environmental parameters are combined with each antenna offset parameter and input into the antenna impact offset analyzer, and a plurality of antenna impact offset parameters are obtained as output; The steps of constructing the antenna impact offset analyzer include: Based on the base station antenna operation and maintenance data in the historical period, a sample antenna offset parameter set, a sample environment parameter set, and antenna impact offset parameters under the influence of different sample antenna offset parameters and sample environment parameters are collected to obtain a sample antenna impact offset parameter set; Build a machine learning-based antenna impact offset analyzer; The antenna impact offset analyzer is supervised and trained using the sample antenna offset parameter set, the sample environment parameter set, and the sample antenna impact offset parameter set, and is constructed after convergence.

[0042] Wind can cause the antenna to deflect, affecting signal characteristics. Therefore, meteorological parameters should be taken into consideration to make base station operation and maintenance more comprehensive and accurate. In the embodiment of the present application, the environmental parameters of the environment where the communication base station is located are obtained based on weather station data, where the environmental parameters include meteorological parameters such as wind force level and wind direction. For example, the wind force level is level 3 and the wind direction is northeasterly.

[0043] The base station antenna operation and maintenance data is collected to obtain a sample antenna offset parameter set, a sample environmental parameter set, and antenna impact offset parameters under the influence of different sample antenna offset parameters and sample environmental parameters, and a sample antenna impact offset parameter set is obtained. Among them, the antenna impact offset parameter refers to the parameter that causes the antenna offset due to changes in environmental parameters such as strong winds during the operation and maintenance process. The antenna impact offset parameter includes the impact offset direction and the impact offset scale. For example, the east direction is recorded as 0 degrees, the clockwise offset angle is the impact offset direction, and the unit is degree. The impact offset scale is characterized by the straight-line distance between the antenna end position after offset and the antenna end position before offset, and the unit is centimeter.

[0044] Construct an antenna impact offset analyzer based on machine learning. Preferably, a four-layer structure is adopted, wherein the input layer is used to receive sample antenna offset parameters and environmental parameters, the first hidden layer uses 32 nodes and is activated by the ReLU function, the second hidden layer uses 16 nodes and is activated by the ReLU function, and the output layer is used to output the analyzed antenna impact offset parameters.

[0045] The antenna impact offset analyzer is supervised and trained using a set of sample antenna offset parameters, a set of sample environmental parameters, and a set of sample antenna impact offset parameters until convergence. For example, if the antenna offset parameters and environmental parameters are input and the error of the output antenna impact offset parameters is within 0.2 degrees and 3 cm, the training converges and the antenna impact offset analyzer training is completed.

[0046] The environmental parameters are combined with each antenna offset parameter respectively, input into the antenna impact offset analyzer, and the antenna impact offset parameter is obtained as output.

[0047] By designing an antenna impact offset analyzer, environmental parameters and antenna offset parameters at each position are analyzed collaboratively, and antenna impact offset parameters that integrate environmental information are output. This realizes the coupled analysis of environmental factors and physical offsets, greatly improving the accuracy of offset parameters in complex environments.

[0048] S40: Calculate and obtain an antenna fault scale based on the multiple offset credibility and multiple antenna impact offset parameters as a base station operation and maintenance fault prediction result.

[0049] In the final fault prediction stage, existing methods often directly aggregate multi-location offset data without distinguishing the contribution weights of data with different credibility. This makes the prediction results susceptible to the influence of low-credibility data and difficult to support operation and maintenance decisions.

[0050] Step S40 in the method provided in the embodiment of the present application includes: Calculating the magnitudes by which the impact offset parameters of multiple antennas exceed the fault offset parameters respectively, and obtaining the fault scales of multiple monitoring antennas; Weights are assigned according to multiple offset credibility scores, and multiple monitoring antenna fault scales are weighted and calculated to obtain the antenna fault scale as the base station operation and maintenance fault prediction result.

[0051] In this embodiment, the magnitude by which multiple antenna impact offset parameters exceed the fault offset parameter is calculated to obtain multiple monitoring antenna fault scales. The fault offset parameter indicates a potential fault requiring maintenance. The monitoring antenna fault scale = |antenna impact offset parameter - fault offset parameter|. A tolerance range is set for the monitoring antenna fault scale. For example, the offset direction tolerance range is set to 0.3 degrees, and the offset scale tolerance range is set to 5 centimeters. Fault scales within this tolerance range are considered acceptable.

[0052] Weights are assigned to multiple offset credibility levels and weighted calculations are performed on multiple monitoring antenna fault scales to obtain the antenna fault scale, which serves as the base station operation and maintenance fault prediction result. For example, if one monitoring antenna has a fault scale of 1 degree in offset direction, 10 cm in offset scale, and a credibility of 0.65, and another has a fault scale of 1.5 degrees in offset direction, 8 cm in offset scale, and a credibility of 0.7, then the antenna fault scale is calculated as follows: the offset direction fault scale = ∑[offset direction × (credibility ÷ sum of credibility)] = 1 × (0.65 ÷ 1.35) + 1.5 × (0.7 ÷ 1.35) = 1.25, and the offset scale fault scale = ∑[offset scale × (credibility ÷ sum of credibility)] = 10 × (0.65 ÷ 1.35) + 8 × (0.7 ÷ 1.35) = 8.95. The offset direction fault scale and the offset scale fault scale are compared with the offset scale tolerance range. If the offset direction or offset scale is greater than the offset scale tolerance range, it indicates a high probability of failure. A fault warning message is sent to the operation and maintenance personnel, such as a text message such as "The base station antenna may be faulty, please check it in time."

[0053] By dynamically weighting each location's fault scale based on offset credibility and aggregating it to generate a fault scale, this application uses credibility as the basis for weighting, mitigating the negative impact of low-credibility data. Furthermore, by setting a tolerance range, it reduces false alarms caused by minor changes, improves warning accuracy, and provides a reliable basis for operational and maintenance decisions.

[0054] Example 2, as Figure 2 As shown, based on the same inventive concept as the automatic fault prediction method for base station operation and maintenance provided in Example 1, an embodiment of the present invention further provides an automatic fault prediction system for base station operation and maintenance, including: The signal characteristic analysis module 100 is used to collect multiple signal characteristics at multiple monitoring locations of the communication base station, perform signal characteristic change analysis on the base station antenna, and obtain multiple signal change parameters; The credibility analysis module 200 is used to perform base station antenna offset analysis based on multiple signal change parameters to obtain multiple antenna offset parameters, perform offset credibility analysis, and obtain multiple offset credibility; The impact offset analysis module 300 is used to obtain environmental parameters in the environment where the communication base station is located, and perform base station antenna impact offset analysis in combination with multiple antenna offset parameters to obtain multiple antenna impact offset parameters; The fault prediction module 400 is configured to calculate an antenna fault scale based on multiple offset credibility and multiple antenna impact offset parameters, as a base station operation and maintenance fault prediction result.

[0055] In one embodiment, the signal feature analysis module 100 is further configured to: collecting a plurality of signal characteristics at a plurality of monitoring locations of a communication base station, wherein the signal characteristics include signal quality; Acquiring a plurality of standard signal characteristics at a plurality of monitoring locations; The change amplitudes of the plurality of signal features and the plurality of standard signal features are calculated respectively to obtain a plurality of signal change parameters.

[0056] In one embodiment, the credibility analysis module 200 is further configured to: Inputting each signal variation parameter into an antenna offset analyzer, and outputting a plurality of antenna offset parameters, wherein each antenna offset parameter includes an offset direction and an offset scale; The step of obtaining the antenna offset analyzer includes: Based on the offset operation and maintenance data of the base station antenna over a historical period, multiple sample signal change parameter sets are collected from multiple monitoring locations. The antenna offset parameters of the base station antenna under different signal change parameters are also collected, and multiple sample antenna offset parameter sets are obtained by annotation. Based on machine learning, multiple antenna offset analysis paths with the same architecture are constructed; Multiple antenna offset analysis paths are supervised and trained using multiple sample signal change parameter sets and multiple sample antenna offset parameter sets, and integrated after convergence to obtain an antenna offset analyzer. Calculating the similarity between each antenna offset parameter and the mean of the plurality of antenna offset parameters to obtain a plurality of first offset credibility; Acquire multiple monitoring distances between multiple monitoring positions and a base station antenna, and calculate multiple second offset credibility levels, wherein the magnitude of the monitoring distance is negatively correlated with the magnitude of the second offset credibility level; A plurality of offset confidence levels are calculated based on the plurality of first offset confidence levels and the plurality of second offset confidence levels.

[0057] In one embodiment, the impact shift analysis module 300 is further configured to: Acquiring environmental parameters within an environment where the communication base station is located, wherein the environmental parameters include meteorological parameters; The environmental parameters are combined with each antenna offset parameter and input into the antenna impact offset analyzer, and a plurality of antenna impact offset parameters are obtained as output; The steps of constructing the antenna impact offset analyzer include: Based on the base station antenna operation and maintenance data in the historical period, a sample antenna offset parameter set, a sample environment parameter set, and antenna impact offset parameters under the influence of different sample antenna offset parameters and sample environment parameters are collected to obtain a sample antenna impact offset parameter set; Build a machine learning-based antenna impact offset analyzer; The antenna impact offset analyzer is supervised and trained using the sample antenna offset parameter set, the sample environment parameter set, and the sample antenna impact offset parameter set, and is constructed after convergence.

[0058] In one embodiment, the fault prediction module 400 is further configured to: Calculating the magnitudes by which the impact offset parameters of multiple antennas exceed the fault offset parameters respectively, and obtaining the fault scales of multiple monitoring antennas; Weights are assigned according to multiple offset credibility scores, and multiple monitoring antenna fault scales are weighted and calculated to obtain the antenna fault scale as the base station operation and maintenance fault prediction result.

[0059] In summary, the embodiments of the present application have at least the following technical effects: This application proposes a method and system for automatic fault prediction for base station operation and maintenance. By collecting signal features at multiple monitoring locations and analyzing their change parameters, the antenna fault scale is dynamically calculated in combination with environmental factors and offset credibility, which significantly improves the accuracy and reliability of early prediction of potential offset faults of base station antennas. Specifically, by extracting and comparing the change parameters of multi-position signals, it is possible to keenly capture the early weak signs of antenna physical offset; further introducing an offset credibility analysis mechanism, it effectively quantifies the reliability differences of data from different monitoring locations, and significantly reduces the interference of local noise or abnormal data on the overall judgment; by coupling environmental parameters with antenna offset parameters, it deeply analyzes the actual impact of external dynamic disturbances on antenna stability, overcoming the defects of traditional methods that view base station data in isolation and ignore the effect of environmental coupling; finally, based on the dynamic weighted calculation of offset credibility, a comprehensive antenna fault scale is calculated, so that the prediction results can not only reflect the severity of the potential offset, but also take into account the credibility of the data source, greatly improving the accuracy of the prediction conclusion. Through systematic multi-source information fusion and credibility quantification mechanism, the generalization ability and anti-interference ability of fault prediction are significantly optimized. Compared with traditional methods, the technical solution provided by this application breaks through the limitations of passive threshold alarms, realizes multi-dimensional collaborative analysis and quantitative evaluation of fault causes, and can stably output high-reliability fault warning information in complex and changeable actual deployment environments. Ultimately, it achieves the technical effect of accurately predicting base station antenna offset failures and guiding timely operation and maintenance under environmental interference.

[0060] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0061] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0062] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A method for automatic fault prediction for base station operation and maintenance, characterized in that: The method comprises: At multiple monitoring locations of a communication base station, multiple signal characteristics are collected, and the signal characteristic change analysis of the base station antenna is performed to obtain multiple signal change parameters; Performing base station antenna offset analysis based on multiple signal change parameters to obtain multiple antenna offset parameters, performing offset credibility analysis to obtain multiple offset credibility; Acquire environmental parameters in the environment where the communication base station is located, and perform base station antenna impact offset analysis in combination with multiple antenna offset parameters to obtain multiple antenna impact offset parameters; Based on multiple offset credibility and multiple antenna-affecting offset parameters, the antenna fault scale is calculated and used as the base station operation and maintenance fault prediction result.

2. The automatic fault prediction method for base station operation and maintenance according to claim 1, characterized in that: At multiple monitoring locations of the communication base station, multiple signal characteristics are collected, and the signal characteristic changes of the base station antenna are analyzed to obtain multiple signal change parameters, including: collecting a plurality of signal characteristics at a plurality of monitoring locations of a communication base station, wherein the signal characteristics include signal quality; Acquiring a plurality of standard signal characteristics at a plurality of monitoring locations; The change amplitudes of the plurality of signal features and the plurality of standard signal features are calculated respectively to obtain a plurality of signal change parameters.

3. The automatic fault prediction method for base station operation and maintenance according to claim 1, characterized in that: Perform base station antenna offset analysis based on multiple signal change parameters to obtain multiple antenna offset parameters, perform offset credibility analysis to obtain multiple offset credibility levels, including: Inputting each signal variation parameter into an antenna offset analyzer, and outputting a plurality of antenna offset parameters, wherein each antenna offset parameter includes an offset direction and an offset scale; Calculating the similarity between each antenna offset parameter and the mean of the plurality of antenna offset parameters to obtain a plurality of first offset credibility; Acquire multiple monitoring distances between multiple monitoring positions and a base station antenna, and calculate multiple second offset credibility levels, wherein the magnitude of the monitoring distance is negatively correlated with the magnitude of the second offset credibility level; A plurality of offset confidence levels are calculated based on the plurality of first offset confidence levels and the plurality of second offset confidence levels.

4. The automatic fault prediction method for base station operation and maintenance according to claim 3, characterized in that: The steps of obtaining the antenna offset analyzer include: Based on the offset operation and maintenance data of the base station antenna over a historical period, multiple sample signal change parameter sets are collected from multiple monitoring locations. The antenna offset parameters of the base station antenna under different signal change parameters are also collected, and multiple sample antenna offset parameter sets are obtained by annotation. Based on machine learning, multiple antenna offset analysis paths with the same architecture are constructed; Multiple antenna offset analysis paths are supervised and trained using multiple sample signal change parameter sets and multiple sample antenna offset parameter sets respectively. After convergence, they are integrated to obtain an antenna offset analyzer.

5. The automatic fault prediction method for base station operation and maintenance according to claim 1, characterized in that: Acquiring environmental parameters within the environment where the communication base station is located, and performing base station antenna impact offset analysis in combination with multiple antenna offset parameters to obtain multiple antenna impact offset parameters, including: Acquiring environmental parameters within an environment where the communication base station is located, wherein the environmental parameters include meteorological parameters; The environmental parameters are respectively combined with each antenna offset parameter and input into the antenna impact offset analyzer, and a plurality of antenna impact offset parameters are obtained as output.

6. The automatic fault prediction method for base station operation and maintenance according to claim 5, characterized in that: The steps of constructing the antenna impact offset analyzer include: Based on the base station antenna operation and maintenance data in the historical period, a sample antenna offset parameter set, a sample environment parameter set, and antenna impact offset parameters under the influence of different sample antenna offset parameters and sample environment parameters are collected to obtain a sample antenna impact offset parameter set; Build a machine learning-based antenna impact offset analyzer; The antenna impact offset analyzer is supervised and trained using the sample antenna offset parameter set, the sample environment parameter set, and the sample antenna impact offset parameter set, and is constructed after convergence.

7. The automatic fault prediction method for base station operation and maintenance according to claim 1, characterized in that: Based on multiple offset credibility factors and multiple antenna-affecting offset parameters, the antenna fault scale is calculated and used as the base station operation and maintenance fault prediction result, including: Calculating the magnitudes by which the impact offset parameters of multiple antennas exceed the fault offset parameters respectively, and obtaining the fault scales of multiple monitoring antennas; Weights are assigned according to multiple offset credibility scores, and multiple monitoring antenna fault scales are weighted and calculated to obtain the antenna fault scale as the base station operation and maintenance fault prediction result.

8. An automatic fault prediction system for base station operation and maintenance, characterized in that: A system for implementing the automatic fault prediction method for base station operation and maintenance according to any one of claims 1 to 7, comprising: A signal feature analysis module is used to collect multiple signal features at multiple monitoring locations of a communication base station, analyze changes in the signal features of the base station antenna, and obtain multiple signal change parameters; A credibility analysis module is used to perform base station antenna offset analysis based on multiple signal change parameters to obtain multiple antenna offset parameters, perform offset credibility analysis, and obtain multiple offset credibility; An impact offset analysis module is used to obtain environmental parameters in the environment where the communication base station is located, and perform base station antenna impact offset analysis in combination with multiple antenna offset parameters to obtain multiple antenna impact offset parameters; The fault prediction module is used to calculate the antenna fault scale based on multiple offset credibility and multiple antenna impact offset parameters as the base station operation and maintenance fault prediction result.

Images