Fault detection method and device, electronic equipment, storage medium and product

Abstract

The invention discloses a fault detection method and device, electronic equipment, a storage medium and a product. Relates to the technical field of data processing. The fault detection method comprises the following steps: acquiring power supply state data, link state data and power state data of a radio remote unit, and taking the power supply state data, the link state data and the power state data as target monitoring data; determining a fault state judgment parameter corresponding to the target monitoring data based on a preset fault detection model; and determining the fault type of the remote radio unit according to the fault state judgment parameter. According to the embodiment of the invention, the method achieves the real-time and quick recognition of the fault type of the remote radio unit, and improves the recognition efficiency of the fault type of the remote radio unit. And meanwhile, the problem of high cost of manual troubleshooting is reduced.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a fault detection method, apparatus, electronic device, storage medium, and product. Background Technology

[0002] As a key remote device for base station signal transmission and reception, the failure of the Remote Radio Unit (RRU) will directly affect network services. In order to ensure the coverage quality and operational stability of the mobile communication network, it is necessary to perform real-time fault detection on the RRU.

[0003] Traditional RRU fault diagnosis relies on manual on-site inspection, which is inefficient and costly. Alternatively, multiple inspection items can be set up to detect faults in the RRU, and a weighted value can be assigned to the nodes involved in each inspection item based on the inspection results. Finally, the weighted values ​​of each node are summed to obtain the weighted result, and the node with the highest weighted result is located as the faulty node. RRU fault location is achieved through joint detection of multiple inspection items. However, current technologies for RRU fault detection lack real-time capability, and the detection methods are fixed and cannot be learned and updated. Therefore, how to perform RRU fault detection in a real-time and convenient manner has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a fault detection method, device, electronic device, storage medium, and product to solve the problem that existing technologies cannot detect RRU faults in real time and conveniently.

[0005] According to one aspect of the present invention, a fault detection method is provided, wherein the method includes:

[0006] Acquire power supply status data, link status data, and power status data of the radio frequency remote unit, and use the power supply status data, link status data, and power status data as target monitoring data;

[0007] The fault status judgment parameters corresponding to the target monitoring data are determined based on a preset fault detection model.

[0008] The fault type of the radio frequency remote unit is determined based on the fault status determination parameters.

[0009] According to another aspect of the present invention, a fault detection device is provided, wherein the device comprises:

[0010] The data acquisition module is used to acquire the power supply status data, link status data, and power status data of the radio frequency remote unit, and to use the power supply status data, the link status data, and the power status data as target monitoring data.

[0011] The parameter determination module is used to determine the fault status judgment parameters corresponding to the target monitoring data based on a preset fault detection model.

[0012] The fault detection module is used to determine the fault type of the radio frequency remote unit based on the fault status determination parameters.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform a fault detection method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement a fault detection method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, embodiments of the present invention also provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the fault detection method of any embodiment of the present invention.

[0019] The technical solution of this invention acquires the power supply status data, link status data, and power status data of the radio frequency remote unit, uses the power supply status data, link status data, and power status data as target monitoring data, determines the fault status judgment parameters corresponding to the target monitoring data based on a preset fault detection model, and determines the fault type of the radio frequency remote unit according to the fault status judgment parameters, thereby realizing real-time and rapid identification of the fault type of the radio frequency remote unit and improving the efficiency of identifying the fault type of the radio frequency remote unit; at the same time, it reduces the problem of high cost of manual fault investigation.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a fault detection method provided in Embodiment 1 of the present invention;

[0023] Figure 2 This is a diagram of a radio frequency remote unit architecture provided in Embodiment 1 of the present invention;

[0024] Figure 3 This is a flowchart of a fault detection method provided according to Embodiment 2 of the present invention;

[0025] Figure 4 This is a power supply architecture diagram of a radio frequency remote unit according to Embodiment 3 of the present invention;

[0026] Figure 5 This is a schematic diagram of a power status data monitoring point of a radio frequency remote unit according to Embodiment 3 of the present invention;

[0027] Figure 6 This is a framework diagram of a preset fault detection model provided according to Embodiment 3 of the present invention;

[0028] Figure 7 This is a schematic diagram of the structure of a fault detection device according to Embodiment 4 of the present invention;

[0029] Figure 8 This is a schematic diagram of the structure of an electronic device that implements a fault detection method according to an embodiment of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Example 1

[0033] Figure 1 This is a flowchart of a fault detection method according to Embodiment 1 of the present invention. This embodiment is applicable to fault detection of radio frequency remote units. The method can be executed by a fault detection device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0034] S110. Acquire the power supply status data, link status data, and power status data of the radio frequency remote unit, and use the power supply status data, link status data, and power status data as target monitoring data.

[0035] The radio frequency remote unit (RF remote unit) is a key remote device in a mobile communication base station responsible for transmitting and receiving radio frequency signals and amplifying power. Its core function is to convert the digital signals from the baseband unit into transmittable radio frequency signals, and simultaneously receive radio frequency signals from user terminals (such as mobile phones) and transmit them back to the baseband unit. It is one of the core hardware components for achieving base station signal coverage. In one embodiment, Figure 2 This is a diagram of a radio frequency remote unit architecture provided in Embodiment 1 of the present invention, as follows: Figure 2As shown, the remote radio unit (RRU) may include a digital front-end chip, an RF transceiver chip, a power amplifier, a low-noise power amplifier, a clock chip, a circulator, a filter, and an antenna. The digital front-end chip is responsible for controlling the RRU, data processing, and digital intermediate frequency (IF) functions. The RF transceiver chip is responsible for digital-to-analog conversion, frequency conversion, and gain control. The power amplifier amplifies the small RF signal to achieve the required signal power intensity. The low-noise power amplifier amplifies the received small RF signal while minimizing noise. The filter removes out-of-band interference and spurious signals to ensure output signal quality. The circulator fixes the signal transmission direction. The clock chip provides the clock signal input to other chips in the RRU, such as the digital front-end chip and the RF transceiver chip.

[0036] Power supply status data can be understood as data used to detect the health of the power supply branch of the radio frequency remote unit. Generally, power supply status data can include power supply branch voltage and power supply branch current. For example, it can include the power supply branch voltage and current of the digital front-end chip; the power supply branch voltage and current of the radio frequency transceiver chip; the power supply branch voltage and current of the clock chip; the power supply branch voltage and current of the power amplifier; and the power supply branch voltage and current of the low-noise power amplifier.

[0037] Link status data can be understood as data indicating the signal operating mode, core configuration parameters, and environmental status of key modules of the radio frequency remote unit. For example, link status data may include downlink signal mode, downlink signal carrier frequency, downlink signal rated output power, downlink signal bandwidth, power amplifier operating temperature, uplink signal mode, uplink signal carrier frequency, and uplink signal bandwidth, etc.

[0038] Power status data can be understood as power monitoring parameters of key nodes in the uplink and downlink of a radio frequency remote unit. Generally, power monitoring parameters can include digital domain signal power and radio frequency domain signal power. Specifically, digital domain signal power can include the power of the downlink output signal and the power of the uplink received signal in the digital domain; radio frequency domain signal power can include the downlink output power and uplink input power of the radio frequency transceiver chip, as well as the power amplifier output power and low-noise amplifier input power of the low-noise amplifier, etc.

[0039] In this embodiment, the power supply branch voltage and current of the digital front-end chip, the power supply branch voltage and current of the RF transceiver chip, the power supply branch voltage and current of the clock chip, the power amplifier, and the low-noise power amplifier can be collected as power supply status data. The downlink signal mode, downlink signal carrier frequency, downlink signal configured rated output power, downlink signal bandwidth, power amplifier operating temperature, uplink signal mode, uplink signal carrier frequency, and uplink signal bandwidth can be collected as link status data. The power of the downlink output signal in the digital domain, the power of the uplink received signal in the digital domain, the downlink output power and uplink input power of the RF transceiver chip, and the power amplifier output power and low-noise amplifier input power of the low-noise power amplifier can be collected as power status data. The power supply status data, link status data, and power status data are used as target monitoring data. In actual operation, time intervals can be preset, and power status data, link status data, and power status data can be collected according to the preset time intervals. Generally, signal monitoring points can be set in the radio frequency remote unit to monitor the power status data, link status data, and power status data of the radio frequency remote unit in real time. In one embodiment, the target monitoring data can be in the form of feature vectors.

[0040] S120. Determine the fault status judgment parameters corresponding to the target monitoring data based on the preset fault detection model.

[0041] The preset fault detection model includes a Multi-Layer Perceptron (MLP) model. The preset fault detection model consists of an input layer, at least one hidden layer, and an output layer. The number of neurons in the input layer is consistent with the length of the input target monitoring data. The fault state determination parameter can be understood as a parameter used to determine whether the radio frequency remote unit is faulty. Generally, each fault type corresponds to one fault state determination parameter. For example, a fault state determination parameter of 0 indicates a fault, while a fault state determination parameter of 1 indicates normal operation, i.e., no fault.

[0042] In this embodiment, the feature vector form corresponding to the target monitoring data can be input into a preset fault detection model. The preset fault detection model determines the fault state determination parameters corresponding to the target monitoring data. The number of fault state determination parameters can be at least one. For example, the number of generated fault state determination parameters can be the same as the vertical dimension of the fault types, with each fault type corresponding to one fault state determination parameter. In practical applications, the target monitoring data can be input. After receiving the target monitoring data, the input layer can convert it into an input vector. The input vector can be multiplied by the weight matrix of the hidden layer of the preset fault detection model, and then a bias and activation function are added to obtain the hidden layer output. When there are multiple hidden layers, the above calculation can be repeated, and finally passed to the output layer, which maps the fault state determination parameters corresponding to each fault type for output.

[0043] S130. Determine the fault type of the radio frequency remote unit based on the fault status judgment parameters.

[0044] The fault types can include at least hardware faults and software configuration faults, such as hardware faults of digital front-end chip modules, software configuration faults of digital front-end chip modules, hardware faults of RF transceiver chip modules, software configuration faults of RF transceiver chip modules, hardware faults of power amplifier modules, hardware faults of low-noise amplifier modules, hardware faults of clock chip modules, and software configuration faults of clock chip modules.

[0045] In this embodiment, it can be determined whether a fault-corresponding parameter exists among the fault status determination parameters. If it does, the fault type corresponding to the fault-corresponding parameter is taken as the fault type of the radio frequency remote unit. Generally, there can be multiple fault types. When no fault-corresponding parameter exists, the fault type of the radio frequency remote unit can be determined to be fault-free.

[0046] In this embodiment of the invention, by acquiring the power supply status data, link status data, and power status data of the radio frequency remote unit, and using these data as target monitoring data, the fault status judgment parameters corresponding to the target monitoring data are determined based on a preset fault detection model. The fault type of the radio frequency remote unit is then determined based on the fault status judgment parameters, thereby achieving real-time and rapid identification of the fault type of the radio frequency remote unit and improving the efficiency of identifying the fault type of the radio frequency remote unit. At the same time, it reduces the high cost of manual fault diagnosis.

[0047] In one embodiment, training a preset fault model includes:

[0048] Acquire historical power supply status data, historical link status data, historical power status data, and historical fault types of the radio frequency remote unit;

[0049] Historical power supply status data, historical link status data, historical power status data, and historical fault types belonging to the same moment are used as training data.

[0050] Input the training data into the preset fault model, adjust the parameters of the preset fault model until the accuracy of the output result of the preset fault model is greater than the preset probability, and the training of the preset fault model is completed.

[0051] Historical power supply status data, historical link status data, historical power status data, and historical fault types can be obtained by simulating fault behavior through fault simulation, i.e., artificially setting certain hardware or software configuration problems. Alternatively, historical power supply status data, link status data, power status data, and fault types can be acquired as historical power supply status data, historical link status data, historical power status data, and historical fault types.

[0052] In this embodiment, historical power supply status data, historical link status data, historical power status data, and historical fault types of the radio frequency remote unit can be collected. The historical power supply status data, historical link status data, historical power status data, and historical fault types at the same time are determined as a set of training data. The training data is input into a preset fault model to obtain the model output. The difference between the predicted fault type and the actual fault type is calculated by calculating the loss function. The gradient of the loss with respect to each weight and bias is calculated backward along the network to determine the direction of parameter adjustment. The weights and biases are adjusted until the accuracy of the preset fault model's output is greater than the preset probability, thus completing the training of the preset fault model. In one embodiment, the loss function can be the cross-entropy loss function. The preset probability can be set according to user needs, such as 94%, 95%, and 96%.

[0053] In one embodiment, after determining the fault type of the radio frequency remote unit based on the fault status determination parameters, the method further includes:

[0054] Power supply status data, link status data, power status data, and fault type are used as the primary data.

[0055] Update the parameters of the preset fault model according to the first data.

[0056] In this embodiment, after determining the fault type of the radio frequency remote unit, the current power supply status data, link status data, power status data, and fault type can be used as the first data. The model can be iterated again according to the first data to update the parameters of the preset fault model and ensure the accuracy of the preset fault model.

[0057] Example 2

[0058] Figure 3This is a flowchart of a fault detection method according to Embodiment 2 of the present invention. This embodiment is a further optimization and extension based on the above embodiments, and can be combined with various optional technical solutions in the above embodiments. Figure 3 As shown, the method includes:

[0059] S210. Collect the power supply status of the target functional module in the radio frequency remote unit according to the target time interval, and use the power supply status of the target functional module as power supply status data.

[0060] The target time interval can be a pre-set time interval for acquiring power supply status data, link status data, and power status data from the remote radio unit. The target functional module includes at least a digital front-end chip, an RF transceiver chip, a clock chip, a power amplifier, and a low-noise power amplifier.

[0061] In this embodiment, the power supply branch current and power supply branch voltage of target functional modules such as digital front-end chips, RF transceiver chips, clock chips, power amplifiers, and low-noise power amplifiers can be collected at target time intervals, and the power supply branch current and power supply branch voltage of the target functional modules can be used as power supply status data.

[0062] S220. Collect downlink and uplink signal configuration parameters of the radio frequency remote unit according to the target time interval, and use the downlink and uplink signal configuration parameters as link status data.

[0063] The downlink signal configuration parameters can be understood as parameters configuring the downlink signal, such as the downlink signal mode, the downlink signal carrier frequency, the downlink signal rated output power, the downlink signal bandwidth, and the operating temperature of the power amplifier. The uplink signal configuration parameters can be understood as parameters configuring the uplink signal, such as the uplink signal mode, the uplink signal carrier frequency, and the uplink signal bandwidth. In one embodiment, the uplink and downlink signal modes may include New Radio (NR), corresponding to the remote radio unit operating under the 5G standard, and Long Term Evolution (LTE), corresponding to the remote radio unit operating under the 4G standard.

[0064] In this embodiment, downlink signal configuration parameters such as downlink signal mode, downlink signal carrier frequency, downlink signal rated output power, downlink signal bandwidth, and power amplifier operating temperature can be collected at time intervals, as well as uplink signal configuration parameters such as uplink signal mode, uplink signal carrier frequency, and uplink signal bandwidth. The downlink signal configuration parameters and uplink signal configuration parameters are used as link status data.

[0065] S230. Collect the digital domain signal power and radio frequency domain signal power of the radio frequency remote unit according to the target time interval, and use the digital domain signal power and radio frequency domain signal power as power status data.

[0066] The digital domain signal power can include at least the power of the downlink output signal in the digital domain and the power of the uplink received signal in the digital domain; the radio frequency domain signal power can include at least the downlink output power and uplink input power of the radio frequency transceiver chip, as well as the power amplifier output power and low noise amplifier input power of the low noise power amplifier.

[0067] In this embodiment, the power of the downlink output signal in the digital domain, the power of the uplink received signal in the digital domain, the downlink output power and uplink input power of the RF transceiver chip, and the power amplifier output power and low-noise amplifier input power of the low-noise amplifier can be collected at target time intervals as power status data.

[0068] S240. Input the target monitoring data into the preset detection fault model, and determine the judgment parameters corresponding to each fault state of the target monitoring data as fault state judgment parameters through the preset fault model.

[0069] The determination parameter is used to indicate whether each fault type is in a fault state. The determination parameter can include 0 and 1. When the determination parameter is 0, it can be considered a fault. When the determination parameter is 1, it can be considered normal operation, i.e., no fault.

[0070] S250. Determine whether a target type parameter exists in the fault status determination parameters.

[0071] Among them, the target type parameter can be understood as the parameter used to indicate the fault in the fault status determination parameter.

[0072] In the embodiment, it can be determined whether there is a target type parameter in the fault status determination parameters, that is, whether there is 1.

[0073] S260. When a target type parameter exists, determine the fault type corresponding to the target type parameter as the fault type of the radio frequency remote unit.

[0074] In this embodiment, since each fault type has a corresponding fault status determination parameter, when it is determined that a target type parameter exists, the fault type corresponding to the target type parameter can be determined, and the fault type corresponding to the target type parameter can be used as the fault type of the radio frequency remote unit.

[0075] S270. When the target type parameter does not exist, the fault type is determined to be no fault.

[0076] In this embodiment, when it is determined that the target type parameter does not exist, the fault type can be determined as no fault.

[0077] This invention achieves real-time acquisition of power supply status, link status, and power status data by collecting the power supply status of target functional modules in a radio frequency remote unit at target time intervals, using the power supply status of the target functional modules as power supply status data, collecting downlink and uplink signal configuration parameters of the radio frequency remote unit at target time intervals, using the downlink and uplink signal configuration parameters as link status data, and collecting digital domain signal power and radio frequency domain signal power of the radio frequency remote unit at target time intervals, using the digital domain signal power and radio frequency domain signal power as power status data. By inputting the target monitoring data into a preset fault detection model, the preset fault model determines the judgment parameters corresponding to each fault status of the target monitoring data as fault status judgment parameters. It then determines whether a target type parameter exists in the fault status judgment parameters. If a target type parameter exists, the fault type corresponding to the target type parameter is determined as the fault type of the radio frequency remote unit; if no target type parameter exists, the fault type is determined to be no fault. This achieves accurate judgment of the fault type of the radio frequency remote unit, improving the user experience.

[0078] Example 3

[0079] In one embodiment, an artificial neural network model is used as the preset fault detection model. Figure 4 This is a power supply architecture diagram of a radio frequency remote unit according to Embodiment 3 of the present invention, as shown below. Figure 4 As shown, the power supply architecture of the RF remote unit includes a digital front-end chip branch, an RF transceiver chip branch, a clock chip branch, a power amplifier branch, and a low-noise power amplifier branch. Monitoring points can be set for each power supply branch for monitoring. By adding power supply monitoring, 10 monitoring parameters can be obtained, as shown in Table 1:

[0080] Table 1 Power Supply Status Data Table

[0081]

[0082] In one embodiment, Figure 5 This is a schematic diagram of a power status data monitoring point for a radio frequency remote unit according to Embodiment 3 of the present invention, as shown below. Figure 5 As shown, the red arrows represent the power status data monitoring points added to the four modules. Parameters 11, 13, and 15 are downlink signal monitoring points. Parameters 12, 14, and 16 are uplink signal monitoring points. By adding link signal monitoring points, six monitoring parameters can be obtained, and the power status data are shown in Table 2.

[0083] Table 2 Power Status Data Table

[0084]

[0085] Finally, the link status data is determined using the signal configuration parameters of the RRU and existing monitoring parameters, including but not limited to those shown in Table 3.

[0086] Table 3 Link Status Data Table

[0087]

[0088] The above, by adding hardware monitoring and adopting the existing internal monitoring of the RRU, serves as the input layer parameters for the artificial neural network (preset fault detection model). RRU fault monitoring can be divided into two main categories: hardware faults and software configuration problems. The scope of fault detection is divided into five parts: digital front-end chip module, RF transceiver chip module, power amplifier module, low-noise amplifier module, and clock chip module. The fault types are shown below, and these fault types collectively constitute the output of the artificial neural network (preset fault detection model). In the table, a parameter of 0 indicates a fault, and a parameter of 1 indicates normal operation. For example, E_DFE_HW=0 indicates a hardware fault in the digital front-end chip module; E_DFE_HW=1 indicates that the digital front-end chip module is operating normally. Table 4 lists the possible anomaly types of the RRU.

[0089] Table 4. Exception Type Table

[0090]

[0091] In practical use, the input and output parameters of the artificial neural network can be adjusted according to the target monitoring data in the application scenario. That is, the monitoring parameters of the RRU can be selected based on the RRU in actual application, and the fault types can be added, deleted or further subdivided based on the actual RRU.

[0092] The artificial neural network model employs a multilayer perceptron model. The input layer parameters consist of the monitoring parameters of the RRU (Remote Response Unit), and the output layer parameters consist of the fault types of the RRU. The number of hidden layers and the number of neurons in each hidden layer are adjusted and optimized during practical use. Taking the RRU monitoring parameters and fault types in this embodiment as an example, the model's input layer has 24 inputs, representing the 24 monitoring parameters; the model's output layer has 8 outputs, representing the 8 fault types of the RRU. In one embodiment, Figure 6 This is a framework diagram of a preset fault detection model provided according to Embodiment 3 of the present invention. Figure 6 The diagram shows a fully connected multilayer perceptron architecture. A multilayer perceptron architecture consists of an input layer, at least one hidden layer, and an output layer.

[0093] Before actual testing, a pre-set fault detection model needs to be trained. The training of the model consists of three steps:

[0094] Step 1: Acquiring Training Data: Training data can generally be acquired in two ways. One is by simulating faults, that is, artificially setting certain hardware or software configuration problems to simulate fault behavior. The other is the accumulation of various faults during design, debugging, and maintenance. Of course, training data can be acquired through methods including but not limited to the two mentioned above.

[0095] Step 2, Model Training: The artificial neural network model is trained based on the acquired training data.

[0096] Step 3, Model Validation: The accuracy of fault detection of the artificial neural network model, which has been trained to a certain extent, is validated based on the existing training data.

[0097] If the accuracy of the trained artificial neural network model reaches a certain level, it can be applied. If the model does not reach the target accuracy for fault detection, more training data needs to be obtained and training continued until the target accuracy for fault detection is achieved.

[0098] After the model is used in the later stages, it can continuously learn based on the continuously acquired training data, thereby continuously enhancing the fault detection capability of the RRU and improving the accuracy of fault detection.

[0099] In this embodiment, an artificial neural network model is employed. The model's inherent learning characteristics allow for continuous training by acquiring training data, thereby continuously improving its fault detection capabilities. Once trained, the artificial neural network can perform real-time fault detection of the RRU based on the real-time input parameters, i.e., the monitoring parameters of the RRU.

[0100] Example 4

[0101] Figure 7 This is a schematic diagram of a fault detection device according to Embodiment 4 of the present invention. Figure 7 As shown, the device includes: a data acquisition module 71, a parameter determination module 72, and a fault detection module 73.

[0102] The data acquisition module 71 is used to acquire the power supply status data, link status data and power status data of the radio frequency remote unit, and use the power supply status data, link status data and power status data as target monitoring data.

[0103] The parameter determination module 72 is used to determine the fault status judgment parameters corresponding to the target monitoring data based on the preset fault detection model.

[0104] The fault detection module 73 is used to determine the fault type of the radio frequency remote unit based on the fault status judgment parameters.

[0105] The technical solution of this invention acquires power supply status data, link status data, and power status data of the radio frequency remote unit through a data acquisition module. This data is then used as target monitoring data. A parameter determination module determines fault status judgment parameters corresponding to the target monitoring data based on a preset fault detection model. The fault detection module determines the fault type of the radio frequency remote unit based on these fault status judgment parameters, enabling real-time and rapid identification of the fault type and improving the efficiency of fault type identification. Simultaneously, it reduces the high cost of manual fault diagnosis.

[0106] In one embodiment, the data acquisition module 71 includes:

[0107] The power supply data acquisition unit is used to collect the power supply status of the target functional modules in the radio frequency remote unit according to the target time interval, and use the power supply status of the target functional modules as power supply status data.

[0108] The link data acquisition unit is used to collect downlink signal configuration parameters and uplink signal configuration parameters of the radio frequency remote unit according to the target time interval, and use the downlink signal configuration parameters and uplink signal configuration parameters as link status data;

[0109] The power data acquisition unit is used to collect the digital domain signal power and radio frequency domain signal power of the radio frequency remote unit according to the target time interval, and use the digital domain signal power and radio frequency domain signal power as power status data.

[0110] In one embodiment, the parameter determination module 72 includes:

[0111] The parameter determination unit is used to input target monitoring data into a preset detection fault model, and determine the judgment parameters corresponding to each fault state of the target monitoring data as fault state judgment parameters through the preset fault model; wherein, the preset detection fault model includes a multilayer perceptron model.

[0112] In one embodiment, the fault detection module 73 includes:

[0113] The parameter judgment unit is used to determine whether there is a target type parameter among the fault status judgment parameters;

[0114] The first judgment unit is used to determine the fault type corresponding to the target type parameter as the fault type of the radio frequency remote unit when a target type parameter exists.

[0115] The second judgment unit is used to determine the fault type as no fault when the target type parameter does not exist.

[0116] In one embodiment, the fault detection device further includes:

[0117] The historical data acquisition module is used to acquire historical power supply status data, historical link status data, historical power status data, and historical fault types of the radio frequency remote unit;

[0118] The training data determination module is used to use historical power supply status data, historical link status data, historical power status data, and historical fault types belonging to the same moment as training data.

[0119] The module training module is used to input training data into the preset fault model, adjust the parameters of the preset fault model, and complete the training of the preset fault model until the accuracy of the output result of the preset fault model is greater than the preset probability.

[0120] In one embodiment, the fault detection device further includes:

[0121] The data determination module is used to use power supply status data, link status data, power status data, and fault type as the first data.

[0122] The parameter update module is used to update the parameters of the preset fault model according to the first data.

[0123] The fault detection device provided in the embodiments of the present invention can execute the fault detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0124] Example 5

[0125] Figure 8 This is a schematic diagram of an electronic device implementing a fault detection method according to an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0126] like Figure 8As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0127] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0128] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a fault detection method.

[0129] In some embodiments, a fault detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of a fault detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform a fault detection method by any other suitable means (e.g., by means of firmware).

[0130] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0131] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0132] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0133] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0134] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0135] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0136] In one embodiment, the present invention further includes a computer program product, which includes a computer program that, when executed by a processor, implements a fault detection method according to any embodiment of the present invention.

[0137] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0138] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0139] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A fault detection method, characterized in that, include: Acquire power supply status data, link status data, and power status data of the radio frequency remote unit, and use the power supply status data, link status data, and power status data as target monitoring data; The fault status judgment parameters corresponding to the target monitoring data are determined based on a preset fault detection model. The fault type of the radio frequency remote unit is determined based on the fault status determination parameters.

2. The method according to claim 1, characterized in that, The acquisition of power supply status data, link status data, and power status data of the radio frequency remote unit, and the use of the power supply status data, link status data, and power status data as target monitoring data, includes: The power supply status of the target functional module in the radio frequency remote unit is collected according to the target time interval, and the power supply status of the target functional module is used as power supply status data. The downlink signal configuration parameters and uplink signal configuration parameters of the radio frequency remote unit are collected according to the target time interval, and the downlink signal configuration parameters and uplink signal configuration parameters are used as link status data; The digital domain signal power and radio frequency domain signal power of the radio frequency remote unit are collected according to the target time interval, and the digital domain signal power and the radio frequency domain signal power are used as power status data.

3. The method according to claim 1, characterized in that, The step of determining the fault status judgment parameters corresponding to the target monitoring data based on the preset fault detection model includes: The target monitoring data is input into a preset fault detection model, and the preset fault model determines the judgment parameters corresponding to each fault state of the target monitoring data as fault state judgment parameters; wherein, the preset fault detection model includes a multilayer perceptron model.

4. The method according to claim 1, characterized in that, Determining the fault type of the radio frequency remote unit based on the fault status determination parameters includes: Determine whether a target type parameter exists among the fault status determination parameters; When the target type parameter exists, the fault type corresponding to the target type parameter is determined as the fault type of the radio frequency remote unit; If the target type parameter is not present, the fault type is determined to be fault-free.

5. The method according to claim 1, characterized in that, The training of the preset fault model includes: Acquire historical power supply status data, historical link status data, historical power status data, and historical fault types of the radio frequency remote unit; Historical power supply status data, historical link status data, historical power status data, and historical fault types belonging to the same moment are used as training data. The training data is input into a preset fault model, and the parameters of the preset fault model are adjusted until the accuracy of the output result of the preset fault model is greater than the preset probability, thus completing the training of the preset fault model.

6. The method according to claim 1, characterized in that, After determining the fault type of the radio frequency remote unit based on the fault status determination parameters, the method further includes: Power supply status data, link status data, power status data, and fault type are used as the primary data. Update the parameters of the preset fault model according to the first data.

7. A fault detection device, characterized in that, include: The data acquisition module is used to acquire the power supply status data, link status data, and power status data of the radio frequency remote unit, and to use the power supply status data, the link status data, and the power status data as target monitoring data. The parameter determination module is used to determine the fault status judgment parameters corresponding to the target monitoring data based on a preset fault detection model. The fault detection module is used to determine the fault type of the radio frequency remote unit based on the fault status determination parameters.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the fault detection method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the fault detection method according to any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the fault detection method according to any one of claims 1-6.

Images