Communication equipment fault type diagnosis method and device based on electric signals

Abstract

The invention belongs to the field of intelligent operation and maintenance of communication equipment, and particularly discloses a communication equipment fault type diagnosis method and device based on an electric signal, and the method comprises the steps: obtaining the electric signal data of the communication equipment under different working conditions and different function module fault combinations; extracting fault features, and constructing fault feature data sets of the first working condition and the second working condition; constructing a fault type sensing model corresponding to the first working condition based on a one-dimensional convolutional neural network, and training the fault type sensing model corresponding to the first working condition based on the fault feature data set of the first working condition; adjusting a network structure and parameters of a fault type sensing model corresponding to the first working condition based on the fault feature data sets of the first working condition and the second working condition, and obtaining a fault type sensing model corresponding to the second working condition; and inputting the electric signal data of the to-be-diagnosed communication equipment into the trained fault type sensing model corresponding to the first working condition or the second working condition to obtain a fault type diagnosis result of the to-be-diagnosed communication equipment.

Description

Technical Field

[0001] The present application relates to the field of intelligent operation and maintenance of communication equipment, and more specifically, to a method and device for diagnosing the fault type of communication equipment based on electrical signals. Background Art

[0002] In the prior art, the fault type of communication equipment is usually diagnosed based on the vibration signal of the equipment. However, the vibration sensor that collects the vibration signal requires a complicated installation and debugging process, and the vibration signal is greatly affected by the interference of the external environment, which makes the reliability and stability of the fault type diagnosis results of the communication equipment poor. Summary of the invention

[0003] In view of the defects of the prior art, the purpose of the present application is to provide a method and device for diagnosing the fault type of communication equipment based on electrical signals, aiming to solve the problem of poor reliability and stability caused by the prior art of diagnosing the fault type of communication equipment based on equipment vibration signals.

[0004] To achieve the above objectives, the present application provides a method for diagnosing the fault type of communication equipment based on electrical signals, comprising:

[0005] Obtain electrical signal data of communication equipment under different working conditions and different functional module failure combinations;

[0006] Extracting fault features of the electrical signal data, and constructing a fault feature data set of a first working condition and a fault feature data set of a second working condition;

[0007] Building a fault type perception model corresponding to the first working condition based on a one-dimensional convolutional neural network, and training the fault type perception model corresponding to the first working condition based on a fault feature data set of the first working condition;

[0008] Based on the fault feature data set of the first working condition and the fault feature data set of the second working condition, adjusting the network structure and parameters of the fault type perception model corresponding to the first working condition after training, to obtain the fault type perception model corresponding to the second working condition;

[0009] The electrical signal data of the communication equipment to be diagnosed is input into the fault type perception model corresponding to the first working condition or the fault type perception model corresponding to the second working condition that has been trained to obtain the fault type diagnosis result of the communication equipment to be diagnosed.

[0010] According to the communication equipment fault type diagnosis method based on electrical signals provided by the present invention, the network structure and parameters of the fault type perception model corresponding to the first working condition that has been trained are adjusted based on the fault feature data set of the first working condition and the fault feature data set of the second working condition to obtain the fault type perception model corresponding to the second working condition, including:

[0011] Inputting the fault feature data set of the first working condition and the fault feature data set of the second working condition into the fault type perception model corresponding to the first working condition that has been trained;

[0012] Obtaining feature distribution distances of the fault feature data of the first working condition and the fault feature data of the second working condition on each convolutional layer and the fully connected layer in the fault type perception model corresponding to the trained first working condition;

[0013] Based on the feature distribution distance, part or all of the convolutional layers and fully connected layers in the fault type perception model corresponding to the first working condition that has been trained are migrated to the initial fault type perception model corresponding to the second working condition, and the convolutional layers and fully connected layers that are not migrated are initialized and the initial fault type perception model corresponding to the second working condition is completed;

[0014] Based on the fault feature data set of the second operating condition, an initial fault type perception model corresponding to the second operating condition is trained to obtain a fault type perception model corresponding to the second operating condition.

[0015] According to the communication equipment fault type diagnosis method based on electrical signals provided by the present invention, the extracting fault characteristics of the electrical signal data includes:

[0016] The frequency domain features and time domain features of the electrical signal data are extracted.

[0017] According to the communication equipment fault type diagnosis method based on electrical signals provided by the present invention, the frequency domain features include one or more of the following:

[0018] Center of gravity frequency, mean frequency, frequency root mean square, frequency variance.

[0019] According to the communication equipment fault type diagnosis method based on electrical signals provided by the present invention, the time domain features include one or more of the following:

[0020] The maximum value of the electrical signal data, the maximum absolute value of the electrical signal data, the minimum value of the electrical signal data, the mean value of the electrical signal data, the peak-to-peak value of the electrical signal data, the absolute mean value of the electrical signal data, the root mean square value of the electrical signal data, the root square amplitude of the electrical signal data, the standard deviation of the electrical signal data, the kurtosis of the electrical signal data, the skewness of the electrical signal data, the margin index of the electrical signal data, the waveform index of the electrical signal data, the pulse index of the electrical signal data, and the peak index of the electrical signal data.

[0021] According to the communication equipment fault type diagnosis method based on electrical signals provided by the present invention, after extracting the fault characteristics of the electrical signal data, the method further includes:

[0022] The fault characteristics are normalized.

[0023] In a second aspect, the present application provides a communication equipment fault type diagnosis device based on electrical signals, comprising:

[0024] An acquisition module is used to acquire electrical signal data of communication equipment under different working conditions and different functional module failure combinations;

[0025] An extraction module, used to extract the fault characteristics of the electrical signal data, and construct a fault characteristic data set of a first working condition and a fault characteristic data set of a second working condition;

[0026] A training module, used to construct a fault type perception model corresponding to the first working condition based on a one-dimensional convolutional neural network, and to train the fault type perception model corresponding to the first working condition based on a fault feature data set of the first working condition;

[0027] An adjustment module, configured to adjust the network structure and parameters of the fault type perception model corresponding to the first working condition after training based on the fault feature data set of the first working condition and the fault feature data set of the second working condition, so as to obtain the fault type perception model corresponding to the second working condition;

[0028] The diagnosis module is used to input the electrical signal data of the communication equipment to be diagnosed into the fault type perception model corresponding to the first working condition or the fault type perception model corresponding to the second working condition that has been trained to obtain the fault type diagnosis result of the communication equipment to be diagnosed.

[0029] In a third aspect, the present application provides an electronic device comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory. When the programs stored in the memory are executed, the processor is used to execute the communication equipment fault type diagnosis method based on electrical signals described in the first aspect or any possible implementation method of the first aspect.

[0030] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the communication equipment fault type diagnosis method based on electrical signals described in the first aspect or any possible implementation of the first aspect.

[0031] In a fifth aspect, the present application provides a computer program product, which, when executed on a processor, enables the processor to execute the communication equipment fault type diagnosis method based on electrical signals as described in the first aspect or any possible implementation of the first aspect.

[0032] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0033] In general, the above technical solutions conceived by this application have the following beneficial effects compared with the prior art:

[0034] (1) By diagnosing communication equipment faults based on electrical signals, compared with the existing equipment fault diagnosis method based on vibration signals, since the internal electrical signals of the equipment are less affected by external environmental interference, it can provide more stable and reliable data support for equipment fault diagnosis, improve the reliability and stability of communication equipment fault diagnosis, and the electrical signal acquisition sensor only needs to be installed on the equipment bus, which is simple to install and has low maintenance costs.

[0035] (2) By constructing a fault type perception model based on deep transfer learning, the fault type perception model under conditions with more fault data is transferred to the fault type perception model under conditions with less fault data, thereby solving the problem of scarce fault sample data under different working conditions, realizing rapid and accurate classification of fault types of communication equipment under different working conditions, and improving the reliability and stability of fault diagnosis of communication equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 It is a flow chart of a method for diagnosing a fault type of communication equipment based on electrical signals provided in an embodiment of the present application;

[0038] Figure 2 It is a schematic diagram of fault current, voltage and power electrical signal data of communication equipment provided in an embodiment of the present application;

[0039] Figure 3 is a structural schematic diagram of a fault type perception model corresponding to the first working condition provided in an embodiment of the present application;

[0040] Figure 4 It is a schematic diagram of comparison results between the predicted value and the true value of the fault type perception model corresponding to the first working condition provided in an embodiment of the present application;

[0041] Figure 5 It is a schematic diagram of comparison results between the predicted value and the actual value of the fault type perception model corresponding to the second working condition provided in an embodiment of the present application;

[0042] Figure 6 It is a structural schematic diagram of a communication equipment fault type diagnosis device based on electrical signals provided in an embodiment of the present application;

[0043] Figure 7 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0045] The term "and / or" in this article is a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The symbol " / " in this article indicates that the associated objects are in an or relationship, for example, A / B means A or B.

[0046] The terms "first" and "second" in the specification and claims herein are used to distinguish different objects rather than to describe a specific order of the objects. For example, a first response message and a second response message are used to distinguish different response messages rather than to describe a specific order of the response messages.

[0047] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0048] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two. For example, multiple processing units refer to two or more processing units, etc.; multiple elements refer to two or more elements, etc.

[0049] First, the following contents are introduced:

[0050] Communication equipment has a complex internal structure and a harsh working environment. Faults are sudden and uncontrollable. Therefore, in order to ensure the normal operation of communication equipment, improve equipment utilization and reduce maintenance costs, it is extremely important to study the fault type perception of communication equipment in working condition.

[0051] Communication equipment is a complex circuit system composed of multiple functional modules coupled together. Current, voltage and power are the three major types of signals that measure whether the circuit system is operating normally. They can provide an important basis for diagnosing potential faults in the circuit system.

[0052] By accurately measuring these signals and analyzing them with intelligent diagnostic methods, hidden fault feature information can be discovered and fault prediction can be performed. In the prior art, the fault type of communication equipment is usually diagnosed based on the equipment vibration signal. The fault diagnosis method based on equipment vibration signal is mainly applicable to mechanical equipment. The vibration sensor that collects the vibration signal requires a complex installation and debugging process, and the vibration signal is greatly affected by the external environment. This makes the reliability and stability of the diagnosis results of the fault type of communication equipment poor.

[0053] In view of the above-mentioned defects, the purpose of the present application is to provide a method and device for diagnosing the fault type of communication equipment based on electrical signals, aiming to solve the problems of poor reliability and stability caused by the prior art of diagnosing the fault type of communication equipment based on equipment vibration signals.

[0054] Next, combine Figure 1-Figure 5 The communication equipment fault type diagnosis method based on electrical signals provided in the embodiment of the present application is introduced.

[0055] Figure 1 FIG. 1 is a flow chart of a method for diagnosing a fault type of communication equipment based on electrical signals provided in an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0056] Step 100, obtaining electrical signal data of the communication equipment under different working conditions and different functional module failure combinations;

[0057] Since different functional modules of communication equipment may fail in different working conditions, in order to make the fault data more diverse and comprehensive and to improve the reliability of the diagnosis of communication equipment fault types, the electrical signal data of the communication equipment under different working conditions and different functional module fault combinations can be obtained.

[0058] Optionally, the electrical signal data may include voltage signal data, current signal data, power signal data, and the like.

[0059] Figure 2 is a schematic diagram of fault current, voltage and power electrical signal data of communication equipment provided in an embodiment of the present application, such as Figure 2 As shown, in one embodiment of the present application, an electrical signal sensor is installed in the communication equipment to collect equipment fault electrical signal data of the communication equipment under different working conditions and different functional module fault combinations.

[0060] Optionally, after obtaining the electrical signal data, a fault type label may be marked according to the fault condition of the functional module.

[0061] Step 110, extracting fault features of the electrical signal data, and constructing a fault feature data set of a first working condition and a fault feature data set of a second working condition;

[0062] Optionally, after obtaining the electrical signal data, a feature extraction algorithm may be used to extract fault features of the electrical signal data, and the fault features may be divided into a fault feature data set of a first working condition and a fault feature data set of a second working condition according to the working condition.

[0063] In one embodiment of the present application, the first operating condition and the second operating condition may be a bus communication operating condition and a wireless communication operating condition.

[0064] Step 120, constructing a fault type perception model corresponding to the first working condition based on a one-dimensional convolutional neural network, and training the fault type perception model corresponding to the first working condition based on a fault feature data set of the first working condition;

[0065] The present application utilizes a one-dimensional convolutional neural network (CNN) to construct a fault type perception model corresponding to the first operating condition.

[0066] Figure 3 is a structural diagram of a fault type perception model corresponding to the first working condition provided in an embodiment of the present application, such as Figure 3 As shown in the figure, the convolution layer and pooling layer of the fault type perception model corresponding to the first working condition are both one-dimensional structures, including 2 convolution layers, two pooling layers and two fully connected layers. The one-dimensional fault feature signal is directly used as input, and then forward propagation is performed. Features are extracted layer by layer through alternating convolution layers and pooling layers, and the extracted features are globally integrated through the fully connected layers. The Softmax classifier is used for classification, and the cross entropy measurement of the difference between the output probability distribution of the Softmax function and the probability distribution of the fault category is used as the loss function.

[0067] The calculation formula of cross entropy is:

[0068]

[0069] Where p(x) is the true classification result of sample x, and q(x) is the Softmax output classification result of sample x.

[0070] After constructing the fault type perception model corresponding to the first working condition, the fault type perception model corresponding to the first working condition is trained based on the fault feature data set of the first working condition.

[0071] Specifically, the fault feature data set of the first working condition is divided into a training set and a test set. The training set is used to train the fault type perception model corresponding to the first working condition, and the test set is used to verify the robustness and generalization ability of the trained model.

[0072] In one embodiment of the present application, the model training parameters are set as follows:

[0073] CNN architecture: input layer-convolution layer-max pooling layer-convolution layer-max pooling layer-linear layer-output layer.

[0074] Parameter settings: learning rate is 0.001; batch size is 32; activation function is Relu function; optimizer is Adam; loss function is cross entropy function.

[0075] Regularization strategy: dropout is 0.5; both the training set and the test set must be regularized before entering the model.

[0076] Model training: The training set is input into the model. The number of training iterations (epochs) is 500. The cross entropy function and optimizer are used to continuously modify the model weights.

[0077] Model validation: Input the test set into the trained CNN model to compare the actual classification results with the predicted results.

[0078] Figure 4 is a schematic diagram of the comparison results of the predicted value and the true value of the fault type perception model corresponding to the first working condition provided in the embodiment of the present application, such as Figure 4 As shown, in one embodiment of the present application, Figure 4 The comparison results between the predicted value and the actual value of the fault type perception model corresponding to the first working condition are illustrated.

[0079] Step 130, based on the fault feature data set of the first working condition and the fault feature data set of the second working condition, adjusting the network structure and parameters of the fault type perception model corresponding to the first working condition that has been trained, to obtain the fault type perception model corresponding to the second working condition;

[0080] The present application adopts a transfer learning strategy to transfer the knowledge learned by the fault type perception model corresponding to the first working condition to the second working condition, and obtains the fault type perception model corresponding to the second working condition by adjusting the network structure and parameters of the fault type perception model corresponding to the first working condition. This strategy can solve the problem of difficulty in fault type identification due to the uneven distribution of fault feature data under different working conditions of communication equipment and only a small amount of labeled data.

[0081] Figure 5 : is a schematic diagram of the comparison results of the predicted value and the true value of the fault type perception model corresponding to the second working condition provided in the embodiment of the present application, such as Figure 5 As shown, in one embodiment of the present application, Figure 5 The comparison results between the predicted value and the actual value of the fault type perception model corresponding to the second working condition are illustrated.

[0082] Step 140 , input the electrical signal data of the communication equipment to be diagnosed into the trained fault type perception model corresponding to the first working condition or the fault type perception model corresponding to the second working condition, to obtain a fault type diagnosis result of the communication equipment to be diagnosed.

[0083] After the fault type perception models corresponding to the first working condition and the second working condition are trained, the electrical signal equipment of the communication equipment to be detected can be input into the corresponding model to obtain its fault type.

[0084] The communication equipment fault type diagnosis method based on electrical signals provided by the present invention performs fault diagnosis on the communication equipment based on electrical signals. Compared with the existing equipment fault diagnosis method based on vibration signals, since the internal electrical signals of the equipment are less affected by the interference of the external environment, more stable and reliable data support can be provided for equipment fault diagnosis, thereby improving the reliability and stability of communication equipment fault diagnosis. Moreover, the electrical signal acquisition sensor only needs to be installed on the equipment bus, and its installation is simple and the maintenance cost is low. By constructing a fault type perception model based on deep transfer learning, the fault type perception model under the working condition with more fault data is transferred to the fault type perception model under the working condition with less fault data, thereby solving the problem of scarcity of fault sample data under different working conditions, realizing rapid and accurate classification of fault types of communication equipment under different working conditions, and improving the reliability and stability of communication equipment fault diagnosis.

[0085] In some embodiments, step 130 specifically includes:

[0086] Step 1301, inputting the fault feature data set of the first working condition and the fault feature data set of the second working condition into the fault type perception model corresponding to the first working condition that has been trained;

[0087] Step 1302, obtaining the feature distribution distance of the fault feature data of the first working condition and the fault feature data of the second working condition on each convolutional layer and the fully connected layer in the fault type perception model corresponding to the first working condition after training;

[0088] In one embodiment of the present application, the maximum mean discrepancy (MMD) is used to measure the feature distribution distance between the fault feature data of the first working condition and the fault feature data of the second working condition on each convolutional layer and the fully connected layer in the fault type perception model corresponding to the first working condition after training.

[0089] Step 1303: Based on the feature distribution distance, part or all of the convolutional layers and fully connected layers in the fault type perception model corresponding to the first working condition that has been trained are migrated to the initial fault type perception model corresponding to the second working condition, and the convolutional layers and fully connected layers that are not migrated are initialized and the initial fault type perception model corresponding to the second working condition is completed;

[0090] Optionally, the feature distribution distance may be compared with a preset threshold. When the feature distribution distance is less than the preset threshold, it is considered that the convolutional layer or the fully connected layer can be migrated, otherwise it is not migrated.

[0091] In one embodiment of the present application, the preset threshold is set to 0.1, that is, the convolutional layer or the fully connected layer with a feature distribution distance less than 0.1 can be migrated, otherwise it will not be migrated.

[0092] Step 1304: Based on the fault feature data set of the second operating condition, an initial fault type perception model corresponding to the second operating condition is trained to obtain a fault type perception model corresponding to the second operating condition.

[0093] Specifically, the fault feature data set of the second working condition is divided into a training set and a test set. The training set is used to train the fault type perception model corresponding to the second working condition, and the test set is used to verify the robustness and generalization ability of the trained model.

[0094] In some embodiments, step 110 specifically includes:

[0095] Step 1101: extract frequency domain features and time domain features of electrical signal data.

[0096] Optionally, Fourier transform and time domain analysis method can be used to extract frequency domain features and time domain features of the electrical signal data.

[0097] In some embodiments, the frequency domain features in step 1101 include one or more of the following:

[0098] Center of gravity frequency, mean frequency, frequency root mean square, frequency variance.

[0099] Among them, the calculation formula of the center of gravity frequency F1 is expressed as:

[0100]

[0101] Where S(k) is the spectrum sequence of the voltage, current and power time domain signal sequence, K is the number of spectral lines, and f k is the frequency value of the kth spectral line.

[0102] The calculation formula of average frequency F2 is expressed as:

[0103]

[0104] Where S(k) is the spectrum sequence of the voltage, current and power time domain signal sequence, and K is the number of spectrum lines.

[0105] The frequency root mean square F3 calculation formula is expressed as:

[0106]

[0107] Where S(k) is the spectrum sequence of the voltage, current and power time domain signal sequence, K is the number of spectral lines, and f k is the frequency value of the kth spectral line.

[0108] The frequency variance F4 calculation formula is expressed as:

[0109]

[0110] Where S(k) is the spectrum sequence of the voltage, current and power time domain signal sequence, K is the number of spectral lines, and f k is the frequency value of the kth spectral line.

[0111] In some embodiments, the time domain features in step 1101 include one or more of the following:

[0112] The maximum value of the electrical signal data, the maximum absolute value of the electrical signal data, the minimum value of the electrical signal data, the mean value of the electrical signal data, the peak-to-peak value of the electrical signal data, the absolute mean value of the electrical signal data, the root mean square value of the electrical signal data, the root square amplitude of the electrical signal data, the standard deviation of the electrical signal data, the kurtosis of the electrical signal data, the skewness of the electrical signal data, the margin index of the electrical signal data, the waveform index of the electrical signal data, the pulse index of the electrical signal data, and the peak index of the electrical signal data.

[0113] Among them, the margin index F 16 The calculation formula is expressed as:

[0114]

[0115] Where X(i) is the time domain signal sequence of voltage, current and power, and N is the number of sampling points of the time domain signal sequence.

[0116] Waveform Index F 17 The calculation formula is expressed as:

[0117]

[0118] Where X(i) is the time domain signal sequence of voltage, current and power, and N is the number of sampling points of the time domain signal sequence.

[0119] Pulse Index F 18 The calculation formula is expressed as:

[0120]

[0121] Where X(i) is the time domain signal sequence of voltage, current and power, and N is the number of sampling points of the time domain signal sequence.

[0122] Peak Index F 19The calculation formula is expressed as:

[0123]

[0124] Where X(i) is the time domain signal sequence of voltage, current and power, and N is the number of sampling points of the time domain signal sequence.

[0125] In some embodiments, after extracting the fault features of the electrical signal data in step 110, the method further includes:

[0126] Normalize the fault characteristics.

[0127] Optionally, the extracted frequency domain and time domain features may be normalized using a deviation normalization method, and the fault feature data set of the first working condition and the fault feature data set of the second working condition may be constructed in combination with the fault type label information.

[0128] The deviation normalization conversion function can be expressed as:

[0129]

[0130] Where max is the maximum value of the frequency domain and time domain feature data, and min is the minimum value of the frequency domain and time domain feature data.

[0131] Combine the following Figure 6 The communication equipment fault type diagnosis device based on electrical signals provided by the present invention is described. The communication equipment fault type diagnosis device based on electrical signals described below and the communication equipment fault type diagnosis method based on electrical signals described above can be referenced to each other.

[0132] Figure 6 FIG. 1 is a schematic diagram of a communication equipment fault type diagnosis device based on electrical signals provided in an embodiment of the present application. Figure 6 As shown, the device includes an acquisition module 610, an extraction module 620, a training module 630, an adjustment module 640 and a diagnosis module 650, wherein:

[0133] An acquisition module 610 is used to acquire electrical signal data of the communication equipment under different working conditions and different functional module failure combinations;

[0134] An extraction module 620, used to extract fault features of the electrical signal data, and construct a fault feature data set of a first working condition and a fault feature data set of a second working condition;

[0135] A training module 630 is used to construct a fault type perception model corresponding to the first working condition based on a one-dimensional convolutional neural network, and to train the fault type perception model corresponding to the first working condition based on a fault feature data set of the first working condition;

[0136] An adjustment module 640 is used to adjust the network structure and parameters of the fault type perception model corresponding to the first working condition after training based on the fault feature data set of the first working condition and the fault feature data set of the second working condition, so as to obtain the fault type perception model corresponding to the second working condition;

[0137] The diagnosis module 650 is used to input the electrical signal data of the communication equipment to be diagnosed into the fault type perception model corresponding to the first working condition or the fault type perception model corresponding to the second working condition that has been trained to obtain the fault type diagnosis result of the communication equipment to be diagnosed.

[0138] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, which will not be repeated here.

[0139] Based on the method in the above embodiment, Figure 7 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 7 As shown, an embodiment of the present application provides an electronic device, which may include: a processor 710, a communication interface 720, a memory 730 and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the communication equipment fault type diagnosis method based on electrical signals in the above embodiment.

[0140] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the communication equipment fault type diagnosis method based on electrical signals described in various embodiments of the present application.

[0141] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the communication equipment fault type diagnosis method based on electrical signals in the above embodiment.

[0142] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the communication equipment fault type diagnosis method based on electrical signals in the above embodiment.

[0143] It is understandable that the processor in the embodiment of the present application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor can be a microprocessor or any conventional processor.

[0144] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0145] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0146] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0147] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for diagnosing fault types of communication equipment based on electrical signals, characterized in that: include: Acquire electrical signal data of communication equipment under different working conditions and different functional module fault combinations; Extracting fault features from the electrical signal data to construct a fault feature data set for a first operating condition and a fault feature data set for a second operating condition; Constructing a fault type perception model corresponding to a first operating condition based on a one-dimensional convolutional neural network, and training the fault type perception model corresponding to the first operating condition based on a fault feature dataset of the first operating condition; Based on the fault feature data set of the first working condition and the fault feature data set of the second working condition, adjusting the network structure and parameters of the fault type perception model corresponding to the first working condition that has been trained, to obtain a fault type perception model corresponding to the second working condition; The electrical signal data of the communication equipment to be diagnosed is input into the fault type perception model corresponding to the first working condition or the fault type perception model corresponding to the second working condition that has been trained to obtain a fault type diagnosis result of the communication equipment to be diagnosed.

2. The method for diagnosing fault types of communication equipment based on electrical signals according to claim 1, characterized in that: The method of adjusting the network structure and parameters of the trained fault type perception model corresponding to the first working condition based on the fault feature dataset of the first working condition and the fault feature dataset of the second working condition to obtain the fault type perception model corresponding to the second working condition includes: Inputting the fault feature data set of the first working condition and the fault feature data set of the second working condition into the fault type perception model corresponding to the first working condition that has been trained; Obtaining feature distribution distances of the fault feature data of the first working condition and the fault feature data of the second working condition on each convolutional layer and the fully connected layer in the fault type perception model corresponding to the trained first working condition; Based on the feature distribution distance, some or all of the convolutional layers and fully connected layers in the fault type perception model corresponding to the first working condition that has been trained are migrated to the initial fault type perception model corresponding to the second working condition, and the convolutional layers and fully connected layers that are not migrated are initialized and used to complete the initial fault type perception model corresponding to the second working condition; Based on the fault feature data set of the second working condition, an initial fault type perception model corresponding to the second working condition is trained to obtain a fault type perception model corresponding to the second working condition.

3. The method for diagnosing fault types of communication equipment based on electrical signals according to claim 1 or 2, characterized in that: The extracting the fault characteristics of the electrical signal data includes: The frequency domain features and time domain features of the electrical signal data are extracted.

4. The method for diagnosing fault types of communication equipment based on electrical signals according to claim 3, characterized in that: The frequency domain features include one or more of the following: Center of gravity frequency, mean frequency, root mean square frequency, frequency variance.

5. The method for diagnosing fault types of communication equipment based on electrical signals according to claim 3, characterized in that: The time domain characteristics include one or more of the following: The maximum value of the electrical signal data, the maximum absolute value of the electrical signal data, the minimum value of the electrical signal data, the mean value of the electrical signal data, the peak-to-peak value of the electrical signal data, the absolute mean value of the electrical signal data, the root mean square value of the electrical signal data, the root square amplitude of the electrical signal data, the standard deviation of the electrical signal data, the kurtosis of the electrical signal data, the skewness of the electrical signal data, the margin index of the electrical signal data, the waveform index of the electrical signal data, the pulse index of the electrical signal data, and the peak index of the electrical signal data.

6. The method for diagnosing fault types of communication equipment based on electrical signals according to claim 1 or 3, characterized in that: After extracting the fault characteristics of the electrical signal data, the method further includes: Normalization processing is performed on the fault characteristics.

7. A communication equipment fault type diagnosis device based on electrical signals, characterized in that: include: An acquisition module is used to obtain electrical signal data of communication equipment under different working conditions and different functional module fault combinations; An extraction module, configured to extract fault features from the electrical signal data and construct a fault feature data set for a first operating condition and a fault feature data set for a second operating condition; a training module, configured to construct a fault type perception model corresponding to a first operating condition based on a one-dimensional convolutional neural network, and train the fault type perception model corresponding to the first operating condition based on a fault feature dataset of the first operating condition; an adjustment module, configured to adjust the network structure and parameters of the trained fault type perception model corresponding to the first operating condition based on the fault feature dataset of the first operating condition and the fault feature dataset of the second operating condition, to obtain a fault type perception model corresponding to the second operating condition; The diagnostic module is used to input the electrical signal data of the communication equipment to be diagnosed into the fault type perception model corresponding to the first working condition or the fault type perception model corresponding to the second working condition that has been trained to obtain the fault type diagnosis result of the communication equipment to be diagnosed.

8. An electronic device, characterized in that: include: at least one memory for storing a computer program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the communication equipment fault type diagnosis method based on electrical signals as described in any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed on a processor, the processor is enabled to execute the method for diagnosing fault types of communication equipment based on electrical signals according to any one of claims 1 to 6.

10. A computer program product, characterized in that When the computer program product runs on a processor, the processor is enabled to execute the communication equipment fault type diagnosis method based on electrical signals according to any one of claims 1 to 6.

Images