Server fault diagnosis method and system and electronic equipment

Abstract

The invention provides a server fault diagnosis method and system and electronic equipment, and the method comprises the steps: obtaining the operation information of a server, the operation information comprises the vibration information and sound information of the server, and the position information corresponding to the sound information; analyzing and processing the operation information to obtain an analysis and processing result, the analysis and processing at least comprising sound pressure level analysis and fast Fourier transform, and the analysis and processing result at least comprising sound intensity and sound frequency distribution; according to the analysis processing result and a server state judgment model, whether the server breaks down or not is judged, if yes, an early warning signal is sent out, and the server state judgment model is used for judging whether the current running state of the server is normal or not. The problem that normal use of a service system is affected due to the fact that the server is located in a remote machine room and the running state of the server cannot be known in time in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the technical field of equipment monitoring, and in particular to a method, system, computer-readable storage medium and electronic device for diagnosing server failures. Background Art

[0002] In the prior art, servers are important devices for information storage and application and middleware deployment in information technology projects, and are of great significance to the production and operation of enterprises. However, due to server failures, data loss and inability to access applications may occur, which brings inconvenience to the production and operation of enterprises. In particular, remote computer rooms cannot monitor performance indicators such as processors, memory, disk I / O, and network transmission in real time, and system administrators cannot understand the system operation status in a timely manner, which is likely to cause server downtime and affect the normal use of business systems. Summary of the invention

[0003] The main purpose of the present application is to provide a method, system, computer-readable storage medium and electronic device for diagnosing server failures, so as to at least solve the problem in the prior art that the server is located in a remote computer room and the operating status of the server cannot be understood in a timely manner, which affects the normal use of the business system.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for diagnosing a server fault is provided, the method comprising: obtaining operation information of the server, the operation information comprising: vibration information, sound information of the server and position information corresponding to the sound information; analyzing and processing the operation information to obtain an analysis and processing result, the analysis and processing at least comprising: sound pressure level analysis and fast Fourier transform, the analysis and processing result at least comprising: the intensity of the sound and the frequency distribution of the sound; judging whether the server has a fault according to the analysis and processing result and a server status judgment model, and issuing a warning signal when the judgment indication is yes, the server status judgment model being used to judge whether the current operation status of the server is normal.

[0005] Optionally, obtaining the operation information of the server includes: performing two-dimensional collection of the vibration information and sound information of the server; performing three-dimensional collection of the vibration information and sound information of the server; and when the judgment indication is no, obtaining the abnormal position of the server according to the sound information and the vibration information.

[0006] Optionally, the diagnostic method further includes: establishing the server status judgment model according to the analysis and processing results and the learning algorithm.

[0007] Optionally, establishing the server status judgment model includes: obtaining multiple groups of acoustic data sets based on the analysis and processing results, each group of the acoustic data sets includes the vibration information of the server and the sound information, and the acoustic data sets include a training set and a verification set; preprocessing the acoustic data sets, the preprocessing includes at least one of the following: denoising, extracting characteristic coefficients and normalization; constructing the server status judgment model, and optimizing the parameters of the server status judgment model based on the multiple groups of the training sets and the multiple groups of the verification sets to establish the server status judgment model.

[0008] Optionally, the learning algorithm includes a machine learning algorithm and a deep learning algorithm.

[0009] According to another aspect of the present application, a server fault diagnosis system is provided, which is driven by the diagnosis method, and includes: a collection unit, used to obtain operation information of the server, the operation information includes: vibration information, sound information of the server and position information corresponding to the sound information; an analysis unit, electrically connected to the collection unit, used to analyze and process the operation information to obtain an analysis and processing result, the analysis and processing at least includes: sound pressure level analysis and fast Fourier transform, and the analysis and processing result at least includes: the intensity of the sound and the frequency distribution of the sound; a voiceprint analysis and diagnosis platform, electrically connected to the analysis unit, used to receive the analysis and processing result, the voiceprint analysis and diagnosis determines whether the server has a fault based on the analysis and processing result and a server status judgment model, and sends a warning signal when the judgment indication is yes, and the server status judgment model is used to determine whether the current operation status of the server is normal.

[0010] Optionally, the collection unit includes: a contact voiceprint collection module, a non-contact voiceprint collection module and an audio-visual device, wherein: the contact voiceprint collection module is in contact with the server to enable planar collection of the vibration information and sound information of the server; the non-contact voiceprint collection module is located within a preset range with the server as the center to enable stereoscopic collection of the vibration information and sound information of the server; the audio-visual device is electrically connected to the voiceprint analysis and diagnosis platform, and is used to obtain the abnormal position of the server according to the sound information and the vibration information when the judgment indication is no.

[0011] Optionally, the diagnostic system also includes an acoustic database, the analysis and processing results include multiple groups of acoustic data sets, the acoustic database is electrically connected to the voiceprint analysis and diagnosis platform, and the acoustic database is used to store the acoustic data sets and manage the acoustic data sets, and the management at least includes: storing historical acoustic data sets and initializing processing of real-time acoustic data sets.

[0012] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the server failure diagnosis method.

[0013] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the server failure diagnosis method.

[0014] By applying the technical solution of the present application, the diagnostic method of the above-mentioned server failure first obtains the vibration information, sound information and the location information of the above-mentioned server corresponding to the above-mentioned sound information and other operating information of the server, performs sound pressure level analysis and fast Fourier transform and other processing on the above-mentioned operating information to obtain the intensity of the above-mentioned sound and the frequency distribution of the above-mentioned sound, and judges whether the above-mentioned server has a fault at least based on the intensity of the above-mentioned sound and the frequency distribution of the above-mentioned sound, and sends out a warning signal when the judgment indication is yes. Through the diagnostic method of the present application, the operating status of the above-mentioned server can be monitored and diagnosed in real time, thereby solving the problem in the prior art that the server is located in a remote computer room and the operating status of the server cannot be timely understood, which affects the normal use of the business system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0016] Figure 1 A hardware structure block diagram of a mobile terminal for executing a method for diagnosing a server failure provided in an embodiment of the present application is shown;

[0017] Figure 2 A schematic diagram of a process flow of a method for diagnosing a server failure provided according to an embodiment of the present application is shown;

[0018] Figure 3 A structural block diagram of a server failure diagnosis system provided according to an embodiment of the present application is shown;

[0019] Figure 4 A schematic diagram of the structure of a server failure diagnosis system provided according to an embodiment of the present application is shown.

[0020] The above drawings include the following reference numerals:

[0021] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0022] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] As introduced in the background technology, servers are important devices for information storage and application and middleware deployment of information projects, and are of great significance to the production and operation of enterprises. However, due to the possibility of server failure, data loss and application inaccessibility on the server may cause inconvenience to the production and operation of enterprises. In particular, remote computer rooms cannot monitor performance indicators such as CPU, memory, disk I / O, and network transmission in real time, and system administrators cannot understand the system operation status in a timely manner, which is likely to cause server downtime and affect the normal use of business systems.

[0026] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0027] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1FIG. 1 is a hardware structure block diagram of a mobile terminal of a method for diagnosing server failures according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0028] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the diagnostic method of server failure in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0029] In this embodiment, a method for diagnosing server failures running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] Figure 2 FIG. 1 is a flow chart of a method for diagnosing a server failure according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0031] Step S201, obtaining operation information of the server, the operation information including: vibration information, sound information of the server and position information corresponding to the sound information;

[0032] Step S202, analyzing and processing the above operation information to obtain analysis and processing results, wherein the above analysis and processing at least includes: sound pressure level analysis and fast Fourier transform, and the above analysis and processing results at least include: the intensity of the above sound and the frequency distribution of the above sound;

[0033] Step S203, judging whether the server has a fault based on the above analysis and processing results and the server status judgment model, and sending a warning signal when the judgment indication is yes. The server status judgment model is used to judge whether the current operating status of the server is normal.

[0034] By obtaining the vibration information, sound information and the location information of the server corresponding to the sound information, the operation information is subjected to sound pressure level analysis and fast Fourier transform and other processing to obtain the intensity of the sound and the frequency distribution of the sound, and at least according to the intensity of the sound and the frequency distribution of the sound, it is judged whether the server has a fault, and when the judgment indication is yes, an early warning signal is issued. Through the diagnostic method of the present application, the operation status of the server can be monitored and diagnosed in real time, thereby solving the problem in the prior art that the server is located in a remote computer room and the operation status of the server cannot be timely understood, which affects the normal use of the business system.

[0035] In some optional embodiments, obtaining the operation information of the server includes: performing two-dimensional collection of the vibration information and sound information of the server; performing three-dimensional collection of the vibration information and sound information of the server; and when the above judgment indicates no, obtaining the abnormal position of the server based on the above sound information and the above vibration information.

[0036] In the above optional implementation, the above plane acquisition is to collect the sound information on each surface of the above server, and the above three-dimensional acquisition is to collect the sound information within a radius of 1 to 2 meters of the above server, and the sound information is acquired in an all-round way, thereby improving the accuracy of the subsequent judgment on whether the above server is faulty. In the case of judging that the above server has a fault, the abnormal position of the server corresponding to the sound information of the fault and the above vibration information is obtained based on the sound information of the fault and the above vibration information. This allows the auxiliary operation and maintenance personnel to confirm the fault location in the first place, thereby realizing all-round 24-hour all-weather fault monitoring and fault alarm for the server.

[0037] In some optional implementations, the above-mentioned diagnostic method further includes: establishing the above-mentioned server status judgment model according to the above-mentioned analysis and processing results and the learning algorithm.

[0038] In the above optional implementation, the process of establishing the above server status judgment model by combining the above analysis and processing results with the learning algorithm involves multiple key steps, including data collection, preprocessing, model training, verification and testing, etc. This process will be described in detail below, and relevant calculation methods and formulas will be supplemented as much as possible. After the above server status judgment model is established, the above server status judgment model can intelligently perform server fault diagnosis based on the sound information of the above server.

[0039] In some optional embodiments, the server status judgment model is established, including: obtaining multiple groups of acoustic data sets based on the above analysis and processing results, each group of the above acoustic data sets includes the vibration information of the above server and the above sound information, and the above acoustic data sets include a training set and a verification set; preprocessing the above acoustic data sets, and the above preprocessing includes at least one of the following: denoising, extracting characteristic coefficients and normalization; constructing the server status judgment model, and optimizing the parameters of the server status judgment model based on the multiple groups of the above training sets and the multiple groups of the above verification sets to establish the server status judgment model.

[0040] In the above optional implementation, first, it is necessary to collect enough acoustic data sets, and the data sets should contain all the diversity to cover various situations that may be encountered in practical applications; before the data is input into the machine learning or deep learning model, a series of preprocessing steps are usually required to ensure the quality and consistency of the data. These steps may include: denoising, feature extraction and normalization / standardization, among which denoising: removes background noise in the audio to improve signal quality. Feature extraction: extracts useful features from the original audio signal, such as Mel frequency cepstral coefficients (MFCC), linear prediction cepstral coefficients (LPCC), etc. These features can more effectively represent the key information in the audio signal. Normalization / standardization: adjusts the range or distribution of feature values ​​to make the model easier to learn. In the model training stage, the preprocessed data is divided into a training set and a validation set, and sometimes a test set. The training set is used to train the model, and the validation set is used to adjust the model parameters to prevent overfitting. After the model training is completed, the validation set and test set are needed to evaluate the performance of the model. The validation set is used to adjust the hyperparameters during the training process, and the test set is used to finally evaluate the generalization ability of the model. Finally, the trained model is deployed in real applications to process new acoustic data and generate prediction results. The process of combining acoustic datasets with machine learning and deep learning algorithms to build a perception model is a complex but systematic process involving multiple key steps and calculation methods. Through continuous optimization and adjustment, a high-performance and high-accuracy acoustic perception model can be built.

[0041] In some optional implementations, the above-mentioned learning algorithm includes a machine learning algorithm and a deep learning algorithm.

[0042] In the above optional implementations, machine learning algorithms, such as support vector machines (SVMs), random forests, etc., take the extracted feature voiceprint vectors as input and target variables (such as text labels in speech recognition) as output. The algorithm learns the mapping relationship from feature vectors to target variables. The calculation process of machine learning algorithms usually involves optimizing an objective function (such as a loss function) to find the best parameters. These parameters determine the predictive ability of the model. The objective function in SVM is to maximize the interval, and the parameters include the coefficients of the support vector and the decision boundary. Deep learning algorithms, including methods such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs), are particularly effective in acoustic perception models. These algorithms can automatically learn higher-level feature representations from raw data. In deep learning models, the calculation process usually includes two stages: forward propagation and back propagation. Forward propagation is used to calculate the predicted output of the model, while back propagation is used to update the weights and biases of the model based on the prediction error.

[0043] Formula example: The calculation process of a single neural network layer for forward propagation can be expressed as:

[0044] z=Wx+b;

[0045] a=σ(z);

[0046] Where W is the weight matrix, x is the input feature vector, b is the bias vector, z is the output of the linear combination, σ is the activation function (such as ReLU and sigmoid, etc.), and a is the output after activation. In the back-propagation phase, the weights W and biases b need to be updated according to the gradient of the loss function L with respect to them. The gradient can be calculated by the chain rule and updated using an optimization algorithm (such as gradient descent, Adam, etc.).

[0047] The embodiment of the present application also provides a diagnostic system for server failures. It should be noted that the diagnostic system for server failures in the embodiment of the present application can be used to execute the diagnostic method for server failures provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0048] The following is an introduction to the server failure diagnosis system provided in the embodiment of the present application.

[0049] Figure 3 Schematic diagram of a server failure diagnosis system according to an embodiment of the present application. Figure 3 As shown, the above-mentioned diagnostic method is used to drive the above-mentioned diagnostic system, which includes: an acquisition unit 100 for obtaining the operation information of the server, and the above-mentioned operation information includes: vibration information, sound information of the above-mentioned server and position information corresponding to the above-mentioned sound information; an analysis unit 200 is electrically connected to the above-mentioned acquisition unit, and is used to analyze and process the above-mentioned operation information to obtain an analysis and processing result, and the above-mentioned analysis and processing at least includes: sound pressure level analysis and fast Fourier transform, and the above-mentioned analysis and processing result at least includes: the intensity of the above-mentioned sound and the frequency distribution of the above-mentioned sound; a voiceprint analysis and diagnosis platform 300 is electrically connected to the above-mentioned analysis unit, and is used to receive the above-mentioned analysis and processing result, and the above-mentioned voiceprint analysis and diagnosis determines whether the above-mentioned server has a fault according to the above-mentioned analysis and processing result and the server status judgment model, and sends a warning signal when the judgment indication is yes, and the above-mentioned server status judgment model is used to determine whether the current operation status of the above-mentioned server is normal.

[0050] The above-mentioned server fault diagnosis system of the present application includes a collection unit, an analysis unit and a voiceprint analysis and diagnosis platform, wherein the collection unit obtains the vibration information, sound information of the server and the location information of the above-mentioned server corresponding to the above-mentioned sound information and other operating information, and the analysis unit performs sound pressure level analysis and fast Fourier transform and other processing on the above-mentioned operating information to obtain the intensity of the above-mentioned sound and the frequency distribution of the above-mentioned sound, and the voiceprint analysis and diagnosis platform determines whether the above-mentioned server has a fault based on at least the intensity of the above-mentioned sound and the frequency distribution of the above-mentioned sound, and sends out a warning signal when the judgment indication is yes. Through the diagnostic method of the present application, the operating status of the above-mentioned server can be monitored and diagnosed in real time, thereby solving the problem in the prior art that the server is located in a remote computer room and the operating status of the server cannot be timely understood, which affects the normal use of the business system.

[0051] In the above optional implementation, the status analysis results of the voiceprint analysis and diagnosis platform are transmitted to the data center or auxiliary control platform through IEC61850, HTTP and other protocols. The system function indicators are as follows:

[0052] (1) Voiceprint spectrogram analysis of the server;

[0053] (2) Classify and manage the voiceprint features of the server;

[0054] (3) The alarm fault signal can be traced back and the fault sound signal of the server can be played / replayed;

[0055] (4) Equipped with a voiceprint feature database to support voiceprint feature data query and development trend analysis;

[0056] (5) Audio and video cloud map positioning of local failures of server equipment.

[0057] In some optional embodiments, the above-mentioned collection unit includes: a contact voiceprint collection module, a non-contact voiceprint collection module and an audio-visual device, wherein: the above-mentioned contact voiceprint collection module is in contact with the above-mentioned server to enable planar collection of the vibration information and sound information of the above-mentioned server; the above-mentioned non-contact voiceprint collection module is located within a preset range with the above-mentioned server as the center of the circle to enable stereoscopic collection of the vibration information and sound information of the above-mentioned server; the above-mentioned audio-visual device is electrically connected to the above-mentioned voiceprint analysis and diagnosis platform, and is used for obtaining the abnormal position of the above-mentioned server according to the above-mentioned sound information and the above-mentioned vibration information when the above-mentioned judgment indication is no.

[0058] In the above optional implementation, the collection unit performs three-dimensional and all-round accurate perception and real-time collection of the vibration and sound information of the server. In view of this situation, the collection unit includes a contact voiceprint sensor and a non-contact voiceprint sensor. The contact voiceprint sensor can be directly installed on the server by magnetic attraction to realize the plane collection of acoustics and vibrations. The non-contact voiceprint sensor is installed within 1 to 2 meters around the server. The sensor is equipped with an outdoor protective cover to effectively reduce the intensity attenuation caused by the conduction of sound through the protective cover. The non-contact voiceprint sensor senses the running sound and vibration noise of the server to realize the all-round and three-dimensional collection of acoustic data. The server audio and video camera is installed in the center of the periphery of the server, and is aimed at the server at an elevation angle of 15°-45° to avoid the influence of ground noise, and objects should be avoided to ensure clear imaging. The specific height and corresponding specific can be adjusted according to the actual situation. When used together with the voiceprint sensor, when the voiceprint sensor recognizes an abnormal voiceprint, it will trigger the audio and video camera to capture the abnormal position, assisting the operation and maintenance personnel to confirm the fault position in the first time, thereby realizing all-round 24-hour all-weather fault monitoring and fault alarm of the server.

[0059] In the above optional implementation, the acquisition unit and the analysis unit perform real acquisition and analysis of the measured sound or vibration. The acquisition unit host adopts RJ45 100M network port and communicates with the host computer through TCP / IP transmission protocol, which is particularly suitable for online monitoring of industrial sites. Supports IEPE / ICP power supply, single machine supports up to 8 channels of sound signal and vibration signal synchronous input, and can support up to 256 channels cascaded through the network. The analysis frequency range is 0.3Hz~50kHz, and the dynamic range is 123dB, which is sufficient to meet the high-precision acquisition and high-quality analysis of voiceprints and vibrations. CRY2700 software is designed based on the Windows operating system, with a simple and beautiful interface, simple and intuitive operation, and real-time acquisition and analysis of the measured sound or vibration. The analysis unit can analyze time domain waveforms, sound pressure levels, vibration levels, octaves and fast Fourier transforms (FFT), supports recording and playback of the test process, and supports data export in multiple formats. The analysis that can be performed includes time domain waveform, sound pressure level, vibration level, octave and FFT. The analysis unit performs real-time analysis of the measured sound or vibration. The analysis methods it covers, such as time domain waveform, sound pressure level, vibration level, octave and FFT, each has a unique working principle, a wide range of application scenarios and corresponding advantages and disadvantages.

[0060] Among them, time domain waveform analysis directly studies the characteristics of signal changes over time, and displays information such as amplitude and frequency through waveform graphs. It is often used to diagnose equipment failures and optimize system performance. Its advantage is that it is intuitive and easy to understand, but it may be difficult to directly identify the spectral characteristics of complex signals. Sound pressure level is a physical quantity that measures the strength of sound. It is measured by a sound level meter and is often used for noise assessment and control. Its advantage is that it is easy to measure, but it is necessary to pay attention to the selection of weighting to match the hearing characteristics of the human ear. Vibration level analysis focuses on the vibration intensity of mechanical equipment, and collects signals through acceleration sensors for health monitoring and fault diagnosis. The advantage is that potential problems can be discovered early, but the installation location of the sensor has a significant impact on the results. Octave analysis divides sound or vibration signals into different frequency bands, which is convenient for identifying noise sources of specific frequencies. It is suitable for noise source identification in complex environments, but it may ignore the details of some non-octave components. FFT converts time domain signals into frequency domain signals for spectrum analysis, filtering, etc. Its advantages are high analysis efficiency and can accurately reveal the spectral characteristics of signals, but it has a large amount of calculations and high hardware requirements.

[0061] Taking server noise monitoring as an example, the acquisition unit can collect sound signals in real time, and the analysis unit observes sound changes through time domain waveform analysis, evaluates sound intensity in combination with sound pressure level, and then uses octave and FFT analysis to identify the main sound source and its frequency distribution, providing a scientific basis for sound management. Acoustic analysis function: Noise statistical analysis, supports Lp, Lmax, Lmin, Lpeak, etc., supports Leq testing, and the average time setting range is 1s to 24h; vibration statistical analysis: supports Lmax, Lrms, Lexpavg, RunningRMS, deltaMaxMin, etc., supports displacement, velocity and acceleration analysis.

[0062] The analysis unit also supports recording and playback of the test process, and supports data export in multiple formats (WAV, MP3, MP4, AAC, FLAC). It provides a programmable interface for raw data and measurement results, which can be easily integrated into the voiceprint analysis and diagnosis platform.

[0063] In some optional embodiments, the above-mentioned diagnostic system also includes an acoustic database, the above-mentioned analysis and processing results include multiple groups of acoustic data sets, the above-mentioned acoustic database is electrically connected to the above-mentioned voiceprint analysis and diagnosis platform, and the above-mentioned acoustic database is used to store the above-mentioned acoustic data sets and manage the above-mentioned acoustic data sets. The above-mentioned management at least includes: storing the above-mentioned historical acoustic data sets and initializing the above-mentioned real-time acoustic data sets.

[0064] In the above optional implementation, the voiceprint sensor of the terminal perception layer collects acoustic information, and after signal processing and analysis, it is aggregated and transmitted to the data center. The data center is a data storage unit. The data is classified according to the business type, and the data is uniformly managed by the data center. Data management undertakes four major functions: initialization of historical database, real-time database, data maintenance, access proxy and real-time library sampling and preservation, providing support for application software and data interaction. Among them, the initialization of the real-time database is a specific process, which aims to set an initial state for the newly created real-time database system to ensure that the database can operate normally and provide the expected functions and performance. The core idea of ​​access proxy, also known as proxy access or proxy Internet access, is to achieve IP change or sharing through the jump of network signals. Specifically, when a user's computer or device needs to access a website, the network request is not sent directly to the target website, but first to the proxy server. As an intermediary, the proxy server receives and parses the request, and then communicates with the target website as its own identity to complete the forwarding of the request and the return of the response. In this process, the target website will think that the request comes from the proxy server, not the original user, thereby realizing the hiding or change of the IP address.

[0065] For example, Figure 4 As shown, the acquisition unit includes a contact voiceprint sensor and a non-contact voiceprint sensor, and the contact voiceprint sensor and the non-contact voiceprint sensor respectively perform planar and stereoscopic acquisition of the sound information and vibration information of multiple servers, and the above-mentioned sound information and vibration information are transmitted by the acquisition unit to the analysis unit, and the above-mentioned analysis unit analyzes and processes the above-mentioned sound information and vibration information. The voiceprint analysis and diagnosis platform judges whether the above-mentioned server is faulty according to the processed sound information, vibration information and server status judgment model. When the judgment result indicates yes, the acquisition unit collects the collective position of the server corresponding to the above-mentioned sound information and the above-mentioned vibration information, and issues an early warning signal, and at the same time, the server can be shut down. The sound information, vibration information and position information collected by the above-mentioned acquisition signal are stored in the acoustic database. The above-mentioned acoustic database is classified and managed according to the voiceprint characteristics, such as sound information, vibration information and position information with primary faults, sound information, vibration information and position information with intermediate faults, and sound information, vibration information and position information without faults.

[0066] The server fault diagnosis system includes a processor and a memory. The acquisition unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0067] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters are adjusted to solve the problem of security risks in multi-source power data caused by the influence of malicious nodes on the security of power Internet of Things data transmission in the prior art.

[0068] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0069] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the server failure diagnosis method.

[0070] Specifically, the server failure diagnosis method includes:

[0071] Step S201, obtaining operation information of the server, the operation information including: vibration information, sound information of the server and position information corresponding to the sound information;

[0072] Step S202, analyzing and processing the above operation information to obtain analysis and processing results, wherein the above analysis and processing at least includes: sound pressure level analysis and fast Fourier transform, and the above analysis and processing results at least include: the intensity of the above sound and the frequency distribution of the above sound;

[0073] Step S203, judging whether the server has a fault based on the above analysis and processing results and the server status judgment model, and sending a warning signal when the judgment indication is yes. The server status judgment model is used to judge whether the current operating status of the server is normal.

[0074] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the server failure diagnosis method is executed when the program is running.

[0075] Specifically, the server failure diagnosis method includes:

[0076] Step S201, obtaining operation information of the server, the operation information including: vibration information, sound information of the server and position information corresponding to the sound information;

[0077] Step S202, analyzing and processing the above operation information to obtain analysis and processing results, wherein the above analysis and processing at least includes: sound pressure level analysis and fast Fourier transform, and the above analysis and processing results at least include: the intensity of the above sound and the frequency distribution of the above sound;

[0078] Step S203, judging whether the server has a fault based on the above analysis and processing results and the server status judgment model, and sending a warning signal when the judgment indication is yes. The server status judgment model is used to judge whether the current operating status of the server is normal.

[0079] An embodiment of the present invention provides an electronic device, the device comprising a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the following steps are implemented:

[0080] Step S201, obtaining operation information of the server, the operation information including: vibration information, sound information of the server and position information corresponding to the sound information;

[0081] Step S202, analyzing and processing the above operation information to obtain analysis and processing results, wherein the above analysis and processing at least includes: sound pressure level analysis and fast Fourier transform, and the above analysis and processing results at least include: the intensity of the above sound and the frequency distribution of the above sound;

[0082] Step S203, judging whether the server has a fault based on the above analysis and processing results and the server status judgment model, and sending a warning signal when the judgment indication is yes. The server status judgment model is used to judge whether the current operating status of the server is normal.

[0083] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0084] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing at least the following method steps:

[0085] Step S201, obtaining operation information of the server, the operation information including: vibration information, sound information of the server and position information corresponding to the sound information;

[0086] Step S202, analyzing and processing the above operation information to obtain analysis and processing results, wherein the above analysis and processing at least includes: sound pressure level analysis and fast Fourier transform, and the above analysis and processing results at least include: the intensity of the above sound and the frequency distribution of the above sound;

[0087] Step S203, judging whether the server has a fault based on the above analysis and processing results and the server status judgment model, and sending a warning signal when the judgment indication is yes. The server status judgment model is used to judge whether the current operating status of the server is normal.

[0088] Obviously, it should be understood by those skilled in the art that the above-mentioned units and platforms or steps of the present invention can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0089] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0090] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0091] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0092] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0093] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0094] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0095] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0096] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0097] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0098] 1) The diagnostic method of the server failure of the present application obtains the vibration information, sound information and the location information of the server corresponding to the sound information and other operating information of the server, performs sound pressure level analysis and fast Fourier transform and other processing on the operating information to obtain the intensity of the sound and the frequency distribution of the sound, and judges whether the server has a fault at least based on the intensity of the sound and the frequency distribution of the sound, and sends a warning signal when the judgment indication is yes. Through the diagnostic method of the present application, the operating status of the server can be monitored and diagnosed in real time, thereby solving the problem in the prior art that the server is located in a remote computer room and the operating status of the server cannot be timely understood, which affects the normal use of the business system.

[0099] 2) The server fault diagnosis system of the present application obtains the vibration information, sound information and the location information of the server corresponding to the sound information and other operation information of the server through the collection unit. The analysis unit performs sound pressure level analysis and fast Fourier transform and other processing on the operation information to obtain the intensity of the sound and the frequency distribution of the sound. The voiceprint analysis and diagnosis platform determines whether the server has a fault based on at least the intensity of the sound and the frequency distribution of the sound. If the judgment indication is yes, an early warning signal is issued. Through the diagnostic method of the present application, the operation status of the server can be monitored and diagnosed in real time, thereby solving the problem in the prior art that the server is located in a remote computer room and the operation status of the server cannot be understood in time, which affects the normal use of the business system.

[0100] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for diagnosing server failures. It is characterized in that The diagnostic method comprises: Acquire operation information of the server, the operation information including: vibration information, sound information of the server and position information corresponding to the sound information; Analyzing and processing the operation information to obtain an analysis and processing result, wherein the analysis and processing at least includes: sound pressure level analysis and fast Fourier transform, and the analysis and processing result at least includes: the intensity of the sound and the frequency distribution of the sound; Based on the analysis and processing results and the server status judgment model, it is judged whether the server has a fault. If the judgment indication is yes, an early warning signal is issued. The server status judgment model is used to judge whether the current operating status of the server is normal.

2. The diagnostic method according to claim 1, It is characterized in that Get the server's running information, including: Performing planar collection of vibration information and sound information of the server; Performing stereoscopic collection of vibration information and sound information of the server; When the judgment indication is negative, the abnormal position of the server is acquired according to the sound information and the vibration information.

3. The diagnostic method according to claim 1, It is characterized in that The diagnostic method further comprises: The server status judgment model is established based on the analysis and processing results and the learning algorithm.

4. The diagnostic method according to claim 3, It is characterized in that Establishing the server status judgment model includes: According to the analysis and processing results, a plurality of groups of acoustic data sets are obtained, each group of the acoustic data sets includes the vibration information of the server and the sound information, and the acoustic data sets include a training set and a verification set; Preprocessing the acoustic data set, wherein the preprocessing includes at least one of the following: denoising, extracting characteristic coefficients, and normalization; The server status judgment model is constructed, and the parameters of the server status judgment model are optimized according to the multiple groups of the training sets and the multiple groups of the validation sets to establish the server status judgment model.

5. The diagnostic method according to claim 3, It is characterized in that The learning algorithms include machine learning algorithms and deep learning algorithms.

6. A server failure diagnosis system, It is characterized in that The diagnostic system is driven by the diagnostic method according to any one of claims 1 to 5, and the diagnostic system comprises: A collection unit, used to obtain operation information of the server, the operation information including: vibration information, sound information of the server and position information corresponding to the sound information; An analysis unit, electrically connected to the acquisition unit, for analyzing and processing the operation information to obtain an analysis and processing result, wherein the analysis and processing at least includes: sound pressure level analysis and fast Fourier transform, and the analysis and processing result at least includes: the intensity of the sound and the frequency distribution of the sound; The voiceprint analysis and diagnosis platform is electrically connected to the analysis unit and is used to receive the analysis and processing results. The voiceprint analysis and diagnosis determines whether the server has a fault based on the analysis and processing results and a server status judgment model. If the judgment indication is yes, an early warning signal is issued. The server status judgment model is used to determine whether the current operating status of the server is normal.

7. The diagnostic system according to claim 6, It is characterized in that The acquisition unit includes: a contact voiceprint acquisition module, a non-contact voiceprint acquisition module and an audio-visual device, wherein: The contact voiceprint collection module contacts the server to collect vibration information and sound information of the server in a planar manner; The non-contact voiceprint collection module is located within a preset range with the server as the center, so as to perform stereoscopic collection of vibration information and sound information of the server; The audio-visual device is electrically connected to the voiceprint analysis and diagnosis platform, and is used to obtain the abnormal position of the server according to the sound information and the vibration information when the judgment indication is no.

8. The diagnostic system according to claim 7, It is characterized in that The diagnostic system also includes an acoustic database, and the analysis and processing results include multiple groups of acoustic data sets. The acoustic database is electrically connected to the voiceprint analysis and diagnosis platform. The acoustic database is used to store the acoustic data sets and manage the acoustic data sets. The management at least includes: storing the historical acoustic data sets and initializing the real-time acoustic data sets.

9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the server failure diagnosis method according to any one of claims 1 to 5.

10. An electronic device, It is characterized in that include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for performing a server failure diagnosis method as described in any one of claims 1 to 5.

Images