A fan state monitoring method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a fan state monitoring method and device, electronic equipment and storage medium, the method is applied to a server, the server includes a fan and a microphone, and the method comprises: obtaining fan noise data collected by the microphone; identifying the fan noise data to obtain a target noise segment; the target noise segment is a noise data segment with noise intensity greater than a noise intensity threshold; the total duration of the target noise segment and the number of target noise segments are counted; when the total duration of the target noise segment is greater than a duration threshold, and the number of target noise segments is greater than a number threshold, it is determined that the fan has failed. By monitoring the noise of the fan, the health status of the fan can be determined in time, and the reliability of the server operation is improved.

Description

Technical Field

[0001] This invention relates to the field of server technology, and in particular to a fan status monitoring method, device, electronic device, and storage medium. Background Technology

[0002] With the development of cloud computing, big data, and AI technologies, user demand for servers has surged. As the core of computing and storage, the stability of servers is paramount. Fans are a crucial component of the server cooling system, responsible for dissipating heat and ensuring the server operates within a normal temperature range. A fan malfunction can lead to insufficient heat dissipation, resulting in anything from reduced server performance to server crashes and hardware damage. Summary of the Invention

[0003] In view of the above problems, embodiments of the present invention are proposed to provide a fan status monitoring method, apparatus, electronic device and storage medium that overcomes or at least partially solves the above problems.

[0004] In a first aspect, embodiments of the present invention disclose a fan status monitoring method, applied to a server, the server including a fan and a microphone, the method comprising:

[0005] Acquire the fan noise data collected by the microphone;

[0006] The fan noise data is identified to obtain the target noise segment; the target noise segment is a noise data segment whose noise intensity is greater than the noise intensity threshold.

[0007] The total duration of the target noise segments and the number of target noise segments are calculated.

[0008] When the total duration of the target noise segment exceeds the duration threshold and the number of the target noise segments exceeds the number threshold, the fan is determined to have malfunctioned.

[0009] Optionally, the step of identifying the fan noise data to obtain the target noise segment includes:

[0010] The fan noise data is denoised using a histogram noise estimation algorithm to obtain the processed fan noise data.

[0011] The processed fan noise data is then identified to obtain the target noise segment.

[0012] Optionally, the target noise segment is identified from multiple target noise segments collected simultaneously by multiple microphones, and the step of calculating the total duration of the target noise segment includes:

[0013] Determine whether the durations of the target noise segments overlap;

[0014] If the durations of the target noise segments do not overlap, the durations of each target noise segment are added together to obtain the total duration of the target noise segment.

[0015] If the durations of the target noise segments overlap, the durations of each target noise segment are added together and the overlap duration is subtracted to obtain the total duration of the target noise segments.

[0016] Optionally, the server includes a Universal Serial Bus (USB) interface connected to a USB hub, the USB hub being connected to the microphone used for recording audio from the fan.

[0017] Optionally, the server is connected to a flash memory card; the method further includes:

[0018] Poll the connection status between the flash memory card and the microphone;

[0019] The acquisition of fan noise data collected by the microphone includes:

[0020] When a flash memory card is detected to be connected, and a microphone is also connected, a recording command is sent to the microphone;

[0021] The system receives fan noise data transmitted by the microphone and stores the fan noise data in the flash memory card; the fan noise data is obtained by the microphone recording the fan in response to the recording command.

[0022] Optionally, identifying the fan noise data includes:

[0023] The fan noise data stored in the flash memory card is identified.

[0024] Optionally, the method further includes:

[0025] The fan is determined to be normal when the total duration of the target noise segment is less than or equal to the duration threshold, or when the number of the target noise segments is less than or equal to the number threshold.

[0026] Secondly, embodiments of the present invention disclose a fan status monitoring device, the device being applied to a server, the server including a fan and a microphone, the device comprising:

[0027] A noise data acquisition module is used to acquire fan noise data collected by the microphone;

[0028] The noise data identification module is used to identify the fan noise data and obtain the target noise segment; the target noise segment is a noise data segment whose noise intensity is greater than the noise intensity threshold.

[0029] The noise data statistics module is used to calculate the total duration of the target noise segment and the number of the target noise segments.

[0030] The fan status determination module is used to determine that the fan has malfunctioned when the total duration of the target noise segment is greater than a duration threshold and the number of the target noise segments is greater than a number threshold.

[0031] Optionally, the noise data recognition module is specifically used for:

[0032] The fan noise data is denoised using a histogram noise estimation algorithm to obtain the processed fan noise data.

[0033] The processed fan noise data is then identified to obtain the target noise segment.

[0034] Optionally, the target noise segments are multiple target noise segments identified from fan noise data collected simultaneously by multiple microphones, and the noise data statistics module is specifically used for:

[0035] Determine whether the durations of the target noise segments overlap;

[0036] If the durations of the target noise segments do not overlap, the durations of each target noise segment are added together to obtain the total duration of the target noise segment.

[0037] If the durations of the target noise segments overlap, the durations of each target noise segment are added together and the overlap duration is subtracted to obtain the total duration of the target noise segments.

[0038] Optionally, the server includes a Universal Serial Bus (USB) interface connected to a USB hub, the USB hub being connected to the microphone used for recording audio from the fan.

[0039] Optionally, the server is connected to a flash memory card; the device further includes:

[0040] A connection status detection module is used to poll and detect the connection status between the flash memory card and the microphone;

[0041] The noise data acquisition module is specifically used for: when a flash memory card is detected to be connected and a microphone is also connected, sending a recording command to the microphone; receiving fan noise data sent by the microphone and storing the fan noise data in the flash memory card; the fan noise data is obtained by the microphone recording the fan in response to the recording command.

[0042] Optionally, the noise data recognition module is specifically used to: recognize the fan noise data stored in the flash memory card.

[0043] Optionally, the fan status determination module is further configured to: determine that the fan is normal when the total duration of the target noise segment is less than or equal to the duration threshold, or when the number of the target noise segments is less than or equal to the number threshold.

[0044] Thirdly, embodiments of the present invention also disclose an electronic device, including: a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps of the fan status monitoring method as described above.

[0045] Fourthly, embodiments of the present invention also disclose a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the fan status monitoring method as described above.

[0046] The embodiments of the present invention have the following advantages:

[0047] By identifying fan noise data collected by the microphone, target noise segments are determined. These segments are then analyzed to determine their total duration and number. A fan malfunction is confirmed when the total duration exceeds a duration threshold and the number of target noise segments exceeds a number threshold. Detecting fan malfunctions through noise analysis allows for timely reporting to maintenance personnel, facilitating the replacement of faulty fans and improving server reliability. Attached Figure Description

[0048] Figure 1 This is a flowchart illustrating the steps of a fan status monitoring method provided in an embodiment of the present invention;

[0049] Figure 2 This is a schematic diagram of a microphone connection method provided in an embodiment of the present invention;

[0050] Figure 3 This is a flowchart of a fan status monitoring method provided in an embodiment of the present invention;

[0051] Figure 4This is a structural block diagram of a fan status monitoring device provided in an embodiment of the present invention;

[0052] Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present invention;

[0053] Figure 6 This is a structural block diagram of a computer-readable storage medium provided in an embodiment of the present invention. Detailed Implementation

[0054] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0055] In complex computer systems such as servers, with the rapid development of computer hardware, fans, as crucial heat dissipation components, can cause abnormal server noise or even server shutdown due to overheating protection if they malfunction. One of the core concepts of this invention is to monitor fan health by collecting fan noise data and promptly report any fan malfunctions to maintenance personnel for timely repair.

[0056] Reference Figure 1 The diagram illustrates a flowchart of a fan status monitoring method according to an embodiment of the present invention. The method is applied to a server, which includes a fan and a microphone. The method may specifically include the following steps:

[0057] Step 101: Obtain the fan noise data collected by the microphone.

[0058] The server is connected to a fan and a microphone. The microphone can be located near the fan to record fan noise. When the fan status needs to be monitored, the server can send a recording command to the microphone. This command can include the recording duration and recording cycle. After receiving the recording command, the microphone can record the fan noise data. The fan noise data can be time-domain data, meaning the independent variable is time and the dependent variable is noise intensity.

[0059] In one embodiment, the server has a Universal Serial Bus (USB) interface, which can be connected to a USB hub, and the USB hub can be connected to a microphone. The executing entity of this embodiment is a server, more specifically, the Baseboard Management Controller (BMC) within the server. The BMC typically has only one USB interface. If a microphone is directly connected through the USB interface, only one microphone can be connected to record fan audio, reducing the accuracy of fan detection. Therefore, a USB hub can be connected to the USB interface, allowing multiple microphones to be connected simultaneously for fan audio recording.

[0060] Reference Figure 2 This diagram illustrates a microphone connection method according to an embodiment of the present invention. A USB hub is connected to the USB interface on the BMC (Browser Control Center), and two recording boards are connected through the USB hub. Each recording board is then connected to three microphones. Thus, more microphones can be connected via the USB hub. Typically, a single USB hub directly connected to microphones can connect a maximum of four microphones. However, by connecting other USB hubs or recording boards to the USB hub, even more microphones can be connected through interconnection of multiple USB hubs or through connection between recording boards and USB hubs.

[0061] The microphone responds to the recording command, recording the fan noise data. This data can then be transmitted back to the server's BMC via a USB transfer channel. The BMC can install the ALSA (Advanced Linux Sound Architecture) sound card driver to provide the necessary drivers, and integrate the alsa-utils-aplay tool for audio acquisition. During acquisition, the sampling rate, sample length (bit depth), and number of channels can be selected. Audio can be recorded as PCM (Pulse-Code-Modulated) data and stored in WAV format.

[0062] In one embodiment, the server may include a Trans-flash Card (TF card) for storing fan noise data. The server may poll to detect the connection status between the Trans-flash Card and the microphone. When both a Trans-flash Card and a microphone are connected, the server sends a recording command to the microphone. The server receives the fan noise data sent by the microphone and stores the fan noise data in the Trans-flash Card. The fan noise data is obtained by the microphone recording the fan noise in response to the recording command.

[0063] The TF card is used to store fan noise data. Recording requires the TF card to be present before the fan noise data can be recorded. Therefore, the connection status of the TF card needs to be checked; recording of the fan noise can only begin when the TF card is connected.

[0064] The server also needs to poll and check the microphone's presence. This is necessary to ensure a microphone is connected for recording to the fan, and also to enable dynamic construction and destruction of the recording management object after hot-swapping of devices. In other words, it needs to monitor the number of connected microphones in real time, and send recording commands to connected microphones as soon as they connect or disconnect.

[0065] The server detects and identifies microphones connected via USB, and after detecting the number of microphones, instantiates the first object of its class. Instantiation means passing the name of the detected microphone as a parameter to the class's constructor. The class constructor can be the constructor of the Sound class, which defines a timer. After the microphone object is instantiated, the microphone's recording behavior will be performed according to the timer's defined time intervals.

[0066] The server can asynchronously acquire data from multiple USB channels simultaneously. It maintains sampling consistency when multiple microphones are present and multiple USB hubs access the system concurrently. The server can call the `arecord` command to send recording commands to the microphones and define the filename of the acquired fan noise data file as: `serial number-device number-timestamp-recording time-sampling rate-bit width-channel number.wav`. Here, the serial number can be the file identifier, the device number can be the microphone identifier, the timestamp can be the start time of the recording, the recording time can be the recording duration, and the sampling rate, also known as the sampling speed, defines the number of samples extracted from a continuous signal per second to form a discrete signal, expressed in Hertz (Hz). The bit width is a measure of the sampling points; each sampling point needs to be assigned a range value, typically stored as 2 bytes (16 bits). The higher the bit width, the more precise the audio measurement, and the higher the sound quality. The number of channels can be understood as the number of recording devices; the minimum number is 1, and generally, the more channels, the better the sound quality. WAV format files, also known as waveform files, can directly store sound waveforms, reproducing very realistic waveform curves. The sound waves emitted by the sound source are converted into continuously changing electrical signals. After amplification and anti-aliasing filtering, they are sampled at a fixed frequency. Each sample is the amplitude value of the electrical signal detected within one sampling period. Next, the analog electrical signal is quantized into an integral value represented by a binary number. Finally, it is encoded and stored to obtain the WAV format audio stream data.

[0067] After the server obtains the fan noise data file, it stores the fan noise data file in a BMC high-capacity storage TF card.

[0068] Step 102: Identify the fan noise data to obtain the target noise segment; the target noise segment is a noise data segment with a noise intensity greater than the noise intensity threshold.

[0069] After acquiring fan noise data, it can be converted into a digital audio signal. The server then identifies the digital audio signal to determine the target noise segment. The target noise segment is the noise data fragment where the fan noise intensity exceeds a noise intensity threshold. The noise intensity threshold can be obtained by analyzing the noise during normal fan operation and during fan malfunction. Different fan types and operating environments will result in different noise intensity thresholds. Therefore, this embodiment of the invention does not impose specific limitations on the noise intensity threshold.

[0070] In one embodiment, fan noise data is stored in a TF card. The specific steps for identifying the fan noise data may include: identifying the fan noise data stored in the TF card. When the server detects that fan noise data has been stored in the TF card, it can identify the fan noise data in the TF card.

[0071] In one embodiment, the step of identifying fan noise data to obtain a target noise segment may specifically include: performing noise reduction processing on the fan noise data using a histogram noise estimation algorithm to obtain processed fan noise data; and identifying the processed fan noise data to obtain the target noise segment.

[0072] After acquiring fan noise data, it can be denoised to more effectively identify target noise segments. The process of denoising fan noise data collected by each microphone using a histogram noise estimation algorithm includes the following steps;

[0073] Step 1: Calculate the energy spectrum of each single-channel audio speech, using |Y(λ, K)| 2 Where λ represents the number of frames and K represents the frequency point;

[0074] Step 2: Calculate the power spectral density (PSD) of the audio speech using first-order recursion:

[0075] S(λ,K)=αS(λ-1,K)+(1-α)|Y(λ,K)|2, where α is a constant;

[0076] Step 3: Calculate the histogram of the audio speech power spectral density for the first D frames (duration);

[0077] S(λ,K){S(λ-1,K), S(λ-2,K),…S(λ-D,K)}

[0078] Step 4: Select the power corresponding to the maximum value in the histogram as the noise spectrum estimate;

[0079]

[0080] H mac (λ, K) = S(C) max )

[0081] Step 5: The noise spectrum estimated in Step 4 is further estimated using first-order regression.

[0082] in, It is an estimate of the noise spectrum, α m It is a constant.

[0083] After processing using the above formula, we can obtain the fan noise data after noise reduction and smoothing. The processed fan noise data is still time-domain data, with time as the independent variable and noise intensity as the dependent variable.

[0084] Step 103: Calculate the total duration of the target noise segment and the number of the target noise segments.

[0085] A target noise segment can include one or more. After obtaining the target noise segments, the total duration and number of target noise segments can be calculated. For example, after recording a fan, a 5-minute recording of fan noise data is obtained. Identifying this 5-minute fan noise data yields two target noise segments: one segment is a fan noise data fragment from 1 minute to 1.5 minutes, with a calculated duration of 0.5 minutes; the other segment is a fan noise data fragment from 2 minutes to 3 minutes, with a calculated duration of 1 minute. Statistical analysis of the target noise segments shows that the total duration of the target noise segments is 0.5 minutes plus 1 minute, which is 1.5 minutes; the number of target noise segments is 2.

[0086] In one embodiment, the target noise segment is identified from multiple target noise segments collected simultaneously by multiple microphones. The specific steps for calculating the total duration of the target noise segment may include: determining whether the durations of the target noise segments overlap; if the durations of the target noise segments do not overlap, then adding the durations of each target noise segment to obtain the total duration of the target noise segment; if the durations of the target noise segments overlap, then adding the durations of each target noise segment and subtracting the overlap duration to obtain the total duration of the target noise segment.

[0087] When the target noise segment is identified from multiple fan noise data collected simultaneously by multiple microphones, the durations of the target noise segments may overlap. For example, when multiple microphones include microphone 1 and microphone 2, target noise segment 1 is identified from the fan noise data collected by microphone 1, with a duration of 5 minutes from 4:00 pm to 4:05 pm; target noise segment 2 is identified from the fan noise data collected by microphone 2, with a duration of 5 minutes from 4:01 pm to 4:06 pm. Therefore, based on the durations of target noise segment 1 and 2, the overlap time is 4:01 pm to 4:05 pm, with an overlap duration of 4 minutes. Therefore, adding the durations of target noise segment 1 and 2 and subtracting the overlap time (5 minutes plus 5 minutes minus 4 minutes) yields a total duration of 6 minutes for the target noise segments.

[0088] Alternatively, based on the duration of target noise segment 1 and the duration of target noise segment 2, the total duration of the target noise segment can be calculated as 4:00pm to 4:06pm, which also gives the total duration of the target noise segment as 6 minutes.

[0089] When the target noise segments do not overlap in duration, for example, when multiple microphones are used, including microphone 3 and microphone 4, target noise segment 3 is identified from the fan noise data collected by microphone 3. The duration of target noise segment 3 is from 5:00 pm to 5:05 pm, which is calculated to be 5 minutes. Target noise segment 4 is identified from the fan noise data collected by microphone 4. The duration of target noise segment 4 is from 5:10 pm to 5:15 pm, which is also calculated to be 5 minutes. Based on the durations of target noise segment 3 and target noise segment 4, it can be determined that the two times do not overlap. In this case, the duration of target noise segment 3 can be directly added to the duration of target noise segment 4, i.e., 5 minutes plus 5 minutes, to obtain the total duration of the target noise segments, which is 10 minutes.

[0090] When there is only one connected microphone, the durations of the identified target noise segments cannot overlap. In this case, the durations of the target noise segments can be directly added together to obtain the total duration of the target noise segments.

[0091] The overlap of the durations of the target noise segments does not affect the counting of the target noise segments. Regardless of the number of microphones connected to the server, the number of identified target noise segments can be directly counted.

[0092] Step 104: When the total duration of the target noise segment is greater than the duration threshold and the number of the target noise segments is greater than the number threshold, it is determined that the fan has malfunctioned.

[0093] After obtaining the total duration and number of target noise segments, it can be determined whether the total duration of the target noise segments is greater than the duration threshold and whether the number of target noise segments is greater than the number threshold. If the total duration of the target noise segments is greater than the duration threshold and the number of target noise segments is greater than the number threshold, it can be determined that the fan has malfunctioned. If the total duration of the target noise segments is less than or equal to the duration threshold, or the number of target noise segments is less than or equal to the number threshold, it can be determined that the fan is normal.

[0094] The duration threshold can be set to 10 seconds, or it can be determined and set by analyzing the noise during normal fan operation and during fan malfunction. This embodiment of the invention does not impose a specific limitation on the duration threshold. Similarly, the quantity threshold can also be set by the user, either to 1 or a value greater than 1. When the quantity threshold is set to 1, it means that when one target noise segment is detected and its duration exceeds the duration threshold, a fan malfunction can be determined; or when multiple target noise segments are detected and their total duration exceeds the duration threshold, a fan malfunction can be determined. When the quantity threshold is set to a value greater than 1, it means that when there are multiple target noise segments and their total duration exceeds the duration threshold, a fan malfunction can be determined. Setting the quantity threshold to a value greater than 1 can reduce false detections to some extent. Because identifying only one target noise segment may be a false detection, while identifying multiple target noise segments increases the probability of determining that the fan has malfunctioned.

[0095] By identifying fan noise data collected by the microphone, target noise segments are determined. These segments are noise data fragments with intensity exceeding a certain threshold. Analysis of these target noise segments yields their total duration and number. A fan malfunction is confirmed when both the total duration and number of target noise segments exceed a duration threshold and a number threshold, respectively. Detecting fan malfunctions through noise analysis allows for timely reporting to maintenance personnel, facilitating prompt replacement of faulty fans and improving server reliability.

[0096] Reference Figure 3 The diagram illustrates a flowchart of a fan status monitoring method provided by an embodiment of the present invention. A noise monitoring management process can be set up in the server's BMC (Blower Control Center). The BMC noise monitoring process mainly defines two classes: one class, Sound, which implements recording and file storage functions; and the other class, Tasks, which detects the recorded files, generates corresponding results, records alarm information, and activates fault indicators.

[0097] The BMC noise monitoring process polls the microphone and TF card to check their presence, enabling dynamic construction and destruction of the recording management object after hot-swapping. Once the BMC noise monitoring process confirms that both the microphone and TF card are present, it checks the number of microphones and instantiates microphone objects to record fan noise at preset time intervals. Simultaneously, the BMC noise monitoring process acquires the recording file (including fan noise data) via USB and stores it on the TF card. The BMC noise monitoring process then uses a noise detection algorithm to analyze the recording file on the TF card. This algorithm includes a noise recognition algorithm, employing a histogram noise estimation algorithm to identify noise across multiple channels, obtaining the noise segment corresponding to the high-energy mode in the histogram for each frequency band. After identifying the target noise segment, the algorithm performs statistical analysis and judgment to determine and output the fan operating status, which includes normal fan operation and fan malfunction. When a fan malfunction is detected, a fault indicator light illuminates to alert maintenance personnel, and alarm information is recorded simultaneously.

[0098] For the BMC noise monitoring process, users can close it via command line or GUI (Graphical User Interface). The systemd can be used to start and stop the process service, allowing users to have autonomy and control over their noise monitoring needs.

[0099] By identifying fan noise data collected by the microphone, target noise segments are determined. These segments are then analyzed to determine their total duration and number. A fan malfunction is confirmed when the total duration exceeds a duration threshold and the number of target noise segments exceeds a number threshold. Detecting fan malfunctions through noise analysis allows for timely reporting to maintenance personnel, facilitating the replacement of faulty fans and improving server reliability.

[0100] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0101] Reference Figure 4The diagram illustrates a structural block diagram of a fan status monitoring device according to an embodiment of the present invention. The device is applied to a server, which includes a fan and a microphone. Specifically, the device may include the following modules:

[0102] The noise data acquisition module 201 is used to acquire fan noise data collected by the microphone;

[0103] The noise data identification module 202 is used to identify the fan noise data and obtain the target noise segment; the target noise segment is a noise data segment with a noise intensity greater than a noise intensity threshold.

[0104] The noise data statistics module 203 is used to count the total duration of the target noise segment and the number of the target noise segments.

[0105] The fan status determination module 204 is used to determine that the fan has malfunctioned when the total duration of the target noise segment is greater than the duration threshold and the number of the target noise segments is greater than the number threshold.

[0106] Optionally, the noise data recognition module 202 is specifically used for:

[0107] The fan noise data is denoised using a histogram noise estimation algorithm to obtain the processed fan noise data.

[0108] The processed fan noise data is then identified to obtain the target noise segment.

[0109] Optionally, the target noise segment is identified from multiple target noise segments collected simultaneously by multiple microphones, and the noise data statistics module 203 is specifically used for:

[0110] Determine whether the durations of the target noise segments overlap;

[0111] If the durations of the target noise segments do not overlap, the durations of each target noise segment are added together to obtain the total duration of the target noise segment.

[0112] If the durations of the target noise segments overlap, the durations of each target noise segment are added together and the overlap duration is subtracted to obtain the total duration of the target noise segments.

[0113] Optionally, the server includes a Universal Serial Bus (USB) interface connected to a USB hub, the USB hub being connected to the microphone used for recording audio from the fan.

[0114] Optionally, the server is connected to a flash memory card; the device further includes:

[0115] A connection status detection module is used to poll and detect the connection status between the flash memory card and the microphone;

[0116] The noise data acquisition module is specifically used for: when a flash memory card is detected to be connected and a microphone is also connected, sending a recording command to the microphone; receiving fan noise data sent by the microphone and storing the fan noise data in the flash memory card; the fan noise data is obtained by the microphone recording the fan in response to the recording command.

[0117] Optionally, the noise data recognition module 202 is specifically used to: recognize the fan noise data stored in the flash memory card.

[0118] Optionally, the fan status determination module 204 is further configured to: determine that the fan is normal when the total duration of the target noise segment is less than or equal to the duration threshold, or when the number of the target noise segments is less than or equal to the number threshold.

[0119] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0120] Reference Figure 5 The diagram shows a structural block diagram of an electronic device 30 provided in an embodiment of the present invention. The electronic device 30 includes:

[0121] The processor 301, the memory 302, and the computer program 3021 stored in the memory 302 and capable of running on the processor 301. When the computer program 3021 is executed by the processor 301, it implements the various processes of the above-described cabinet testing method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0122] Reference Figure 6 The diagram shows a structural block diagram of a computer-readable storage medium 40 provided in an embodiment of the present invention. The computer-readable storage medium 40 stores a computer program 401. When the computer program 401 is executed by a processor, it implements the various processes of the above-described cabinet testing method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0123] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0124] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0126] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0128] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0129] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0130] The present invention has provided a detailed description of a fan status monitoring method, device, electronic device, and storage medium. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A fan status monitoring method, characterized in that, Applied to a server, the server including a fan and a microphone, the server being connected to a flash memory card; the method includes: When the polling detects that the flash memory card is connected and the microphone is connected, a recording command is sent to the microphone; the fan noise data collected by the microphone is acquired; the fan noise data is time-domain data with time as the independent variable and noise intensity as the dependent variable; The fan noise data is denoised using a histogram noise estimation algorithm to obtain the processed fan noise data. The processed fan noise data is identified to obtain the target noise segment; the target noise segment is a noise data segment whose noise intensity is greater than the noise intensity threshold. The total duration of the target noise segments and the number of target noise segments are calculated. When the total duration of the target noise segment exceeds the duration threshold and the number of the target noise segments exceeds the number threshold, it is determined that the fan has malfunctioned. The step of performing noise reduction processing on the fan noise data using a histogram noise estimation algorithm to obtain processed fan noise data includes: Calculate the energy spectrum of each single-channel audio speech; The power spectral density of the audio speech is calculated using first-order recursion; Calculate the histogram of the audio speech power spectral density for the first D frames; The power corresponding to the maximum value in the histogram is selected as the noise spectrum estimate; Noise spectrum estimation was performed using first-order regression to obtain the fan noise data after noise reduction and smoothing.

2. The method according to claim 1, characterized in that, The target noise segments are multiple target noise segments identified from fan noise data collected simultaneously by multiple microphones. The step of calculating the total duration of the target noise segments includes: Determine whether the durations of the target noise segments overlap; If the durations of the target noise segments do not overlap, the durations of each target noise segment are added together to obtain the total duration of the target noise segment. If the durations of the target noise segments overlap, the durations of each target noise segment are added together and the overlap duration is subtracted to obtain the total duration of the target noise segments.

3. The method according to claim 1, characterized in that, The server includes a Universal Serial Bus (USB) interface connected to a USB hub, which in turn connects to a microphone used for recording audio from the fan.

4. The method according to claim 3, characterized in that, The method further includes: Poll the connection status between the flash memory card and the microphone; The acquisition of fan noise data collected by the microphone includes: The system receives fan noise data transmitted by the microphone and stores the fan noise data in the flash memory card; the fan noise data is obtained by the microphone recording the fan in response to the recording command.

5. The method according to claim 4, characterized in that, The process of identifying the fan noise data includes: The fan noise data stored in the flash memory card is identified.

6. The method according to claim 1, characterized in that, The method further includes: The fan is determined to be normal when the total duration of the target noise segment is less than or equal to the duration threshold, or when the number of the target noise segments is less than or equal to the number threshold.

7. A fan status monitoring device, characterized in that, Applied to a server, the server including a fan and a microphone, the server being connected to a flash memory card; the device includes: The noise data acquisition module is used to send a recording command to the microphone when the polling detects that the flash memory card is connected and the microphone is connected; and to acquire fan noise data collected by the microphone; the fan noise data is time-domain data with time as the independent variable and noise intensity as the dependent variable; The noise data identification module is used to perform noise reduction processing on the fan noise data using a histogram noise estimation algorithm to obtain processed fan noise data; and to identify the processed fan noise data to obtain a target noise segment; the target noise segment is a noise data segment whose noise intensity is greater than a noise intensity threshold. The noise data statistics module is used to calculate the total duration of the target noise segment and the number of the target noise segments. The fan status determination module is used to determine that the fan has malfunctioned when the total duration of the target noise segment is greater than a duration threshold and the number of the target noise segments is greater than a number threshold. The step of performing noise reduction processing on the fan noise data using a histogram noise estimation algorithm to obtain processed fan noise data includes: Calculate the energy spectrum of each single-channel audio speech; The power spectral density of the audio speech is calculated using first-order recursion; Calculate the histogram of the audio speech power spectral density of the first D frames; the first D frames are the duration of the target noise segment; The power corresponding to the maximum value in the histogram is selected as the noise spectrum estimate; Noise spectrum estimation was performed using first-order regression to obtain the fan noise data after noise reduction and smoothing.

8. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps of the fan status monitoring method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the steps of the fan status monitoring method as described in any one of claims 1-6.

Images