Frequency domain fault diagnosis method and device, computer equipment and medium

Abstract

Embodiments of the invention disclose a frequency domain fault diagnosis method and apparatus, a computer device and a medium. The method comprises the steps of receiving acceleration data transmitted by a sensor in a to-be-diagnosed device; acquiring acceleration frequency spectrum data and / or speed frequency spectrum data according to the acceleration data; fault frequency bands are divided according to a preset frequency band division rule, and an RMS value in each fault frequency band is calculated; and judging whether the equipment has a fault according to the RMS value in each fault frequency band and generating a fault type. According to the frequency domain fault diagnosis method and device, the computer equipment and the medium provided by the embodiment of the invention, the method can be suitable for different equipment, the frequency domain fault diagnosis efficiency is high, and the diagnosis result is more accurate.

Description

Technical Field

[0001] The present application relates to the technical field of mechanical equipment, and in particular to a frequency domain fault diagnosis method, device, computer equipment, and medium. Background Art

[0002] In modern industrial production, condition monitoring and fault diagnosis of mechanical equipment are key to ensuring safe operation and improving production efficiency. Vibration analysis, as a key monitoring method, can capture equipment vibration signals to reveal its operating status and potential faults.

[0003] However, the current vibration data analysis process is highly dependent on the manual judgment of vibration analysts. Non-analysts need to conduct time domain, frequency domain, and trend analysis, and sometimes need to combine other data such as the equipment's structural characteristics, operating conditions, and historical data to accurately determine the fault location and severity. This process requires a high level of professional ability from analysts, but different analysts have different experience and professional capabilities, resulting in low diagnostic efficiency and uneven accuracy of diagnostic results. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems existing in the prior art. To this end, this application proposes a frequency domain fault diagnosis method, apparatus, computer device, and medium to implement frequency domain fault diagnosis that is applicable to different devices and can be performed efficiently and accurately.

[0005] In a first aspect, the present application provides a frequency domain fault diagnosis method, comprising:

[0006] receiving acceleration data transmitted by a sensor in the device to be diagnosed;

[0007] Obtaining acceleration spectrum data and / or velocity spectrum data according to the acceleration data;

[0008] Divide the fault frequency band according to the preset frequency band division rules and calculate the RMS value in each fault frequency band;

[0009] Whether the device is faulty is determined based on the RMS value in each fault frequency band and a fault type is generated.

[0010] The frequency domain fault diagnosis method provided in this application is applicable to different devices, has high frequency domain fault diagnosis efficiency, and more accurate diagnosis results.

[0011] In one embodiment of the above-mentioned frequency domain fault diagnosis method, obtaining acceleration spectrum data and / or velocity spectrum data according to the acceleration data includes:

[0012] Processing the acceleration data using Fourier transform to obtain a complex frequency domain representation of the acceleration;

[0013] Obtaining acceleration spectrum data based on the complex frequency domain representation of the acceleration; and / or,

[0014] Velocity spectrum data is calculated based on the complex frequency domain representation of the acceleration.

[0015] By processing acceleration data with Fourier transform to obtain at least one of acceleration spectrum data and velocity spectrum data, accurate spectrum data can be obtained to meet the needs of different devices.

[0016] In one embodiment of the above-mentioned frequency domain fault diagnosis method, dividing the fault frequency band according to a preset frequency band division rule and calculating the RMS value in each fault frequency band includes:

[0017] Get device information;

[0018] Divide the fault frequency band according to the preset frequency band division rules and the device information;

[0019] Calculate the RMS value within each fault frequency band.

[0020] The fault frequency band is divided according to the device information and preset frequency band division rules. Configuration diagnosis can be performed for different devices, with a wide range of applications and more accurate diagnostic results.

[0021] In one embodiment of the above-mentioned frequency domain fault diagnosis method, calculating the RMS value in each fault frequency band includes:

[0022] Calculate the RMS value of each fault frequency band in the frequency domain.

[0023] In one embodiment of the above-mentioned frequency domain fault diagnosis method, calculating the RMS value in each fault frequency band in the frequency domain includes:

[0024] Obtain the frequency amplitude within each fault frequency band;

[0025] An RMS value in each fault frequency band is calculated based on the frequency amplitude in each fault frequency band.

[0026] In one embodiment of the above-mentioned frequency domain fault diagnosis method, determining whether a device is faulty and generating a fault type based on the RMS value in each fault frequency band includes:

[0027] Determine whether the RMS value in each of the fault frequency bands is higher than a corresponding preset threshold;

[0028] If so, it is determined that the device is faulty and a fault type is generated according to the fault frequency band.

[0029] Whether the device is faulty is determined by whether the RMS value is higher than the corresponding preset threshold. This method is simple, fast and efficient.

[0030] In a second aspect, the present application further provides a frequency domain fault diagnosis device, the device comprising:

[0031] A receiving module, configured to receive acceleration data transmitted by a sensor in the device to be diagnosed;

[0032] a conversion module, configured to obtain acceleration spectrum data and / or velocity spectrum data according to the acceleration data;

[0033] A processing module, configured to divide the fault frequency band according to a preset frequency band division rule and calculate the RMS value in each fault frequency band;

[0034] The judgment module is used to judge whether the device is faulty and generate a fault type according to the RMS value in each fault frequency band.

[0035] In a third aspect, the present application also provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in any one of the first aspects when executing the computer program.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method as described in any one of the first aspects when the computer program is executed by a processor.

[0037] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The disclosure of this application will be more easily understood with reference to the accompanying drawings. Those skilled in the art will readily appreciate that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this application. Furthermore, similar numbers in the figures represent similar components, where:

[0039] Figure 1 This is a flow chart of a frequency domain fault diagnosis method provided by an embodiment of the present application;

[0040] Figure 2 1 is a schematic diagram of the overall speed effective value trend of the speed spectrum of the XD-020 model single-stage rotary vane vacuum pump in an example of an embodiment of the present application;

[0041] Figure 3 1 is a schematic diagram of the RMS value trend in the 24-26 Hz frequency band of the speed spectrum of the XD-020 single-stage rotary vane vacuum pump in an example of an embodiment of the present application;

[0042] Figure 41 is a schematic diagram of the RMS effective value trend in the 74-76 Hz frequency band of the speed spectrum of the XD-020 model single-stage rotary vane vacuum pump in an example of an embodiment of the present application;

[0043] Figure 5 This is a structural diagram of a frequency domain fault diagnosis device provided by an embodiment of the present application;

[0044] Figure 6 This is an architectural diagram provided by an embodiment of the present application. DETAILED DESCRIPTION

[0045] Some embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the scope of protection of the present application.

[0046] As mentioned in the background, vibration data analysis currently relies heavily on the analyst's judgment. However, vibration analysis requires different data in different situations, placing a high level of expertise on the analyst. However, differences in analyst skill and experience result in low diagnostic efficiency and varying accuracy in current vibration data analysis.

[0047] In order to solve the above problems, the present application creatively proposes a frequency domain fault diagnosis method, device, computer equipment and medium. After obtaining the acceleration data transmitted by the sensor in the device, fault diagnosis is performed based on the preset fault frequency band of the device parameters. It is suitable for frequency domain fault diagnosis of different devices, and the diagnostic results are accurate and the diagnostic efficiency is high.

[0048] The present application will be described in detail below through specific embodiments.

[0049] The present invention provides a method for diagnosing faults in the frequency domain. Figure 1 As shown, the method includes:

[0050] S110: Receive acceleration data transmitted by a sensor in the device to be diagnosed.

[0051] The device to be diagnosed may specifically be various types of fan equipment, such as centrifugal, cantilever, DC, and positive displacement; various types of pump equipment, such as centrifugal pumps, Roots pumps, and screw pumps; and various types of motor equipment, such as DC motors, asynchronous motors, and synchronous motors. The device to be diagnosed may also be other mechanical equipment, which is not specifically limited in this application.

[0052] Sensors installed in the equipment monitor its acceleration during operation. Specifically, fans, pumps, and motors all contain bearings, which are the primary load points of the equipment. The rotational state of the bearings reflects the equipment's operating status. Therefore, sensors are installed on the equipment's bearing seats, and the acceleration data they transmit is the equipment's vibration acceleration data.

[0053] In some embodiments, the sensor may also be a velocity sensor, transmitting vibration velocity data of the device.

[0054] S120 : Obtain acceleration spectrum data and / or velocity spectrum data according to the acceleration data.

[0055] Specifically, according to the specific device data to be diagnosed, the received acceleration data is converted into at least one of acceleration spectrum data and velocity spectrum data.

[0056] The device data includes at least one of the device type, device structure, and on-site installation conditions. For the type of spectrum data to be converted from acceleration data, a preset conversion rule may specify the correspondence between the device data and the spectrum data type. For example:

[0057] The device data of the device that currently needs to be diagnosed for fault includes: the device type is a motor, the device structure includes a cooling fan, and the on-site installation is a floor installation. According to the correspondence between the above-mentioned device data and the spectrum data type specified in the preset conversion rules, the spectrum data type corresponding to the above-mentioned device data is acceleration spectrum, and the acceleration data is converted into acceleration spectrum data.

[0058] When the data transmitted by the sensor in the receiving device is velocity data, such as the vibration velocity of the device, the preset conversion rule stipulates that the received velocity data is converted into a velocity spectrum to avoid data distortion caused by converting the velocity data into an acceleration spectrum.

[0059] S130 : Divide the fault frequency bands according to a preset frequency band division rule and calculate the RMS value in each fault frequency band.

[0060] S140: Determine whether the device is faulty based on the RMS value in each fault frequency band and generate a fault type.

[0061] The frequency domain fault diagnosis method provided in this application is applicable to different devices, has high frequency domain fault diagnosis efficiency, and more accurate diagnosis results.

[0062] In some embodiments, S120 includes:

[0063] Processing the acceleration data with Fourier transform to obtain the complex frequency domain representation of acceleration;

[0064] When converting the received acceleration data into acceleration spectrum data according to the device data to be diagnosed as needed, the acceleration spectrum data is obtained by converting the complex frequency domain representation of the acceleration; when converting the received acceleration data into velocity spectrum data according to the device data to be diagnosed as needed, the velocity spectrum data is obtained by calculation based on the complex frequency domain representation of the acceleration; when converting the received acceleration data into acceleration spectrum data and velocity spectrum data according to the device data to be diagnosed as needed, the acceleration spectrum data is obtained by converting the complex frequency domain representation of the acceleration and the velocity spectrum data is obtained by calculation based on the complex frequency domain representation of the acceleration.

[0065] By processing acceleration data with Fourier transform to obtain at least one of acceleration spectrum data and velocity spectrum data, accurate spectrum data can be obtained to meet the needs of different devices.

[0066] In some preferred embodiments, before processing the acceleration data by Fourier transform to obtain a complex frequency domain representation of the acceleration, the method further comprises:

[0067] Preprocess the acceleration data.

[0068] Specifically, preprocessing the acceleration data includes: removing DC offset from the acceleration data to obtain a debiased acceleration speed signal;

[0069] A Hanning window is applied to the debiased acceleration signal to reduce spectrum leakage to obtain a processed acceleration signal. The processed acceleration signal is processed by fast Fourier transform to obtain a complex frequency domain representation of acceleration.

[0070] The Hanning window, also known as the Henning window, is a commonly used window function in digital signal processing. It is a weighted cosine window used to reduce spectral leakage. Applying a Hanning window to a signal before performing a fast Fourier transform (FFT) can improve the results of frequency domain analysis.

[0071] The mathematical expression of the Hanning window is:

[0072]

[0073] Where n = 1, 2, 3, ..., N-1; N represents the total length of the window function. The Hanning window helps to reduce discontinuities at both ends of the signal, thereby reducing spectrum leakage.

[0074] For example, the original acceleration time domain signal is recorded as: a(n), with a sampling frequency of fs and a sampling point number of N. The original acceleration time domain signal is subjected to DC offset processing to remove the DC component of the signal. A Hanning window is then applied to the offset signal to reduce spectral leakage, thereby obtaining the preprocessed acceleration data.

[0075] The acceleration spectrum is obtained by calculating the converted acceleration data using the following method:

[0076] The original acceleration data, i.e., discrete acceleration data, is fast Fourier transformed to obtain the complex frequency domain representation of acceleration. The complex frequency domain representation of acceleration is then modulo-normalized by dividing it by N. The amplitude of the positive frequency component is multiplied by 2 (to combine the negative frequency energy) to obtain the acceleration spectrum data:

[0077]

[0078] in:

[0079] A(k): represents the spectrum amplitude at point k;

[0080] a(n): represents the acceleration value of the nth sampling point;

[0081] N: total number of sampling points;

[0082] j: imaginary unit.

[0083] The acceleration spectrum data is obtained through the above formula.

[0084] The velocity spectrum is obtained by converting the acceleration data using the following formula:

[0085]

[0086] in:

[0087] V(k): represents the velocity spectrum amplitude at point k;

[0088] f: frequency;

[0089] j: imaginary unit.

[0090] In some embodiments, S130 includes:

[0091] Get device information;

[0092] Divide the fault frequency band according to the preset frequency band division rules and the device information;

[0093] Calculate the RMS value within each fault frequency band.

[0094] The preset frequency band division rules specify the fault frequency bands corresponding to equipment of different types and structures. The preset frequency band division rules can be formulated by highly professional and experienced analysts, or based on the analysis and summary of massive historical equipment operation data.

[0095] For example, the preset frequency band division rules specify frequency band division based on the device model, speed, and on-site installation conditions. For example, if the current device model is an XD-020 single-stage rotary vane vacuum pump with three blades, a speed of 1500 rpm, and a floor-mounted installation, the corresponding velocity spectrum generated based on the preset frequency band division rules shows a base loosening fault frequency band of 24-26 Hz, and a blade friction fault frequency band of 74-76 Hz. The RMS values ​​within the base loosening fault frequency band and the blade friction fault frequency band are then calculated.

[0096] Reference Figure 2 As shown, Figure 2 is the overall effective value of speed, which has increased.

[0097] Figure 3 This is the RMS value trend in the 24-26Hz frequency band, with no increase.

[0098] Figure 4 The RMS value trend in the 74-76Hz frequency band shows a significant increase. Under normal operation, it is about 0.4mm / s. The threshold is set to 1mm / s, which has exceeded the threshold and alarmed. This corresponds to the fault blade friction.

[0099] The RMS (Root Mean Square) value, also known as the effective value, is a statistic that measures the amplitude of an AC signal. It represents the square root of the average power of the signal over a period of time and is used to characterize the effective energy in the signal.

[0100] The fault frequency band is divided according to the device information and preset frequency band division rules. Configuration diagnosis can be performed for different devices, with a wide range of applications and more accurate diagnostic results.

[0101] In some embodiments, calculating the RMS value in each fault frequency band includes:

[0102] Calculate the RMS value of each fault frequency band in the frequency domain.

[0103] The calculation of RMS value has time domain method and frequency domain method. In this application, the calculation of RMS value is specifically obtained by the following steps:

[0104] Let F1 be the lower limit of the frequency band, F2 be the upper limit of the frequency band, and let the frequency amplitude between F1 and F2 be A1, A2, A3....A n ; The formula for calculating the RMS value within the frequency band is:

[0105]

[0106] The spectrum amplitude is the peak value.

[0107] Exemplarily, calculating the RMS value in each fault frequency band in the frequency domain includes:

[0108] According to the preset frequency band division rules, the 24-26Hz frequency band is divided as the basic loose fault frequency band.

[0109] Then calculate the position of 24 and 26 Hz in the spectrum horizontal coordinate, that is, the index of the frequency axis, set as f_index1 and f_index2. Then calculate the speed spectrum V(f_index1) to V

[0110] (f_index2) is a valid value between 0 and 1.

[0111] Based on the preset frequency band division rules, the 74-76 Hz frequency band is divided into the blade friction fault frequency band. First, calculate the frequency axis position of 74 and 76 Hz respectively, that is, the index of the frequency axis, and set them as f_index3 and f_index4.

[0112] Then find the effective value between V(f_index1) and V(f_index2) in the velocity spectrum graph.

[0113] In some embodiments, determining whether the device is faulty and generating a fault type based on the RMS value in each fault frequency band in step S140 includes:

[0114] S141 , determine whether the RMS value in each fault frequency band is higher than the corresponding preset threshold; if so, proceed to S142 .

[0115] S142. Determine the equipment fault and generate a fault type according to the fault frequency band.

[0116] Whether a device is faulty is determined by whether the RMS value is higher than the corresponding preset threshold value. The method is simple, fast and efficient. In some embodiments, after calculating the RMS value in each fault frequency band, a curve is generated based on the RMS values ​​in all fault frequency bands, with the RMS value as the vertical axis and the acceleration data acquisition time as the horizontal axis. Whether a fault has occurred is determined based on whether the RMS value in the curve is higher than the corresponding preset threshold value. If the RMS value is higher than the corresponding preset threshold value, it is determined that a fault has occurred, and the corresponding fault type is generated based on the fault frequency band in which it is located. When the RMS value in a certain fault frequency band is abnormal, that is, the RMS value in a certain fault frequency band is higher than the preset threshold value, it is determined that the currently diagnosed device is faulty, and the fault type is determined based on the frequency band in which the fault occurs. This allows for intuitive and rapid diagnosis of device faults.

[0117] The present application also provides a frequency domain fault diagnosis device, referring to Figure 5 As shown, the device includes:

[0118] The receiving module 510 is configured to receive acceleration data transmitted by a sensor in the device to be diagnosed.

[0119] The device to be diagnosed is equipped with a sensor capable of monitoring the vibration acceleration of the device during operation. Specifically, whether it is a fan, a pump, or a motor, each device has a bearing. The bearing is the primary stress point of the device, and the rotational state of the bearing reflects the operating state of the device. The sensor in the device to be diagnosed is installed on the device's bearing seat. The receiving module 510 receives the acceleration data transmitted by the sensor, namely the device's vibration acceleration data.

[0120] The conversion module 520 is configured to obtain acceleration spectrum data and / or velocity spectrum data according to the acceleration data.

[0121] Specifically, the conversion module 520 converts the received vibration acceleration data of the device into at least one of acceleration spectrum data and velocity spectrum data according to the specific device data to be diagnosed.

[0122] The device data includes at least one of the device type, device structure, and on-site installation conditions. For the type of spectrum data to be converted from acceleration data, a preset conversion rule may specify the correspondence between the device data and the spectrum data type. For example:

[0123] The device data of the current device to be diagnosed includes: the device type is a motor, the device structure includes a cooling fan, and the on-site installation is a floor-standing installation. The conversion module 520 converts the acceleration data into acceleration spectrum data according to the correspondence between the above-mentioned device data and the spectrum data type specified in the preset conversion rules. The spectrum data type corresponding to the above-mentioned device data is acceleration spectrum.

[0124] When the data transmitted by the sensor in the receiving device is velocity data, such as the vibration velocity of the device, the conversion module 520 converts the received velocity data into a velocity spectrum according to a preset conversion rule to avoid data distortion caused by converting the velocity data into an acceleration spectrum.

[0125] The processing module 530 is configured to divide the fault frequency bands according to a preset frequency band division rule and calculate the RMS value in each fault frequency band.

[0126] The judgment module 540 is configured to judge whether the device is faulty and generate a fault type based on the RMS value in each fault frequency band.

[0127] In some embodiments, the conversion module 520 includes:

[0128] a first conversion unit, configured to process the acceleration data by Fourier transform to obtain a complex frequency domain representation of the acceleration;

[0129] a second conversion unit, configured to obtain acceleration spectrum data based on the complex frequency domain representation of the acceleration;

[0130] The first calculation unit is configured to calculate and obtain velocity spectrum data based on the complex frequency domain representation of the acceleration.

[0131] In some embodiments, the apparatus further comprises:

[0132] Preprocessing module, used to preprocess acceleration data, including:

[0133] a debiasing unit, configured to remove a DC offset from the acceleration data to obtain a debiased acceleration signal;

[0134] an application unit, configured to apply a Hanning window to the debiased acceleration signal to obtain a processed acceleration signal;

[0135] The first conversion unit is used to process the processed acceleration signal by fast Fourier transform to obtain a complex frequency domain representation of the acceleration.

[0136] In some embodiments, the processing module 530 includes:

[0137] An acquisition unit, used to acquire device information;

[0138] A division unit, configured to divide the fault frequency band according to a preset frequency band division rule and the device information;

[0139] The second calculation unit is used to calculate the RMS value in each fault frequency band.

[0140] In some embodiments, the second calculation unit is configured to calculate the RMS value in each fault frequency band in the frequency domain.

[0141] In some embodiments, the second computing unit includes:

[0142] An acquisition subunit, used to obtain the frequency amplitude within each fault frequency band;

[0143] The calculation subunit is configured to calculate the RMS value in each fault frequency band based on the frequency amplitude in each fault frequency band.

[0144] In some embodiments, the determination module 540 includes:

[0145] The first judgment unit is used to judge whether the RMS value in each fault frequency band is higher than the corresponding preset threshold;

[0146] The second judgment unit is configured to judge that the device has a fault and generate a fault type according to the fault frequency band after the judgment result of the first judgment unit is yes.

[0147] An embodiment of the present application also provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any step of the method described in the above embodiment is implemented.

[0148] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method as described in any one of the first aspects when the computer program is executed by a processor.

[0149] refer to Figure 6 , which exemplarily shows the architecture of a computer device, which may specifically include a processor 610, a video display adapter 611, a disk drive 612, an input / output interface 613, a network interface 614, and a memory 620. The processor 610, video display adapter 611, disk drive 612, input / output interface 613, network interface 614, and memory 620 may be communicatively connected via a communication bus 630.

[0150] Among them, the processor 610 can be implemented by a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in this application.

[0151] The memory 620 can be implemented in the form of a read-only memory (ROM), a random access memory (RAM), a static storage device, a dynamic storage device, etc. The memory 620 can store an operating system 621 and a basic input and output system (BIOS) 622. In addition, it can also store a web browser 623, a data storage manager 624, etc. In short, when the technical solution provided in this application is implemented through software or firmware, the relevant program code is stored in the memory 620 and is called and executed by the processor 610.

[0152] The input / output interface 613 is used to connect to input / output modules to implement information input and output. The input / output modules can be configured as components within the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. Input devices may include a keyboard, mouse, touch screen, microphone, various sensors, etc., and output devices may include a display, speaker, vibrator, indicator light, etc.

[0153] The network interface 614 is used to connect to a communication module (not shown) to enable communication between the device and other devices. The communication module can communicate via a wired method (such as USB, network cable, etc.) or a wireless method (such as mobile network, WiFi, Bluetooth, etc.).

[0154] The communication bus 630 comprises a pathway for transmitting information between the various components of the device (eg, the processor 610 , the video display adapter 611 , the disk drive 612 , the input / output interface 613 , the network interface 614 ), and the memory 620 .

[0155] In addition, the computer device 600 can also obtain information on specific collection conditions from the virtual resource object collection condition information database for use in condition judgment, etc.

[0156] It should be noted that although the computer device 600 shown above only includes a processor 610, a video display adapter 611, a disk drive 612, an input / output interface 613, a network interface 614, a memory 620, and a communication bus 630, in a specific implementation, the computer device may also include other components necessary for normal operation. In addition, those skilled in the art will understand that the device may only include the components necessary to implement the solution of the present application, and does not necessarily include all the components shown in the figure.

[0157] Through the description of the above implementation methods, it can be seen that those skilled in the art can clearly understand that the present application can be implemented by means of software plus the necessary general hardware platform. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a cloud server, or a network device, etc.) to execute the methods of each embodiment of the present application or certain parts of the embodiments.

[0158] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0159] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0160] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A frequency domain fault diagnosis method, characterized in that: include: receiving acceleration data transmitted by a sensor in the device to be diagnosed; Obtaining acceleration spectrum data and / or velocity spectrum data according to the acceleration data; Divide the fault frequency band according to the preset frequency band division rules and calculate the RMS value in each fault frequency band; Whether the device is faulty is determined based on the RMS value in each fault frequency band and a fault type is generated.

2. The frequency domain fault diagnosis method according to claim 1, characterized in that: The obtaining of acceleration spectrum data and / or velocity spectrum data according to the acceleration data includes: Processing the acceleration data using Fourier transform to obtain a complex frequency domain representation of the acceleration; Obtaining acceleration spectrum data based on the complex frequency domain representation of the acceleration; and / or, Velocity spectrum data is calculated based on the complex frequency domain representation of the acceleration.

3. The frequency domain fault diagnosis method according to claim 2, characterized in that: The method further comprises: Preprocessing the acceleration data includes: Processing the acceleration data to remove DC offset to obtain a debiased acceleration signal; Applying a Hanning window to the debiased acceleration signal to obtain a processed acceleration signal; Processing the acceleration data by Fourier transform to obtain a complex frequency domain representation of the acceleration includes: The processed acceleration signal is processed by Fourier transform to obtain a complex frequency domain representation of the acceleration.

4. The frequency domain fault diagnosis method according to claim 1, characterized in that: Dividing the fault frequency band according to the preset frequency band division rule and calculating the RMS value in each fault frequency band includes: Get device information; Divide the fault frequency band according to the preset frequency band division rules and the device information; Calculate the RMS value within each fault frequency band.

5. The frequency domain fault diagnosis method according to claim 1, characterized in that: Calculating the RMS value in each fault frequency band includes: Calculate the RMS value of each fault frequency band in the frequency domain.

6. The frequency domain fault diagnosis method according to claim 4, characterized in that: Calculating the RMS value in each fault frequency band in the frequency domain includes: Obtain the frequency amplitude within each fault frequency band; An RMS value in each fault frequency band is calculated based on the frequency amplitude in each fault frequency band.

7. The frequency domain fault diagnosis method according to claim 1, characterized in that: The determining whether the device is faulty and generating a fault type according to the RMS value in each fault frequency band includes: Determine whether the RMS value in each of the fault frequency bands is higher than a corresponding preset threshold; If so, it is determined that the device is faulty and a fault type is generated according to the fault frequency band.

8. A frequency domain fault diagnosis device, characterized in that: The device comprises: A receiving module, configured to receive acceleration data transmitted by a sensor in the device to be diagnosed; a conversion module, configured to obtain acceleration spectrum data and / or velocity spectrum data according to the acceleration data; A processing module, configured to divide the fault frequency band according to a preset frequency band division rule and calculate the RMS value in each fault frequency band; The judgment module is used to judge whether the device is faulty and generate a fault type according to the RMS value in each fault frequency band.

9. A computer device, characterized in that: The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images