Industrial equipment fault diagnosis method, device, equipment and storage medium

Abstract

The present invention provides a method, device, equipment and storage medium for diagnosing industrial equipment faults. The method includes: obtaining a vibration signal of the equipment to be diagnosed, converting the vibration signal into a frequency spectrum; determining the fault frequency of interest, and using the fault frequency as the fundamental frequency; based on the frequency spectrum, adaptively correcting the fundamental frequency using peak screening and harmonic frequency recursion rules to obtain the corrected fundamental frequency; calculating the narrowband energy and peak significance corresponding to the corrected fundamental frequency according to preset narrowband monitoring parameters; using a hypothesis test method to determine the change trend of the narrowband energy, and triggering a fault alarm if there is a significant upward trend. The present invention realizes accurate fault diagnosis and automatic alarm through joint determination of the narrowband energy of the fault frequency and the significant peak, thereby reducing the manpower cost in fault diagnosis.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to an industrial equipment fault diagnosis method, device, equipment and storage medium. Background Art

[0002] In modern industrial production, the reliability and stability of equipment have a significant impact on production efficiency and product quality. Equipment failure not only causes production line stagnation, but also increases maintenance costs, so timely and accurate fault diagnosis is particularly important. Current industrial equipment, especially rotating mechanical equipment, often relies on vibration spectrum analysis to determine the fault by analyzing the characteristic performance near the fault frequency in the spectrum.

[0003] Fault frequency is the frequency characteristic of periodic vibration signals generated by various defects during the operation of the equipment. When a component of a mechanical device fails, a specific vibration frequency component will be superimposed on the original normal operation signal. By identifying and analyzing these characteristic frequencies, the type, location and severity of the fault can be determined, thereby realizing equipment status monitoring and fault diagnosis. The fault frequency is related to the structural parameters and speed of the equipment itself. In actual applications, the fault frequency often does not correspond to the position of the peak in the spectrum diagram. This phenomenon may be caused by a variety of factors, such as inaccurate calculation of equipment speed, nonlinear characteristics of the equipment, environmental interference, sensor noise, and changes in the operating status of the equipment. These factors may cause the spectrum peak to shift, making the identification of the fault frequency more complicated and difficult. Therefore, the traditional spectrum analysis method cannot accurately reflect the true fault frequency in many cases, which may lead to misdiagnosis or missed diagnosis. Summary of the invention

[0004] In view of this, an object of the present invention is to provide an industrial equipment fault diagnosis method, device, equipment and storage medium to improve the above-mentioned problem.

[0005] A method for diagnosing faults of industrial equipment comprises: obtaining a vibration signal of a device to be diagnosed, and converting the vibration signal into a frequency spectrum; Determine a fault frequency of concern, and use the fault frequency as a base frequency; Based on the spectrum diagram, the fundamental frequency is adaptively corrected by using peak screening and harmonic frequency recursion rules to obtain a corrected fundamental frequency; and the narrowband energy and peak significance corresponding to the corrected fundamental frequency are calculated according to preset narrowband monitoring parameters; A hypothesis testing method is used to determine the variation trend of the narrowband energy, and if there is a significant upward trend, a fault alarm is triggered.

[0006] Preferably, the step of acquiring a vibration signal of a device and converting the vibration signal into a frequency spectrum comprises: Obtain the signal data of the vibration sensor installed on the device to be diagnosed over a period of time to obtain the vibration signal of the device to be diagnosed; Use the fast Fourier transform to convert the vibration signal into a spectrum, take the first half of the spectrum, convert the spectrum amplitude from a complex number to a real number, and obtain a spectrogram composed of a frequency sequence and an amplitude sequence.

[0007] Preferably, the determination of the fault frequency of concern includes: Calculate the fault frequency characterizing a specific fault based on the structural parameters of the device to be diagnosed, and use the fault frequency as the fundamental frequency.

[0008] Preferably, based on the spectrogram, the adaptive correction of the fundamental frequency using the peak screening and harmonic frequency recurrence rule includes: Obtain all peak points in the spectrogram; Search for peak points within the frequency narrowband sequence range formed by the fundamental frequency and its harmonic multiples to obtain a peak point sequence; where each narrowband retains at most one peak point, and when there are multiple peak points, the one with the higher amplitude is retained, and when there is no peak point, None is used as a placeholder; Use the binary search method to find the longest sequence in the peak point sequence that contains at least two non-None points, and the longest sequence conforms to the harmonic frequency recurrence rule; If the longest sequence is found, divide the fundamental frequency peak point frequency or the lowest harmonic multiple peak point frequency in the longest sequence by the multiple as the corrected fundamental frequency, otherwise the fundamental frequency is not corrected.

[0009] Preferably, the harmonic multiple is 1-5 times; the frequency narrowband sequence range is the frequency narrowband sequence range formed by the fundamental frequency and its 1-5 times harmonic multiples and the first error range e1; The harmonic frequency recurrence rule, that is, idx×base×(1 - e2) < a < idx×base×(1 + e2), where base is the fundamental frequency, a is the frequency of a certain point in the peak point sequence, idx is the position of this point in the peak point sequence, e2 is the second error range, and e1 >= e2.

[0010] Preferably, the calculation of the narrowband energy and peak significance corresponding to the corrected fundamental frequency according to the preset narrowband monitoring parameters includes: Calculate the narrowband ranges corresponding to the fundamental frequency and its harmonic multiples and sideband frequencies according to the preset narrowband monitoring parameters; Calculate the maximum amplitude within each narrowband as the energy of the narrowband; Determine whether there is a significant peak in each narrow band whose ratio of prominence to peak width is greater than a preset value; wherein, peak prominence = peak amplitude - max (left valley amplitude, right valley amplitude), and max (left valley amplitude, right valley amplitude) represents the larger value of the left valley amplitude and the right valley amplitude.

[0011] Preferably, the method of determining the narrowband energy trend by using a hypothesis testing method comprises: Obtain the narrowband energy sequence of the spectrum graph within a period of time, and filter out the narrowband energy sequence containing significant peaks; A hypothesis testing method is used to determine whether the narrowband energy sequence has a significant upward trend, and if so, a fault alarm is triggered.

[0012] The embodiment of the present invention further provides an industrial equipment fault diagnosis device, which includes: A frequency spectrum acquisition unit, used to acquire a vibration signal of the device to be diagnosed and convert the vibration signal into a frequency spectrum; A fundamental frequency determination unit is used to determine the fault frequency of concern and use the fault frequency as the fundamental frequency; a fundamental frequency correction unit is used to adaptively correct the fundamental frequency based on the spectrum diagram by using peak screening and harmonic frequency recursion rules to obtain the corrected fundamental frequency; a peak significance calculation unit is used to calculate the narrowband energy and peak significance corresponding to the corrected fundamental frequency according to preset narrowband monitoring parameters; a judgment unit is used to judge the changing trend of the narrowband energy by using a hypothesis testing method, and if there is a significant upward trend, a fault alarm is triggered.

[0013] An embodiment of the present invention further provides an industrial equipment fault diagnosis device, which includes a memory and a processor. The memory stores a computer program, and the computer program can be executed by the processor to implement the industrial equipment fault diagnosis method as described above.

[0014] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. The computer program can be executed by a processor of a device where the computer-readable storage medium is located to implement the above-mentioned industrial equipment fault diagnosis method.

[0015] The present invention obtains the time domain signal of the equipment vibration sensor, uses fast Fourier transform to obtain the spectrum diagram, and determines the fundamental frequency of the fault of concern. Then, an innovative peak-finding and binary search algorithm is used to search for peak points near the fundamental frequency and its harmonics to correct the fundamental frequency. Based on the corrected fundamental frequency, the present invention calculates the energy and peak significance of multiple narrowband ranges, and tracks the recent changing trends of these features. Through the Kendall's tau hypothesis test, it is determined whether there is a narrow band with a significant increase in energy, thereby achieving accurate diagnosis of equipment faults and automatic alarms, reducing the manpower cost in fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a process flow of an industrial equipment fault diagnosis method provided by an embodiment of the present application is shown; Figure 2 A schematic diagram of the structure of an industrial equipment fault diagnosis device provided in an embodiment of the present application is shown; Figure 3 A schematic diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] refer to Figure 1 As shown, the first embodiment of the present invention discloses an industrial equipment fault diagnosis method, which can be executed by an industrial equipment fault diagnosis device (hereinafter referred to as a diagnosis device), and in particular, executed by one or more processors in the diagnosis device to implement the following method: S101, obtaining a vibration signal of a device to be diagnosed, and converting the vibration signal into a frequency spectrum.

[0019] Specifically, firstly, the signal data of the vibration sensor installed on the device to be diagnosed within a period of time is obtained to obtain the vibration signal of the device to be diagnosed; then, the vibration signal is converted into a spectrum using fast Fourier transform, the first half of the spectrum is taken, and the spectrum amplitude is converted from a complex number to a real number to obtain a spectrum diagram consisting of a frequency sequence and an amplitude sequence.

[0020] For example, the vibration sensor data acquisition frequency (sampling rate) is 50000 Hz, and 60 seconds of vibration signal data is obtained. The data unit is , the data length is 3 million. The length of the frequency sequence and amplitude sequence in the spectrum are both 1.5 million, and the range of the frequency sequence is 0~25000Hz.

[0021] S102, determining a concerned fault frequency, and taking the fault frequency as a base frequency.

[0022] In this embodiment, each device has one or more specific faults, so the fault frequency characterizing the specific fault can be calculated based on the structural parameters of the device to be diagnosed, and the fault frequency is used as the base frequency.

[0023] For example, taking the cage as an example, the calculation formula for the cage failure frequency is: FTF = (f / 2) × (1 - d×cos(β) / D) Where: f = rotational speed (rpm or Hz), d = rolling element diameter, D = pitch diameter circle, β = contact angle.

[0024] Exemplarily, assuming the rolling element diameter of the cage is 14.29 mm, the pitch diameter circle is 77.50 mm, the contact angle is 0°, and the rotational speed of this device is 24.83 Hz, then the fault frequency FTF of the cage is (24.83 / 2) × (1 - 14.29×cos(0) / 77.50) = 10.12 Hz. The fundamental frequency is 10.12 Hz.

[0025] S103, based on the spectrogram, adaptively correct the fundamental frequency by using peak screening and harmonic frequency recurrence rules. Specifically: First, use the peak finding method to find all peak points in the spectrogram. Each peak point contains a peak frequency and a peak amplitude; Then, obtain the specified first error range e1 and second error range e2, where e1 >= e2; Next, search for peak points within the frequency narrowband sequence range formed around the fundamental frequency and its 1 - 5 times harmonic frequencies within the e1 range. At most one peak point is retained in each narrowband. When there are multiple peak points, the one with the higher amplitude is retained. When there is no peak point, None is used for placeholder. The retained peak point sequence is denoted as the peak point sequence peaks. It should be noted here that the 1 times harmonic frequency is twice the fundamental frequency; Then, use the binary search method to find the longest sequence in peaks that contains at least two non - None points and conforms to the harmonic frequency recurrence rule idx×base×(1 - e2) < a < idx×base×(1 + e2), where base is the fundamental frequency, a is the frequency of a certain point in this sequence, and idx is the position of this point in peaks.

[0026] If the longest sequence is found, if there is a fundamental frequency peak point in the longest sequence, the frequency of this peak point is the corrected fundamental frequency. If there is no fundamental frequency peak point in the longest sequence, the frequency of the peak point with the lowest multiple divided by this multiple is the corrected fundamental frequency. If the longest sequence is not found, the fundamental frequency is not corrected.

[0027] For example, assume e1 is 1 Hz and e2 is 0.1 Hz.

[0028] Then the narrowband ranges composed of the fundamental frequency and its 1 - 5 times harmonic frequencies are [[9.12, 11.12], [19.24, 21.24], [29.36, 31.36], [39.48, 41.48], [49.6, 51.6], [59.72, 61.72]].

[0029] Assume that the peak point sequence peaks is [(10.5,0.5),None,(31.51,0.2),(44,0.4),(52.53,0.2),(66,0.5)], where None means that there is no peak point in the second interval, and (10.5,0.5) means that the peak point frequency of the first interval is 10.5Hz and the amplitude is 0.5 .

[0030] Because [(10.5,0.5),(31.51,0.2),(52.53,0.2)] is the longest regular combination of octaves, the corrected fundamental frequency is 10.5 Hz.

[0031] S104, calculating the narrowband energy and peak significance corresponding to the corrected fundamental frequency according to preset narrowband monitoring parameters.

[0032] Specifically: Firstly, all narrowband ranges to be monitored are calculated according to the specified narrowband monitoring parameters (narrowband width w, harmonic multiple n, sideband offset frequency sb).

[0033] Where, the fundamental frequency is recorded as bf, then the fundamental frequency narrowband range = [bf×(1-w), bf×(1+w)], the k-fold harmonic narrowband range = [bf×k×(1-w), bf×k×(1+w)], the sideband narrowband range = [(bf+sb)×(1-w), (bf+sb)×(1+w)], where k<=n, so there are n+2 narrowbands for one fault frequency; Then, the energy of each narrow band is calculated, and the energy is the highest amplitude in the narrow band; Finally, calculate whether each narrow band has a significant peak. If there is a peak point in the narrow band, and the ratio of the peak prominence to the peak width is greater than the specified value, it is considered to have a significant peak, otherwise it is considered to have no significant peak. The peak prominence = peak amplitude - max (left valley amplitude, right valley amplitude).

[0034] For example, assuming that the narrowband width w is 0.005, the harmonic multiple n is 5, the sideband offset frequency sb is 3 Hz, and the significant peak designation ratio is 0.1.

[0035] The baseband narrowband range to be monitored is [10.4475, 10.5525].

[0036] The harmonic frequency narrowband range to be monitored is [[10.4475, 10.5525], [20.895, 21.105], [31.3425, 31.6575], [41.79, 42.21], [52.2375, 52.7625], [62.685, 63.315]].

[0037] The sideband narrowband range to be monitored is [13.4475, 13.5525].

[0038] Assume that only the fundamental frequency narrowband range has a peak point (10.5, 0.5), the amplitudes of the left and right valleys of the peak are both 0.02, and the peak width is 2.

[0039] The peak significance is (0.5-0.02) / 2=0.24, which is greater than the specified ratio of 0.1. Therefore, the energy of the returned fundamental frequency narrowband range of 10.4475Hz~10.5525Hz is 0.5. .

[0040] S105, using a hypothesis testing method to determine the variation trend of the narrowband energy, and if there is a significant upward trend, triggering a fault alarm.

[0041] Specific: First, the narrowband energy and peak significance of the spectrum of the vibration signal within a period of time are calculated, and the narrowband containing the significant peak is screened out; Then, the Kendall's tau hypothesis test method is used to determine whether a certain fault frequency or a certain narrow-band energy has a significant upward trend. If so, an alarm is triggered.

[0042] For example, the cage fundamental frequency narrowband range is 10.4475Hz~10.5525Hz. The energy sequence with significant peaks in the past 10 days is [0.355, 0.35 , 0.36 , 0.2, 0.5 , 0.4 , 0.5 , 0.6, 0.55 ,0.56 , 0.615, 0.4 ,0.65 , 0.7 , 0.5, 0.55 , 0.62 , 0.4, 0.8 , 0.7 , 0.6 ], and the correlation between the energy sequence and the [0,1,2,...,20] sequence is calculated using the kendall's tau method. The tau value is 0.55>0, and the p value is 0.0006<the specified 0.01, so the cage fundamental frequency narrowband energy shows a significant upward trend, and an alarm is output.

[0043] The present invention obtains the time domain signal of the equipment vibration sensor, uses fast Fourier transform to obtain the spectrum diagram, and determines the fundamental frequency of the fault of concern. Then, an innovative peak-finding and binary search algorithm is used to search for peak points near the fundamental frequency and its harmonics to correct the fundamental frequency. Based on the corrected fundamental frequency, the present invention calculates the energy and peak significance of multiple narrowband ranges, and tracks the recent changing trends of these features. Through the Kendall's tau hypothesis test, it is determined whether there is a narrow band with a significant increase in energy, thereby achieving accurate diagnosis of equipment faults and automatic alarms, reducing the manpower cost in fault diagnosis.

[0044] See also Figure 2 The second embodiment of the present invention further provides an industrial equipment fault diagnosis device, which includes: A spectrum acquisition unit 210, used to acquire a vibration signal of the device to be diagnosed and convert the vibration signal into a spectrum; The fundamental frequency determination unit 220 is used to determine the fault frequency of concern and use the fault frequency as the fundamental frequency; the fundamental frequency correction unit 230 is used to adaptively correct the fundamental frequency based on the spectrum diagram by using peak screening and harmonic frequency recursion rules to obtain the corrected fundamental frequency; the peak significance calculation unit 240 is used to calculate the narrowband energy and peak significance corresponding to the corrected fundamental frequency according to preset narrowband monitoring parameters; the judgment unit 250 is used to judge the change trend of the narrowband energy by using a hypothesis testing method, and if there is a significant upward trend, a fault alarm is triggered.

[0045] Please refer to Figure 3 , which shows a schematic diagram of an electronic device for implementing the above-mentioned diagnostic method provided by some embodiments of the present application. Figure 3 As shown, the electronic device 20 includes: a processor 200, a memory 201, a bus 202 and a communication interface 203, and the processor 200, the communication interface 203 and the memory 201 are connected via the bus 202; the memory 201 stores a computer program that can be run on the processor 200, and when the processor 200 runs the computer program, the industrial equipment fault diagnosis method provided in any of the aforementioned embodiments of the present application is executed.

[0046] The memory 201 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 203 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0047] The bus 202 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 201 is used to store programs, and the processor 200 executes the programs after receiving execution instructions. The industrial equipment fault diagnosis method disclosed in any implementation of the embodiment of the present application may be applied to the processor 200, or implemented by the processor 200.

[0048] The processor 200 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 200. The above processor 200 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201 and completes the steps of the above method in combination with its hardware.

[0049] The electronic device provided in the embodiment of the present application and the industrial equipment fault diagnosis method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0050] An embodiment of the present application also provides a computer-readable storage medium corresponding to the industrial equipment fault diagnosis method provided in the aforementioned embodiment, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the industrial equipment fault diagnosis method provided in any of the aforementioned embodiments.

[0051] It should be noted that examples of the computer-readable storage medium may also 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 optical or magnetic storage media, which are not listed here one by one.

[0052] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the industrial equipment fault diagnosis method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0053] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application.

Claims

1. A method for diagnosing faults in industrial equipment, characterized in that: Including: Obtain the vibration signal of the device to be diagnosed, and convert the vibration signal into a spectrogram; Determine the fault frequency of concern, and use the fault frequency as the fundamental frequency; Based on the spectrogram, adaptively correct the fundamental frequency using peak screening and harmonic frequency recurrence rules to obtain the corrected fundamental frequency; According to the preset narrowband monitoring parameters, calculate the narrowband energy and peak significance corresponding to the corrected fundamental frequency; Use the hypothesis testing method to judge the change trend of the narrowband energy. If there is a significant upward trend, trigger a fault alarm.

2. The industrial equipment fault diagnosis method according to claim 1, characterized in that: The obtaining of the device vibration signal and converting the vibration signal into a spectrogram includes: Obtain the signal data of the vibration sensor installed on the device to be diagnosed within a period of time to obtain the vibration signal of the device to be diagnosed; Use the fast Fourier transform to convert the vibration signal into a spectrum, take the first half of the spectrum, convert the spectrum amplitude from a complex number to a real number, and obtain a spectrogram composed of a frequency sequence and an amplitude sequence.

3. The industrial equipment fault diagnosis method according to claim 1, characterized in that: The determining of the fault frequency of concern includes: According to the structural parameters of the device to be diagnosed, calculate the fault frequency characterizing a specific fault, and use the fault frequency as the fundamental frequency.

4. The industrial equipment fault diagnosis method according to claim 1, characterized in that: Based on the spectrogram, adaptively correcting the fundamental frequency using peak screening and harmonic frequency recurrence rules includes: Obtain all peak points in the spectrogram; Search for peak points within the frequency narrowband sequence range formed by the fundamental frequency and its harmonic frequencies to obtain a peak point sequence; where, at most one peak point is reserved for each narrowband. When there are multiple peak points, the one with the higher amplitude is reserved. When there is no peak point, None is used for placeholder; Use the binary search method to find the longest sequence in the peak point sequence that contains at least two non-None points, and the longest sequence conforms to the harmonic frequency recurrence rule; If the longest sequence is found, divide the fundamental frequency peak point frequency or the lowest harmonic frequency peak point frequency in the longest sequence by the multiple as the corrected fundamental frequency, otherwise the fundamental frequency is not corrected.

5. The industrial equipment fault diagnosis method according to claim 1, characterized in that: The multiple is 1 - 5 times; the frequency narrowband sequence range is the frequency narrowband sequence range formed by the fundamental frequency and its 1 - 5 times harmonic frequencies and the first error range e1; The harmonic frequency recurrence rule, that is, idx×base×(1 - e2) < a < idx×base×(1 + e2), where base is the fundamental frequency, a is the frequency of a certain point in the peak point sequence, idx is the position of this point in the peak point sequence, e2 is the second error range, and e1 >= e2.

6. The industrial equipment fault diagnosis method according to claim 1, characterized in that: The calculating of the narrowband energy and peak significance corresponding to the corrected fundamental frequency according to the preset narrowband monitoring parameters includes: According to the preset narrowband monitoring parameters, calculate the narrowband ranges corresponding to the fundamental frequency and its harmonic frequencies and sideband frequencies; Calculate the maximum amplitude within each narrowband as the energy of the narrowband; Judge whether there is a significant peak with a ratio of prominence to peak width greater than the preset value within each narrowband; where, the prominence of the peak = peak amplitude - max(left valley amplitude, right valley amplitude), and max(left valley amplitude, right valley amplitude) represents the larger value between the left valley amplitude and the right valley amplitude.

7. The industrial equipment fault diagnosis method according to claim 6, characterized in that: The using of the hypothesis testing method to judge the narrowband energy trend includes: Obtain the narrowband energy sequence of the spectrum graph within a period of time, and filter out the narrowband energy sequence containing significant peaks; A hypothesis testing method is used to determine whether the narrowband energy sequence has a significant upward trend, and if so, a fault alarm is triggered.

8. An industrial equipment fault diagnosis device, characterized in that: include: A frequency spectrum acquisition unit, used to acquire a vibration signal of the device to be diagnosed and convert the vibration signal into a frequency spectrum; A base frequency determination unit, used to determine a concerned fault frequency and use the fault frequency as the base frequency; A fundamental frequency correction unit, configured to adaptively correct the fundamental frequency based on the spectrum diagram by using peak screening and harmonic frequency recursion rules to obtain a corrected fundamental frequency; A peak significance calculation unit, used for calculating the narrowband energy and peak significance corresponding to the corrected fundamental frequency according to preset narrowband monitoring parameters; The judgment unit is used to judge the variation trend of the narrowband energy by using a hypothesis test method, and trigger a fault alarm if there is a significant upward trend.

9. An industrial equipment fault diagnosis device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the computer program can be executed by the processor to implement the industrial equipment fault diagnosis method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored, and the computer program can be executed by a processor of the device where the computer-readable storage medium is located to implement the industrial equipment fault diagnosis method according to any one of claims 1 to 7.

Images